The DOI matches its Crossref record; 56 of the 60 references it cites were found in a registry or an index.
Improving Computer-Aided Detection UsingConvolutional Neural Networks and Random View Aggregation
Open accessAbstract
Automated computer-aided detection (CADe) has been an important tool in clinical practice and research. State-of-the-art methods often show high sensitivities at the cost of high false-positives (FP) per patient rates. We design a two-tiered coarse-to-fine cascade framework that first operates a candidate generation system at sensitivities ∼ 100% of but at high FP levels. By leveraging existing CADe systems, coordinates of regions or volumes of interest (ROI or VOI) are generated and function as input for a second tier, which is our focus in this study. In this second stage, we generate 2D (two-dimensional) or 2.5D views via sampling through scale transformations, random translations and rotations. These random views are used to train deep convolutional neural network (ConvNet) classifiers. In testing, the ConvNets assign class (e.g., lesion, pathology) probabilities for a new set of random views that are then averaged to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. The methods are evaluated on three data sets: 59 patients for sclerotic metastasis detection, 176 patients for lymph node detection, and 1,186 patients for colonic polyp detection. Experimental results show the ability of ConvNets to generalize well to different medical imaging CADe applications and scale elegantly to various data sets. Our proposed methods improve performance markedly in all cases. Sensitivities improved from 57% to 70%, 43% to 77%, and 58% to 75% at 3 FPs per patient for sclerotic metastases, lymph nodes and colonic polyps, respectively.
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?
In the citing paper
“We obtain 86% sensitivity on 3 false positives (FP) per patient, versus the prior state-of-art sensitivities of 78% [36] (stacked shallow learning) and 70% [22] (CNN), as prior state-of-the-art.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [22]
In the citing paper
“GoogLeNet-RI-L | 0.95 | 0.85 | 0.91 | 0.69”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [22]
In the citing paper
“This difference lies in the fact that annotated lymph node segmentation masks are required to learn a mid-level semantic boundary detector [36], whereas CNN approaches only need LN locations for training [22].”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [22]
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
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×
“Potentially, larger and deeper convolutional neural networks could be applied to further improve classification performance [59], [60].”
MethodImageNet 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 10×
“In order to increase the variation of the training data and to avoid overfitting analogous to the data augmentation approach in [14], [17] and [18], multiple 2D or 2.”
BackgroundMethodInfluentialGoing 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×
“Potentially, larger and deeper convolutional neural networks could be applied to further improve classification performance [59], [60].”
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 1×
“This type of cascade classification is similar in spirit to our presented second tier deep classifier (ConvNet), but uses state-of-the-art shallow classifiers (libSVM [47] and sparse linear fusion via the Relevance Vector Machine [48]).”
ResultRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 1×
“Potentially allowing the ConvNet optimization to start from an initialization that is better than starting from Gaussian random parameters [57], [58].”
BackgroundBackpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · cited 2×
“Balancing between positive and negative training populations is generally beneficial for training ConvNets when optimizing with logistic regression cost [15], [14].”
BackgroundMethodTwo-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756 · cited 3×
“Likewise, the compositional two-stream 2D ConvNet models run on separate spatial (RGB) and temporal (i.e., optical flow field) video frames and achieve the mean accuracy of 87.9% in action classification task, based on a middle scale dataset UCF-101 [50].”
BackgroundInfluentialImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382 · cited 1×
“It is a variation of the previously suggested “DropOut” method [29], [30].”
MethodLarge-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 1×
“This result significantly outperforms the direct 3D “spatial-temporal” ConvNet method [51] at 65.”
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“Potentially allowing the ConvNet optimization to start from an initialization that is better than starting from Gaussian random parameters [57], [58].”
Background
Flagged first, then by citations
4 of the 60 references couldn’t be matched to a known paper.
