A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets
Open accessAbstract
BACKGROUND: Deep learning methods for radiomics/computer-aided diagnosis (CADx) are often prohibited by small datasets, long computation time, and the need for extensive image preprocessing. AIMS: We aim to develop a breast CADx methodology that addresses the aforementioned issues by exploiting the efficiency of pre-trained convolutional neural networks (CNNs) and using pre-existing handcrafted CADx features. MATERIALS & METHODS: We present a methodology that extracts and pools low- to mid-level features using a pretrained CNN and fuses them with handcrafted radiomic features computed using conventional CADx methods. Our methodology is tested on three different clinical imaging modalities (dynamic contrast enhanced-MRI [690 cases], full-field digital mammography [245 cases], and ultrasound [1125 cases]). RESULTS: From ROC analysis, our fusion-based method demonstrates, on all three imaging modalities, statistically significant improvements in terms of AUC as compared to previous breast cancer CADx methods in the task of distinguishing between malignant and benign lesions. (DCE-MRI [AUC = 0.89 (se = 0.01)], FFDM [AUC = 0.86 (se = 0.01)], and ultrasound [AUC = 0.90 (se = 0.01)]). DISCUSSION/CONCLUSION: We proposed a novel breast CADx methodology that can be used to more effectively characterize breast lesions in comparison to existing methods. Furthermore, our proposed methodology is computationally efficient and circumvents the need for image preprocessing.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Antropova et al.'s method fusing pre-trained CNN features with hand-designed features using conventional CADx methods on three clinical imaging modality datasets demonstrated significant performance improvement.
“In the work of Antropova et al. [91], a method that fuses the extracted and pooled low-and mid-level features using a pre-trained CNN with hand-designed features using conventional CADx methods was applied to three clinical imaging modality datasets, and demonstrated significant performance improvement.”
From Deep Learning in Medical Ultrasound Analysis: A Review (2019) · cites this paper as [91]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2× · see citing works
“CNN features were extracted from the three datasets with the publicly available VGG19 model,(11) pretrained on ImageNet.(12) The CNN features were further used to train classifiers evaluated as described in Section 5.”
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · see citing works
DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988) · Biometrics · doi:10.2307/2531595 · Cited by 22,649 · cited 1× · see citing works
“In order to assess statistical significance, DeLong tests were performed.(27) Bonferroni-Holm corrections were used to account for multiple comparisons.”
A Simple Sequentially Rejective Multiple Test Procedure
(1979) · Scandinavian Journal of Statistics · doi:10.2307/4615733 · Cited by 21,526 · cited 1× · see citing works
“Bonferroni-Holm corrections were used to account for multiple comparisons.(28)”
Shin, 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 · cited 2× · see citing works
“Shin et al.31 reported that fine-tuning substantially outperformed feature extraction in the task of computer-aided detection, but they only extracted features from the final layer of AlexNet.”
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 1× · see citing works
“Although CNNs typically rely on massive datasets for training and are thus often intractable for CADx, it has been shown that standard transfer learning techniques like fine-tuning or feature extraction based on ImageNet-trained CNNs can be used to reduce the need for larger datasets.(4,5) As a result, deep learning t…”
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2535302 · Cited by 3,277 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W. F., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvprw.2009.5206848 · Cited by 2,714 · see citing works
Greenspan, H. K., van Ginneken, B., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2553401 · Cited by 1,704 · see citing works
Deza, E. I., & Deza, M. M. (2009) · Springer eBooks · doi:10.1007/978-3-642-00234-2 · Cited by 949 · see citing works
Huynh, B. Q., Li, H., & Giger, M. L. (2016) · Journal of medical imaging · doi:10.1117/1.jmi.3.3.034501 · Cited by 541 · cited 2× · see citing works
“Other works have shown that the final layer of AlexNet is significantly inferior to earlier layers for the task of medical image analysis.(6,7) Our method employs a more advanced feature extraction technique by hierarchically integrating multiple layers from VGGNet in order to incorporate both low- and high-level info…”
Chen, W., Giger, M. L., & Bick, U. (2006) · Academic Radiology · doi:10.1016/j.acra.2005.08.035 · Cited by 358 · see citing works
Artificial convolution neural network for medical image pattern recognition
Lo, S. B., Chan, H., Lin, J.-S., Li, H., Freedman, M. T., & Mun, S. K. (1995) · Neural Networks · doi:10.1016/0893-6080(95)00061-5 · Cited by 321 · cited 1× · see citing works
“In the 1990s, early forms of convolutional neural networks (CNNs) were introduced for CADx by learning imaging features directly from regions of interest (ROIs) without explicit manual intervention.(2,3) Recent advances in technology have led to the widespread use of deep learning methods that use deeper and more adva…”
Deep learning with non-medical training used for chest pathology identification
Bar, Y., Diamant, I., Wolf, L., & Greenspan, H. K. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083124 · Cited by 300 · cited 2× · see citing works
“Other works have shown that the final layer of AlexNet is significantly inferior to earlier layers for the task of medical image analysis.(6,7) Our method employs a more advanced feature extraction technique by hierarchically integrating multiple layers from VGGNet in order to incorporate both low- and high-level info…”
Volumetric texture analysis of breast lesions on contrast‐enhanced magnetic resonance images
Chen, W., Giger, M. L., Li, H., Bick, U., & Newstead, G. M. (2007) · Magnetic Resonance in Medicine · doi:10.1002/mrm.21347 · Cited by 293 · see citing works
Textural analysis of contrast‐enhanced MR images of the breast
Gibbs, P., & Turnbull, L. W. (2003) · Magnetic Resonance in Medicine · doi:10.1002/mrm.10496 · Cited by 287 · see citing works
“Proper” Binormal ROC Curves: Theory and Maximum-Likelihood Estimation
Metz, C. E., & Pan, X. (1999) · Journal of Mathematical Psychology · doi:10.1006/jmps.1998.1218 · Cited by 275 · cited 1× · see citing works
“The performances of the classifiers were evaluated by patient using receiver operating characteristic (ROC) analysis.(25,26) Area under the ROC curve (AUC), a metric that is independent of cancer prevalence, served as the figure of merit and was evaluated with five-fold cross-validation.”
