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
Items 201–300 of 545
Lisson, C. S., Lisson, C. S., Mezger, M. F., Wolf, D., Schmidt, S. A., Thaiss, W. M., Tausch, E., Beer, A. J., Stilgenbauer, S., Beer, A. J., et al. (2022) · Cancers · doi:10.3390/cancers14082008 · Cited by 35
“Additionally, this ensures the model focuses on the target lesions rather than various sources of noise [80].”
BackgroundJones, M. A., Faiz, R., Qiu, Y., & Zheng, B. (2022) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac5297 · Cited by 34
Yuan, H., Fan, Z., Wu, Y., & Cheng, J. (2021) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-021-02478-y · Cited by 28
Alkenani, A. H., Li, Y., Xu, Y., & Zhang, Q. (2021) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2021.103803 · Cited by 30
A mixture of views network with applications to multi-view medical imaging
Shachor, Y., Greenspan, H. K., & Goldberger, J. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.09.027 · Cited by 26
Medical Image Analysis Using Deep Learning: A Systematic Literature Review
Kumar, E. S., & Bindu, C. S. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-8300-7_8 · Cited by 33
Image Segmentation and Classification for Sickle Cell Disease using Deformable U-NetPreprint
Zhang, M., Li, X., Xu, M., & Li, Q.-Z. (2017) · arXiv.org · doi:10.48550/arxiv.1710.08149 · Cited by 29
“Besides the technique of deformable convolution, there exist many meth-ods to ensure the spatial invariance, such as data augmentation [16] and spatial transformer networks (STN) [17].”
MethodKabir, M. F., Ahmad, M. Y., Uddin, R., Cordero, M., & Kant, S. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00442-2 · Cited by 28
Li, S., Xie, Y., Wang, G., Zhang, L., & Zhou, W. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3161466 · Cited by 31
“To overcome the lack of data, image re-sampling was adopted for data augmentation to extract numerous 3D patches and multiple 2D orthogonal views (axial, coronal, and sagittal) within a limitednumberoftumors,whichissimilartopreviouswork[26].”
MethodGaddam, P. G., Reddy, A. S., & Sreehari, R. V. (2021) · Journal of Physics, Conference Series · doi:10.1088/1742-6596/2089/1/012058 · Cited by 28
“Thus, addressing time series information in a two-dimensional format could be favorable for some machine learning algorithms [4].”
BackgroundGonzalez, Y., Shen, C., Jung, H., Nguyen, D. T. D., Jiang, S. B., Albuquerque, K., & Jia, X. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101896 · Cited by 35
“D volumes (Roth et al., 2015; Duan et al., 2019).”
Synthetic Gastritis Image Generation via Loss Function-Based Conditional PGGAN
Togo, R., Ogawa, T., & Haseyama, M. (2019) · IEEE Access · doi:10.1109/access.2019.2925863 · Cited by 29
“, CT, MRI, and mammography; hereafter called major inspections) [3]–[5].”
BackgroundLow-Rank Mixture-of-Experts for Continual Medical Image Segmentation
Chen, Q., Zhu, L., He, H., Zhang, X.-L., Zeng, S., Ren, Q.-S., & Lu, Y.-Y. (2024) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.48550/arxiv.2406.13583 · Cited by 27
“Medical image segmentation (MIS) has been extensively studied and is crucial for quantitative disease analysis [10], computer-aided diagnosis [24], and cancer radiotherapy planning [12].”
BackgroundCAN3D: Fast 3D medical image segmentation via compact context aggregation
Dai, W., Woo, B., Liu, S., Marques, M., ENGSTROM, C. M., Greer, P. B., Crozier, ., Dowling, J., & Chandra, S. S. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102562 · Cited by 19
“Workarounds such as slice-wise [Xue et al., 2020, Wang et al., 2019, Roth et al., 2015] or patch-wise [Dolz et al., 2018, Dong et al., 2020, Sun et al., 2019] techniques are often applied to save more VRAM for the large model by constraining the input data size.”