Research works printed but not linked: 6
- wan, 2013, Regularization of neural networks using DropConnect, Proc Int Conf Mach Learn
- organization, 2014, Cancer Fact Sheet
- park, 2015, Polyp detection in colonoscopy videos using deeply-learned hierarchical features, Seoul nat'l univ
- 10.1007/978-3-319-14104-6_16 · DOI
- ciresan, 2012, Deep neural networks segment neuronal membranes in electron microscopy images, Adv Neural Inf Process Syst, 2843
- seff, 2014, MICCAI, 544
Cited by
Sorted by citations
Items 101–200 of 545
Evaluation of deep learning-based approaches for COVID-19 classification based on chest X-ray images
Kamal, K. C., Yin, Z., Wu, M., & Wu, Z. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-020-01820-2 · Cited by 111
Zhou, Z., Sodha, V., Pang, J., Gotway, M. B., & Liang, J. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101840 · Cited by 375
Bermejo-Peláez, D., Ash, S. Y., Washko, G. R., Estépar, R. S. J., & Ledesma‐Carbayo, M. J. (2020) · Scientific Reports · doi:10.1038/s41598-019-56989-5 · Cited by 101
Fernando, K. R. M., & Tsokos, C. P. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.12.013 · Cited by 90
“(2012) introduced multi-stream multi-scale architecture in natural images, and later the idea was implemented by several authors in the context of medical imaging (Roth et al., 2015; Setio et al., 2016; Kamnitsas et al., 2017c; Moeskops et al., 2016).”
BackgroundDeepTarget: Gross tumor and clinical target volume segmentation in esophageal cancer radiotherapy
Jin, D., Guo, D., Ho, T., Harrison, A. P., Xiao, J. Z., Tseng, C., & Lü, L. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101909 · Cited by 85
Self-citationDeep Learning: Current and Emerging Applications in Medicine and Technology
Akay, A. R., & Hess, H. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2894713 · Cited by 100
“tion and classification using CT image datasets [61], malignant tumor growth prediction [62], chemotherapy response prediction [63], a finger-joint detection platform to examine”
MethodMulti-scale gradual integration CNN for false positive reduction in pulmonary nodule detection
Kim, B.-C., Yoon, J. S., Choi, J.-S., & Suk, H. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.03.003 · Cited by 90
“[31] proposed a 2.5D CNN by taking three orthogonal 2D patches as input for volume-level feature representation.”
BackgroundMethodInfluentialProgress in Fully Automated Abdominal CT Interpretation
Summers, R. M. (2016) · American Journal of Roentgenology · doi:10.2214/ajr.15.15996 · Cited by 89
“Sensitivities for abdominopelvic and retroperitoneal lymphadenopathy are 80–83% at about three false-positives per volume [56, 59].”
BackgroundSelf-citationLi, H., Giger, M. L., Huynh, B. Q., & Antropova, N. O. (2017) · Journal of medical imaging · doi:10.1117/1.jmi.4.4.041304 · Cited by 87
Li, S., Xu, P., Li, B., Chen, L., Zhou, Z., Hao, H., Duan, Y., Folkert, M. R., Ma, J., Huang, S., et al. (2019) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ab326a · Cited by 88
An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural Networks
Xu, S., Liu, Y., Hu, W., Zhang, C., Liu, C., Zong, Y., Chen, S., Lu, Y., Yang, L., Ng, E. Y. K., et al. (2019) · IEEE Access · doi:10.1109/access.2019.2950286 · Cited by 98
Qiu, Z., Wang, S., Zeng, Z., & Yu, D. (2019) · Journal of Electronic Imaging · doi:10.1117/1.jei.28.4.043023 · Cited by 84
Ben-Cohen, A., Klang, E., Kerpel, A., Konen, E., Amitai, M., & Greenspan, H. K. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.10.001 · Cited by 79
Rühle, B., Krumrey, J. F., & Hodoroaba, V. (2021) · Scientific Reports · doi:10.1038/s41598-021-84287-6 · Cited by 68
Deep Residual Inception Encoder–Decoder Network for Medical Imaging Synthesis
Gao, F., Wu, T., Chu, X., Yoon, H., Xu, Y., & Patel, B. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2912659 · Cited by 75
“generalized areas: imaging-based classification [1]–[7], object detection [8]–[10], segmentation [11]–[14] and imaging synthesis [15]–[18].”
BackgroundLearning to Read Chest X-Ray Images from 16000+ Examples Using CNN
Dong, Y. C., Pan, Y., Zhang, J., & Xu, W. (2017) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1109/chase.2017.59 · Cited by 77
Breast mass classification via deeply integrating the contextual information from multi-view data
Wang, H., Feng, J., Zhang, Z., Su, H., Cui, L., He, H., & Liu, L. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.02.026 · Cited by 68
Chow, D. S., Chang, P. D., Weinberg, B. D., Bota, D. A., Grinband, J., & Filippi, C. G. (2017) · American Journal of Roentgenology · doi:10.2214/ajr.17.18754 · Cited by 73
“Nonetheless, early use of CNNs has yielded promising results in the detection of pulmonary nodules [62], colon cancer [63], and cerebral microbleeds [64].”