A review of optimization methodologies in support vector machines
Shawe-Taylor, J. S., & Sun, S. (2011) · Neurocomputing · doi:10.1016/j.neucom.2011.06.026 · Cited by 256 · see citing works
Breast Image Analysis for Risk Assessment, Detection, Diagnosis, and Treatment of Cancer
Giger, M. L., Karssemeijer, N., & Schnabel, J. A. (2013) · Annual Review of Biomedical Engineering · doi:10.1146/annurev-bioeng-071812-152416 · Cited by 211 · cited 1× · see citing works
“In order to assist radiologists in the interpretation of diagnostic imaging, computer-aided diagnosis (CADx) techniques continue to be developed to potentially improve the accuracy of evaluating suspicious breast lesions.(1) In the 1990s, early forms of convolutional neural networks (CNNs) were introduced for CADx by…”
Computerized diagnosis of breast lesions on ultrasound
Horsch, K., Giger, M. L., Venta, L. A., & Vyborny, C. J. (2002) · Medical Physics · doi:10.1118/1.1429239 · Cited by 207 · see citing works
Computerized analysis of breast lesions in three dimensions using dynamic magnetic‐resonance imaging
Gilhuijs, K. G. A., Giger, M. L., & Bick, U. (1998) · Medical Physics · doi:10.1118/1.598345 · Cited by 195 · see citing works
Bhooshan, N., Giger, M. L., Jansen, S. A., Li, H., Li, L., & Newstead, G. M. (2010) · Radiology · doi:10.1148/radiol.09090838 · Cited by 193 · see citing works
Analysis of spiculation in the computerized classification of mammographic masses
Huo, Z., Giger, M. L., Vyborny, C. J., Bick, U., Lu, P., Wolverton, D., & Schmidt, R. A. (1995) · Medical Physics · doi:10.1118/1.597626 · Cited by 173 · cited 1× · see citing works
“and Li et al.(8,16) The resulting FFDM features described quantitative physical properties of the segmented lesion, such as size, shape, texture, and morphology.”
Zhang, W., Doi, K., Giger, M. L., Wu, Y. C., Nishikawa, R. M., & Schmidt, R. A. (1994) · Medical Physics · doi:10.1118/1.597177 · Cited by 168 · cited 1× · see citing works
“In the 1990s, early forms of convolutional neural networks (CNNs) were introduced for CADx by learning imaging features directly from regions of interest (ROIs) without explicit manual intervention.(2,3) Recent advances in technology have led to the widespread use of deep learning methods that use deeper and more adva…”
Jamieson, A. R., Giger, M. L., Drukker, K., Li, H., Yuan, Y., & Bhooshan, N. (2009) · Medical Physics · doi:10.1118/1.3267037 · Cited by 151 · cited 2× · see citing works
“The breast ultrasound dataset contained 1125 unique breast lesions (patients) presented through 2393 regions of interest (ROIs), selected from the images acquired using a Philips HDI5000 scanner.(9,10) The ultrasound ROIs were characterized TABLE I.”
Good Practice in CNN Feature TransferPreprint
Zheng, L., Zhao, Y., Wang, S., Wang, J., & Tian, Q. C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.00133 · Cited by 149 · see citing works
Pan, X., & Metz, C. E. (1997) · Academic Radiology · doi:10.1016/s1076-6332(97)80121-3 · Cited by 103 · cited 1× · see citing works
“The performances of the classifiers were evaluated by patient using receiver operating characteristic (ROC) analysis.(25,26) Area under the ROC curve (AUC), a metric that is independent of cancer prevalence, served as the figure of merit and was evaluated with five-fold cross-validation.”
Computerized analysis of lesions in US images of the breast
Giger, M. L., Al‐Hallaq, H., Huo, Z., Moran, C. J., Wolverton, D., Chan, C. W., & Zhong, W. (1999) · Academic Radiology · doi:10.1016/s1076-6332(99)80115-9 · Cited by 69 · cited 2× · see citing works
“Further details of the image features and how they are obtained can be found in the literature of Giger et al.(18) as well as other, more recent works.”
Automated Method for Improving System Performance of Computer-Aided Diagnosis in Breast Ultrasound
Drukker, K., Sennett, C. A., & Giger, M. L. (2009) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2008.928178 · Cited by 48 · cited 2× · see citing works
“The breast ultrasound dataset contained 1125 unique breast lesions (patients) presented through 2393 regions of interest (ROIs), selected from the images acquired using a Philips HDI5000 scanner.(9,10) The ultrasound ROIs were characterized TABLE I.”
Evaluation of Computer-aided Diagnosis on a Large Clinical Full-field Digital Mammographic Dataset
Li, H., Giger, M. L., Yuan, Y., Chen, W., Horsch, K., Li, L., Jamieson, A. R., Sennett, C. A., & Jansen, S. A. (2008) · Academic Radiology · doi:10.1016/j.acra.2008.05.004 · Cited by 37 · cited 2× · see citing works
“and Li et al.(8,16) The resulting FFDM features described quantitative physical properties of the segmented lesion, such as size, shape, texture, and morphology.”
