NAS-Unet: Neural Architecture Search for Medical Image Segmentation
Open accessAbstract
Neural architecture search (NAS) has significant progress in improving the accuracy of image classification. Recently, some works attempt to extend NAS to image segmentation which shows preliminary feasibility. However, all of them focus on searching architecture for semantic segmentation in natural scenes. In this paper, we design three types of primitive operation set on search space to automatically find two cell architecture DownSC and UpSC for semantic image segmentation especially medical image segmentation. Inspired by the U-net architecture and its variants successfully applied to various medical image segmentation, we propose NAS-Unet which is stacked by the same number of DownSC and UpSC on a U-like backbone network. The architectures of DownSC and UpSC updated simultaneously by a differential architecture strategy during the search stage. We demonstrate the good segmentation results of the proposed method on Promise12, Chaos, and ultrasound nerve datasets, which collected by magnetic resonance imaging, computed tomography, and ultrasound, respectively. Without any pretraining, our architecture searched on PASCAL VOC2012, attains better performances and much fewer parameters (about 0.8M) than U-net and one of its variants when evaluated on the above three types of medical image datasets.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
NAS-Unet explored differentiable NAS strategies on a U-shaped backbone for medical image segmentation.
“NAS-Unet, proposed in 2019, explored differentiable NAS strategies (e.g., DARTS/ProxylessNAS-style methods) on a U-shaped backbone for medical image segmentation [10].”
From Optimizing Neural Network Architecture for Medical Image Segmentation Using Monte Carlo Tree Search (2026) · cites this paper as [10]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1× · see citing works
“From the earliest LeNet [9] to AlexNet [10], VggNet [11], GoogleNet [12], ResNet [13] and the recent DenseNet [14], the performance of CNN models getting stronger and more mature.”
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1× · see citing works
“From the earliest LeNet [9] to AlexNet [10], VggNet [11], GoogleNet [12], ResNet [13] and the recent DenseNet [14], the performance of CNN models getting stronger and more mature.”
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · cited 4× · see citing works
“The baseline methods are U-Net [8], FC-Densenet [27].”
BackgroundMethodResultInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · cited 1× · see citing works
“From the earliest LeNet [9] to AlexNet [10], VggNet [11], GoogleNet [12], ResNet [13] and the recent DenseNet [14], the performance of CNN models getting stronger and more mature.”
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1× · see citing works
“From the earliest LeNet [9] to AlexNet [10], VggNet [11], GoogleNet [12], ResNet [13] and the recent DenseNet [14], the performance of CNN models getting stronger and more mature.”
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566 · cited 4× · see citing works
“Our work reveals that NasUnets are more efficient in the parameters usage and get a much better performance than U-Net and FC-DenseNet [27] (a variant U-Net) in all types of medical image dataset we mentioned before.”
InfluentialGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 1× · see citing works
“From the earliest LeNet [9] to AlexNet [10], VggNet [11], GoogleNet [12], ResNet [13] and the recent DenseNet [14], the performance of CNN models getting stronger and more mature.”
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 8× · see citing works
“Different from FCNs, the number of down-sampling layers and up-sampling layers and convolution layers between them in the U-net is the same.”
BackgroundMethodInfluentialSqueeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667 · cited 2× · see citing works
“conv [47] and cweight [48], are prevalent in current NAS methods.”
MethodChen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392 · cited 1× · see citing works
“conv [47] and cweight [48], are prevalent in current NAS methods.”
MethodV-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931 · cited 1× · see citing works
“[30] proposed a 3D deformation architecture called V-net based on U-Net.”
Method(2017) · Cited by 11,625 · see citing works
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_49 · Cited by 7,945 · cited 1× · see citing works
“[29] first proposed a 3D U-Net network architecture that implements 3D image segmentation by inputting a continuous 2D slice sequence of 3D images.”
BackgroundThe Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139 · cited 3× · see citing works
“We want to search proxy cell architectures on a much complicated image dataset (PASCALVOC 2012 dataset [26]) and transfer it to medical image datasets.”
BackgroundMethodInfluentialLearning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00907 · Cited by 6,631 · cited 2× · see citing works
“However, since NASNet [37] successfully stacks the cell together on ImageNet, more recent works [20], [22], [23], [45], [46] prefer to search the repeatable cell structure, but keep the backbone network fixed at first.”
BackgroundNeural Architecture Search with Reinforcement LearningPreprint
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 5,091 · cited 1× · see citing works
“The former works try to directly build the entire network architecture [36], [44].”
BackgroundWu, Y., & He, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01261-8_1 · Cited by 3,601 · see citing works
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00293 · Cited by 3,416 · cited 1× · see citing works
“However, since NASNet [37] successfully stacks the cell together on ImageNet, more recent works [20], [22], [23], [45], [46] prefer to search the repeatable cell structure, but keep the backbone network fixed at first.”
BackgroundEvolving Neural Networks through Augmenting Topologies
Stanley, K. O., & Miikkulainen, R. P. (2002) · Evolutionary Computation · doi:10.1162/106365602320169811 · Cited by 3,269 · cited 1× · see citing works
“The search algorithms mainly includes heuristic algorithm [19], [21], [32]–[34], reinforcement learning [35]–[38], [38], [39], the Bayesian optimization method [40], [41] and the gradient-based method [20], [42], [43].”
MethodDARTS: Differentiable architecture search
Liu, H., Simonyan, K., & Yang, Y. (2018) · arXiv · doi:10.48550/arxiv.1806.09055 · Cited by 3,248 · cited 16× · see citing works
“and not overly expansive search space, even use a random searchmay achieve strong results [20], [40].”
BackgroundMethodInfluentialProgressive Neural Architecture Search
Liu, C., Zoph, B., Neumann, M., Shlens, J., Wei, H., Li, L.-J., Fei-Fei, L., Yuille, A., Huang, J., & Murphy, K. P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01246-5_2 · Cited by 1,946 · cited 1× · see citing works
“Much work has been done on the NAS, most of which focus on image classification task [18]–[23].”
