Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification

Abstract

We propose a patch sampling strategy based on a sequential Monte-Carlo method for high resolution image classification in the context of Multiple Instance Learning. When compared with grid sampling and uniform sampling techniques, it achieves higher generalization performance. We validate the strategy on two artificial datasets and two histological datasets for breast cancer and sun exposure classification.

accepted at 4th International Workshop on Deep Learning for Medical Image Analysis (DLMIA), MICCAI 2018, Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer International Publishing, 2018

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Attention-based Deep Multiple Instance Learning
• Revisiting Multiple Instance Neural Networks
• Fully Convolutional Multi-Class Multiple Instance Learning

Cited by in corpus (9)

• Correcting rural building annotations in OpenStreetMap using convolutional neural networks
• MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images
• Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses
• Conditional Generative Adversarial Networks for Data Augmentation and Adaptation in Remotely Sensed Imagery
• Gesture-aware Interactive Machine Teaching with In-situ Object Annotations
• Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean
• Spatial-temporal V-Net for automatic segmentation and quantification of right ventricles in gated myocardial perfusion SPECT images
• SemSegLoss: A python package of loss functions for semantic segmentation
• Machine learning application to Fermi-LAT data: sharpening all-sky map and emphasizing variable sources