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
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
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
“The incorpora- ion of contextual or 3D information is also handled using multi- tream CNNs ( Section 2.4.2 , for example by Barbu et al., 2016 and oth et al., 2016b ).”
MethodInfluentialShin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759
Self-citationDeep learning in medical image analysis
Shen, D., Wu, G., & Suk, H.-I. (2017) · Annual Review of Biomedical Engineering · doi:10.1146/annurev-bioeng-071516-044442 · Cited by 4,968
“…generating samples via affine transformation (i.e., data augmentation) and then train their network from scratch with the augmented dataset (35, 36, 37, 38); (iii) to use deep models trained over a huge number of natural images in computer vision as ‘off-the-shelf’ feature extractor and then…”
MethodOpportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
Deep Learning for Health Informatics
Ravì, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., & Yang, G.-Z. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2636665 · Cited by 2,000
“Implicit features could determine fibroids and polyps [1], and characterize irregularities in tissue morphology such as tumors [2].”
BackgroundFrid-Adar, M., Diamant, I., Klang, E., Amitai, M. M., Goldberger, J., & Greenspan, H. K. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.09.013 · Cited by 2,055
“T HE greatest challenge in the medical imaging domain is how to cope with the small datasets and limited amount of annotated samples [1]–[5], especially when employing supervised machine learning algorithms that require labeled data and larger training examples.”
BackgroundMethodDeep learning in bioinformatics
Min, S., Lee, B., & Yoon, S. (2016) · Briefings in Bioinformatics · doi:10.1093/bib/bbw068 · Cited by 1,571
“[125] applied CNNs to three different CT image datasets to classify sclerotic metastases, lymph nodes and colonic polyps.”
MethodDeep Learning Applications in Medical Image Analysis
Ker, J., Wang, L., Rao, J. P., & Lim, C. C. T. (2017) · IEEE Access · doi:10.1109/access.2017.2788044 · Cited by 1,574
Medical image analysis using convolutional neural networks: a review
Anwar, S. M., Majid, M., Qayyum, A., Awais, M., Alnowami, M., & Khan, M. K. (2018) · Journal of Medical Systems · doi:10.1007/s10916-018-1088-1 · Cited by 1,431
“The study presented in [98] aims at improving computer aided detection using a CNN and random view generation.”
MethodZhou, S. K., Greenspan, H. K., Davatzikos, C. A., Duncan, J. S., van Ginneken, B., Madabhushi, A., Prince, J. L., Rueckert, D., & Summers, R. M. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3054390 · Cited by 1,373
“Studies have assessed abdominal lymph nodes on CT in general and for specific diseases, such as prostate cancer [35], [199], [200].”
BackgroundSelf-citationDeep Learning: A Primer for Radiologists
Chartrand, G., Cheng, P. M., Vorontsov, E., Drozdzal, M., Turcotte, S., Pal, C. J., Kadoury, S., & Tang, A. (2017) · RadioGraphics · doi:10.1148/rg.2017170077 · Cited by 1,115
Recent advances and clinical applications of deep learning in medical image analysis
Chen, X., Wang, X., Zhang, K., Fung, K.-M. A., Thai, T., Moore, K. N., Mannel, R. S., Liu, H., Zheng, B., & Qiu, Y. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102444 · Cited by 1,180
Road crack detection using deep convolutional neural network
Zhang, L., Yang, F., Zhang, Y. D., & Zhu, Y. J. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7533052 · Cited by 1,655
“Inspired by the method proposed in [11], the probability of a point can be calculated by averaging probability {P1, .”
MethodGreenspan, H. K., van Ginneken, B., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2553401 · Cited by 1,725
“, [13] axial, coronal and sagittal images were taken centered on a voxel in a colonic polyp or lymph node candidate and fed into the cudaconvnet CNN, which incorporates three channels normally used to represent the red, green and blue color channels of a natural light image.”
MethodSelf-citationMR-based synthetic CT generation using a deep convolutional neural network method
Han, X. (2017) · Medical Physics · doi:10.1002/mp.12155 · Cited by 890
Cheng, J.-Z., Ni, D., Chou, Y.-H., Qin, J., Tiu, C.-M., Chang, Y.-C., Huang, C.-S., Shen, D., & Chen, C.-M. (2016) · Scientific Reports · doi:10.1038/srep24454 · Cited by 755
“In the context of CAD, most works focused on the problem of abnormality detection (CADe) 36–38 .”