BackgroundNeural Architecture Search: A Survey
Elsken, T., Metzen, J. H., & Hutter, F. (2018) · arXiv · doi:10.48550/arxiv.1808.05377 · Cited by 1,763 · see citing works
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
Jégou, S., Drozdzal, M., Vázquez, D., Romero, A., & Bengio, Y. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.156 · Cited by 1,762 · cited 8× · see citing works
“The baseline methods are U-Net [8], FC-Densenet [27].”
BackgroundMethodInfluentialProxylessNAS: Direct Neural Architecture Search on Target Task and HardwarePreprint
Cai, H., Zhu, L., & Han, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00332 · Cited by 1,652 · cited 6× · see citing works
“However, since NASNet [37] successfully stacks the cell together on ImageNet, more recent works [20], [22], [23], [45], [46] prefer to search the repeatable cell structure, but keep the backbone network fixed at first.”
BackgroundMethodInfluentialLarge-Scale Evolution of Image ClassifiersPreprint
Real, E., Moore, S., Selle, A. P., Saxena, S., Suematsu, Y. I. L., Tan, J., Le, Q. V., & Kurakin, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.01041 · Cited by 1,372 · cited 1× · see citing works
“The former works try to directly build the entire network architecture [36], [44].”
Background(2012) · neural information processing systems · Cited by 1,291 · see citing works
Brain intelligence: go beyond artificial intelligence
Lu, H., Li, Y., Chen, M., Kim, H., & Serikawa, S. (2018) · Mobile Networks and Applications · doi:10.1007/s11036-017-0932-8 · Cited by 1,153 · cited 2× · see citing works
“[15] H. Lu et al. (2018).”
BackgroundSelf-citationThe Importance of Skip Connections in Biomedical Image Segmentation
Drozdzal, M., Vorontsov, E., Chartrand, G., Kadoury, S., & Pal, C. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46976-8_19 · Cited by 1,114 · cited 1× · see citing works
“[31] make a different between long skip connections (which means a skip connection between two feature maps that are far away) and short skip connections (which usually called single residual block) and find that both of them to be beneficial in creating deep architectures for medical image segmentation.”
BackgroundAuto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Liu, C., Chen, L.-C., Schroff, F., Adam, H., Hua, W., Yuille, A., & Fei-Fei, L. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00017 · Cited by 1,076 · cited 3× · see citing works
“So the total size of the search space is in the order of 1010, which is much smaller than [25].”
BackgroundResultDesigning Neural Network Architectures using Reinforcement LearningPreprint
Baker, B., Gupta, O., Naik, N., & Raskar, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02167 · Cited by 938 · cited 1× · see citing works
“The search algorithms mainly includes heuristic algorithm [19], [21], [32]–[34], reinforcement learning [35]–[38], [38], [39], the Bayesian optimization method [40], [41] and the gradient-based method [20], [42], [43].”
MethodHealth-CPS: Healthcare Cyber-Physical System Assisted by Cloud and Big Data
Zhang⋆, Y., Meikang Qiu, A., Tsai, C., Hassan, M. M., & Alamri, A. M. (2015) · IEEE Systems Journal · doi:10.1109/jsyst.2015.2460747 · Cited by 927 · cited 1× · see citing works
“The mutual promotion of deep learning and big data and cloud computing has brought much development to computer vision [6].”
BackgroundXie, L., & Yuille, A. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.154 · Cited by 904 · cited 1× · see citing works
“The search algorithms mainly includes heuristic algorithm [19], [21], [32]–[34], reinforcement learning [35]–[38], [38], [39], the Bayesian optimization method [40], [41] and the gradient-based method [20], [42], [43].”
MethodEvaluation of prostate segmentation algorithms for mri: The promise12 challenge
Litjens, G., Toth, R., van de Ven, W., Hoeks, C., Kerkstra, S., van Ginneken, B., Vincent, G., Guillard, G., Birbeck, N., Zhang, J., et al. (2014) · Medical Image Analysis · doi:10.1016/j.media.2013.12.002 · Cited by 857 · cited 4× · see citing works
“On Promise12, NAS-Unet significantly outperforms the baseline methods.”
BackgroundMethodInfluentialMiikkulainen, R. P., Liang, J., Meyerson, E., Rawal, A., Fink, D., Francon, O., Raju, B., Shahrzad, H., Navruzyan, A., Duffy, N., et al. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-815480-9.00015-3 · Cited by 854 · cited 1× · see citing works
“The search algorithms mainly includes heuristic algorithm [19], [21], [32]–[34], reinforcement learning [35]–[38], [38], [39], the Bayesian optimization method [40], [41] and the gradient-based method [20], [42], [43].”
MethodHierarchical Representations for Efficient Architecture SearchPreprint
Liu, H., Simonyan, K., Vinyals, O., Fernando, C., & Kavukcuoglu, K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.00436 · Cited by 851 · cited 1× · see citing works
“The search algorithms mainly includes heuristic algorithm [19], [21], [32]–[34], reinforcement learning [35]–[38], [38], [39], the Bayesian optimization method [40], [41] and the gradient-based method [20], [42], [43].”
MethodA Hypercube-Based Encoding for Evolving Large-Scale Neural Networks
Stanley, K. O., D’Ambrosio, D. B., & Gauci, J. (2009) · Artificial Life · doi:10.1162/artl.2009.15.2.15202 · Cited by 781 · see citing works
Efficient Architecture Search by Network Transformation
Cai, H., Chen, T., Zhang, W., Yu, Y. H., & Wang, Y.-X. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11709 · Cited by 594 · cited 1× · see citing works
“The search algorithms mainly includes heuristic algorithm [19], [21], [32]–[34], reinforcement learning [35]–[38], [38], [39], the Bayesian optimization method [40], [41] and the gradient-based method [20], [42], [43].”