BackgroundConvolutional Invasion and Expansion Networks for Tumor Growth Prediction
Zhang, L., Lü, L., Summers, R. M., Kebebew, E., & Yao, J. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2774044 · Cited by 68
“In particular, deep convolutional neural networks (ConvNets) [17], [18] have significantly improved performance in a variety of traditional medical imaging applications [19], including lesion detection [20], anatomy segmentation [21], and pathology discrimination [22].”
BackgroundSelf-citation3D Fully Convolutional Networks for Intervertebral Disc Localization and Segmentation
Chen, H., Dou, Q., Wang, X., Qin, J., Cheng, J. C. Y., & Heng, P. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-43775-0_34 · Cited by 57
“Therefore, researchers attempted to deal with the 3D data by using several adaptations of 2D convolutional neural networks (CNNs) [4,10,11].”
BackgroundShi, G., Wang, J., Qiang, Y., Yang, X., Zhao, J., Hao, R., Yang, W., Du, Q., & Kazihise, N. G. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105611 · Cited by 69
A 3D Spatially Weighted Network for Segmentation of Brain Tissue From MRI
Sun, L., Ma, W., Ding, X., Huang, Y., Liang, D., & Paisley, J. W. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2937271 · Cited by 70
“Some previous work has taken advantage of such triplanar information [4], [27], [30].”
BackgroundAn enhanced multi-modal brain graph network for classifying neuropsychiatric disorders
Liu, L., Wang, Y., Wang, Y., Zhang, P., & Xiong, S. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102550 · Cited by 58
AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging
Yousefirizi, F., Decazes, P., Amyar, A., Ruan, S., Saboury, B., & Rahmim, A. (2021) · PET Clinics · doi:10.1016/j.cpet.2021.09.010 · Cited by 76
Karimi-Bidhendi, S., Arafati, A., Cheng, A. L., Wu, Y., Kheradvar, A., & Jafarkhani, H. (2020) · Journal of Cardiovascular Magnetic Resonance · doi:10.1186/s12968-020-00678-0 · Cited by 70
Tajbakhsh, N., Shin, J. Y., Gotway, M. B., & Liang, J. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101541 · Cited by 65
“Our image representation differs from the 2.5D approach in that it interpolates the volume according to the vessel axis rather than along random directions as in Roth et al. (2016, 2014).”
BackgroundMethodInfluentialClassification of breast lesions using cross-modal deep learning
Hadad, O., Bakalo, R., Ben‐Ari, R., Hashoul, S., & Amit, G. (2017) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2017.7950480 · Cited by 68
“In the medical imaging domain CNN have been reported useful in tasks such as abnormality detection [1], segmentation [2] and classification [3][4].”
MethodLee, J. H., Baek, J. H., Kim, J. H., Shim, W. H., Chung, S. R., Choi, Y. J., & Lee, J. H. (2018) · Thyroid · doi:10.1089/thy.2018.0082 · Cited by 74
“Therefore, we applied a data augmentation strategy to these images to ensure that our model would focus on the lymph nodes rather than noise (17).”
Lung cancer detection and classification with DGMM-RBCNN technique
Jena, S. R., George, S. T., & Ponraj, D. N. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06182-5 · Cited by 59
Alzheimer’s disease Classification from Brain MRI based on transfer learning from CNN
Khagi, B., Lee, C., & Kwon, G.-R. (2018) · Biomedical Engineering International Conference · doi:10.1109/bmeicon.2018.8609974 · Cited by 59
“Similarly, Hoo-Chang Shin et al. [11] tested CNN architecture for Lymph-Node detection and Interstitial Lung disease Classification, where they also tested pretrained CNN network (Alexnet, GoogLeNet and CifarNet [12]) and also used transfer learning technique from this CNN.”
