Improving whole slide segmentation through visual context: a systematic study

Conference item

While challenging, the dense segmentation of histology images is a necessary first step to assess changes in tissue architecture and cellular morphology. Although specific convolutional neural network architectures have been applied with great success to the problem, few effectively incorporate visual context information from multiple scales. With this paper, we present a systematic comparison of different architectures to assess how including multi-scale information affects segmentation performance. A publicly available breast cancer and a locally collected prostate cancer datasets are being utilised for this study. The results support our hypothesis that visual context and scale plays a crucial role in histology image classification problems.

Authors: Sirinukunwattana, K; Khalid Alham, N; Verrill, C; Rittscher, J

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer, Cham
• Host title: MICCAI 2018: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018
• Journal: International Conference On Medical Image Computing & Computer Assisted Intervention (MICCAI) 2018
• Volume: 11071
• Pages: 192-200
• Series: Lecture Notes in Computer Science
• Publication date: 2018-09-26
• Acceptance date: 2018-05-30
• DOI: 10.1007/978-3-030-00934-2_22
• ISSN: 0302-9743
• ISBN: 9783030009342
• Keywords: whole slide imaging; digital pathology; deep learning; dense segmentation