Reinforced Auto-Zoom Net: Towards Accurate and Fast Breast Cancer Segmentation in Whole-Slide Images

• Main Authors: Dong, Nanqing, Kampffmeyer, Michael C, Liang, Xiaodan, Wang, Zeya, Dai, Wei, Xing, Eric P
• Format: Book Chapter
• Language: English
• Subjects: Breast cancer; Deep reinforcement learning; Fysikk: 430; Matematikk og Naturvitenskap: 400; Mathematics and natural science: 400; Medical image segmentation; Physics: 430; VDP; Whole-slide images
• ISSN: 1611-3349; 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-00889-5_36

Convolutional neural networks have led to significant breakthroughs in the domain of medical image analysis. However, the task of breast cancer segmentation in whole-slide images (WSIs) is still underexplored. WSIs are large histopathological images with extremely high resolution. Constrained by the hardware and field of view, using high-magnification patches can slow down the inference process and using low-magnification patches can cause the loss of information. In this paper, we aim to achieve two seemingly conflicting goals for breast cancer segmentation: accurate and fast prediction. We propose a simple yet efficient framework Reinforced Auto-Zoom Net (RAZN) to tackle this task. Motivated by the zoom-in operation of a pathologist using a digital microscope, RAZN learns a policy network to decide whether zooming is required in a given region of interest. Because the zoom-in action is selective, RAZN is robust to unbalanced and noisy ground truth labels and can efficiently reduce overfitting. We evaluate our method on a public breast cancer dataset. RAZN outperforms both single-scale and multi-scale baseline approaches, achieving better accuracy at low inference cost.