BackgroundApplications of deep learning and reinforcement learning to biological data
Mahmud, M., Kaiser, M. S., Hussain, A., & Vassanelli, S. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2790388 · Cited by 765
“76]) in detecting colon polyp from CT colonographs [137].”
BackgroundMethodDeep learning in medical imaging and radiation therapy
Sahiner, B., Pezeshk, A. X., Hadjiiski, L. M., Wang, X., Drukker, K., Cha, K. H., Summers, R. M., & Giger, M. L. (2018) · Medical Physics · doi:10.1002/mp.13264 · Cited by 763
“166,168 More recently, 3D CNNs that use 3D convolution kernels are successfully replacing 2D CNNs for volumetric data.”
BackgroundSelf-citationAutomatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks
Dou, Q., Chen, H., Yu, L., Zhao, L., Qin, J., Wang, D., Mok, V. C., Shi, L., & Heng, P.-A. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528129 · Cited by 679
“Most previous approaches adapted 2D CNNs for processing 3D volumetric data [18], [45], [46], with difficulties being reported when attempting to employ 3D CNNs.”
MethodCovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
Waheed, A., Goyal, M., Gupta, D. K., Khanna, A. K., Al-Turjman, F., & Pinheiro, P. R. (2020) · IEEE Access · doi:10.1109/access.2020.2994762 · Cited by 779
“With limited quantity and variety of samples, the biggest challenge in the medical imaging domain is small datasets [5]–[7].”
BackgroundGiger (2018) · doi:10.1016/j.jacr.2017.12.028 · Cited by 634
Yan, K., Wang, X., Lu, L., & Summers, R. M. (2018) · Journal of medical imaging · doi:10.1117/1.jmi.5.3.036501 · Cited by 573
“7 – 9 Instead, they reflect the relative performance of different types and sizes.”
BackgroundResultSelf-citationMazurowski, M. A., Buda, M., Saha, A., & Bashir, M. R. (2019) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.26534 · Cited by 554
“thors performed detection of 3D anatomy in chest CT images by processing data slice by slice in one direction. Combining output from dierent planes was performed in several studies. Most of the them [102, 103, 104] used orthogonal planes of MRI and CT images performing detection in each direction separately. The resul…”
MethodRoad Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding
Fan, R., Bocus, M. J., Zhu, Y., Jiao, J., Wang, L., Ma, F., Cheng, S., & Liu, M. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8814000 · Cited by 247
“Furthermore, some machine learning-based crack detection approaches [30]–[35] have been proposed in recent years, and the features produced by neural network are very likely to replace the local features utilized in traditional”
BackgroundFang, L., Cunefare, D., Wang, C., Guymer, R. H., Shutao Li, A., & Farsiu, S. (2017) · Biomedical Optics Express · doi:10.1364/boe.8.002732 · Cited by 484
“In this paper, we use a modified Cifar-CNN [38,57] architecture.”
MethodDeepPap: Deep Convolutional Networks for Cervical Cell Classification
Zhang, L., Lu, L., Nogues, I., Summers, R. M., Liu, S., & Yao, J. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2705583 · Cited by 520
“They have also significantly improved performance in a variety of medical imaging applications [33], [34], such as classification of lung diseases and lymph nodes in CT images [35], [36], segmentation (pixel classification) of brain tissues [37] in MRI, vessel segmentation [38] in fundus images, and detecting cervical…”
BackgroundMethodSelf-citationBreast cancer detection using deep convolutional neural networks and support vector machines
Ragab, D., Sharkas, M., Marshall, S., & Ren, J.-C. (2019) · PeerJ · doi:10.7717/peerj.6201 · Cited by 438
“There are many CNN architectures such as CiFarNet ( Krizhevsky, 2009 ; Roth et al., 2016 ), AlexNet ( Krizhevsky, Sutskever & Hinton, 2012 ), GoogLeNet ( Szegedy et al., 2015 ), The AlexNet architecture achieved significantly better performance over the other deep learning methods for ImageNet…”
MethodArtificial intelligence in oncology
Shimizu, H., & Nakayama, K. I. (2020) · Cancer Science · doi:10.1111/cas.14377 · Cited by 388
Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas
Chang, P. D., Grinband, J., Weinberg, B. D., Bardis, M. D., Khy, M., Cadena, G., Su, M., Cha, S., Filippi, C. G., Bota, D. A., et al. (2018) · American Journal of Neuroradiology · doi:10.3174/ajnr.a5667 · Cited by 476
“24-26 Recent use of CNNs has started to yield promising results in multiple medical imaging disciplines, including the detection of pulmonary nodules, 27 colon cancer, 28 and cerebral microbleeds.”