MethodDeep convolutional networks for automated detection of posterior-element fractures on spine CT
Roth, H. R., Wang, Y., Yao, J.-H., Lu, L., Burns, J. E., & Summers, R. (2016) · SPIE Medical Imaging · doi:10.1117/12.2217146 · Cited by 59
Self-citationA hybrid CNN feature model for pulmonary nodule malignancy risk differentiation
Wang, H., Zhao, T., Li, L. C., Pan, H., Liu, W., Gao, H., Han, F., Wang, Y., Qi, Y., & Liang, Z. (2017) · Journal of X-Ray Science and Technology · doi:10.3233/xst-17302 · Cited by 68
“Roth et al. 2015 trained deep convolutional neural networks to be able to detect sclerotic spine metastases, lymph nodes, and colonic polyps and were able to increase sensitivity from 57% to 70%, 43% to 77%, and 58% to 75% for each task respectively [15].”
Wang, S., Shen, Y., Chen, W., Xiao, T., & Hu, J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68600-4_43 · Cited by 66
“[10] employed convolutional neural networks to improve three existing CAD systems for the recognition of colonic polyps on CT colonography, sclerotic spine metastases on body CT and enlarged lymph nodes on body CT.”
Texture analysis in radiology: Does the emperor have no clothes?
Summers, R. (2017) · Abdominal Radiology · doi:10.1007/s00261-016-0950-1 · Cited by 57
Self-citationHippocampus segmentation through multi-view ensemble ConvNets
Chen, Y., Shi, B., Wang, Z.-W., Zhang, P., Smith, C. D., & Liu, J.-D. (2017) · IEEE International Symposium on Biomedical Imaging · doi:10.1109/isbi.2017.7950499 · Cited by 56
“Several neural network based multi-view solutions [17, 18] have recently been developed to solve the ComputerAided Detection (CAD) problems.”
MethodSelf-citationAgnes, S. A., Anitha, J., & Solomon, A. A. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106059 · Cited by 56
Deep learning–based algorithm improved radiologists’ performance in bone metastases detection on CT
Noguchi, S., Nishio, M., Sakamoto, R., Yakami, M., Fujimoto, K., Emoto, Y., Kubo, T., Iizuka, Y., Nakagomi, K., Miyasa, K., et al. (2022) · European Radiology · doi:10.1007/s00330-022-08741-3 · Cited by 55
“From a technical point of view, the previous studies applied deep CNN in combination with traditional machine learning algorithms processing handcrafted image features [8, 14].”
BackgroundMethodZhi, W., Yueng, H. W. F., Chen, Z., Zandavi, S. M., Lu, Z., & Chung, Y. Y. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70093-9_71 · Cited by 74
Tango: A Deep Neural Network Benchmark Suite for Various Accelerators
Karki, A., Keshava, C. P., Shivakumar, S. M., Skow, J., Hegde, G. M., & Jeon, H. (2019) · IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) · doi:10.1109/ispass.2019.00021 · Cited by 53
“The proposed benchmark suite currently include CifarNet [12], [33], AlexNet [13], SqueezeNet [14], ResNet [15], and VGGNet [16] as CNNs and GRU [17] and LSTM [18] as RNNs.”
MethodKooi, T., & Karssemeijer, N. (2017) · Journal of medical imaging · doi:10.1117/1.jmi.4.4.044501 · Cited by 61
“5D simplification of volumetric scans.(40,48,49) In this paper, we extend previous work(50) and investigate the addition of symmetry and temporal information to a deep CNN with the purpose of detecting malignant soft tissue lesions in mammography.”
MethodAhmadian, H., Mageswaran, P., Walter, B. A., Blakaj, D. M., Bourekas, E. C., Mendel, E., Marras, W. S., & Soghrati, S. (2022) · International Journal for Numerical Methods in Biomedical Engineering · doi:10.1002/cnm.3601 · Cited by 54
“Classic data augmentation techniques for grayscale images typically involve image manipulations such as translation, rotation, scaling, flipping, random noise addition, and shearing.(68) In this work, transformations causing shape deformation such as shearing must be avoided during the augmentation process to preserve…”
Guy, A., Ben‐Ari, R., Hadad, O., Monovich, E., Granot, N., & Hashoul, S. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2249981 · Cited by 54
Deep feature learning for pulmonary nodule classification in a lung CT
Kim, B.-C., Sung, Y. S., & Suk, H. (2016) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2016.7457462 · Cited by 52
“, used Convolution Neural Network (CNN) [3], one of most widely used deep learning models, for nodule detection [4].”