MethodUnderstanding and Simplifying One-Shot Architecture Search
Bender, G., Kindermans, P.-J., Zoph, B., Vasudevan, V., & Le, Q. V. (2018) · International Conference on Machine Learning · Cited by 558 · see citing works
Practical Block-Wise Neural Network Architecture Generation
Zhong, Z., Yan, J., Wu, W., Shao, J., & Liu, C. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00257 · Cited by 555 · cited 1× · see citing works
“However, since NASNet [37] successfully stacks the cell together on ImageNet, more recent works [20], [22], [23], [45], [46] prefer to search the repeatable cell structure, but keep the backbone network fixed at first.”
BackgroundNeural Architecture OptimizationPreprint
Luo, R., Tian, F., Qin, T., Chen, E., & Liu, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.07233 · Cited by 522 · cited 3× · see citing works
“Because this article focuses constructing an efficient cell search space for medical image segmentation, any method of differential search strategy will be work [20], [22], [23], [50].”
BackgroundMethodMotor Anomaly Detection for Unmanned Aerial Vehicles Using Reinforcement Learning
Lu, H., Li, Y., Mu, S., Wang, D., Kim, H., & Serikawa, S. (2017) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2737479 · Cited by 505 · cited 2× · see citing works
“Many works have designed network structures for specific tasks [15], [16].”
BackgroundSelf-citationDeep Feature Learning for Medical Image Analysis with Convolutional Autoencoder Neural Network
Chen, M., Shi, X., Zhang⋆, Y., Wu, D., & Guizani, M. (2017) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2017.2717439 · Cited by 443 · cited 1× · see citing works
“recognition of images at the pixel level (the object category to each pixel in the image belongs is marked) [4], [5].”
BackgroundUnderwater image dehazing using joint trilateral filter
Serikawa, S., & Lu, H. (2013) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2013.10.016 · Cited by 423 · cited 1× · see citing works
“For the sake of fairness, we re-implement them by Pytorch [55] and use the same data augmentation(we also try to improve the quality of some noisy images [56], [57]).”
MethodNeural Architecture Search with Bayesian Optimisation and Optimal TransportPreprint
Kandasamy, K., Neiswanger, W., Schneider, J., Póczos, B., & Xing, E. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.07191 · Cited by 347 · cited 1× · see citing works
“The search algorithms mainly includes heuristic algorithm [19], [21], [32]–[34], reinforcement learning [35]–[38], [38], [39], the Bayesian optimization method [40], [41] and the gradient-based method [20], [42], [43].”
MethodSearching for Efficient Multi-Scale Architectures for Dense Image Prediction
Chen, L.-C., Collins, M. D., Zhu, Y., Papandreou, G., Zoph, B., Schroff, F., Adam, H., & Shlens, J. (2018) · arXiv · doi:10.48550/arxiv.1809.04184 · Cited by 347 · cited 3× · see citing works
“Some work has been trying to solve the above two problems and achieved some success — exactly the idea that recent work has followed [24], [25].”
BackgroundResultAutomated model-based vertebra detection, identification, and segmentation in CT images
Klinder, T., Östermann, J., Ehm, M., et al. (2009) · Medical Image Analysis · doi:10.1016/j.media.2009.02.004 · Cited by 331 · cited 1× · see citing works
“region based method [1] or threshold based method [2]) and mathematical modeling to construct compound rulebased systems that solved particular tasks [3].”
MethodLu, H., Li, Y., Uemura, T., Kim, H., & Serikawa, S. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2018.01.001 · Cited by 290 · cited 2× · see citing works
“[15] H. Lu et al. (2018).”
MethodSelf-citationSimple And Efficient Architecture Search for Convolutional Neural NetworksPreprint
Elsken, T., Metzen, J. H., & Hutter, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.04528 · Cited by 190 · cited 1× · see citing works
“The search algorithms mainly includes heuristic algorithm [19], [21], [32]–[34], reinforcement learning [35]–[38], [38], [39], the Bayesian optimization method [40], [41] and the gradient-based method [20], [42], [43].”
MethodCONet: A Cognitive Ocean Network
Lu, H., Wang, D., Li, Y., et al. (2019) · IEEE Wireless Communications · doi:10.1109/mwc.2019.1800325 · Cited by 182 · cited 1× · see citing works
“Many works have designed network structures for specific tasks [15], [16].”
BackgroundSelf-citationDifferentiable Neural Network Architecture Search
Shin, R., Packer, C., & Song, D. X. (2018) · International Conference on Learning Representations · Cited by 84 · see citing works
Efficient Neural Architecture Search with Network MorphismPreprint
Jin, H., Song, Q., & Hu, X. (2018) · arXiv (Cornell University) · Cited by 62 · see citing works
An automatic method for colon segmentation in CT colonography
Bert, A., Dmitriev, I., Agliozzo, S., et al. (2009) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2009.02.004 · Cited by 30 · cited 1× · see citing works
“region based method [1] or threshold based method [2]) and mathematical modeling to construct compound rulebased systems that solved particular tasks [3].”
MethodSegmentation of liver vessels as seen in MR and CT images
Eidheim, O. C., Aurdal, L., Omholt-Jensen, T., et al. (2004) · International Congress Series · doi:10.1016/j.ics.2004.03.184 · Cited by 18 · cited 1× · see citing works
“region based method [1] or threshold based method [2]) and mathematical modeling to construct compound rulebased systems that solved particular tasks [3].”
MethodGradient-based Optimization of Neural Network Architecture.
Grathwohl, W., Creager, E., Ghasemipour, S. K. S., et al. (2018) · International Conference on Learning Representations · Cited by 9 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- kingma, 2014, A method for stochastic optimization
- rebetez, 2016, FHTAGN Net Kaggle Ultrasound Nerve Segmentation (25th with 0 70679 Final Ranking)
- 2016, Ultrasound Nerve Segmentation
- 2019, CHAOS—Combined (CT-MR) Healthy Abdominal Organ Segmentation
Cited by
Sorted by citations
U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications
Siddique, N. A., Paheding, S., Elkin, C. P., & Devabhaktuni, V. (2021) · IEEE Access · doi:10.1109/access.2021.3086020 · Cited by 2,060 · see citing works
“Medical ultrasound use cases also include analysis of soft tissue such as nerve bundles [39], [50], [156], [305], [306].”