BackgroundLymph Node Metastasis Prediction from Primary Breast Cancer US Images Using Deep Learning
Zhou, L.-Q., Wu, X.-L., Huang, S.-Y., Wu, G.-G., Ye, H.-R., Wei, Q., Bao, L.-Y., Deng, Y.-B., Li, X.-R., Cui, X.-W., et al. (2020) · Radiology · doi:10.1148/radiol.2019190372 · Cited by 384
A deep learning framework for supporting the classification of breast lesions in ultrasound images
Han, S., Kang, H.-K., Jeong, J.-Y., Park, M.-H., Kim, W., Bang, W.-C., & Seong, Y.-K. (2017) · Physics in Medicine & Biology · doi:10.1088/1361-6560/aa82ec · Cited by 358
“problem of abnormality detection (CADe)[56, 57, 58].”
Deep learning in drug discovery: opportunities, challenges and future prospects
Lavecchia, A. (2019) · Drug Discovery Today · doi:10.1016/j.drudis.2019.07.006 · Cited by 353
Focus: Querying Large Video Datasets with Low Latency and Low CostPreprint
Hsieh, K., Ananthanarayanan, G., Bodík, P., Venkataraman, S., Bahl, P., Philipose, M., Gibbons, P. B., & Mutlu, O. (2018) · USENIX Symposium on Operating Systems Design and Implementation · doi:10.48550/arxiv.1801.03493 · Cited by 313
“, [57, 72]), information decoding in biomedical signal recordings (e.”
BackgroundShafique, S., & Tehsin, S. (2018) · Technology in Cancer Research and Treatment · doi:10.1177/1533033818802789 · Cited by 311
“So lot of groups in medical imaging deployed DCNNs and they were able to achieve good accuracy.(10-15) As per our knowledge for leukemia detection only, Vogado et al(16) investigated a pretrained CNN for the features extraction and used ensemble classifiers for classification of normal and blast cells.”
MethodSurvey on deep learning for radiotherapy
Meyer, P., Noblet, V., Mazzara, C., & Lallement, A. (2018) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2018.05.018 · Cited by 302
Moon, W. K., Lee, Y., Ke, H.-H., Lee, S. H., Huang, C., & Chang, R. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105361 · Cited by 329
Designing deep learning studies in cancer diagnostics
Kleppe, A., Skrede, O.-J., Raedt, S. D., Liestøl, K., Kerr, D. J., & Danielsen, H. E. (2021) · Nature reviews. Cancer · doi:10.1038/s41568-020-00327-9 · Cited by 328
Classification of teeth in cone-beam CT using deep convolutional neural network
Miki, Y., Muramatsu, C., Hayashi, T., Zhou, X.-R., Hara, T., Katsumata, A., & Fujita, H. (2017) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2016.11.003 · Cited by 301
A deep feature based framework for breast masses classification
Jiao, Z., Gao, X., Wang, Y., & Li, J. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.02.060 · Cited by 308
“According to the successful application of [60] on medical image and followed the diagnosis habits of the radiologist who we consulted from, instances we applied had been rotated angles of 90 ° , 180 ° , 270 ° to enlarge the dataset 3 times.”
MethodLiterature review: efficient deep neural networks techniques for medical image analysis
Abdou, M. A. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-06960-9 · Cited by 341
“New features can lead to missing information within the first stage and thus could lead to a better classification; FPs could be then reduced to the minimum extent [30].”
