Few-shot breast cancer metastases classification via unsupervised cell ranking

Tumor metastases detection is of great importance for the treatment of breast cancer patients. Various CNN (convolutional neural network) based methods get excellent performance in object detection/segmentation. However, the detection of metastases in hematoxylin and eosin (H&E) stained whole-sl...

Full description

Saved in:
Bibliographic Details
Main Authors: CHEN, Jiaojiao, JIAO, Jianbo, HE, Shengfeng, HAN, Guoqiang, QIN, Jing
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7859
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8862
record_format dspace
spelling sg-smu-ink.sis_research-88622023-06-15T09:00:05Z Few-shot breast cancer metastases classification via unsupervised cell ranking CHEN, Jiaojiao JIAO, Jianbo HE, Shengfeng HAN, Guoqiang QIN, Jing Tumor metastases detection is of great importance for the treatment of breast cancer patients. Various CNN (convolutional neural network) based methods get excellent performance in object detection/segmentation. However, the detection of metastases in hematoxylin and eosin (H&E) stained whole-slide images (WSI) is still challenging mainly due to two aspects. (1) The resolution of the image is too large. (2) lacking labeled training data. Whole-slide images generally stored in a multi-resolution structure with multiple downsampled tiles. It is difficult to feed the whole image into memory without compression. Moreover, labeling images for the pathologists are time-consuming and expensive. In this paper, we study the problem of detecting breast cancer metastases in the pathological image on patch level. To address the abovementioned challenges, we propose a few-shot learning method to classify whether an image patch contains tumor cells. Specifically, we propose a patch-level unsupervised cell ranking approach, which only relies on images with limited labels. The main idea of the proposed method is that when cropping a patch A from the WSI and further cropping a sub-patch B from A, the cell number of A is always larger than that of B. Based on this observation, we make use of the unlabeled images to learn the ranking information of cell counting to extract the abstract features. Experimental results show that our method is effective to improve the patch-level classification accuracy, compared to the traditional supervised method. The source code is publicly available at https://github.com/fewshot-camelyon. 2021-09-01T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/7859 info:doi/10.1109/TCBB.2019.2960019 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Breast cancer Pathology Tumors Machine learning Training data Task analysis Few-shot learning metastases classification unsupervised learning Information Security
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Breast cancer
Pathology
Tumors
Machine learning
Training data
Task analysis
Few-shot learning
metastases classification
unsupervised learning
Information Security
spellingShingle Breast cancer
Pathology
Tumors
Machine learning
Training data
Task analysis
Few-shot learning
metastases classification
unsupervised learning
Information Security
CHEN, Jiaojiao
JIAO, Jianbo
HE, Shengfeng
HAN, Guoqiang
QIN, Jing
Few-shot breast cancer metastases classification via unsupervised cell ranking
description Tumor metastases detection is of great importance for the treatment of breast cancer patients. Various CNN (convolutional neural network) based methods get excellent performance in object detection/segmentation. However, the detection of metastases in hematoxylin and eosin (H&E) stained whole-slide images (WSI) is still challenging mainly due to two aspects. (1) The resolution of the image is too large. (2) lacking labeled training data. Whole-slide images generally stored in a multi-resolution structure with multiple downsampled tiles. It is difficult to feed the whole image into memory without compression. Moreover, labeling images for the pathologists are time-consuming and expensive. In this paper, we study the problem of detecting breast cancer metastases in the pathological image on patch level. To address the abovementioned challenges, we propose a few-shot learning method to classify whether an image patch contains tumor cells. Specifically, we propose a patch-level unsupervised cell ranking approach, which only relies on images with limited labels. The main idea of the proposed method is that when cropping a patch A from the WSI and further cropping a sub-patch B from A, the cell number of A is always larger than that of B. Based on this observation, we make use of the unlabeled images to learn the ranking information of cell counting to extract the abstract features. Experimental results show that our method is effective to improve the patch-level classification accuracy, compared to the traditional supervised method. The source code is publicly available at https://github.com/fewshot-camelyon.
format text
author CHEN, Jiaojiao
JIAO, Jianbo
HE, Shengfeng
HAN, Guoqiang
QIN, Jing
author_facet CHEN, Jiaojiao
JIAO, Jianbo
HE, Shengfeng
HAN, Guoqiang
QIN, Jing
author_sort CHEN, Jiaojiao
title Few-shot breast cancer metastases classification via unsupervised cell ranking
title_short Few-shot breast cancer metastases classification via unsupervised cell ranking
title_full Few-shot breast cancer metastases classification via unsupervised cell ranking
title_fullStr Few-shot breast cancer metastases classification via unsupervised cell ranking
title_full_unstemmed Few-shot breast cancer metastases classification via unsupervised cell ranking
title_sort few-shot breast cancer metastases classification via unsupervised cell ranking
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/7859
_version_ 1770576570928332800