Semi-supervised breast cancer histology classification using deep multiple instance learning and contrast predictive coding (Conference Presentation)
Ming Y. Lu, Richard J. Chen, Faisal Mahmood
Abstract
Subjective interpretation of histology slides forms the basis of cancer diagnosis, prognosis, and therapeutic response prediction. Deep learning models can potentially help serve as an efficient, unbiased tool for this task if trained on large amounts of labeled data. However, labeled medical data, such as small regions of interests, are often costly to curate. In this work, we propose a flexible, semi-supervised framework for histopathological classification that first uses Contrastive Predictive Coding (CPC) to learn semantic features in an unsupervised manner and then use an attention-based multiple Instance Learning (MIL) for classification without requiring patch-level annotations.
Topics & Concepts
Computer scienceArtificial intelligenceMachine learningCoding (social sciences)Predictive codingDeep learningContrast (vision)Breast cancerSupervised learningNatural language processingPattern recognition (psychology)CancerArtificial neural networkMedicineMathematicsInternal medicineStatisticsAI in cancer detectionColorectal Cancer Screening and DetectionRadiomics and Machine Learning in Medical Imaging