Inconsistent Performance of Deep Learning Models on Mammogram Classification

Akselrod-Ballin, 2019, Predicting breast cancer by applying deep learning to linked health records and mammograms, Radiology, 292, 331, 10.1148/radiol.2019182622 Choe, 2019, Deep learning-based image conversion of CT reconstruction kernels improves radiomics reproducibility for pulmonary nodules or masses, Radiology, 292, 365, 10.1148/radiol.2019181960 Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 115, 10.1038/nature21056 Liang G, Fouladvand S, Zhang J, Brooks M, Jacobs N, Chen J. GANai: standardizing CT images using generative adversarial network with alternative improvement. 2019 IEEE International Conference on Health Informatics (ICHI). Xi’an, Shanxi, China, June, 10-13, 2019. Mihail, 2019, Automatic hand skeletal shape estimation from radiographs, IEEE Trans Nanobioscience, 18, 296, 10.1109/TNB.2019.2911026 Ribli, 2018, Detecting and classifying lesions in mammograms with deep learning, Sci Rep, 8, 4165, 10.1038/s41598-018-22437-z Anthimopoulos, 2016, Lung pattern classification for interstitial lung diseases using a deep convolutional neural network, IEEE Trans Med Imaging, 35, 1207, 10.1109/TMI.2016.2535865 Gupta, 2018, CNN-based projected gradient descent for consistent CT image reconstruction, IEEE Trans Med Imaging, 37, 1440, 10.1109/TMI.2018.2832656 Janowczyk, 2016, Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases, J Pathol Inform, 7, 29, 10.4103/2153-3539.186902 Lee, 2018, A deep-learning system for fully-automated peripherally inserted central catheter (PICC) tip detection, J Digit Imaging, 31, 393, 10.1007/s10278-017-0025-z Tseng K, Lin Y, Hsu W, Huang C. Joint sequence learning and cross-modality convolution for 3D biomedical segmentation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, Hawaii, July, 10-13, 2017:3739-3746. Yang, 2018, Low-Dose CT Image denoising using a generative adversarial network with Wasserstein distance and perceptual loss, IEEE Trans Med Imaging, 37, 1348, 10.1109/TMI.2018.2827462 Dhungel N, Carneiro G, Bradley A. Automated mass detection in mammograms using cascaded deep learning and random forests. 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA). Adelaide, Australia. November 23-25, 2015. Jadoon, 2017, Three-class mammogram classification based on descriptive CNN features, Biomed Res Int, 2017, 3640901, 10.1155/2017/3640901 Lévy D, Jain A. Breast mass classification from mammograms using deep convolutional neural networks. 2016. arxiv.org/abs/1612.00542. Mendel, 2019, Transfer learning from convolutional neural networks for computer-aided diagnosis: a comparison of digital breast tomosynthesis and full-field digital mammography, Acad Radiol, 26, 735, 10.1016/j.acra.2018.06.019 Yi D, Sawyer RL, Cohn D, Dunnmon J, Lam C, Xiao X, Rubin D. Optimizing and visualizing deep learning for benign/malignant classification in breast tumors. 2017. arXiv:170506362. Dhungel, 2015, Deep learning and structured prediction for the segmentation of mass in mammograms, Med Image Comput Comput Assist Interv, 9349, 605 Cole, 2014, Impact of computer-aided detection systems on radiologist accuracy with digital mammography, AJR Am J Roentgenol, 203, 909, 10.2214/AJR.12.10187 Sahiner, 2019, Deep learning in medical imaging and radiation therapy, Med Phys, 46, e1, 10.1002/mp.13264 Abdelhafiz, 2019, Deep convolutional neural networks for mammography: advances, challenges and applications, BMC Bioinformatics, 20, 281, 10.1186/s12859-019-2823-4 Bray, 2018, Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA Cancer J Clin, 68, 394, 10.3322/caac.21492 McGuire, 2016, World Cancer Report 2014. Geneva, Switzerland: World Health Organization, International Agency for Research on Cancer, WHO Press, 2015, Adv Nutr, 7, 418, 10.3945/an.116.012211 Siegel, 2016, Cancer statistics, 2016, CA Cancer J Clin, 66, 7, 10.3322/caac.21332 Siegel, 2019, Cancer statistics, 2019, CA Cancer J Clin, 69, 7, 10.3322/caac.21551 Gardezi, 2019, Breast cancer detection and diagnosis using mammographic data: systematic review, J Med Internet Res, 21, e14464, 10.2196/14464 Harvey, 2019, Deep learning in breast cancer screening, 187 Tsochatzidis, 2019, Deep learning for breast cancer diagnosis from mammograms—a comparative study, J Imaging, 5 Wu, 2019, Deep neural networks improve radiologists’ performance in breast cancer screening [E-pub ahead of print], IEEE Trans Med Imaging Shen, 2017, End-to-end training for whole image breast cancer diagnosis using an all convolutional design, Sci Rep, 9 Heath M, Bowyer K, Kopans D, Moore R, Kegelmeyer WP. The digital database for screening mammography. Proceedings of the 5th International Workshop on Digital Mammography. 212-218, Medical Physics Publishing, Madison, 2001. Moreira, 2012, INbreast: toward a full-field digital mammographic database, Acad Radiol, 19, 236, 10.1016/j.acra.2011.09.014 Suckling J, Parker J, Dance D, et al. (2015). Mammographic Image Analysis Society (MIAS) database v1.21 [Dataset]. Chen Q, Liu J, Luo K, Zhang X, Wang X. Transfer deep learning mammography diagnostic model from public datasets to clinical practice: a comparison of model performance and mammography datasets. The Fourteenth International Workshop on Breast Imaging (IWBI 2018):10718. International Society for Optics and Photonics. Bellingham, USA, 2018. Lee, 2017, A curated mammography data set for use in computer-aided detection and diagnosis research, Sci Data, 4, 170177, 10.1038/sdata.2017.177 Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, June 20-25, 2009. http://www.image-net.org/papers/imagenet_cvpr09.pdf. Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. MIT Press, 2016. Olivas ES. Handbook of research on machine learning applications and trends: algorithms, methods, and techniques. IGI Global, 2009. Dai J, Li Y, He K, Sun J. R-FCN: Object detection via region-based fully convolutional networks. 2016. arxiv.org/abs/1605.06409. Redmon J, Farhadi A. YOLO9000: better, faster, stronger. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263-7271. Honolulu, Hawaii, July 22-25, 2017. Krizhevsky, 2017, ImageNet classification with deep convolutional neural networks, Commun ACM, 60, 84, 10.1145/3065386 Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. arxiv.org/abs/1409.1556. He, 2016, Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770 Liang, 2017, Radiomic features of lung cancer and their dependency on CT image acquisition parameters, Med Phys, 44, 3024 Geras, 2019, Artificial intelligence for mammography and digital breast tomosynthesis: current concepts and future perspectives, Radiology, 293, 246, 10.1148/radiol.2019182627 Kim, 2019, Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers, Korean J Radiol, 20, 405, 10.3348/kjr.2019.0025 Hosny, 2018, Artificial intelligence in radiology, Nat Rev Cancer, 18, 500, 10.1038/s41568-018-0016-5 Thrall, 2018, Artificial intelligence and machine learning in radiology: opportunities, challenges, pitfalls, and criteria for success, J Am Coll Radiol, 15, 504, 10.1016/j.jacr.2017.12.026 Rubin, 2019, Artificial intelligence in imaging: the radiologist's role, J Am Coll Radiol, 16, 1309, 10.1016/j.jacr.2019.05.036