Fast ScanNet: Fast and Dense Analysis of Multi-Gigapixel Whole-Slide Images for Cancer Metastasis Detection

• Published in: IEEE transactions on medical imaging Vol. 38; no. 8; pp. 1948 - 1958
• Main Authors: Lin, Huangjing, Chen, Hao, Graham, Simon, Dou, Qi, Rajpoot, Nasir, Heng, Pheng-Ann
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Breast cancer; computational pathology; Deep Learning; Histocytochemistry; Histology; Histopathology image analysis; Human performance; Humans; Image analysis; Image detection; Image Interpretation, Computer-Assisted - methods; Image segmentation; Localization; Lymph nodes; Lymph Nodes - diagnostic imaging; Lymph Nodes - pathology; Lymphatic Metastasis - diagnostic imaging; Lymphatic Metastasis - pathology; Lymphatic system; Machine learning; Medical imaging; Metastases; Metastasis; metastasis detection; State of the art; Task analysis; Technology assessment; Tumors; whole-slide image; Workload
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2019.2891305

Lymph node metastasis is one of the most important indicators in breast cancer diagnosis, that is traditionally observed under the microscope by pathologists. In recent years, with the dramatic advance of high-throughput scanning and deep learning technology, automatic analysis of histology from whole-slide images has received a wealth of interest in the field of medical image computing, which aims to alleviate pathologists' workload and simultaneously reduce misdiagnosis rate. However, the automatic detection of lymph node metastases from whole-slide images remains a key challenge because such images are typically very large, where they can often be multiple gigabytes in size. Also, the presence of hard mimics may result in a large number of false positives. In this paper, we propose a novel method with anchor layers for model conversion, which not only leverages the efficiency of fully convolutional architectures to meet the speed requirement in clinical practice but also densely scans the whole-slide image to achieve accurate predictions on both micro- and macro-metastases. Incorporating the strategies of asynchronous sample prefetching and hard negative mining, the network can be effectively trained. The efficacy of our method is corroborated on the benchmark dataset of 2016 Camelyon Grand Challenge. Our method achieved significant improvements in comparison with the state-of-the-art methods on tumor localization accuracy with a much faster speed and even surpassed human performance on both challenge tasks.