BackgroundAutoML: A survey of the state-of-the-art
He, X. J., Zhao, K., & Chu, X. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106622 · Cited by 1,778 · see citing works
“Therefore, NAS has also been applied to many other computer vision tasks, such as object detection [153, 154, 155], semantic segmentation [156, 157], image restoration [158], GAN [159], graph neural network (GNN) [160].”
MethodMedical image segmentation using deep learning: A survey
Wang, R., Lei, T., Cui, R., Zhang, B., Meng, H., & Nandi, A. K. (2022) · IET Image Processing · doi:10.1049/ipr2.12419 · Cited by 947 · see citing works
“Weng et al [137]first proposed a NAS-UNet for medical image segmentation.”
BackgroundDeep semantic segmentation of natural and medical images: a review
Taghanaki, S. A., Abhishek, K., Cohen, J., Cohen‐Adad, J., & Hamarneh, G. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09854-1 · Cited by 888 · see citing works
“rger images/(sub)volumes in case of processing volumetric and high-resolution 2D images such as CT, MRI, and histopathology images, several methods have attempted to compress deep models. Weng et al. [153] applied a neural architecture search method to U-Net to obtain a smaller network with a better organ/tumor segmen…”
MethodHossain, E., Rana, R., Higgins, N., Soar, J., Barua, P. D., Pisani, A. R., & Turner, K. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106649 · Cited by 407 · see citing works
IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks
Li, L., Verma, M., Nakashima, Y., Nagahara, H., & Kawasaki, R. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093621 · Cited by 384 · see citing works
“The emergence of UNet [1] leads to a new era of image segmentation in the medical domain, and has revolutionized most image segmentation tasks in relevant domain [15, 16, 17, 18, 19].”
BackgroundQureshi, I., Yan, J., Abbas, Q., Shaheed, K., Riaz, A. B., Wahid, A., Khan, M. W. J., & Szczuko, P. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.09.031 · Cited by 302 · see citing works
A Survey on Neural Architecture SearchPreprint
Wistuba, M., Rawat, A., & Pedapati, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.01392 · Cited by 285 · see citing works
“…that address more complex tasks with image data such as object detection and segmentation (Zoph et al., 2018; Tan et al., 2018; Liu et al., 2019a; Weng et al., 2019), as well as works that address safety-critical issues such as the discovery of architectures that are robust against adversarial…”
BackgroundA Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends
Younesi, A., Ansari, M., Fazli, M., Ejlali, A., Shafique, M., & Henkel, J. (2024) · IEEE Access · doi:10.1109/access.2024.3376441 · Cited by 228 · see citing works
“Medical image analysis involves the examination and interpretation of medical images, such as MRI scans, CT scans, and X-rays [92], [222], [223], [224], [225], [226], [227], [228], [229], [230], [231], [232], [233], [234], [235], [236], [237], [238], [239].”
A survey on deep learning for skin lesion segmentation
Mirikharaji, Z., Abhishek, K., Bissoto, A. E., Barata, C., Avila, S., Junior, E. A. D. V., Celebi, M. E., & Hamarneh, G. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102863 · Cited by 205 · see citing works
Current and Emerging Trends in Medical Image Segmentation With Deep Learning
Conze, P.-H., Andrade-Miranda, G. X., Singh, V. K., Jaouen, V., & Visvikis, D. (2023) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2023.3265863 · Cited by 166 · see citing works
“Among the existing research works in this area, NAS-UNet [111] is based on the design of three types of primitive operation set on search space to automatically find two cell architectures (DownSC and UpSC) for semantic segmen-”
MethodC2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
Yu, Q., Yang, D., Roth, H. R., Bai, Y., Zhang, Y., Yuille, A., & Xu, D. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00418 · Cited by 153 · see citing works
Wei, J., Zhu, G., Fan, Z., et al. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3111679 · Cited by 137 · see citing works
A bird's-eye view of deep learning in bioimage analysis
Meijering, E. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.08.003 · Cited by 126 · see citing works
“First successful applications have recently been reported in medical imaging [252,280,281], suggesting NAS holds great potential also for bioimage analysis.”
BackgroundAdaEn-Net: An ensemble of adaptive 2D–3D Fully Convolutional Networks for medical image segmentation
Baldeon-Calisto, M., & Lai-Yuen, S. K. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.03.007 · Cited by 138 · see citing works
DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation
He, Y., Yang, D., Roth, H. R., Zhao, C., & Xu, D. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00578 · Cited by 130 · see citing works
“In medical image segmentation, NAS-UNet [40], V-NAS [48] and Kim et al [15] search cells and apply it to a U-Net-like topology.”
MethodHalf-UNet: A Simplified U-Net Architecture for Medical Image Segmentation
Lu, H., She, Y., Tie, J., & Xu, S. (2022) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2022.911679 · Cited by 130 · see citing works
“Weng et al. (2019) proposed NAS-UNet, using three types of primitive operation sets and search space to automatically find two cell architectures, DownSC and UpSC, for medical image segmentation, which attains better performance and uses much fewer parameters (about 0.8 M) than standard U-Net.”
MethodInfluentialAutomated Machine Learning for Healthcare and Clinical Notes Analysis
Mustafa, A., & Azghadi, M. R. (2021) · Computers · doi:10.3390/computers10020024 · Cited by 131 · see citing works
“Images Cancer [12] [61] Covid-19 [62] Generic [44] [46] [63] Liver Injury [64] Pachychoroid [65] Structured Tabular Alzheimer [14] BioSignature [13] Brain Age [58] Brain Tumor [59] Cardiac [25] Diabetes [66] Generic [37] [11] Metabolic [60] As the table shows, most of the unstructured data is…”
BackgroundMethodA hybrid deep segmentation network for fundus vessels via deep-learning framework
Yang, L., Wang, H., Zeng, Q., Liu, Y., & Bian, G. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.085 · Cited by 127 · see citing works
Jiang, H., Shen, F., Gao, F., & Han, W. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107825 · Cited by 120 · see citing works
“Besides, several NAS based 3D medical image segmentation methods are proposed in [20, 21].”