BackgroundRoth, H. R., Lu, L., Lay, N., Harrison, A. P., Farag, A., Sohn, A., & Summers, R. M. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.01.006 · Cited by 325
Self-citationAubreville, M., Knipfer, C., Oetter, N., Jaremenko, C., Rodner, E., Denzler, J., Bohr, C., Neumann, H., Stelzle, F., & Maier, A. (2017) · Scientific Reports · doi:10.1038/s41598-017-12320-8 · Cited by 345
FUIQA: Fetal Ultrasound Image Quality Assessment with Deep Convolutional Networks
Wu, L., Cheng, J.-Z., Li, S., Lei, B., Wang, T., & Ni, D. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2671898 · Cited by 242
Saba, T. (2020) · Journal of Infection and Public Health · doi:10.1016/j.jiph.2020.06.033 · Cited by 298
Disease Staging and Prognosis in Smokers Using Deep Learning in Chest Computed Tomography
González, G., Ash, S. Y., Vegas‐Sánchez‐Ferrero, G., Onieva, J. O., Rahaghi, F. N., Ross, J. C., Díaz, A. A., Estépar, R. S. J., & Washko, G. R. (2017) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/rccm.201705-0860oc · Cited by 285
Generating high-fidelity synthetic patient data for assessing machine learning healthcare software
Tucker, A., Wang, Z., Rotalinti, Y., & Myles, P. R. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00353-9 · Cited by 257
Liang, G., Hong, H., Xie, W., & Zheng, L. (2018) · IEEE Access · doi:10.1109/access.2018.2846685 · Cited by 291
“They also significantly improve the performance of various medical imaging applications [30], [31], such as classification of lung diseases and lymph nodes in CT images [32], [33], segmentation (pixel classification) of brain tissues in MRI [34], vessel segmentation based on fundus images [37], and detecting cervical…”
BackgroundDeep learning based classification of breast tumors with shear-wave elastography
Zhang, Q., Xiao, Y., Dai, W., Suo, J., Wang, C., Shi, J., & Zheng, H. (2016) · Ultrasonics · doi:10.1016/j.ultras.2016.08.004 · Cited by 240
Fully Convolutional Network for Liver Segmentation and Lesions Detection
Ben-Cohen, A., Diamant, I., Klang, E., Amitai, M. M., & Greenspan, H. K. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46976-8_9 · Cited by 241
“CNN has been used for detection in several medical applications including pulmonary nodule [10], sclerotic metastases, lymph node and colonic polyp [8] and liver tumours [6].”
MethodGenerative Adversarial Network for Medical Images (MI-GAN)
Iqbal, T., & Ali, H. (2018) · Journal of Medical Systems · doi:10.1007/s10916-018-1072-9 · Cited by 267
Asaoka, R., Murata, H., Hirasawa, K., Fujino, Y., Matsuura, M., Miki, A., Kanamoto, T., Ikeda, Y., Mori, K., Iwase, A., et al. (2018) · American Journal of Ophthalmology · doi:10.1016/j.ajo.2018.10.007 · Cited by 255
Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats
Napel, S. A., Mu, W., Jardim‐Perassi, B. V., Aerts, H. J. W. L., & Gillies, R. J. (2018) · Cancer · doi:10.1002/cncr.31630 · Cited by 235
“…from the 3D medical images, information from 2D patches of the 3 orthogonal views (axial, sagittal, and coronal) can be used, which is a method referred to as 2.5D. 115 These 3 views can be inputted into existing CNNs trained on 3 channels (often the red-green-blue channels of natural images).”
MethodArtificial Intelligence and Acute Stroke Imaging
Soun, J. E., Chow, D. S., Nagamine, M., Takhtawala, R. S., Filippi, C. G., Yu, W., & Chang, P. D. (2020) · American Journal of Neuroradiology · doi:10.3174/ajnr.a6883 · Cited by 308
“12 CNNs have already shown promise in the detection of pulmonary nodules, 13 colon cancer, 14 and cerebral microbleeds.”
BackgroundWang, H., Zhou, Z., Li, Y., Chen, Z., Lu, P., Wang, W., Liu, W., & Yu, L. (2017) · EJNMMI Research · doi:10.1186/s13550-017-0260-9 · Cited by 276
Sun, W., Zheng, B., & Qian, W. (2017) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2017.04.006 · Cited by 227
Deep Learning and Convolutional Neural Networks for Medical Image Computing
Lu, L., Zheng, Y., Carneiro, G., & Yang, L. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-42999-1 · Cited by 208
“There are also several extensions from the decompositional view representation [27, 28], such as using a novel vessel-alignedmulti-planar image representation for pulmonary embolismdetection [29], fusing unregisteredmultiview for mammogram analysis [16], and classifying pulmonary perifissural nodules via an ensemble o…”
BackgroundMethodInfluentialSelf-citationLeger, S., Zwanenburg, A., Pilz, K., Lohaus, F., Linge, A., Zöphel, K., Kotzerke, J., Schreiber, A., Tinhofer, I., Budach, V., et al. (2017) · Scientific Reports · doi:10.1038/s41598-017-13448-3 · Cited by 217
“The application of CNNs have already showed promising results in the medical imaging domain 37 such as image segmentation 38 or lesion detection 39 .”