MethodChang, C. Y., Buckless, C. G., Yeh, K. J., & Torriani, M. (2021) · Skeletal Radiology · doi:10.1007/s00256-021-03873-x · Cited by 30
Liu, S., Zhang, D., Song, Y., Peng, H., & Cai, W. (. (2017) · MLMI@MICCAI · doi:10.1007/978-3-319-67389-9_22 · Cited by 27
Saba, T., Abunadi, I., Sadad, T., Khan, A. R., & Bahaj, S. A. (2021) · Microscopy Research and Technique · doi:10.1002/jemt.24008 · Cited by 32
“Yap et al. (2017) There are several CNN architectures, for example, the CiFarNet (Roth et al., 2015), AlexNet (Krizhevsky, Sutskever, & Hinton, 2012; Sadad et al., 2021), GoogLeNet (Szegedy et al., 2015), ResNet (He, Zhang, Ren, & Sun, 2016), VGG16, and VGG 19 ().”
MethodNeuron Image Segmentation via Learning Deep Features and Enhancing Weak Neuronal Structures
Yang, B., Chen, W., Luo, H., Tan, Y., Liu, M., & Wang, Y. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3017540 · Cited by 36
“In[24],the2.”
DeepHealth: Review and challenges of artificial intelligence in health informaticsPreprint
Kwak, G. H., & Hui, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.00384 · Cited by 44
“Firstofall, multi-scale image analysis reliably detected detection points for irregularly shaped diseases with various intensity distributions and densities [127, 129, 182, 220, 237, 243].”
BackgroundXiao, Z., Du, N., Geng, L., Zhang, F., Wu, J., & Liu, Y. (2019) · Applied Sciences · doi:10.3390/app9163261 · Cited by 32
“Firstly, the system that uses volumetric information has fewer false positives than methods that use two-dimensional (2D) slice information alone [5,16,17].”
MethodDetailed Characterization of Deep Neural Networks on GPUs and FPGAs
Karki, A., Keshava, C. P., Shivakumar, S. M., Skow, J., Hegde, G. M., & Jeon, H. (2019) · GPGPU@ASPLOS · doi:10.1145/3300053.3319418 · Cited by 32
A clinically applicable AI system for detection and diagnosis of bone metastases using CT scans
Zhang, Y., Li, J., Yang, Q., Yin, S., Hou, J., Cao, X., Ma, S., Wang, B., Luo, M., Zhou, F., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-59433-7 · Cited by 27
Sathya, B., & Neelaveni, R. (2020) · Journal of Forensic and Legal Medicine · doi:10.1016/j.jflm.2020.102066 · Cited by 27
Yuan, H., Wu, Y., Cheng, J., Fan, Z., & Zeng, Z. (2021) · IEEE Access · doi:10.1109/access.2021.3137317 · Cited by 22
“Roth et al. [19] used deep learning-based 2DCNN technology to detect lung nodules.”
BackgroundChao, C.-H., Zhu, Z., Guo, D., Yan, K., Ho, T.-Y., Cai, J., Harrison, A. P., Ye, X., Xiao, J., Yuille, A., et al. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-59728-3_75 · Cited by 29
Self-citationThe impact of AI on modern oncology from early detection to personalized cancer treatment
Li, J., Zhang, L., Yu, Z., Bao, Z., Li, D., & Wang, L. (2026) · npj Precision Oncology · doi:10.1038/s41698-026-01276-6 · Cited by 24
“Deep neural networks have also been developed for identifying enlarged lymph nodes and colonic polyps on CT images, and a real-time DL computer-aided detection system for colonoscopy has received FDA approval to enhance polyp detection 22,23 .”
Deep Learning With Radiogenomics Towards Personalized Management of Gliomas
Mitra, S. (2021) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2021.3075500 · Cited by 26
“5D volumetric framework [59] for improved performance.”
Generative Adversarial U-Net for Domain-free Medical Image AugmentationPreprint
Chen, X., Li, Y., Yao, L., Adeli, E., & Zhang, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.04793 · Cited by 14
“Deep learning based methods require a large amount of annotated training samples to support the inference which is hard to be fulfilled on medical imaging analysis [1]–[3].”