MethodAdvancements in Deep Learning for B-Mode Ultrasound Segmentation: A Comprehensive Review
Ansari, M. Y., Mangalote, I. A. C., Meher, P. K., Aboumarzouk, O. M., Al-Ansari, A. A., Halabi, O., & Dakua, S. P. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3377676 · Cited by 116 · see citing works
“Weng et al. [134] utilize the idea of neural architecture search (NAS) for finding the optimal combination of layers within a convolutional block of a U-Net architecture to segment MRI, CT, and US images.”
BackgroundZhang, J., Qin, Q., Ye, Q., & Ruan, T. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106516 · Cited by 111 · see citing works
MFSNet: A multi focus segmentation network for skin lesion segmentation
Basak, H., Kundu, R., & Sarkar, R. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108673 · Cited by 112 · see citing works
“Weng et al. [51] proposed another modification in the U-Net backbone by incorporating neural architecture search (NAS), thereby improving the segmentation performance significantly.”
BackgroundFung, D. L. X., Liu, Q., Zammit, J., Leung, C. K.-S., & Hu, P. (2021) · Journal of Translational Medicine · doi:10.1186/s12967-021-02992-2 · Cited by 104 · see citing works
Flexible sensors and machine learning for heart monitoring
Kwon, S. H., & Dong, L. (2022) · Nano Energy · doi:10.1016/j.nanoen.2022.107632 · Cited by 97 · see citing works
Chen, M., Lupoiu, R. C., Mao, C., Huang, D.-H., Jiang, J., Lalanne, P., & Fan, J. A. (2022) · ACS Photonics · doi:10.1021/acsphotonics.2c00876 · Cited by 93 · see citing works
Hussain, T., & Shouno, H. (2024) · IEEE Access · doi:10.1109/access.2024.3374108 · Cited by 91 · see citing works
“Skip connections have been proposed to eliminate these gaps [1], [22].”
BackgroundWeight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Xie, L., Chen, X., Bi, K., Wei, L., Xu, Y., Wang, L., Chen, Z., Xiao, A., Chang, J., Zhang, X., et al. (2021) · ACM Computing Surveys · doi:10.1145/3473330 · Cited by 108 · see citing works
“though searching for efficient blocks is also verified useful [152], [266], [276].”
BackgroundGuo, L., Lei, B., Chen, W., Du, J., Frangi, A. F., Qin, J., Zhao, C., Shi, P., Xia, B., & Wang, T. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102042 · Cited by 85 · see citing works
Tao, J., Chen, Z., Sun, Z., Guo, H., Leng, B., Yu, Z., Wang, Y., He, Z., Lei, X., & Yang, J. (2023) · Remote Sensing · doi:10.3390/rs15061602 · Cited by 85 · see citing works
Marzola, F., van Alfen, N., Doorduin, J., et al. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104623 · Cited by 83 · see citing works
Tran, S.-T., Cheng, C.-H., Nguyen, T.-T., Le, M.-H., & Liu, D. (2021) · Healthcare · doi:10.3390/healthcare9010054 · Cited by 81 · see citing works
Sorghum Panicle Detection and Counting Using Unmanned Aerial System Images and Deep Learning
Lin, Z., & Guo, W. (2020) · Frontiers in Plant Science · doi:10.3389/fpls.2020.534853 · Cited by 79 · see citing works
“The spatial dimensions of the feature maps were halved and the number of feature maps was doubled repeatedly through the down-sampling layer (Guan et al., 2019; Weng et al., 2019).”
BackgroundJiao, Y., Yang, K., Song, D., & Tao, D. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3148276 · Cited by 73 · see citing works
“Previous works about AutoML mostly focus on the domains of computer vision and natural language processing, including object detection [35, 36], semantic segmentation [37, 38], translation [39], and sequence labeling [40].”
BackgroundArtificial intelligence in musculoskeletal ultrasound imaging
Shin, Y., Yang, J., Lee, Y. H., & Kim, S. J. (2020) · ULTRASONOGRAPHY · doi:10.14366/usg.20080 · Cited by 73 · see citing works
“[61] employed neural architecture search, which used autoML algorithms that returned the best neural network through the sampling of building blocks to create an end-to-end structure, and achieved encouraging results (mean intersection over union, 0.”
MethodResUNet+: A New Convolutional and Attention Block-Based Approach for Brain Tumor Segmentation
Metlek, S., & Çetıner, H. (2023) · IEEE Access · doi:10.1109/access.2023.3294179 · Cited by 73 · see citing works
“In order to eliminate these semantic gaps, some improvements have been suggested in the literature by using different skip connections [21], [22].”
BackgroundHuang, G., Zhu, J., Li, J., Wang, Z., Cheng, L., Liu, L., Li, H., & Zhou, J. (2020) · IEEE Access · doi:10.1109/access.2020.3007719 · Cited by 71 · see citing works
Neural Architecture Search for Skin Lesion Classification
Kwasigroch, A., Grochowski, M., & Mikołajczyk, A. (2020) · IEEE Access · doi:10.1109/access.2020.2964424 · Cited by 67 · see citing works
BB-UNet: U-Net With Bounding Box Prior
Jurdi, R. E., Petitjean, C., Honeiné, P., & Abdallah, F. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3001502 · Cited by 67 · see citing works
“emerged in order to increase model performance given different tasks [6], [7].”