Flagged first, then by citations
Research works printed but not linked: 1
- [4]Yosinski J Clune J Bengio Y Lipson H Advances in Neural Information Processing Systems 27 Ghahramani Z Welling M Cortes C Lawrence ND Weinberger KQ 3320 3328 Curran Associates, Inc 2014
Cited by
Sorted by citations
Artificial intelligence in cancer imaging: Clinical challenges and applications
Bi, W. L., Hosny, A., Schabath, M. B., Giger, M. L., Birkbak, N. J., Mehrtash, A., Allison, T., Arnaout, O., Abbosh, C., Dunn, I. F., et al. (2019) · CA: A Cancer Journal for Clinicians · doi:10.3322/caac.21552 · Cited by 1,846 · see citing works
Liu, Z., Wang, S., Dong, D., Wei, J., Fang, C., Zhou, X., Sun, K., Li, L., Li, B., Wang, M., et al. (2019) · Theranostics · doi:10.7150/thno.30309 · Cited by 969 · see citing works
“Several previous studies utilized radiomics for the prediction of breast cancer subtype or the status of ER, PR, Ki67 and HER2 with US [46], mammography [118], PET/CT [119, 120], and MRI [121, 122].”
BackgroundMethodDeep Learning in Medical Ultrasound Analysis: A Review
Liu, S., Wang, Y., Yang, X., Lei, B., Liu, L., Li, S. X., Ni, D., & Wang, T. (2019) · Engineering · doi:10.1016/j.eng.2018.11.020 · Cited by 798 · see citing works
“In the work of Antropova et al. [91], a method that fuses the extracted and pooled low-and mid-level features using a pre-trained CNN with hand-designed features using conventional CADx methods was applied to three clinical imaging modality datasets, and demonstrated significant performance…”
MethodDeep 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 739 · see citing works
“196,197 Figure 4 shows one possible method for combining CNN-extracted and conventional radiomics features.”
BackgroundMethodGiger (2018) · doi:10.1016/j.jacr.2017.12.028 · Cited by 634 · see citing works
Machine and deep learning methods for radiomics
Avanzo, M., Wei, L., Stancanello, J., Vallières, M., Rao, A. U. K., Morin, O., Mattonen, S. A., & Naqa, I. E. (2020) · Medical Physics · doi:10.1002/mp.13678 · Cited by 614 · see citing works
Mazurowski, M. A., Buda, M., Saha, A., & Bashir, M. R. (2019) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.26534 · Cited by 554 · see citing works
“Off-the-shelf features have performed well in a variety of domains,(23) and this technique has been successfully applied to medical imaging.(29,30) In Antropova et al,(29) the authors combined the deep off-the-shelf features extracted from a pretrained deep CNN network with hand-crafted features for determining malign…”
MethodConvolutional Neural Networks for Radiologic Images: A Radiologist’s Guide
Soffer, S., Ben-Cohen, A., Shimon, O., Amitai, M. M., Greenspan, H. K., & Klang, E. (2019) · Radiology · doi:10.1148/radiol.2018180547 · Cited by 514 · see citing works
Deep Learning for Medical Anomaly Detection – A Survey
Fernando, T., Gammulle, H., Denman, S., Sridharan, S., & Fookes, C. (2021) · ACM Computing Surveys · doi:10.1145/3464423 · Cited by 414 · see citing works
Radiomics in breast cancer classification and prediction
Conti, A., Duggento, A., Indovina, I., Guerrisi, M., & Toschi, N. (2020) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2020.04.002 · Cited by 397 · see citing works
From Handcrafted to Deep-Learning-Based Cancer Radiomics: Challenges and Opportunities
Afshar, P., Mohammadi, A., Plataniotis, K. N., Oikonomou, A., & Benali, H. (2019) · IEEE Signal Processing Magazine · doi:10.1109/msp.2019.2900993 · Cited by 334 · see citing works
“[52] Mammogram, ultrasound, MRI — Breast cancer benign/ malignant classification Combination of HCR and DLR 2,060 Semiautomatic”
BackgroundMethodBreast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network
Byra, M., Jarosik, P., Szubert, A., Galperin, M. Y., Ojeda‐Fournier, H., Olson, L. K., O'Boyle, M. K., Comstock, C., & André, M. P. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102027 · Cited by 328 · see citing works
A survey on incorporating domain knowledge into deep learning for medical image analysis
Xie, X., Niu, J., Liu, X., Chen, Z., Tang, S., & Yu, S. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.101985 · Cited by 316 · see citing works
“Features doctors focus on Decision level fusion [61] [84] [85] [86] [87] [88] Feature level fusion [36] [89] [57] [90] [91] [92] Input level fusion [93] [54] [94] [95] [96] As labels of CNNs [39] [59] [97] Other related information Multi-task learning /network design [52] [98] [99] [100] [101]”
BackgroundChen, Z., Lin, L., Wu, C., Li, C., Xu, R., & Sun, Y. H. (2021) · 癌症：英文版 · doi:10.1002/cac2.12215 · Cited by 291 · see citing works
“Improvement in breast cancer screening with AI mammography has also been verified in preclinical studies [20–24], as well as in clinical settings [25].”
BackgroundTahmassebi, A., Wengert, G., Helbich, T. H., Bagó-Horváth, Z., Alaei, S., Bartsch, R., Dubsky, P. C., Baltzer, P., Clauser, P., Kapetas, P., et al. (2018) · Investigative Radiology · doi:10.1097/rli.0000000000000518 · Cited by 274 · see citing works
Deep convolutional neural networks for mammography: advances, challenges and applications
Abdelhafiz, D., Yang, C., Ammar, R., & Nabavi, S. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-2823-4 · Cited by 274 · see citing works
“However, the authors in [21, 23, 54, 71, 87, 96–100] have demonstrated the importance of combining the extracted features using deep CNNs with hand-crafted features like texture, and shape.”