BackgroundDecoding Behavior Tasks From Brain Activity Using Deep Transfer Learning
Gao, Y., Zhang, Y., Wang, H., Guo, X., & Zhang, J. (2019) · IEEE Access · doi:10.1109/access.2019.2907040 · Cited by 29
“[42] created a model transferred from pre-trained ImageNet via fine-tuning to diagnose interstitial lung disease on a public interstitial lung disease dataset.”
MethodSeeking an optimal approach for Computer-aided Diagnosis of Pulmonary Embolism
Islam, N. U., Zhou, Z., Gehlot, S., Gotway, M. B., & Liang, J. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102988 · Cited by 24
Instance importance-Aware graph convolutional network for 3D medical diagnosis
Chen, Z., Liu, J., Zhu, M., Woo, P. Y., & Yuan, Y. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102421 · Cited by 29
Self-citationDetecting cerebral microbleeds via deep learning with features enhancement by reusing ground truth
Li, T., Zou, Y. L., Bai, P., Li, S., Wang, H., Chen, X., Meng, Z., Kang, Z., & Zhou, G. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106051 · Cited by 23
Chen, W., Liu, M., Zhan, Q., Tan, Y., Meijering, E. H. W., Radojević, M., & Wang, Y. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3031289 · Cited by 27
“5D is an improved version of the 2.5D patches extraction method [41].”
MethodZhou, W., Wang, G., Xie, G., & Zhang, L. (2019) · Medical Physics · doi:10.1002/mp.13642 · Cited by 26
Learning From Limited and Imbalanced Medical Images With Finer Synthetic Images From GANs
Qin, X., Bui, F. M., Nguyen, H. H., & Han, Z. (2022) · IEEE Access · doi:10.1109/access.2022.3202560 · Cited by 20
“CNN architectures [1], [17], [18], [19] have been widely introduced for many medical image classification tasks.”
BackgroundCancer diagnosis using artificial intelligence: a review
Shastry, K. A., & Sanjay, H. A. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-021-10074-4 · Cited by 40
“There exist numerous “CNN” operational models such as “Alex Net”, “CiFarNet” (Roth et al. 2016), “Google Net” (Szegedy et al. 2015), “VGG16” and “VGG 19” (Saba et al. 2020; Ejaz 2019).”
Automated identification of clinical features from sparsely annotated 3-dimensional medical imaging
Rakocz, N., Chiang, J. N., Nittala, M. G., Corradetti, G., Tiosano, L., Velaga, S. B., Thompson, M., Hill, B. L., Sankararaman, S., Haines, J. L., et al. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00411-w · Cited by 20
Polyp detection algorithm can detect small polyps: Ex vivo reading test compared with endoscopists
Guo, Z., Nemoto, D., Zhu, X., Li, Q., Aizawa, M., Utano, K., Isohata, N., Endo, S., Lefor, A. K., & Togashi, K. (2020) · Digestive Endoscopy · doi:10.1111/den.13670 · Cited by 22
Jiang, Z., Ardywibowo, R., Samereh, A., Evans, H. L., Lober, W. B., Chang, X., Qian, X., Wang, Z., & Huang, S. (2019) · Surgical Infections · doi:10.1089/sur.2019.154 · Cited by 19
Zhao, Y. S., Cumming, P. D., Rominger, A., Zuo, C., Shi, K., Wu, P., Wang, J., Li, H., Navab, N., Yakushev, I. Y., et al. (2019) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2019.8856747 · Cited by 25
“It has been also applied in computerized diagnosis on medical imaging, such as differential diagnosis [14], abnormality detection [15] and prognosis [16].”
Xiong, J., Li, X., Lü, L., Schwartz, L. H., Fu, X., Zhao, J., & Zhao, B. (2019) · IEEE Access · doi:10.1109/access.2019.2916557 · Cited by 27
“To do so, a 3D image volume needs to be sliced into 2D images [16], [17], [20], either along the transverse direction or at an arbitrary direction in 3D.”