BackgroundShuvo, M. B., Ahommed, R., Reza, S., & Hashem, M. M. A. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102959 · Cited by 62 · see citing works
Techniques for Automated Machine Learning
Chen, Y., Song, Q., & Hu, X. (2021) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3447556.3447567 · Cited by 62 · see citing works
A Comprehensive Survey on Hardware-Aware Neural Architecture SearchPreprint
Benmeziane, H., Maghraoui, K. E., Ouarnoughi, H., Niar, S., Wistuba, M., & Wang, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.09336 · Cited by 78 · see citing works
“…[90], [136], [121], [137], [61], [62], [67], [68], [70], [71], [95], [96], [97], [102], [99], [107], [108], [109], [113] MCU [123], [63], [111], [138], [23], [89] Mobile Devices [47], [53], [23], [57], [59], [66], [18], [60], [87], [85], [86], [110], [84], [80], [99] ASICs [72], [118], [119],…”
BackgroundTesting and quality validation for AI software–perspectives, issues, and practices
Tao, C., Gao, J., & Wang, T. (2019) · IEEE Access · doi:10.1109/access.2019.2937107 · Cited by 60 · see citing works
VesNet-RL: Simulation-Based Reinforcement Learning for Real-World US Probe Navigation
Bi, Y., Jiang, Z., Gao, Y., Wendler, T., Karlas, A., & Navab, N. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3176112 · Cited by 62 · see citing works
MS-NAS: Multi-scale Neural Architecture Search for Medical Image Segmentation
Yan, X., Jiang, W., Shi, Y., & Zhuo, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59710-8_38 · Cited by 58 · see citing works
LAEDNet: A Lightweight Attention Encoder–Decoder Network for ultrasound medical image segmentation
Zhou, Q., Wang, Q., Bao, Y., et al. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107777 · Cited by 58 · see citing works
Baldeon-Calisto, M., & Lai-Yuen, S. K. (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102154 · Cited by 54 · see citing works
2D to 3D Evolutionary Deep Convolutional Neural Networks for Medical Image Segmentation
Hassanzadeh, T., Essam, D., & Sarker, R. A. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3035555 · Cited by 55 · see citing works
“Besides, NAS U–Net [36] obtained almost the similar results of the manual–designed networks, because, NAS U–Net also uses a unique network structure for segmentation.”
MethodResultInfluentialAhmad, I., Xia, Y., Cui, H., & Islam, Z. U. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118945 · Cited by 54 · see citing works
LSPnet: A 2D Localization-oriented Spacecraft Pose Estimation Neural Network
Garcia, A., Musallam, M. A., Gaudillière, V., Ghorbel, E., Ismaeil, K. A., Perez, M. D., & Aouada, D. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00233 · Cited by 53 · see citing works
A Multi-Attention and Depthwise Separable Convolution Network for Medical Image Segmentation
Zhou, Y., Kang, X., Ren, F., Lu, H., Nakagawa, S., & Xiao, S. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126970 · Cited by 53 · see citing works
Comprehensive Review: Machine and Deep Learning in Brain Stroke Diagnosis
Fernandes, J. N. D., Cardoso, V. E. M., Comesaña-Campos, A., & Pinheira, A. G. (2024) · Sensors · doi:10.3390/s24134355 · Cited by 58 · see citing works
“This field of work already presents relevant literature, as can be seen in the works of Zhu et al. [118] and Weng et al. [119].”
MethodAutomated Design of Deep Neural Networks
Talbi, E. (2021) · ACM Computing Surveys · doi:10.1145/3439730 · Cited by 57 · see citing works
“Then, the problem consists in finding the optimal architecture at the outer-level using this fixed set of inner-level cells [49, 181, 197, 215] (Figure 6).”
BackgroundMethodMonchot, P., Coquelin, L., Guerroudj, K., Feltin, N., Delvallée, A., Crouzier, L., & Fischer, N. (2021) · Nanomaterials · doi:10.3390/nano11040968 · Cited by 51 · see citing works
“While semantic methods are adapted to numerous cases of study such as medical images [14,15], mineral characterization [16] or meteorology [17], they can not be applied to our images, where TiO2 particles tend to agglomerate.”
MethodExploring applications of blockchain in healthcare: road map and future directions
Singh, Y., Jabbar, M. A., Shandilya, S. K., Вовк, О., & Hnatiuk, Y. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1229386 · Cited by 60 · see citing works
Chen, S., Yang, H., Fu, J., Mei, W.-J., Ren, S., Liu, Y., Zhu, Z., Liu, L., Li, H., & Chen, H. (2019) · IEEE Access · doi:10.1109/access.2019.2923760 · Cited by 49 · see citing works
Adaptive segmentation model for liver CT images based on neural network and level set method
Shu, X., Yang, Y., & Wu, B. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.01.081 · Cited by 48 · see citing works
DSRNA: Differentiable Search of Robust Neural Architectures
Hosseini, R., Yang, X., & Xie, P. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00613 · Cited by 48 · see citing works
Imaging through diffuse media using multi-mode vortex beams and deep learning
Balasubramaniam, G. M., Biton, N., & Arnon, S. (2022) · Scientific Reports · doi:10.1038/s41598-022-05358-w · Cited by 48 · see citing works
“Although initially, this architecture was used for a segmentation problem, recent studies have shown that this architecture is very efficient for the required restoration 16,53,54 .”
MethodGuo, X., Zhang, N., Guo, J., et al. (2019) · Medical Physics · doi:10.1002/mp.13865 · Cited by 47 · see citing works
Kendrick, J., Francis, R. J., Hassan, G. M., Rowshanfarzad, P., Ong, J. S. L., & Ebert, M. A. (2022) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-022-05927-1 · Cited by 46 · see citing works
M-Net: An encoder-decoder architecture for medical image analysis using ensemble learning
Sreelakshmi, S., Malu, G., Sherly, E., et al. (2023) · Results in Engineering · doi:10.1016/j.rineng.2023.100927 · Cited by 44 · see citing works
Xiao, X., Zhang, J., Shao, Y., Liu, J., Shi, K., He, C., & Kong, D. (2025) · Sensors · doi:10.3390/s25082361 · Cited by 46 · see citing works
“Weng et al. [46], inspired by the U-net architecture and its successful variants applied to various medical image segmentation tasks, proposed NAS-Unet.”