BackgroundMethodInfluentialGómez-Valverde, J. J., Antón, A., Fatti, G., Liefers, B. J., Cabarcos, A. H., Santos, A., Sánchez, C. I., & Ledesma‐Carbayo, M. J. (2019) · Biomedical Optics Express · doi:10.1364/boe.10.000892 · Cited by 267 · see citing works
“We can find applications of this network in several studies, for the fixed features extraction in CADx for breast cancer detection with different imaging modalities [54] or for classification of 19 different skin diseases [55].”
MethodMachine learning for medical ultrasound: status, methods, and future opportunities
Brattain, L. J., Telfer, B. A., Dhyani, M., Grajo, J. R., & Samir, A. E. (2018) · Abdominal Radiology · doi:10.1007/s00261-018-1517-0 · Cited by 262 · see citing works
Rapid review: radiomics and breast cancer
Valdora, F., Houssami, N., Rossi, F., Calabrese, M., & Tagliafico, A. S. (2018) · Breast Cancer Research and Treatment · doi:10.1007/s10549-018-4675-4 · Cited by 259 · see citing works
“[13] Retrospective 245 Mammography Nna/na VGG19 model 512–64* Antropova et al.”
BackgroundMethodInfluentialByra, M., Galperin, M., Ojeda‐Fournier, H., Olson, L., O'Boyle, M., Comstock, C., & Andre, M. (2019) · Medical Physics · doi:10.1002/mp.13361 · Cited by 253 · see citing works
“First, we used the grayscale images to perform classification of the B-mode images from the main dataset following the standard approach.(19,20,22,25) For each US image, the gray level intensities were copied to RGB channels and the VGG19 CNN was tuned.”
Criteria for the translation of radiomics into clinically useful tests
Huang, E. P., O’Connor, J. P. B., McShane, L. M., Giger, M. L., Lambin, P., Kinahan, P. E., Siegel, E. L., & Shankar, L. K. (2022) · Nature Reviews Clinical Oncology · doi:10.1038/s41571-022-00707-0 · Cited by 244 · see citing works
Papadimitroulas, P., Brocki, L., Christopher Chung, N., Marchadour, W., Vermet, F., Gaubert, L., Eleftheriadis, V., Plachouris, D., Visvikis, D., Kagadis, G. C., et al. (2021) · Physica Medica · doi:10.1016/j.ejmp.2021.03.009 · Cited by 226 · see citing works
“On the other hand, the attempts for predictive modeling in radiomics [10 – 12] where labels are on a patient basis (i.e., one label per 3D image volume, instead of per pixel/voxel) did not lead to very large improvements compared to the standard radiomics approach, showing in some instances similar…”
BackgroundArtificial intelligence in the interpretation of breast cancer on MRI
Sheth, D., & Giger, M. L. (2019) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.26878 · Cited by 220 · see citing works
“These human-engineered radiomic approaches were later augmented with deep-learning approaches.(56,57) FIGURE 3: Illustration of the first publication of a CNN (aka shift-invariant neural network) used in medical image analysis.”
BackgroundMethodBakkouri, I., & Afdel, K. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07988-1 · Cited by 208 · see citing works
“Starting from the idea that different feature representations of the dermoscopic image could bring different information [5], we study the effects of the fusing dermoscopic features extracted from three CNN models.”
BackgroundDeep learning in head & neck cancer outcome prediction
Diamant, A., Chatterjee, A., Vallières, M., Shenouda, G., & Seuntjens, J. P. (2019) · Scientific Reports · doi:10.1038/s41598-019-39206-1 · Cited by 202 · see citing works
Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy
Arabi, H., & Zaidi, H. (2020) · European Journal of Hybrid Imaging · doi:10.1186/s41824-020-00086-8 · Cited by 196 · see citing works
“In this regard, combining conventional radiomics-based computer-aided diagnosis with deep learning-based feature fusion resulted in statistically significant enhanced level of diagnostic accuracy (Antropova et al. 2017).”
BackgroundA Brief Survey on Breast Cancer Diagnostic With Deep Learning Schemes Using Multi-Image Modalities
Mahmood, T., Li, J., Pei, Y., Akhtar, F., Imran, A., & Rehman, K. U. (2020) · IEEE Access · doi:10.1109/access.2020.3021343 · Cited by 187 · see citing works
“MRI is a diagnostics image modality that uses strong radio waves and magnetic fields to capture the 3D image of breast tissue and display it in a clear view than DMG, ULS [28].”
BackgroundInfluentialA deep learning methodology for improved breast cancer diagnosis using multiparametric MRI
Hu, Q., Whitney, H. M., & Giger, M. L. (2020) · Scientific Reports · doi:10.1038/s41598-020-67441-4 · Cited by 186 · see citing works
Survey of deep learning in breast cancer image analysis
Debelee, T. G., Schwenker, F., Ibenthal, A., & Yohannes, D. (2019) · Evolving Systems · doi:10.1007/s12530-019-09297-2 · Cited by 177 · see citing works
CAD and AI for breast cancer—recent development and challenges
Chan, H., Samala, R. K., & Hadjiiski, L. M. (2019) · British Journal of Radiology · doi:10.1259/bjr.20190580 · Cited by 174 · see citing works
“The majority of the studies were related to breast mass characterization, 44,76–82 followed by mass segmentation, 83–85 and detection.”
BackgroundMethodA deep neural network to assess spontaneous pain from mouse facial expressions
Tuttle, A. H., Molinaro, M. J., Jethwa, J. F., Sotocinal, S. G., Prieto, J. C., Styner, M. A., Mogil, J. S., & Zylka, M. J. (2018) · Molecular Pain · doi:10.1177/1744806918763658 · Cited by 165 · see citing works
“Researchers used large data sets (from previously established diagnostic testing) to train convolutional neural networks to detect human health issues with a high degree of accuracy, including skin cancer, 29,30 breast cancer, 31–34 and thoracic abnormalities.”