BackgroundSelf-citationA New Deep Learning Algorithm for Detecting Spinal Metastases on Computed Tomography Images
Motohashi, M., Funauchi, Y., Adachi, T., Fujioka, T., Otaka, N., Kamiko, Y., Okada, T., Tateishi, U., Okawa, A., Yoshii, T., et al. (2023) · Spine · doi:10.1097/brs.0000000000004889 · Cited by 21
“Roth et al. 23 applied a deep convolutional neural network to the output of a preexisting computer-aided detection system and demonstrated its ef fi cacy in FP reduction.”
BackgroundMagnuska, Z., Theek, B., Darguzyte, M., Palmowski, M., Stickeler, E., Schulz, V., & Kiessling, F. M. (2022) · Cancers · doi:10.3390/cancers14020277 · Cited by 26
“Although deep learning algorithms often represent a black box, and the ability to explain results remains a critical issue, they already outperform the machine learning-based CAD systems in the sensitivity of cancer diagnosis [33].”
BackgroundIntroduction to deep learning: minimum essence required to launch a research
Wataya, T., Nakanishi, K., Suzuki, Y., Kido, S., & Tomiyama, N. (2020) · Japanese Journal of Radiology · doi:10.1007/s11604-020-00998-2 · Cited by 24
Rai, R., & Sisodia, D. S. (2020) · Lecture notes in bioengineering · doi:10.1007/978-981-15-6329-4_39 · Cited by 27
Yang, Z., Chen, M., Kazemimoghadam, M., Ma, L., Stojadinović, S., Timmerman, R. D., Dan, T., Wardak, Z., Lu, W., & Gu, X. (2021) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac4667 · Cited by 21
Classification of Volumetric Images Using Multi-Instance Learning and Extreme Value Theorem
Tennakoon, R., Bortsova, G., Ørting, S. N., Gostar, A. K., Wille, M. M. W., Saghir, Z., Hoseinnezhad, R., de Bruijne, M., & Bab‐Hadiashar, A. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2936244 · Cited by 20
“instances), and train a CNN using human expert annotation of each instance (analogous to object detection framework) [4], [5].”
MethodData Augmentation for Improved Brain Tumor Segmentation
Biswas, A., Bhattacharya, P., Maity, S., & Banik, R. (2021) · Journal of the Institution of Electronics and Telecommunication Engineers · doi:10.1080/03772063.2021.1905562 · Cited by 19
“However, the foremost task in ML-based medical image segmentation is to find a way to deal with the undersized datasets having an inadequate quantity of interpreted samples [3].”
BackgroundRehman, A.-U., Ali, N., Taj, I. A., Sajid, M., & Karimov, K. S. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/4864835 · Cited by 24
Utilization of a convolutional method for Alzheimer disease diagnosis
Allioui, H., Sadgal, M., & Fazziki, A. E. (2020) · Machine Vision and Applications · doi:10.1007/s00138-020-01074-5 · Cited by 25
Automated Asphalt Pavement Crack Detection and Classification using Deep Convolution Neural Network
Yusof, N. M., Osman, M. K., Hussain, Z., Noor, M. H. M., Ibrahim, A., Tahir, N., & Abidin, N. (2019) · IEEE International Conference on Control System, Computing and Engineering · doi:10.1109/iccsce47578.2019.9068551 · Cited by 19
EMPT: a sparsity Transformer for EEG-based motor imagery recognition
Liu, M., Liu, Y., Shi, W., Lou, Y., Sun, Y., Qi, M., Wang, D., Xu, F., Zhang, Y., Zhang, L., et al. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1366294 · Cited by 15
You, H.-Y., Wang, J.-F., Ma, R.-H., Chen, Y.-Y., Li, L.-J., Song, C.-Y., Dong, Z., Feng, S., & Zhou, X.-Q. (2023) · Bioengineering · doi:10.3390/bioengineering10080948 · Cited by 18
“In the training set, image resampling included data resizing and augmentation, which was similar to a previous study [27].”
