Multi-Stage Pathological Image Classification using Semantic Segmentation

10/10/2019
by   Shusuke Takahama, et al.
14

Histopathological image analysis is an essential process for the discovery of diseases such as cancer. However, it is challenging to train CNN on whole slide images (WSIs) of gigapixel resolution considering the available memory capacity. Most of the previous works divide high resolution WSIs into small image patches and separately input them into the model to classify it as a tumor or a normal tissue. However, patch-based classification uses only patch-scale local information but ignores the relationship between neighboring patches. If we consider the relationship of neighboring patches and global features, we can improve the classification performance. In this paper, we propose a new model structure combining the patch-based classification model and whole slide-scale segmentation model in order to improve the prediction performance of automatic pathological diagnosis. We extract patch features from the classification model and input them into the segmentation model to obtain a whole slide tumor probability heatmap. The classification model considers patch-scale local features, and the segmentation model can take global information into account. We also propose a new optimization method that retains gradient information and trains the model partially for end-to-end learning with limited GPU memory capacity. We apply our method to the tumor/normal prediction on WSIs and the classification performance is improved compared with the conventional patch-based method.

READ FULL TEXT

page 1

page 6

research
10/31/2018

Methods for Segmentation and Classification of Digital Microscopy Tissue Images

High-resolution microscopy images of tissue specimens provide detailed i...
research
06/30/2021

Fast whole-slide cartography in colon cancer histology using superpixels and CNN classification

Whole-slide-image cartography is the process of automatically detecting ...
research
05/09/2018

Fast and Accurate Tumor Segmentation of Histology Images using Persistent Homology and Deep Convolutional Features

Tumor segmentation in whole-slide images of histology slides is an impor...
research
01/06/2020

Multi-scale domain-adversarial multiple-instance CNN for cancer subtype classification with non-annotated histopathological images

We propose a new method for cancer subtype classification from histopath...
research
08/19/2021

Patch-Based Cervical Cancer Segmentation using Distance from Boundary of Tissue

Pathological diagnosis is used for examining cancer in detail, and its a...
research
04/29/2022

Understanding the impact of image and input resolution on deep digital pathology patch classifiers

We consider annotation efficient learning in Digital Pathology (DP), whe...
research
09/14/2021

Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning

Medulloblastoma (MB) is a primary central nervous system tumor and the m...

Please sign up or login with your details

Forgot password? Click here to reset