MethodSurvey on Machine Learning and Deep Learning Applications in Breast Cancer Diagnosis
Chugh, G., Kumar, S., & Singh, N. (2021) · Cognitive Computation · doi:10.1007/s12559-020-09813-6 · Cited by 172 · see citing works
Application of Deep Learning in Breast Cancer Imaging
Balkenende, L., Teuwen, J., & Mann, R. M. (2022) · Seminars in Nuclear Medicine · doi:10.1053/j.semnuclmed.2022.02.003 · Cited by 174 · see citing works
Joint EANM/SNMMI guideline on radiomics in nuclear medicine
Hatt, M., Krizsan, A. K., Rahmim, A., Bradshaw, T., Costa, P. F., Forgács, A., Seifert, R., Zwanenburg, A., Naqa, I. E., Kinahan, P. E., et al. (2022) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-022-06001-6 · Cited by 156 · see citing works
“An example of this was shown in the context of breast lesion classification (as malignant or benign) in three different image modalities (full field digital mammography, DCE MRI and ultrasound), where a standard radiomic approach and a DL-based analysis of the images were compared and fused, the fusion always produced…”
MethodMachine learning in breast MRI
Reig, B., Heacock, L. C., Geras, K. J., & Moy, L. P. (2019) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.26852 · Cited by 148 · see citing works
“61,62 Truhn et al 61 noted that the performance of their deep-learning classi-fi er improved when the number of training cases increased, although the accuracy of the radiomics algorithm did not.”
BackgroundArtificial intelligence in cancer diagnosis and therapy: Current status and future perspective
Sufyan, M., Shokat, Z., & Ashfaq, U. A. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107356 · Cited by 149 · see citing works
Saeed, F., Khan, M. A., Sharif, M. I., Mittal, M., Goyal, L. M., & Roy, S. S. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107164 · Cited by 139 · see citing works
Clinical applications of artificial intelligence and radiomics in neuro-oncology imaging
Razek, A. A. K. A., Alksas, A., Shehata, M., AbdelKhalek, A., Abdel-Baki, K., El-Baz, A. S., & Helmy, E. M. (2021) · Insights into Imaging · doi:10.1186/s13244-021-01102-6 · Cited by 140 · see citing works
Mammography with deep learning for breast cancer detection
Wang, L. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2024.1281922 · Cited by 134 · see citing works
A Technical Review of Convolutional Neural Network-Based Mammographic Breast Cancer Diagnosis
Zou, L., Yu, S., Meng, T., Zhang, Z., Liang, X., & Xie, Y. (2019) · Computational and Mathematical Methods in Medicine · doi:10.1155/2019/6509357 · Cited by 125 · see citing works
“Most publications address this question by comprehensive experiments to make a trade-off between the diagnosis efficiency and effectiveness, while only [56] proposes using the frequency of the CNN feature selected in the training stage as the weighting of the feature importance.”
BackgroundMethodInfluentialMachine (Deep) Learning Methods for Image Processing and Radiomics
Hatt, M., Parmar, C., Qi, J., & Naqa, I. E. (2019) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2019.2899538 · Cited by 109 · see citing works
Moridian, P., Ghassemi, N., Jafari, M., Salloum‐Asfar, S., Sadeghi, D., Khodatars, M., Shoeibi, A., Khosravi, A., Ling, S. H., Subaşı, A., et al. (2022) · Frontiers in Molecular Neuroscience · doi:10.3389/fnmol.2022.999605 · Cited by 121 · see citing works
“Feature fusion technique is a new field in diagnosing different diseases, and many studies are being conducted in this field (Antropova et al., 2017; Fan et al., 2018; Hermessi et al., 2019; Liu et al., 2021; Wang et al., 2021b; Amemiya et al., 2022).”
BackgroundArtificial Intelligence in Brain Tumor Imaging: A Step toward Personalized Medicine
Cè, M., Irmici, G., Foschini, C., Danesini, G. M., Falsitta, L. V., Serio, M. L., Fontana, A., Martinenghi, C. M. A., Oliva, G., & Cellina, M. I. (2023) · Current Oncology · doi:10.3390/curroncol30030203 · Cited by 132 · see citing works
Luo, Y., Tseng, H.-H., Cui, S., Wei, L., Haken, R. K. T., & Naqa, I. E. (2019) · BJR|Open · doi:10.1259/bjro.20190021 · Cited by 118 · see citing works
Radiomics: Data Are Also Images
Hatt, M., Rest, C. C. L., Tixier, F., Badic, B., Schick, U., & Visvikis, D. (2019) · Journal of Nuclear Medicine · doi:10.2967/jnumed.118.220582 · Cited by 117 · see citing works
Jiao, J., Zhou, J., Li, X., Xia, M., Huang, Y., Huang, L., Wang, N., Zhang, X., Zhou, S., Wang, Y., et al. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103202 · Cited by 119 · see citing works
“…its integration with artificial intelligence, driving substantial progress in the automatic analysis of US images, such as tissue segmentation (Xia et al., 2022), tumor detection (Antropova et al., 2017), disease diagnosis (Kang et al., 2022), and treatment planning (Fontanarosa et al., 2015).”
BackgroundTowards Clinical Application of Artificial Intelligence in Ultrasound Imaging
Komatsu, M., Sakai, A., Dozen, A., Shozu, K., Yasutomi, S., Machino, H., Asada, K., Kaneko, S., & Hamamoto, R. (2021) · Biomedicines · doi:10.3390/biomedicines9070720 · Cited by 119 · see citing works
“employed VGG and the support vector machine for classification using the CNN features and conventional computer-aided diagnosis features [67].”