ResultApplications of Machine Learning in Digital Forensics
Qadir, S., & Noor, B. (2021) · 2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) · doi:10.1109/icodt252288.2021.9441543 · Cited by 18
“For LN, dataset of [39] was used 771 patients”
MethodUniversal Lesion Detection by Learning from Multiple Heterogeneously Labeled DatasetsPreprint
Yan, K., Cai, J., Harrison, A. P., Jin, D., Xiao, J. Z., & Lü, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.13753 · Cited by 8
“For example, lung nodules [20,48,10,7], liver tumors [39,18,3], and lymph nodes [5,31,23,34] have been extensively studied.”
BackgroundSelf-citationKhan, A., & Narejo, G. B. (2019) · Current Medical Imaging Reviews · doi:10.2174/1573405615666190716122040 · Cited by 18
Zhang, J., Li, X., Li, Y., Wang, M., Huang, B., Yao, S., & Shen, L. (2019) · Brain Imaging and Behavior · doi:10.1007/s11682-019-00186-5 · Cited by 21
Wang, X., Guo, Y., Wang, Y., & Yu, J.-H. (2017) · Neural computing & applications (Print) · doi:10.1007/s00521-017-3138-x · Cited by 18
“5-D input is firstly cropped to train on translations of the cropped image for data augmentation [19, 21].”
BackgroundMethodGuo, H., Zhang, J., Huang, J., Mok, T. C. W., Guo, D.-Z., Yan, K., Lu, L., Jin, D.-K., & Xu, M.-F. (2024) · AAAI Conference on Artificial Intelligence · doi:10.48550/arxiv.2403.15063 · Cited by 17
“…analysis, with ubiquitous clinical applications such as disease quantification (Iyer et al. 2016; Ferr´e et al. 2019), computer-aided diagnosis (Roth et al. 2015; Chil-amkurthy et al. 2018; Mitani et al. 2020; McKinney et al. 2020), and radiotherapy planning (Jin et al. 2021; Ye et al. 2022;…”
Self-citationHan, C., Zhang, J., Yu, B., Zheng, H., Wu, Y., Lin, Z., Ning, B., Yi, J., Xie, C., & Jin, X. (2023) · Radiation Oncology · doi:10.1186/s13014-023-02311-7 · Cited by 15
“With the development of DL, studies indicated that combining the DL models with the handcrafted features with learned knowledge may improve the performance of these deep learning models [38, 39], In this study, the AUCs of DL models were improved from 0.”
MethodMulti-planar 2.5D U-Net for image quality enhancement of dental cone-beam CT
Ryu, K., Lee, C., Han, Y., Pang, S., Kim, Y. H., Choi, C., Jang, I., & Han, S. (2023) · PLoS ONE · doi:10.1371/journal.pone.0285608 · Cited by 20
Small Object Detection via Pixel Level Balancing With Applications to Blood Cell Detection
Hu, B., Liu, Y., Chu, P.-Z., Tong, M., & Kong, Q. (2022) · Frontiers in Physiology · doi:10.3389/fphys.2022.911297 · Cited by 17
“Ross et al. utilized CNN to improve three existing CAD systems for the detection of colonic polyps, sclerosing spinal deformity, and lymphadenopathy in CT imaging (Roth et al., 2016).”
MethodLiu, X., Sun, Z., Han, C., Cui, Y., Huang, J.-H., Wang, X.-P., Zhang, X.-D., & Wang, X.-Y. (2021) · BMC Medical Imaging · doi:10.1186/s12880-021-00703-3 · Cited by 17
“Multiple studies have been published on the development of U-Net-based LN segmentation methods, most of which use CT [15, 16], PET/CT [17, 18], or MR lymphography images [19] rather than DWI images.”