MethodMulti-Scale and Multi-Direction GAN for CNN-Based Single Palm-Vein Identification
Qin, H., El‐Yacoubi, M. A., Li, Y., & Liu, C. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3059340 · Cited by 73
“Some works [53], [54] incorporate the multi-scale scheme into the GAN model to learn a robust feature representation from a coarse scale to a fine one.”
BackgroundMethodInfluentialGAN-Based Image Augmentation for Finger-Vein Biometric Recognition
Zhang, J., Lu, Z., Li, M., & Wu, H. (2019) · IEEE Access · doi:10.1109/access.2019.2960411 · Cited by 66
A Deep Learning Approach Towards Railway Safety Risk Assessment
Alawad, H., Kaewunruen, S., & An, M. (2020) · IEEE Access · doi:10.1109/access.2020.2997946 · Cited by 80
Identification of COPD From Multi-View Snapshots of 3D Lung Airway Tree via Deep CNN
Du, R., Qi, S., Feng, J., Xia, S., Kang, Y., Qian, W., & Yao, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2974617 · Cited by 63
“The common ways to transfer 3D to 2D include the combination of axial, coronal and sagittal images, several axial slices, several canonical CT slices [30], [56], [57].”
BackgroundMurakami, S., Hatano, K., Tan, J., Kim, H., & Aoki, T. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5449-4 · Cited by 58
“In the field of medical image, DCNN is applied to segmentation [5, 18, 20, 22], registration [17] and lesion identification [1, 4, 10, 23] and is expected to be utilized for CAD development.”
MethodWan, S., Lee, H.-C., Huang, X., Xu, T., Xu, T., Zeng, X., Zhang, Z., Sheikine, Y., Connolly, J., Fujimoto, J., et al. (2017) · Medical Image Anal. · doi:10.1016/j.media.2017.03.002 · Cited by 50
Ma, J., Yu, J., Liu, S., Chen, L., Li, X., Feng, J., Chen, Z., Zeng, S., Liu, X., & Cheng, S. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2980839 · Cited by 58
“Since the traditional manual screening is subjective and time-consuming, computer-aided diagnosis is gradually developed [2], [3].”
BackgroundMittal, A., Hooda, R., & Sofat, S. (2017) · IET Image Processing · doi:10.1049/iet-ipr.2016.0526 · Cited by 83
Image Augmentation-Based Food Recognition with Convolutional Neural Networks
Pan, L., Qin, J.-H., Chen, H., Xiang, X.-Y., Li, C., & Chen, R. (2019) · Computers Materials & Continua · doi:10.32604/cmc.2019.04097 · Cited by 47
Khachnaoui, H., Mabrouk, R., & Khlifa, N. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2020.1048 · Cited by 57
“CAD encompasses somputer-aided detection (CADe; detection) [72] and computeraided diagnosis (CADx: classification) [73] that aim to assist physicians interpreting medical imaging [71].”
BackgroundDeep model with Siamese network for viable and necrotic tumor regions assessment in osteosarcoma
Fu, Y., Xue, P., Ji, H., Cui, W., & Dong, E. (2020) · Medical Physics · doi:10.1002/mp.14397 · Cited by 55
Yuan, Y., Qin, W., Ibragimov, B., Zhang, G., Han, B., Meng, M. Q. ‐., & Xing, L. (2019) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2019.2936645 · Cited by 58
“The majority of existing deep learning algorithms for polyp recognition do not consider these problems [15], [16], [27], [37], [38].”
BackgroundDiscovery Radiomics for Pathologically-Proven Computed Tomography Lung Cancer Prediction
Kumar, D., Chung, A., Shafiee, M., Khalvati, F., Haider, M., & Wong, A. (2015) · International Conference on Image Analysis and Recognition · doi:10.1007/978-3-319-59876-5_7 · Cited by 46
Tu, X., Xie, M., Gao, J., Ma, Z., Chen, D.-Q., Wang, Q., Finlayson, S. G., Ou, Y., & Cheng, J. (2017) · Scientific Reports · doi:10.1038/s41598-017-08040-8 · Cited by 46
“In this study, we implemented two slice selection strategies: SINGLE and ALL 7 , with samples obtained in each case from transversal, coronal and sagittal views 35 .”
