Hematoxylin and Eosin (HE) Stained Liver Portal Area Segmentation Using Multi-Scale Receptive Field Convolutional Neural Network

Qi En Xiao, Pau Choo Chung, Hung Wen Tsai, Kuo Sheng Cheng, Nan Haw Chow, Ying Zong Juang, Hann Huei Tsai, Cheng Hsiung Wang, Tsan An Hsieh

研究成果: Article

摘要

Portal area segmentation is an important step in the quantitative histological analysis process for hepatitis grading. However, portal areas often appear of different sizes and appearances due to the variations of surrounding components such as the ductule, bile duct, artery, and portal vein. The slim fibrosis expanding from the portal area further increases challenges of the portal area segmentation. A Multi-scale Receptive Field Convolutional Neural Network (MRF-CNN) for the segmentation of the liver portal areas in hematoxylin and eosin (HE) stained whole slide images (WSIs) is proposed in this paper. The MRF-CNN adopts the atrous spatial pyramid pooling (ASPP) with multiple atrous rates and symmetric encoder-decoder with feature concatenation architecture. The atrous rates in ASPP are devised of receptive fields to extract features of meaningful tissue components in parallel in portal areas. Along with the MRF-CNN, a small object sensitive loss function is also proposed to have the network focus on small portal areas and slim fibrosis. The results show that the proposed model achieves Intersection over Union (IOU) of 0.87 and sensitivity of 0.92. Compared to recent segmentation researches such as Fully Convolutional Network (FCN), U-Net and SegNet, the proposed network achieves an overall the best IOU and sensitivity performance. Experimental results also show that the designed ASPP block benefits in feature extraction, and the ability of identifying small objects in proposed small object sensitive loss has a significant improvement of the segmentation result comparing to the original cross entropy loss.

原文English
文章編號8892562
頁(從 - 到)623-634
頁數12
期刊IEEE Journal on Emerging and Selected Topics in Circuits and Systems
9
發行號4
DOIs
出版狀態Published - 2019 十二月

指紋

Liver
Neural networks
Ducts
Feature extraction
Entropy
Tissue
Chemical analysis

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

引用此文

@article{84e887020e6f43cd8499fea7899faf12,
title = "Hematoxylin and Eosin (HE) Stained Liver Portal Area Segmentation Using Multi-Scale Receptive Field Convolutional Neural Network",
abstract = "Portal area segmentation is an important step in the quantitative histological analysis process for hepatitis grading. However, portal areas often appear of different sizes and appearances due to the variations of surrounding components such as the ductule, bile duct, artery, and portal vein. The slim fibrosis expanding from the portal area further increases challenges of the portal area segmentation. A Multi-scale Receptive Field Convolutional Neural Network (MRF-CNN) for the segmentation of the liver portal areas in hematoxylin and eosin (HE) stained whole slide images (WSIs) is proposed in this paper. The MRF-CNN adopts the atrous spatial pyramid pooling (ASPP) with multiple atrous rates and symmetric encoder-decoder with feature concatenation architecture. The atrous rates in ASPP are devised of receptive fields to extract features of meaningful tissue components in parallel in portal areas. Along with the MRF-CNN, a small object sensitive loss function is also proposed to have the network focus on small portal areas and slim fibrosis. The results show that the proposed model achieves Intersection over Union (IOU) of 0.87 and sensitivity of 0.92. Compared to recent segmentation researches such as Fully Convolutional Network (FCN), U-Net and SegNet, the proposed network achieves an overall the best IOU and sensitivity performance. Experimental results also show that the designed ASPP block benefits in feature extraction, and the ability of identifying small objects in proposed small object sensitive loss has a significant improvement of the segmentation result comparing to the original cross entropy loss.",
author = "Xiao, {Qi En} and Chung, {Pau Choo} and Tsai, {Hung Wen} and Cheng, {Kuo Sheng} and Chow, {Nan Haw} and Juang, {Ying Zong} and Tsai, {Hann Huei} and Wang, {Cheng Hsiung} and Hsieh, {Tsan An}",
year = "2019",
month = "12",
doi = "10.1109/JETCAS.2019.2952063",
language = "English",
volume = "9",
pages = "623--634",
journal = "IEEE Journal on Emerging and Selected Topics in Circuits and Systems",
issn = "2156-3357",
publisher = "IEEE Circuits and Systems Society",
number = "4",