BackgroundSadad, T., Khan, A., Hussain, A., Tariq, U., Fati, S., Bahaj, S. A. O., & Munir, A. (2021) · Microscopy research and technique (Print) · doi:10.1002/jemt.23773 · Cited by 17
“There are various types of CNN frameworks available, such as the CiFarNet (Roth et al., 2016), AlexNet (Krizhevsky, Sutskever, & Hinton, 2012), GoogLeNet (Szegedy et al., 2015), VGGNet (Simonyan & Zisserman, 2015), ResNet (He, Zhang, Ren, & Sun, 2016), and DenseNet (Huang, Liu, Van Der Maaten, & Weinberger, 2017).”
MethodYao, Z., Hu, X., Liu, X., Xie, W., Dong, Y., Qiu, H., Chen, Z., Shi, Y., Xu, X., Huang, M., et al. (2021) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-021-02335-y · Cited by 17
Optimization of FireNet for Liver Lesion Classification
Kabe, G. K., Song, Y., & Liu, Z. (2020) · Electronics · doi:10.3390/electronics9081237 · Cited by 18
“The biggest challenge in applying deep learning for medical imaging domain is the small dataset with the lack of labeled data [1,2].”
BackgroundPattern Recognition in Musculoskeletal Imaging Using Artificial Intelligence
Gorelik, N., Chong, J., & Lin, D. J. (2020) · Seminars in Musculoskeletal Radiology · doi:10.1055/s-0039-3400266 · Cited by 18
“25, 31 Burns et al developed a CADe system to automatically detect and quantitatively characterize characterize sclerotic spine lesions using an SVM 32 – 34 Oh et al presented an automatic method to detect changes in bone metastases through the subtraction of two registered CT volumes on…”
BackgroundMethodAn Improved CNN-Based Pneumoconiosis Diagnosis Method on X-ray Chest Film
Zheng, R., Deng, K., Jin, H., Liu, H., & Zhang, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-37429-7_66 · Cited by 18
Hu, X., Chung, A. G., Fieguth, P., Khalvati, F., Haider, M. A., & Wong, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.05817 · Cited by 19
“Traditional data augmentation methods include image intensity normalization, rotation, re-scaling, cropping, flipping, and Gaussian noise injection [2, 3, 4].”
MethodAntonio, V. A. A., Ono, N., Saitō, A., Sato, T., Altaf-Ul-Amin, M., & Kanaya, S. (2018) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-018-1835-2 · Cited by 17
“On the other hand, an analysis of biomedical images requires a more specific viewpoint focusing extensively on their biological features [2,12,14,15].”
BackgroundMachine learning approach for homolog chromosome classification
Devaraj, S. (2018) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22287 · Cited by 25
“12 Development of machine learning algorithms applied to medical images 13,14 like lung diseases, lymph nodes in CT, 15,16 and brain images.”
MethodRen, Y., Ma, J., Xiong, J., Lu, L., & Zhao, J. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2631245 · Cited by 17
“[46] 2015 792 173 6 Yes Yes Independent test 75% by-polyp 3 FPs/patient 792 37 10 Yes Yes Independent test 95% by-polyp 1 FPs/dataset The proposed scheme – 76 103 5 Yes Yes fourfold cross validation98.”
MethodSelf-citationMutual Informative MapReduce and Minimum Quadrangle Classification for Brain Tumor Big Data
Manikandan, R., Patan, R., Kumar, A., Hosseini, S., & Gandomi, A. H. (2021) · IEEE Transactions on Engineering Management · doi:10.1109/tem.2021.3073018 · Cited by 19
“[34], studied a two-tier cascade framework by applying coordinates of the region of interest, performed sampling through scale transformations, random translations, and rotations based on the extracted region of interest to different medical imaging datasets.”
BackgroundUse of artificial intelligence for the diagnosis of cholesteatoma
Tseng, C. C., Lim, V., & Jyung, R. W. (2023) · Laryngoscope Investigative Otolaryngology · doi:10.1002/lio2.1008 · Cited by 16
Alyami, J., Sadad, T., Rehman, A., Almutairi, F. F., Saba, T., Bahaj, S. A. O., & Alkhurim, A. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/7403302 · Cited by 16
“The state of the art presents different CNNs models, CiFarNet [26], AlexNet [27], GoogLeNet [28], ResNet [29], VGG16, and VGG 19 [30].”