MethodKwon, J.-H., & Cho, G.-H. (2020) · Accident Analysis & Prevention · doi:10.1016/j.aap.2020.105716 · Cited by 45
Liang, S.-J., Thung, K., Nie, D., Zhang, Y., & Shen, D. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2975853 · Cited by 43
“Recently, deep convolutional neural networks (CNNs) have shown their outstanding performances in various medical image computing tasks [9]–[12].”
BackgroundZhi-hua, W., Yu, L., Ding, X., Liao, X., & Wang, L. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3171418 · Cited by 58
A Practical Guide to Artificial Intelligence–Based Image Analysis in Radiology
Weikert, T., Cyriac, J., Yang, S., Nešić, I., Parmar, V., & Stieltjes, B. (2019) · Investigative Radiology · doi:10.1097/rli.0000000000000600 · Cited by 53
Artificial Intelligence in Musculoskeletal Imaging: A Paradigm Shift
Burns, J. E., Yao, J., & Summers, R. M. (2019) · Journal of Bone and Mineral Research · doi:10.1002/jbmr.3849 · Cited by 62
Self-citationHussein, I. J., Burhanuddin, M. A., Mohammed, M. A., Benameur, N., Maashi, M. S., & Maashi, M. S. (2021) · Expert Systems · doi:10.1111/exsy.12789 · Cited by 35
Zhou, W., Jian, W., Cen, X., Zhang, L., Guo, H., Liu, Z., Liang, C., & Wang, G. (2021) · Frontiers in Oncology · doi:10.3389/fonc.2021.588010 · Cited by 44
“Data augmentation used the image resampling method (27) to extract more 3D samples from the current limited tumor sample area.”
MethodLei, W., Mei, H., Sun, Z., Ye, S., Gu, R., Wang, H., Huang, R., Zhang, S., Zhang, S., & Wang, G. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.01.135 · Cited by 38
“Thirdly, applying 2.5D network [35, 36], which firstly use 2D convolu-tions separately in three orthogonal views and fuse these multi-view information together in final stage, so that 3D contextual features can be used.”
MethodKhachnaoui, H., Khlifa, N., & Mabrouk, R. (2022) · Journal of Imaging · doi:10.3390/jimaging8040097 · Cited by 40
Machine learning-enabled multiplexed microfluidic sensors
Dabbagh, S. R., Rabbi, F., Doğan, Z., Yetisen, A. K., & Taşoğlu, S. (2020) · Biomicrofluidics · doi:10.1063/5.0025462 · Cited by 43
Cao, H., Liu, H., Song, E., Ma, G., Xu, X., Jin, R., Liu, T., & Hung, C. (2019) · IEEE Access · doi:10.1109/access.2019.2906116 · Cited by 43
Mubarak, A. S., Serte, S., Al‐Turjman, F., Ameen, Z. S., & Özsöz, M. (2021) · Expert Systems · doi:10.1111/exsy.12842 · Cited by 47
“Due to the limited number of datasets, limited datasets prove to be the most challenging problem in the medical imaging domain (Greenspan, 2016; Roth et al., 2015; Tajbakhsh et al., 2016).”
BackgroundDeep Learning Protein Conformational Space with Convolutions and Latent Interpolations
Ramaswamy, V. K., Musson, S. C., Willcocks, C. G., & Degiacomi, M. T. (2021) · Physical Review X · doi:10.1103/physrevx.11.011052 · Cited by 42
3D Neuron Microscopy Image Segmentation via the Ray-Shooting Model and a DC-BLSTM Network
Jiang, Y. H., Chen, W., Liu, M., Wang, Y., & Meijering, E. H. W. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3021493 · Cited by 45
“In [19], the 2.5D CNN was used to segment sclerotic, lymph node and colonic polyps.”
MethodKhagi, B., Lee, B., Pyun, J.-Y., & Kwon, G.-R. (2019) · International Conference on Electronics, Information and Communications · doi:10.23919/elinfocom.2019.8706339 · Cited by 38
“Interstitial Lung disease Classification, where they also tested pretrained CNN network (Alexnet, GoogLeNet and CifarNet [7]) and also used transfer learning technique from this CNN.”
