Domain Generalization for Mammographic Image Analysis with Contrastive Learning

The deep learning technique has been shown to be effectively addressed several image analysis tasks in the computer-aided diagnosis scheme for mammography. The training of an efficacious deep learning model requires large data with diverse styles and qualities. The diversity of data often comes from the use of various scanners of vendors. But, in practice, it is impractical to collect a sufficient amount of diverse data for training. To this end, a novel contrastive learning is developed to equip the deep learning models with better style generalization capability. Specifically, the multi-style and multi-view unsupervised self-learning scheme is carried out to seek robust feature embedding against style diversity as a pretrained model. Afterward, the pretrained network is further fine-tuned to the downstream tasks, e.g., mass detection, matching, BI-RADS rating, and breast density classification. The proposed method has been evaluated extensively and rigorously with mammograms from various vendor style domains and several public datasets. The experimental results suggest that the proposed domain generalization method can effectively improve performance of four mammographic image tasks on the data from both seen and unseen domains, and outperform many state-of-the-art (SOTA) generalization methods.

[1]  M. Ghassemi,et al.  The medical algorithmic audit. , 2022, The Lancet. Digital health.

[2]  Oliver Díaz,et al.  Artificial Intelligence In Medicine , 2022 .

[3]  A. Jemal,et al.  Cancer statistics, 2022 , 2022, CA: a cancer journal for clinicians.

[4]  Dinggang Shen,et al.  Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning , 2021, MICCAI.

[5]  Hyeran Byun,et al.  Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization , 2021, ACM Multimedia.

[6]  Yoshua Bengio,et al.  Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization , 2021, NeurIPS.

[7]  Qifei Wang,et al.  Adversarially Adaptive Normalization for Single Domain Generalization , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Gwénolé Quellec,et al.  Towards improved breast mass detection using dual-view mammogram matching , 2021, Medical Image Anal..

[9]  Seunghyun Park,et al.  SelfReg: Self-supervised Contrastive Regularization for Domain Generalization , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[10]  Mohamed Abdel-Mottaleb,et al.  Convolutional neural networks for breast cancer detection in mammography: A survey , 2021, Comput. Biol. Medicine.

[11]  Shekoofeh Azizi,et al.  Big Self-Supervised Models Advance Medical Image Classification , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[12]  William Lotter,et al.  Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach , 2021, Nature Medicine.

[13]  Andrew Y. Ng,et al.  MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models , 2020, MIDL.

[14]  Kevin Smith,et al.  External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms. , 2020, JAMA oncology.

[15]  Xu Li,et al.  Domain generalization in rotating machinery fault diagnostics using deep neural networks , 2020, Neurocomputing.

[16]  Lequan Yu,et al.  Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization , 2020, ECCV.

[17]  Pheng-Ann Heng,et al.  Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains , 2020, MICCAI.

[18]  Zhi Tian,et al.  FCOS: A Simple and Strong Anchor-Free Object Detector , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Pierre H. Richemond,et al.  Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning , 2020, NeurIPS.

[20]  Amit Sharma,et al.  Domain Generalization using Causal Matching , 2020, ICML.

[21]  Jianhua Yao,et al.  Unsupervised domain adaptation with adversarial learning for mass detection in mammogram , 2020, Neurocomputing.

[22]  Kaiming He,et al.  Improved Baselines with Momentum Contrastive Learning , 2020, ArXiv.

[23]  R. Duits,et al.  Lesion Segmentation in Ultrasound Using Semi-Pixel-Wise Cycle Generative Adversarial Nets , 2020, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[24]  Changhe Tu,et al.  Unsupervised Learning of Intrinsic Structural Representation Points , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Aaron C. Courville,et al.  Out-of-Distribution Generalization via Risk Extrapolation (REx) , 2020, ICML.

[26]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[27]  Daguang Xu,et al.  Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation , 2020, IEEE Transactions on Medical Imaging.

[28]  David S. Melnick,et al.  International evaluation of an AI system for breast cancer screening , 2020, Nature.

[29]  Jiye G. Kim,et al.  Robust breast cancer detection in mammography and digital breast tomosynthesis using annotation-efficient deep learning approach , 2019, ArXiv.

[30]  Ross B. Girshick,et al.  Momentum Contrast for Unsupervised Visual Representation Learning , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Daniel C. Castro,et al.  Domain Generalization via Model-Agnostic Learning of Semantic Features , 2019, NeurIPS.

[32]  K. Keutzer,et al.  Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[33]  Zhitang Chen,et al.  Domain Generalization via Multidomain Discriminant Analysis , 2019, UAI.

[34]  Changick Kim,et al.  Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Slobodan Ilic,et al.  DeceptionNet: Network-Driven Domain Randomization , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[36]  Fabio Maria Carlucci,et al.  Domain Generalization by Solving Jigsaw Puzzles , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Yingli Tian,et al.  Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  L. Gool,et al.  DLOW: Domain Flow for Adaptation and Generalization , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Jaewoo Kang,et al.  Detection of masses in mammograms using a one-stage object detector based on a deep convolutional neural network , 2018, PloS one.

[40]  Xiaoou Tang,et al.  Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net , 2018, ECCV.

[41]  Luis Miguel Bergasa,et al.  Train Here, Deploy There: Robust Segmentation in Unseen Domains , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[42]  Silvio Savarese,et al.  Generalizing to Unseen Domains via Adversarial Data Augmentation , 2018, NeurIPS.

[43]  Gilles Blanchard,et al.  Domain Generalization by Marginal Transfer Learning , 2017, J. Mach. Learn. Res..

[44]  Donald A. Adjeroh,et al.  Unified Deep Supervised Domain Adaptation and Generalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[45]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[46]  Jaime S. Cardoso,et al.  INbreast: toward a full-field digital mammographic database. , 2012, Academic radiology.

[47]  Qingxia Wu,et al.  Whole Mammography Diagnosis via Multi-instance Supervised Discriminative Localization and Classification , 2022, MLMI@MICCAI.

[48]  Yide Ma,et al.  BASCNet: Bilateral adaptive spatial and channel attention network for breast density classification in the mammogram , 2021, Biomed. Signal Process. Control..

[49]  Yanbo Zhang,et al.  MommiNet-v2: Mammographic multi-view mass identification networks , 2021 .

[50]  Dinggang Shen,et al.  Self-adversarial Learning for Detection of Clustered Microcalcifications in Mammograms , 2021, MICCAI.

[51]  Tongliang Liu,et al.  Domain Generalization via Entropy Regularization , 2020, NeurIPS.

[52]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[53]  Richard H. Moore,et al.  THE DIGITAL DATABASE FOR SCREENING MAMMOGRAPHY , 2007 .