Shah, S., Mishra, R., Szczurowska, A., & Guziński, M. (2021) · Polish Journal of Radiology · doi:10.5114/pjr.2021.108257 · Cited by 22
“One of the difficulties faced by researchers in developing an advanced CAD system is the availability of labelled datasets [17-19].”
BackgroundCao, B., Zhang, K., Wei, B., & Chen, L. (2021) · World Journal of Gastroenterology · doi:10.3748/wjg.v27.i21.2681 · Cited by 21
A Survey on Domain Knowledge Powered Deep Learning for Medical Image Analysis
Xie, X.-Z., Niu, J., Liu, X., Chen, Z.-S., & Tang, S. (2020) · arXiv.org · doi:10.48550/arxiv.2004.12150 · Cited by 16
“…analysis adopt techniques designed for addressing overfitting in traditional computer vision tasks, like reducing the complexity of the network [10], [11], [12], [13], [14], [15], adopting some regularization techniques [16], [17], or using data augmentation strategies [18], [19] [20], [21] [22].”
BackgroundMethodElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
Jiang, C., Wang, S., Liang, X., Xu, H., & Xiao, N. (2020) · AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6765 · Cited by 16
“(Roth et al. 2015) trained classifiers on the aggregation of multiple 2D slices for false positive reduction, but it has two stages and is not end-to-end.”
Debats, O. A., Litjens, G. J. S., & Huisman, H. J. (2019) · PeerJ · doi:10.7717/peerj.8052 · Cited by 16
“A modest number of studies have been published on the development of lymph node CAD systems, most of them using CT imaging rather than MR imaging (Kitasaka et al., 2007; Roth et al., 2014; Roth et al., 2016; Seff et al., 2014).”
BackgroundRen, Y., Ma, J., Xiong, J., Chen, Y., Lu, L., & Zhao, J. (2019) · IEEE journal of biomedical and health informatics · doi:10.1109/jbhi.2018.2808199 · Cited by 16
“[17] reduced FPs using”
Self-citationWang, X., Lü, L., Shin, H.-C., Kim, L., Nogues, I., Yao, J., & Summers, R. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.07965 · Cited by 16
“Computer Aided Detection (CAD) [41], require precise labels of lesions or diseases as the training/testing ground-truth.”
BackgroundInfluentialSelf-citationOn the Necessity of Fine-Tuned Convolutional Neural Networks for Medical Imaging
Tajbakhsh, N., Shin, J. Y., Gurudu, S., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2017) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-42999-1_11 · Cited by 17
Deep Learning and Computer-Aided Diagnosis for Medical Image Processing: A Personal Perspective
Summers, R. M. (2017) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-42999-1_1 · Cited by 19
Self-citationKulkarni, P., Sarwe, N. K., Pingale, A., Sarolkar, Y., Patil, R. R., Shinde, G. R., & Kaur, G. (2024) · MethodsX · doi:10.1016/j.mex.2024.103034 · Cited by 20
Küstner, T., Vogel, J., Hepp, T., Forschner, A., Pfannenberg, C., Schmidt, H., Schwenzer, N. F., Nikolaou, K., la Fougère, C. J., & Seith, F. (2022) · Diagnostics · doi:10.3390/diagnostics12092102 · Cited by 14
Emerging artificial intelligence methods for fighting lung cancer: A survey
Zhou, J., & Xin, H. (2022) · Clinical eHealth · doi:10.1016/j.ceh.2022.04.001 · Cited by 19
Kamran, S. A., Hossain, K. F., Moghnieh, H., Riar, S., Bartlett, A., Tavakkoli, A., Sanders, K. M., & Baker, S. A. (2022) · iScience · doi:10.1016/j.isci.2022.104277 · Cited by 15
“In recent years there has been a surge in the use of automated-computer-aided detection for biomedical image processing and analysis (Cai et al., 2016; De Vos et al., 2016; Leigh et al., 2020; Roth et al., 2015; Ter-amoto et al., 2016).”