MethodMendel, K. R., Li, H., Sheth, D., & Giger, M. L. (2018) · Academic Radiology · doi:10.1016/j.acra.2018.06.019 · Cited by 109 · see citing works
“Different domains typically have different population characteristics and different classification categories, thus necessitating a classifier such as SVM (15,16).”
BackgroundLang, N., Zhang, Y., Zhang, E., Zhang, J., Chow, D. S., Chang, P., Yu, H. J., Yuan, H., & Su, M. (2019) · Magnetic Resonance Imaging · doi:10.1016/j.mri.2019.02.013 · Cited by 109 · see citing works
Madani, M., Behzadi, M. M., & Nabavi, S. (2022) · Cancers · doi:10.3390/cancers14215334 · Cited by 122 · see citing works
“Therefore, some developed MRI models put three consecutive slices of grayscale MRI together and build a 3D image [227,228].”
BackgroundChen, L., Zhou, Z., Sher, D. J., Zhang, Q., Shah, J. L., Pham, N.-L., Jiang, S. B., & Wang, J. (2019) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ab083a · Cited by 107 · see citing works
Malebary, S. J., & Hashmi, A. (2021) · IEEE Access · doi:10.1109/access.2021.3071297 · Cited by 105 · see citing works
“From the past few years, the DL technique has gained wide attention from researchers in various fields due to the capability of automatic feature removal, extract DL is widely used in bioinformatics [21]–[23].”
MethodMulti-View Convolutional Neural Networks for Mammographic Image Classification
Sun, L., Wang, J., Hu, Z., Xu, Y. D., & Cui, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2939167 · Cited by 102 · see citing works
“[18] used the method in [19] to extract features from mammographic images, then they also extracted features from mammographic images by VGG19 [20] for mammographic image classification.”
MethodLee, S. E., Han, K., Kwak, J. Y., Lee, E., & Kim, E. (2018) · Scientific Reports · doi:10.1038/s41598-018-31906-4 · Cited by 101 · see citing works
Artificial Intelligence: reshaping the practice of radiological sciences in the 21st century
Naqa, I. E., Haider, M. A., Giger, M. L., & Haken, R. K. T. (2020) · British Journal of Radiology · doi:10.1259/bjr.20190855 · Cited by 101 · see citing works
“60 ML advances are also contributing to cancer discovery where, through the benefit of multidisciplinary, multi-institution collaborations, the computer-extracted tumor information ( i.e. image-based phenotypes) is mapped to other “-omics” such as histopathology and genomics.”
BackgroundLiu, Z., Feng, B., Li, C., Chen, Y., Chen, Q., Li, X., Guan, J., Chen, X., Cui, E., Li, R., et al. (2019) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.26688 · Cited by 99 · see citing works
A holistic overview of deep learning approach in medical imaging
Yousef, R., Gupta, G., Yousef, N., & Khari, M. (2022) · Multimedia Systems · doi:10.1007/s00530-021-00884-5 · Cited by 105 · see citing works
“It is commonly possible to combine deep learning approach with the knowledge learned from the handcrafted features for analyzing medical images [153, 200, 217].”
BackgroundAntropova, N. O., Abé, H., & Giger, M. L. (2018) · Journal of medical imaging · doi:10.1117/1.jmi.5.1.014503 · Cited by 95 · see citing works
“The same population was previously analyzed using CNN features extracted from MRI central slices of each tumor but including precontrast and two postcontrast images.(11) The current work builds upon and advances the analysis by incorporating both temporal and volumetric components of DCE-MRIs into the classification b…”
MethodSemantic segmentation of breast cancer images using DenseNet with proposed PSPNet
Samudrala, S., & Mohan, C. K. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17411-5 · Cited by 95 · see citing works
“Deep-learning-based approaches for suspicious ROI segmentation and categorization utilizing MRI modalities were developed by the authors [34, 35].”
Satake, H., Ishigaki, S., Ito, R., & Naganawa, S. (2021) · La radiologia medica · doi:10.1007/s11547-021-01423-y · Cited by 88 · see citing works
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 85 · see citing works
“Conventional fusion algorithms for combining handcrafted features (HF) and CNN extracted features usually use the CNN features learned at the FFL (Antropova et al., 2017), rather than the output layer.”
BackgroundMethodInfluentialBreast mass classification with transfer learning based on scaling of deep representations
Byra, M. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102828 · Cited by 91 · see citing works
Byra, M., Wu, M., Zhang, X., Jang, H., Ma, Y., Chang, E. Y., Shah, S. B., & Du, J. (2019) · Magnetic Resonance in Medicine · doi:10.1002/mrm.27969 · Cited by 84 · see citing works
Oyelade, O. N., & Ezugwu, A. E.-S. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102366 · Cited by 83 · see citing works
“Mammogram-based CNN based models include [52] which exploited the efficiency of pre-trained convolutional neural networks (CNNs) in a combination of pre-existing handcrafted features.”
MethodWhitney, H. M., Li, H., Ji, Y., Liu, P., & Giger, M. L. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2950187 · Cited by 82 · see citing works
“The application of both radiomics- and CNN-based CADx to classification tasks in medical imaging, particularly in breast imaging [23]–[27], has shown promise.”
MethodHu, H., Wang, W., Chen, L., Ruan, S., Chen, S., Li, X., Lu, M., Xie, X., & Kuang, M. (2021) · Journal of Gastroenterology and Hepatology · doi:10.1111/jgh.15522 · Cited by 77 · see citing works
Byra, M., Dobruch‐Sobczak, K., Klimonda, Z., Piotrzkowska‐Wróblewska, H., & Litniewski, J. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3008040 · Cited by 76 · see citing works
“For this task we use deep learning techniques that have been successfully utilized for the differentiation of malignant and benign breast masses [21].”