MethodDeep Convolutional Neural Network for Image Classification on CUDA Platform
Gavali, P. R., & Banu, J. S. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-816718-2.00013-0 · Cited by 48
Generative adversarial U-Net for domain-free few-shot medical diagnosis
Chen, X., Li, Y., Yao, L., Adeli, E., Zhang, Y., & Wang, X. (2022) · Pattern Recognition Letters · doi:10.1016/j.patrec.2022.03.022 · Cited by 37
A Bottom-Up Review of Image Analysis Methods for Suspicious Region Detection in Mammograms
Oza, P. R., Sharma, P., Patel, S., & Bruno, A. (2021) · Journal of Imaging · doi:10.3390/jimaging7090190 · Cited by 54
Decoding Brain States From fMRI Signals by Using Unsupervised Domain Adaptation
Gao, Y., Zhang, Y., Cao, Z., Guo, X., & Zhang, J. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2940695 · Cited by 38
“In the area of medical image analysis, researchers have applied the DTL methods to computer-aided detection [32], [33] and image segmentation [27], [34], but rarely used for neural decoding.”
MethodSuresh, S., & Mohan, S. (2019) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2019.11.013 · Cited by 42
“But the process is time consuming and complicated (Roth et al., 2016).”
Tahir, M., Norouzi, M., Khan, S. S., Davie, J., Yamanaka, S., & Ashraf, A. B. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109302 · Cited by 50
“CNNs constitute a prominent class of DL neural network architecture which have proven to be highly effective in various fields such as computer vision, image processing, natural language processing, and bioinformatics [82, 83, 84, 85].”
Zhu, Z., Jin, D., Yan, K., Ho, T., Ye, X., Guo, D., Chao, C.-H., Xiao, J. Z., Yuille, A., & Lü, L. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59728-3_73 · Cited by 32
“with large amounts of smaller ones that are harder to detect. Refer Fig. 1 (top row) for an illustration of GTV LN. While many previous works attempt to detect enlarged LNs using contrast-enhanced CT [1,2,4,11,12,13,18], no work, as of yet, has studied the GTV LN detection in non-contrast RTCT scans. Given the evident…”
BackgroundSelf-citationUsing Convolutional Neural Networks and Transfer Learning for Bone Age Classification
Zhou, J.-L., Li, Z., Zhi, W., Liang, B., Moses, D., & Dawes, L. C. (2017) · International Conference on Digital Image Computing: Techniques and Applications · doi:10.1109/dicta.2017.8227503 · Cited by 35
“[19] generated twodimensional (2D) or 2.”
Koh, F. H.-X., Ladlad, J., Foo, F. J., Tan, W. J., Sivarajah, S. S., Ho, L. M. L., Ng, J.-L., Koh, F. H.-X., Chong, C. Z., Aw, D. K. L., et al. (2022) · Surgical Endoscopy · doi:10.1007/s00464-022-09470-w · Cited by 39
Karri, M., Annavarapu, C. S. R., Mallik, S., Zhao, Z., & Acharya, U. R. (2022) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2022.06.003 · Cited by 37
Chen, S., Han, Y., Lin, J., Zhao, X., & Kong, P. (2020) · Artif. Intell. Medicine · doi:10.1016/j.artmed.2020.101881 · Cited by 34
Bag of deep features for preoperative prediction of sentinel lymph node metastasis in breast cancer
Luo, J., Ning, Z., Zhang, S., Feng, Q., & Zhang, Y. (2018) · Physics in Medicine and Biology · doi:10.1088/1361-6560/aaf241 · Cited by 40
“Between convolution layers, pooling operation is performed to summarize the feature responses across adjacent pixels (Roth et al 2016) and the crucial information, which realizes the reduction of feature numbers and achieves translation, rotation, and scale invariance, is selected.”
BackgroundRecurrent Convolutional Networks for Pulmonary Nodule Detection in CT ImagingPreprint
Ypsilantis, P.-P., & Montana, G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.09143 · Cited by 36
Ji, Z., Guo, D., Wang, P., Yan, K., Lü, L., Xu, M., Wang, Q., Ge, J., Gao, M., Ye, X., et al. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01933 · Cited by 30
Self-citationPelka, O., Nensa, F., & Friedrich, C. M. (2018) · PLoS ONE · doi:10.1371/journal.pone.0206229 · Cited by 34
Zhang, J., Li, S., & Wang, R. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00310 · Cited by 38
“According to Roth et al. (2015), this parameter setting can enhance the performance of each CNN model.”