MethodGuo, S., Zhang, B., Yang, T., Lyu, D., & Gao, W. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2942548 · Cited by 225
“With great successes of CNN in image recognition [9], object detection [10], action recognition [11], and disease diagnosis [12], CNN is also widely used in fault diagnosis.”
BackgroundSpatio-temporal deep learning method for ADHD fMRI classification
Mao, Z., Su, Y., Xu, G., Wang, X., Huang, Y., Yue, W., Sun, L., & Xiong, N. N. (2019) · Information Sciences · doi:10.1016/j.ins.2019.05.043 · Cited by 196
3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training
Xia, Y., Liu, F., Yang, D., Cai, J., Yu, L., Zhu, Z., Xu, D., Yuille, A., & Roth, H. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093608 · Cited by 170
“Moreover, [33, 41] illustrates the effectiveness of multiview training on 2D slices, even by simply averaging multiplanar results, indicating complementary latent information exists in the biases of 2D networks.”
BackgroundSelf-citationZhang, R., Zheng, Y., Poon, C. C. Y., Shen, D. G., & Lau, J. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.05.026 · Cited by 182
“The algorithm will be useful to the emerging therapeutic wireless endoscopic capsules [38], or to integrate with classifier that judges whether a polyp should be resected or not [15].”
BackgroundMethodInterpretation and visualization techniques for deep learning models in medical imaging
Huff, D. T., Weisman, A. J., & Jeraj, R. (2021) · Physics in Medicine & Biology · doi:10.1088/1361-6560/abcd17 · Cited by 172
Iakovidis, D. K., Georgakopoulos, S. V., Vasilakakis, M. D., Koulaouzidis, A., & Plagianakos, V. P. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2837002 · Cited by 199
“classifiers, trained using image patches [8], [11]–[13], [27], [28], [31]–[34] and as weakly-supervised classifiers trained”
MethodTajbakhsh, N., & Suzuki, K. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.09.029 · Cited by 170
Deep learning workflow in radiology: a primer
Montagnon, E., Cerny, M., Cadrin-Chênevert, A., Hamilton, V., Derennes, T., Ilinca, A. P., Vandenbroucke‐Menu, F., Turcotte, S., Kadoury, S., & Tang, A. (2020) · Insights into Imaging · doi:10.1186/s13244-019-0832-5 · Cited by 189
“In abdominal radiology, deep learning has been applied to diverse tasks [3], organs [5, 6], and pathologies [7 – 9].”
MethodArtificial intelligence in oral and maxillofacial radiology: what is currently possible?
Heo, M.-S., Kim, J., Hwang, J. J., Han, S., Kim, J.-S., Yi, W.-J., & Park, I.-W. (2020) · Dentomaxillofacial Radiology · doi:10.1259/dmfr.20200375 · Cited by 190
Exploring Deep Learning and Transfer Learning for Colonic Polyp Classification
Ribeiro, E. F., Uhl, A., Wimmer, G., & Häfner, M. (2016) · Computational and Mathematical Methods in Medicine · doi:10.1155/2016/6584725 · Cited by 169
“Additionally, recent studies show the potential of the knowledge transfer between natural and medical images using pretrained (off-the-shelf) CNNs [34, 46]. important object of research in clinical decision support system area.”
BackgroundNishio, M., Sugiyama, O., Yakami, M., Ueno, S., Kubo, T., Kuroda, T., & Togashi, K. (2018) · PLoS ONE · doi:10.1371/journal.pone.0200721 · Cited by 170
Using deep learning techniques in medical imaging: a systematic review of applications on CT and PET
Domingues, I., Pereira, G. C., Martins, P., Duarte, H., Santos, J. A. M., & Abreu, P. H. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-019-09788-3 · Cited by 176
Machine learning and deep learning methods that use omics data for metastasis prediction
Albaradei, S., Thafar, M. A., Alsaedi, A., Neste, C. V., Gojobori, T., Essack, M., & Gao, X. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.09.001 · Cited by 167
“Some methods incorporated clinicopathological-based features [20–22], other methods incorporated image-based features [23– 25] or text-based features [26], while the more recent methods incorporate omics-based data as features.”