Semantic Segmentation on Panoramic Dental X-Ray Images Using U-Net Architectures
Zannah, R., Bashar, M., Mushfiq, R. B., Chakrabarty, A., Hossain, S., & Jung, Y. J. (2024) · IEEE Access · doi:10.1109/access.2024.3380027 · Cited by 47 · see citing works
“In the paper [37], inspired by U-Net architectures, the author introduces the Neural Architecture Search (NAS) system, aligning it with U-Net models.”
MethodOyelade, O. N., & Ezugwu, A. E.-S. (2021) · Scientific Reports · doi:10.1038/s41598-021-98978-7 · Cited by 43 · see citing works
“Studies have shown that DL architectures, convolutional neural networks (CNN) specifically engineered using these approaches, have outperformed the handcrafted architectures applied to some problems 4–6 .”
BackgroundAutomatic void content assessment of composite laminates using a machine-learning approach
Machado, J., Tavares, J., Camanho, P., & Correia, N. (2022) · Composite structures · doi:10.1016/j.compstruct.2022.115383 · Cited by 39 · see citing works
Intraoperative Glioma Grading Using Neural Architecture Search and Multi-Modal Imaging
Xiao, A., Shen, B., Shi, X., Zhang, Z., Zhang, Z., Tian, J., Ji, N., & Hu, Z. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3166129 · Cited by 41 · see citing works
“Some recent studies in the medical field have also used NAS and achieved remarkable results in the segmentation of MRI and CT images [40]–[42].”
Yu, C., Wang, Y., Tang, C., Feng, W., & Lv, J. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107579 · Cited by 44 · see citing works
Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies
Kendrick, J., Francis, R. J., Hassan, G. M., Rowshanfarzad, P., Jeraj, R., Kasisi, C., Rusanov, B., & Ebert, M. A. (2021) · Frontiers in Oncology · doi:10.3389/fonc.2021.771787 · Cited by 41 · see citing works
Deep learning for gastroscopic images: computer-aided techniques for clinicians
Jin, Z., Gan, T., Wang, P., Fu, Z., Zhang, C., Yan, Q., Zheng, X., Liang, X., & Ye, X. (2022) · BioMedical Engineering OnLine · doi:10.1186/s12938-022-00979-8 · Cited by 40 · see citing works
“For example, NASUNet [125], AutoDeepLab [126], MS-NAS [127], and BiX-NAS [128] have achieved SOTA performance on medical image segmentation.”
BackgroundPocketNet: A Smaller Neural Network for Medical Image Analysis
Celaya, A., Actor, J., Rajarajeswari, M., Gates, E. D. H., Chung, C. D., Schellingerhout, D., Rivière, B. M., & Fuentes, D. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3224873 · Cited by 40 · see citing works
Visual geometry Group-UNet: Deep learning ultrasonic image reconstruction for curved parts
Mei, Y., Jin, H., Yu, B., et al. (2021) · The Journal of the Acoustical Society of America · doi:10.1121/10.0004827 · Cited by 39 · see citing works
Tutorial on the Use of Deep Learning in Diffuse Optical Tomography
Balasubramaniam, G. M., Wiesel, B., Biton, N., Kumar, R., Kupferman, J., & Arnon, S. (2022) · Electronics · doi:10.3390/electronics11030305 · Cited by 40 · see citing works
Ruan, D., Han, J., Yan, J., & Gühmann, C. (2023) · Scientific Reports · doi:10.1038/s41598-023-31532-9 · Cited by 39 · see citing works
Liu, X., Liu, X., Yao, C., et al. (2023) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2023.102307 · Cited by 38 · see citing works
Multi-Scale Network for Thoracic Organs Segmentation
Khalil, M. I., Tehsin, S., Humayun, M., Jhanjhi, N. Z., & AlZain, M. A. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.020561 · Cited by 38 · see citing works
“Segmentation segments of the image into cohesive regions, clustering techniques may be extended to subdivision by removing the overall features of the object to efficiently distinguish ROI from the object context [5].”
Yu, Z., Lee, F., & Chen, Q. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04570-z · Cited by 38 · see citing works
Deep Ice Layer Tracking and Thickness Estimation using Fully Convolutional Networks
Varshney, D., Rahnemoonfar, M., Yari, M., et al. (2020) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata50022.2020.9378070 · Cited by 37 · see citing works
“strategy, combined with data augmentation, turned out to be useful in biomedical image segmentation, especially for detecting tissue deformations. The success of UNet in biomedical images [31], [42], [43] led to its application and improvement for other domains such as remote sensing [44], [45] and autonomous driving…”
MethodLu, Z., Xia, W., Huang, Y., et al. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3219286 · Cited by 37 · see citing works
“In the field of medical imaging, most works were proposed for image segmentation and classification [13, 17, 35, 55, 59, 61].”
BackgroundMethodInfluentialYOLO‐UNet Architecture for Detecting and Segmenting the Localized MRI Brain Tumor Image
Iriawan, N., Pravitasari, A. A., Nuraini, U. S., et al. (2024) · Applied Computational Intelligence and Soft Computing · doi:10.1155/2024/3819801 · Cited by 36 · see citing works
Learning deep morphological networks with neural architecture search
Hu, Y., Belkhir, N., Angulo, J., et al. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108893 · Cited by 36 · see citing works
“An alternative approach focuses on automatically finding the network architecture design using Neural Architecture Search (NAS) methods Liu et al. (2019a); Luo et al. (2019); Liu et al. (2018); Pham et al. (2018); Weng et al. (2019) in lieu of manual design.”