MethodInfluentialClassification and Analysis of Android Malware Images Using Feature Fusion Technique
Singh, J., Thakur, D. S., Gera, T., Shah, B., Abuhmed, T., & Ali, F. (2021) · IEEE Access · doi:10.1109/access.2021.3090998 · Cited by 76 · see citing works
“Feature fusion has been widely adopted by researchers for detection and classification tasks relevant to computed vision [45]–[49].”
BackgroundHigh-dimensional role of AI and machine learning in cancer research
Capobianco, E. (2022) · British Journal of Cancer · doi:10.1038/s41416-021-01689-z · Cited by 76 · see citing works
“CNN applications and demonstrations have for instance covered skin cancer from a dataset of 12,940 clinical images [21] and metastatic breast cancer (BC) [22], and in BC it was also shown the feasibility of fusing CNN with other feature extractors [23].”
BackgroundAttallah, O. (2023) · Applied Sciences · doi:10.3390/app13031916 · Cited by 76 · see citing works
“…features is capable of enhancing the diagnostic performance, therefore the results demonstrated in Table 3 were better than those obtained in Tables 1 and 2, which were based on either using handcrafted features only, or merging deep features attained from a single CNN with handcrafted features.”
MethodMurtaza, G., Shuib, L. M., Mujtaba, G., & Raza, G. M. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7525-4 · Cited by 76 · see citing works
Radiomics in PET/CT: Current Status and Future AI-Based Evolutions
Hatt, M., Rest, C. C. L., Antonorsi, N., Tixier, F., Tankyevych, O., Jaouen, V., Lucia, F., Bourbonne, V., Schick, U., Badic, B., et al. (2020) · Seminars in Nuclear Medicine · doi:10.1053/j.semnuclmed.2020.09.002 · Cited by 74 · see citing works
Avanzo, M., Stancanello, J., Pirrone, G., Drigo, A., & Retico, A. (2024) · Cancers · doi:10.3390/cancers16213702 · Cited by 80 · see citing works
“This trend has been highlighted in numerous systematic surveys [1].”
BackgroundMoussa, O., Khachnaoui, H., Guetari, R., & Khlifa, N. (2019) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22363 · Cited by 72 · see citing works
Liu, R., Pan, D., Xu, Y. X., Zeng, H., He, Z., Lin, J., Zeng, W., Wu, Z., Luo, Z., Qin, G., et al. (2021) · European Radiology · doi:10.1007/s00330-021-08195-z · Cited by 70 · see citing works
A Comprehensive Review on Radiomics and Deep Learning for Nasopharyngeal Carcinoma Imaging
Li, S., Deng, Y., Zhu, Z., Hua, H., & Tao, Z. (2021) · Diagnostics · doi:10.3390/diagnostics11091523 · Cited by 71 · see citing works
A Systematic Literature Review of Breast Cancer Diagnosis Using Machine Intelligence Techniques
Nemade, V., Pathak, S. K., & Dubey, A. K. (2022) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-022-09738-3 · Cited by 71 · see citing works
“29 Primary dataset [183] 1 HIPAA-compliant Institutional Review Board protocols”
BackgroundMethodDiagnostic Classification of Cystoscopic Images Using Deep Convolutional Neural Networks
Eminağa, O., Eminaga, N., Semjonow, A., & Breil, B. (2018) · JCO Clinical Cancer Informatics · doi:10.1200/cci.17.00126 · Cited by 69 · see citing works
Artificial Neural Network Based Breast Cancer Screening: A Comprehensive ReviewPreprint
Bharati, S., Podder, P., & Mondal, M. R. H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.01767 · Cited by 69 · see citing works
“2017 245 FFDM VGG19 86% [49]”
Machine Learning and Imaging Informatics in Oncology
Tseng, H.-H., Wei, L., Cui, S., Luo, Y., Ten Haken, R. K., & El Naqa, I. (2020) · Oncology · doi:10.1159/000493575 · Cited by 64 · see citing works
Safdar, M. F., Kobaisi, S. A., & Zahra, F. T. (2020) · Acta Informatica Medica · doi:10.5455/aim.2020.28.29-36 · Cited by 68 · see citing works
“(20) classified breast tumor cells as Benign or Malignant.”
BackgroundHuang, R., Lin, Z., Dou, H., Wang, J., Miao, J., Zhou, G., Jia, X., Xu, W., Mei, Z., Dong, Y., et al. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102137 · Cited by 68 · see citing works
Chen, Q., Li, M., Chen, C., Zhou, P., Lv, X., & Chen, C. (2022) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-022-04180-1 · Cited by 68 · see citing works
“In future research, we will further expand the data fusion model to effectively use different types of clinical information and enhance the scalability of the data fusion model (Antropova et al. 2017; Sedghi et al. 2020; Siddiqui et al. 2021; Wei et al. 2020).”
MethodIntelligent Breast Abnormality Framework for Detection and Evaluation of Breast Abnormal Parameters
Ajay, P., Sharma, A., Kawale, S. R., Diwan, S. P., & Gowda, D., V (2022) · International Conference on Edge Computing and Applications (ICECAA) · doi:10.1109/icecaa55415.2022.9936206 · Cited by 68 · see citing works
“With IoT-based health apps [14], remote health care services may now be affordably and reliably provided.”