MethodDas, N., Hussain, E., & Mahanta, L. B. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.05.003 · Cited by 171
Bhati, D., Neha, F., & Amiruzzaman, M. (2024) · Journal of Imaging · doi:10.3390/jimaging10100239 · Cited by 177
“In medical imaging, filter visualization compares filters in Computer-Aided Detection (CAD) for 3D Computed Tomography (CT) images [9].”
MethodDeep learning and its application to medical image segmentation
Roth, H. R., Shen, C., Oda, H., Oda, M., Hayashi, Y., Misawa, K., & Mori, K. (2018) · arXiv.org · doi:10.11409/mit.36.63 · Cited by 136
“A few examples in radiology are anatomy classification [10], [11], false-positives reduction for computer-aided detection of lymph nodes or colonic polyps [12], the detection of pulmonary nodules [13], and the detection of pulmonary embolisms [14].”
BackgroundSelf-citation3D Context Enhanced Region-Based Convolutional Neural Network for End-to-End Lesion Detection
Yan, K., Bagheri, M. H., & Summers, R. M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00928-1_58 · Cited by 110
“Some researchers trained classifiers on the aggregation of multiple 2D slices (e.g. three orthogonal views (2.5D) or random views of the candidate lesion) for FPR [9].”
BackgroundMethodSelf-citationIslam, M. M. M., & Kim, J.-M. (2019) · Sensors · doi:10.3390/s19194251 · Cited by 142
“Recently, Zhang et al. [26] used a fully convolutional network with a residual network as a backbone for concrete surface crack detection.”
BackgroundSemantic Segmentation of Pathological Lung Tissue With Dilated Fully Convolutional Networks
Anthimopoulos, M., Christodoulidis, S., Ebner, L., Geiser, T., Christe, A., & Mougiakakou, S. G. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2818620 · Cited by 155
“5D, [46].”
Hamraz, H., Jacobs, N., Contreras, M. A., & Clark, C. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.10.011 · Cited by 122
Xu, L., Tetteh, G., Lipková, J., Zhao, Y. S., Li, H., Christ, P. F., Piraud, M., Buck, A. K., Shi, K., & Menze, B. H. (2018) · Contrast Media & Molecular Imaging · doi:10.1155/2018/2391925 · Cited by 127
“They have already demonstrated advantages in computerized diagnosis on medical images, such as abnormality detection [42, 43].”
BackgroundDeep Learning in Visual Computing and Signal Processing
Xie, D., Zhang, L., & Li, B. (2017) · Applied Computational Intelligence and Soft Computing · doi:10.1155/2017/1320780 · Cited by 118
“CNNs have been applied with great success to the object detection [35, 45, 46], object segmentation [47, 48], and recognition of objects and regions in images [49– 54].”
MethodReview of Breast Cancer Pathologigcal Image Processing
Zhang, Y.-N., Ke-rui, X. I. A., Li, C., Ben-li, W. E. I., & Zhang, B. (2021) · BioMed Research International · doi:10.1155/2021/1994764 · Cited by 113
Paçal, İ., Çelik, Ö., Bayram, B., & Cunha, A. M. T. D. S. (2024) · Cluster Computing · doi:10.1007/s10586-024-04532-1 · Cited by 122
“The growth rate, type, stage of advancement, and location of a brain tumor are among the characteristics that determine whether it is malignant or benign [4, 5].”
A feature transfer enabled multi-task deep learning model on medical imaging
Gao, F., Yoon, H., Wu, T., & Chu, X. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.112957 · Cited by 111
“Example applications are colonic polyps in CT images (Roth et al., 2016), cerebral microbleeds in MRI scans (Dou et al., 2016), and breast and lung cancer in Ultrasound images (Lee & Chen, 2015).”
BackgroundFahmy, A. S., El-Rewaidy, H., Nezafat, M., Nakamori, S., & Nezafat, R. (2019) · Journal of Cardiovascular Magnetic Resonance · doi:10.1186/s12968-018-0516-1 · Cited by 122
Yan, K., Cai, J., Zheng, Y., Harrison, A. P., Jin, D., Tang, Y., Tang, Y., Huang, L., Xiao, J. Z., & Lü, L. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3047598 · Cited by 92
“For example, lung nodules [14]–[16], liver tumors [17], and lymph nodes [18]–[20] have been extensively studied.”