MethodMukasa, P., Wakholi, C., Faqeerzada, M. A., Amanah, H. Z., Kim, H., Joshi, R., Suh, H. K., Kim, G., Lee, H., Kim, M. S., et al. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.106799 · Cited by 36 · see citing works
Multi-Scale Fusion U-Net for the Segmentation of Breast Lesions
Li, J., Cheng, L., Xia, T., Ni, H., & Li, J. (2021) · IEEE Access · doi:10.1109/access.2021.3117578 · Cited by 36 · see citing works
Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search
Heuillet, A., Nasser, A., Arioui, H., et al. (2024) · ACM Computing Surveys · doi:10.1145/3665138 · Cited by 35 · see citing works
Discretization-aware architecture search
Tian, Y., Liu, C., Xie, L., Jiao, J., & Ye, Q. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108186 · Cited by 33 · see citing works
Cheng, P., Myronenko, A., Hatamizadeh, A., Nath, V., Siddiquee, M. M. R., He, Y., Xu, D., Chellappa, R., & Yang, D. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.02008 · Cited by 35 · see citing works
“Early attempts [21, 37, 44, 47] build on the prior architecture of U-Net, and modify edge operations and connections while preserving the overall U-shape structure.”
BackgroundWhen Neural Architecture Search Meets Hardware Implementation: from Hardware Awareness to Co-Design
Zhang, X., Jiang, W., Shi, Y., & Hu, J. (2019) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi.2019.00014 · Cited by 37 · see citing works
“Most recently, neural architecture search techniques are extended for more complicated tasks, such as Image Segmentation [14, 43].”
BackgroundZhang, B., Rahmatullah, B., Wang, S. L., Zhang, G., Wang, H., & Ebrahim, N. A. (2021) · Journal of Applied Clinical Medical Physics · doi:10.1002/acm2.13394 · Cited by 35 · see citing works
BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
Wang, X., Xiang, T., Zhang, C., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87193-2_22 · Cited by 34 · see citing works
“Similar to the nuclei segmentation, Table 2 indicates that BiX-Net achieves the best performance of all classes among state-of-the-art NAS searched networks [16,9,18] with much lower computational complexity.”
MethodCombining contrastive learning and shape awareness for semi-supervised medical image segmentation
Chen, Y., Chen, F., & Huang, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122567 · Cited by 33 · see citing works
Low-Memory CNNs Enabling Real-Time Ultrasound Segmentation Towards Mobile Deployment
Vaze, S., Xie, W., & Namburete, A. I. L. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2961264 · Cited by 33 · see citing works
“and familiar taskwhich has beenwidely studied in the ultrasound analysis literature since its publication [13], [14].”
BackgroundYing, W., Zheng, Q., Wu, Y., Yang, K., Zhou, Z., Chen, J., & Ye, Z. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110869 · Cited by 32 · see citing works
DEGAS: differentiable efficient generator search
Doveh, S., & Giryes, R. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06309-8 · Cited by 33 · see citing works
“These include semantic image segmentation [28], medical image segmentation [48], volumetric medical image segmentation [52], object detection [34], and active learning [14].”
BackgroundMulti-scale conv-attention U-Net for medical image segmentation
Pan, P., Zhang, C., Sun, J.-B., & Guo, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-96101-8 · Cited by 48 · see citing works
“Due to its powerful segmentation performance, U-net has been widely used as an indispensable tool in the field of medical image processing and has achieved remarkable success in numerous 2D semantic segmentation tasks 12–14 .”
SliceMamba With Neural Architecture Search for Medical Image Segmentation
Fan, C., Yu, H., Huang, Y., Wang, L., Yang, Z., & Jia, X. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3564381 · Cited by 30 · see citing works
“Additionally, Weng et al. [49] introduced NAS-UNet, which utilizes neural architecture search (NAS) to discover optimal model architectures tailored to different datasets automatically.”
AutoSegNet: An Automated Neural Network for Image Segmentation
Xu, Z., Zuo, S., Lam, E. Y. M., Lee, B., & Chen, N. (2020) · IEEE Access · doi:10.1109/access.2020.2995367 · Cited by 30 · see citing works
“NAS-Unet [24] searches a U-like backbone network for medical image segmentation, and V-NAS [25] formulates the structure learning as differentiable neural architecture search, allowing the network to choose among 2D, 3D or Pseudo-3D (P3D) convolutions at each layer.”
MethodWu, J., Liu, W., Li, C., et al. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09284-4 · Cited by 30 · see citing works
Varshney, D., Rahnemoonfar, M., Yari, M., et al. (2021) · Remote Sensing · doi:10.3390/rs13142707 · Cited by 29 · see citing works
“UNet’s success in processing biomedical images [32,33] inspired its application in remote sensing [34,35] and autonomous driving [36], among other domains.”
BackgroundYu, Y., Chen, S., & Wei, H. (2022) · Flow Measurement and Instrumentation · doi:10.1016/j.flowmeasinst.2022.102300 · Cited by 28 · see citing works
Multiclass Segmentation of Concrete Surface Damages Using U-Net and DeepLabV3+
Hadinata, P. N., Simanta, D., Eddy, L., & Nagai, K. (2023) · Applied Sciences · doi:10.3390/app13042398 · Cited by 29 · see citing works
- Authors
- Weng, Y., Zhou, T., Li, Y., & Qiu, X.
- Affiliations
- Minzu University of China (CN)
- Yangzhou University (CN)
- Shandong University of Traditional Chinese Medicine (CN)
- Venue
- IEEE Access
- Published
- 2019
- Volume
- 7
- Pages
- 44247-44257
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2927980542
- Semantic Scholar
- 90d06dca4796e3b0bd75161beb1a1d9264170769
- Cited by
- 487
- References
- 54
- Citations by year
- 2026: 21 · 2025: 54 · 2024: 89 · 2023: 97 · 2022: 72 · 2021: 87 · 2020: 57 · 2019: 10
- FWCI
- 25.30
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61772575)
- National Key R&D Program of China (2017YFB1402101)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- neural architecture search, medical image segmentation, semantic segmentation, U-Net, magnetic resonance imaging, CT
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
