The DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
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.
Overview
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
Verification
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?
The cited source says what the claim attributes to it.
In the citing paper
“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.
Citations
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×
“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.”
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“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×
“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×
“The baseline methods are U-Net [8], FC-Densenet [27].”
BackgroundMethodResultInfluentialGradient-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×
“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×
“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×
“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×
“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×
“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×
“conv [47] and cweight [48], are prevalent in current NAS methods.”
Method
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 2,185
“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 1,912
“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 1,012
“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 929
“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
Metadata
- 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