BackgroundSelf-citationDetection and Classification of Pulmonary Nodules Using Convolutional Neural Networks: A Survey
Monkam, P., Qi, S., Ma, H., Gao, W., Yao, Y., & Qian, W. (2019) · IEEE Access · doi:10.1109/access.2019.2920980 · Cited by 131
“5D image classification frameworks achieving great detection results [24]–[26].”
BackgroundChmelík, J., Jakubíček, R., Walek, P., Jan, J., Ouředníček, P., Lambert, L., Amadori, E., & Gavelli, G. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.07.008 · Cited by 105
Hamwood, J., Alonso‐Caneiro, D., Read, S. A., Vincent, S. J., & Collins, M. J. (2018) · Biomedical Optics Express · doi:10.1364/boe.9.003049 · Cited by 123
Deep learning modeling using normal mammograms for predicting breast cancer risk
Arefan, D., Mohamed, A. A., Berg, W. A., Zuley, M. L., Sumkin, J. H., & Wu, S. (2019) · Medical Physics · doi:10.1002/mp.13886 · Cited by 131
Khosravan, N., Çelik, H., Türkbey, B., Jones, E. C., Wood, B. J., & Bağcı, U. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.10.010 · Cited by 94
Alkadi, R., Taher, F., El-Baz, A., & Werghi, N. (2018) · Journal of digital imaging · doi:10.1007/s10278-018-0160-1 · Cited by 100
“[33, 34] proposed a multiview CNN variant, coined 2.”
BackgroundMultiple Sclerosis Lesion Segmentation from Brain MRI via Fully Convolutional Neural NetworksPreprint
Roy, S., Butman, J. A., Reich, D. S., Calabresi, P. A., & Pham, D. L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.09172 · Cited by 81
“neural networks can handle 3D images or image patches, both 2D Roth et al. (2016) and 3D Brosch et al. (2016) algorithms have been proposed, with 2D patches often being preferred for memory and speed efficiency.”
BackgroundA deep learning framework for pancreas segmentation with multi-atlas registration and 3D level-set
Zhang, Y., Wu, J., Liu, Y., Chen, Y., Chen, W., Wu, E. X., Li, C., & Tang, X. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101884 · Cited by 110
Wang, Q., Zhou, X., Wang, C., Liu, Z., Huang, J., Zhou, Y., Li, C., Zhuang, H., & Cheng, J. (2019) · IEEE Access · doi:10.1109/access.2019.2896409 · Cited by 110
“Recent advance of deep learning techniques has been shown to effectively address many medical image analysis problems like segmentation [1]–[5], lesion detection [6]–[8], differential diagnosis [9]–[13], quality assessment [14], reference plane retrieval [15], etc.”
BackgroundPredicting brain structural network using functional connectivity
Zhang, L., Wang, L., & Zhu, D. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102463 · Cited by 98
“…( Hinton and Salakhutdinov, 2006 ; LeCun et al., 2015 ) and brought breakthroughs for computational neuroimaging field including reconstruction ( Sun et al., 2019 ), segmentation ( Wang et al., 2015 ), detection ( Sirinukunwattana et al., 2016 ), and computer-aided diagnosis ( Roth et al., 2015 ).”
3-D Convolutional Neural Networks for Automatic Detection of Pulmonary Nodules in Chest CT
Pezeshk, A. X., Hamidian, S., Petrick, N., & Sahiner, B. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2879449 · Cited by 113
“Most existing deep learning systems in the medical imaging literature have therefore relied on 2D CNNs even when being applied to volumetric data [9], [10].”
BackgroundSuresh, S., & Mohan, S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04787-w · Cited by 108
Applications of deep learning for the analysis of medical data
Jang, H., & Cho, K. (2019) · Archives of Pharmacal Research · doi:10.1007/s12272-019-01162-9 · Cited by 108
Deep Fusion of Brain Structure-Function in Mild Cognitive Impairment
Zhang, L., Wang, L., Gao, J., Risacher, S. L., Yan, J., Li, G., Liu, T., & Zhu, D. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102082 · Cited by 99
Requirements and reliability of AI in the medical context
Balagurunathan, Y., Mitchell, R., & Naqa, I. E. (2021) · Physica Medica · doi:10.1016/j.ejmp.2021.02.024 · Cited by 94
“Deep networks have been successfully shown to be useful in detecting polyps in colonoscopy images [46].”
BackgroundElazab, A., Wang, C., Gardezi, S. J. S., Bai, H., Hu, Q., Wang, T., Chang, C., & Lei, B. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.09.004 · Cited by 100
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