BackgroundBreast Lesions Detection and Classification via YOLO-Based Fusion Models
Baccouche, A., García-Zapirain, B., Castillo-Olea, C., & Elmaghraby, A. S. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2021.018461 · Cited by 67 · see citing works
The Integration of Radiomics and Artificial Intelligence in Modern Medicine
Maniaci, A., Lavalle, S., Gagliano, C., Lentini, M., Masiello, E., Parisi, F. M., Iannella, G., Cilia, N. D., Salerno, V. M., Cusumano, G., et al. (2024) · Life · doi:10.3390/life14101248 · Cited by 66 · see citing works
“By offering an abundance of quantitative imaging features that capture the subtle but clinically significant aspects of medical images, radiomics can improve CAD systems [12].”
BackgroundYeo, M., Tahayori, B., Kok, H. K., Maingard, J., Kutaiba, N., Russell, J., Thijs, V., Jhamb, A., Chandra, R. V., Brooks, M., et al. (2021) · Journal of NeuroInterventional Surgery · doi:10.1136/neurintsurg-2020-017099 · Cited by 65 · see citing works
“49 Nonethe-less, TL has been applied successfully in breast tumour diagnosis 50 51 and skin cancer classification.”
MethodAlotaibi, M. O. S., Aljouie, A., Alluhaidan, N., Qureshi, W., Almatar, H., Alduhayan, R., Alsomaie, B., & Almazroa, A. A. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e22406 · Cited by 68 · see citing works
“VGG19 has been widely used to achieve good results in the medical field [25,31,32].”
BackgroundMokni, R., Ayed, N. G. B., Damak, A., Sellami, D., Feki, W., & Mnif, Z. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102914 · Cited by 63 · see citing works
Qu, X., Lu, H., Tang, W., Wang, S., Zheng, D., Hou, Y., & Jiang, J. (2022) · Medical Physics · doi:10.1002/mp.15852 · Cited by 61 · see citing works
Machine learning for radiomics-based multimodality and multiparametric modeling
Wei, L., Osman, S. O. S., Hatt, M., & Naqa, I. E. (2019) · The Quarterly Journal of Nuclear Medicine and Molecular Imaging · doi:10.23736/s1824-4785.19.03213-8 · Cited by 61 · see citing works
Deep feature extraction and classification of breast ultrasound images
Kriti, Virmani, J., & Agarwal, R. (2020) · Multimedia tools and applications · doi:10.1007/s11042-020-09337-z · Cited by 45 · see citing works
Zhang, E., Seiler, S. J., Chen, M., Lu, W., & Gu, X. (2020) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ab7e7d · Cited by 61 · see citing works
Hu, Q., Whitney, H. M., Li, H., Ji, Y., Liu, P., & Giger, M. L. (2021) · Radiology Artificial Intelligence · doi:10.1148/ryai.2021200159 · Cited by 58 · see citing works
“The pooled features were then concatenated to form a final CNN feature vector of 1472 features for a given lesion and normalized again across all features (13,14).”
MethodDeep learning in breast radiology: current progress and future directions
Ou, W. C., Polat, D. S., & Doğan, B. E. (2021) · European Radiology · doi:10.1007/s00330-020-07640-9 · Cited by 57 · see citing works
Breast Tumor Classification in Ultrasound Images Using Combined Deep and Handcrafted Features
Daoud, M. I., Abdel-Rahman, S., Bdair, T. M., Al-Najar, M. S., Al‐Hawari, F., & Alazrai, R. (2020) · Sensors · doi:10.3390/s20236838 · Cited by 57 · see citing works
“Hence, the development of CNN models using limited BUS image datasets has become an important research challenge that was investigated in many previous studies [8,9,16,20–25].”
BackgroundMethodInfluentialQiu, X., Jiang, Y., Zhao, Q., Yan, C., Huang, M., & Jiang, T. (2020) · Journal of Ultrasound in Medicine · doi:10.1002/jum.15294 · Cited by 56 · see citing works
Arieno, A. L., Chan, A. H. L., & Destounis, S. V. (2018) · American Journal of Roentgenology · doi:10.2214/ajr.18.20391 · Cited by 57 · see citing works
A deep survival interpretable radiomics model of hepatocellular carcinoma patients
Wei, L., Owen, D., Rosen, B., Guo, X., Cuneo, K. C., Lawrence, T. S., Haken, R. K. T., & Naqa, I. E. (2021) · Physica Medica · doi:10.1016/j.ejmp.2021.02.013 · Cited by 55 · see citing works
Jones, M. A., Islam, W., Faiz, R., Chen, X., & Zheng, B. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.980793 · Cited by 59 · see citing works
- Authors
- Antropova, N., Huynh, B. Q., & Giger, M. L.
- Affiliations
- University of Chicago (US)
- Corresponding author
- Antropova, Natalia
- Venue
- Medical Physics
- Publisher
- Wiley
- Published
- 2017-08-12
- Volume
- 44
- Issue
- 10
- Pages
- 5162-5171
- ISSN
- 0094-2405 (ISSN-L)
- 2473-4209
- PMC
- PMC5646225
- OpenAlex
- W2725008604
- Cited by
- 389
- References
- 32
- Citations by year
- 2026: 10 · 2025: 27 · 2024: 39 · 2023: 59 · 2022: 65 · 2021: 63 · 2020: 48 · 2019: 49 · 2018: 29
- FWCI
- 26.45
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Medical Physics (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- Funders
- National Institutes of Health (T32 EB002103, U01CA195564)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- breast cancer diagnosis, computer-aided diagnosis, deep feature fusion, radiomics, pre-trained convolutional neural networks, handcrafted features, dynamic contrast-enhanced MRI, full-field digital mammography, breast ultrasound, benign versus malignant breast lesions, feature pooling
- MeSH terms
- Breast Neoplasms, Diagnosis, Computer-Assisted, Humans, Image Processing, Computer-Assisted, Retrospective Studies, ROC Curve, Neural Networks, Computer
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