BackgroundDeep convolutional neural network in medical image processing
Mohapatra, S., Swarnkar, T., & Das, J. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-823014-5.00006-5 · Cited by 54
Asaturyan, H. A., Глигориевски, А., & Villarini, B. (2019) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2019.04.004 · Cited by 39
“…anatomical knowledge relating to abdominal organs, in combination with radiological learning networks suffer from overfitting (Qi et al., 2016; Roth et al., 2016) and would require more training data, recent publications suggest that data augmentation and 3D convolutional neural network…”
A deep learning approach for pose estimation from volumetric OCT data
Gessert, N., Schlüter, M., & Schlaefer, A. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.03.002 · Cited by 33
Chen, H., Wu, X. Y., Gan, T., & Peng, Q. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.06.077 · Cited by 30
“to different computer-aided detection scenarios in [34], such as sclerotic metastases, lymph node and colonic polyp.”
BackgroundJin, D., Guo, D., Ge, J., Ye, X., & Lü, L. (2022) · Journal of the National Cancer Center · doi:10.1016/j.jncc.2022.09.003 · Cited by 27
Self-citationZhang, L., Gooya, A., Pereañez, M., Dong, B., Piechnik, S. K., Neubauer, S., Petersen, S. E., & Frangi, A. F. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2881952 · Cited by 33
“[24] and Prasoon et al.”
A pilot study using kernelled support tensor machine for distant failure prediction in lung SBRT
Li, S., Yang, N., Li, B., Zhou, Z., Hao, H., Folkert, M. R., Iyengar, P., Westover, K. D., Choy, H., Timmerman, R. D., et al. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.09.004 · Cited by 33
Ozdemir, O., Woodward, B., & Berlin, A. A. (2017) · arXiv · doi:10.48550/arxiv.1712.00497 · Cited by 30
Lou, J., Xu, J., Zhang, Y., Sun, Y., Fang, A., Liu, J., Mur, L. A. J., & Ji, B. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107095 · Cited by 27
Self-citationMulti-projection deep learning network for segmentation of 3D medical images
Indraswari, R., Kurita, T., Arifin, A. Z., Suciati, N., & Astuti, E. R. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.08.003 · Cited by 35
Deep learning for biomarker regression: application to osteoporosis and emphysema on chest CT scans
González, G., Washko, G. R., & Estépar, R. S. J. (2018) · SPIE Medical Imaging: Image Processing · doi:10.1117/12.2293455 · Cited by 36
Ashokkumar, N., Meera, S., Anandan, P., Murthy, M. Y. B., Kalaivani, K. S., Alahmadi, T. A., Alharbi, S. A., Raghavan, S. S., & Jayadhas, S. A. (2022) · BioMed Research International · doi:10.1155/2022/8616535 · Cited by 34
“areas instead of random noise sources [40].”
Retracted
Metadata
- Authors
- Roth, H. R., Lu, L., Liu, J., Yao, J., Seff, A., Cherry, K., Kim, L., & Summers, R. M.
- Affiliations
- National Institutes of Health Clinical Center (US)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2016-05
- Volume
- 35
- Issue
- 5
- Pages
- 1170-1181
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- PMC
- PMC7340334
- OpenAlex
- W1871050032
- Cited by
- 608
- References
- 60
- Citations by year
- 2026: 14 · 2025: 19 · 2024: 35 · 2023: 34 · 2022: 72 · 2021: 101 · 2020: 88 · 2019: 84 · 2018: 71 · 2017: 62 · 2016: 27
- FWCI
- 52.62
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (public-domain)
- Funders
- National Institutes of Health
- NIH Clinical Center (Z01CL040004, Z01CL040003)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- computer-aided detection, false positive reduction, convolutional neural networks, lymph node detection, colorectal polyp detection, scale transformation
- MeSH terms
- Machine Learning, Adolescent, Adult, Aged, Child, Colonic Polyps, Female, Humans, Lymph Nodes, Male, Middle Aged, Radiographic Image Interpretation, Computer-Assisted, Spinal Neoplasms, Tomography, X-Ray Computed, Databases, Factual, Neural Networks, Computer, Young Adult
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