BackgroundDourthe, B., Shaikh, N., Anoosha Pai, S., Fels, S., Brown, S. H. M., Wilson, D. R., Street, J., & Oxland, T. R. (2021) · Spine · doi:10.1097/brs.0000000000004308 · Cited by 18
Uemura, T., Näppi, J. J., Ryu, Y., Watari, C., Kamiya, T., & Yoshida, H. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02275-z · Cited by 15
NF-RCNN: Heart localization and right ventricle wall motion abnormality detection in cardiac MRI
Kermani, S., Oghli, M. G., Mohammadzadeh, A., & Kafieh, R. (2020) · Physica Medica · doi:10.1016/j.ejmp.2020.01.011 · Cited by 16
Loraksa, C., Mongkolsomlit, S., Nimsuk, N., Uscharapong, M., & Kiatisevi, P. (2022) · IEEE Access · doi:10.1109/access.2022.3183604 · Cited by 23
“Convolutional Neural Networks or CNNs [25], [26], [28]–[30] are one of the most popular machine learning techniques, especially for image-related applications.”
BackgroundKnee Meniscus Segmentation and Tear Detection from MRI: A Review.
Saygılı, A., & Albayrak, S. (2020) · Current Medical Imaging Reviews · doi:10.2174/1573405614666181017122109 · Cited by 15
The essence and applications of machine vision inspection for textile industry: a review
Xu, C., Xu, L., Luo, K., Zhang, J., Sitahong, A., Yang, M., & Zhang, C. (2024) · Journal of the Textile Institute · doi:10.1080/00405000.2024.2426257 · Cited by 13
“‹ Translation transformation is usually used to detect objects moving at high speed along the horizontal and vertical directions and to collect targets at different positions of the horizontal line (or vertical line) (Roth et al., 2016).”
Gonzales, R. A., Seemann, F., Lamy, J., Mojibian, H. R., Atar, D., Erlinge, D., Steding‐Ehrenborg, K., Arheden, H., Hu, C., Onofrey, J. A., et al. (2021) · Journal of Cardiovascular Magnetic Resonance · doi:10.1186/s12968-021-00824-2 · Cited by 18
“The first stage is enriched by the large-scale study, from different centers, vendors and observers, and data augmentation to further increase the sample diversity [41] allowing model generalization [42].”
BackgroundYuan, H., Fan, Z., Dong, D., & Sun, Z. (2021) · 2021 IEEE 9th International Conference on Bioinformatics and Computational Biology (ICBCB) · doi:10.1109/icbcb52223.2021.9459209 · Cited by 14
“Xie et al. [11] designed a boosting architecture based on 2D CNN for false-positive reduction.”
MethodDhengre, N., Sinha, S., Chinni, B., Dogra, V., & Rao, N. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.101952 · Cited by 14
One stage lesion detection based on 3D context convolutional neural networks
Cai, G., Chen, J., Wu, Z., Tang, H., Liu, Y., Wang, S., & Su, S. (2019) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2019.106449 · Cited by 13
Dou, T., & Zhou, W. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545806 · Cited by 13
“One conventional way is to apply 2D CNN based on single slices, orthogonal planes or multiview aggregation, which has shown promising results for the detection of lymph nodes [9], pulmonary nodule [10], and characterization of pulmonary peri-fissural nodules [11] and HCC [12].”
BackgroundMethodA CADe System for Gliomas in Brain MRI using Convolutional Neural NetworksPreprint
Banerjee, S., Mitra, S., Sharma, A. K., & Shankar, B. U. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.07589 · Cited by 15
“The adoption rate of CNNs in medical imaging has been on the rise [36], with recent research focusing on topics ranging from lesion detection [37, 38, 39, 40] to segmentation and shape modelling [10, 41, 42] However existing literature using CNNs mainly focuses on pixel (or voxel) level tumor…”
Method
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