}

TY - JOUR

T1 - Hematoxylin and Eosin (HE) Stained Liver Portal Area Segmentation Using Multi-Scale Receptive Field Convolutional Neural Network

AU - Xiao, Qi En

AU - Chung, Pau Choo

AU - Tsai, Hung Wen

AU - Cheng, Kuo Sheng

AU - Chow, Nan Haw

AU - Juang, Ying Zong

AU - Tsai, Hann Huei

AU - Wang, Cheng Hsiung

AU - Hsieh, Tsan An

PY - 2019/12

Y1 - 2019/12

N2 - Portal area segmentation is an important step in the quantitative histological analysis process for hepatitis grading. However, portal areas often appear of different sizes and appearances due to the variations of surrounding components such as the ductule, bile duct, artery, and portal vein. The slim fibrosis expanding from the portal area further increases challenges of the portal area segmentation. A Multi-scale Receptive Field Convolutional Neural Network (MRF-CNN) for the segmentation of the liver portal areas in hematoxylin and eosin (HE) stained whole slide images (WSIs) is proposed in this paper. The MRF-CNN adopts the atrous spatial pyramid pooling (ASPP) with multiple atrous rates and symmetric encoder-decoder with feature concatenation architecture. The atrous rates in ASPP are devised of receptive fields to extract features of meaningful tissue components in parallel in portal areas. Along with the MRF-CNN, a small object sensitive loss function is also proposed to have the network focus on small portal areas and slim fibrosis. The results show that the proposed model achieves Intersection over Union (IOU) of 0.87 and sensitivity of 0.92. Compared to recent segmentation researches such as Fully Convolutional Network (FCN), U-Net and SegNet, the proposed network achieves an overall the best IOU and sensitivity performance. Experimental results also show that the designed ASPP block benefits in feature extraction, and the ability of identifying small objects in proposed small object sensitive loss has a significant improvement of the segmentation result comparing to the original cross entropy loss.

AB - Portal area segmentation is an important step in the quantitative histological analysis process for hepatitis grading. However, portal areas often appear of different sizes and appearances due to the variations of surrounding components such as the ductule, bile duct, artery, and portal vein. The slim fibrosis expanding from the portal area further increases challenges of the portal area segmentation. A Multi-scale Receptive Field Convolutional Neural Network (MRF-CNN) for the segmentation of the liver portal areas in hematoxylin and eosin (HE) stained whole slide images (WSIs) is proposed in this paper. The MRF-CNN adopts the atrous spatial pyramid pooling (ASPP) with multiple atrous rates and symmetric encoder-decoder with feature concatenation architecture. The atrous rates in ASPP are devised of receptive fields to extract features of meaningful tissue components in parallel in portal areas. Along with the MRF-CNN, a small object sensitive loss function is also proposed to have the network focus on small portal areas and slim fibrosis. The results show that the proposed model achieves Intersection over Union (IOU) of 0.87 and sensitivity of 0.92. Compared to recent segmentation researches such as Fully Convolutional Network (FCN), U-Net and SegNet, the proposed network achieves an overall the best IOU and sensitivity performance. Experimental results also show that the designed ASPP block benefits in feature extraction, and the ability of identifying small objects in proposed small object sensitive loss has a significant improvement of the segmentation result comparing to the original cross entropy loss.

UR - http://www.scopus.com/inward/record.url?scp=85074830018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074830018&partnerID=8YFLogxK

U2 - 10.1109/JETCAS.2019.2952063

DO - 10.1109/JETCAS.2019.2952063

M3 - Article

AN - SCOPUS:85074830018

VL - 9

SP - 623

EP - 634

JO - IEEE Journal on Emerging and Selected Topics in Circuits and Systems

JF - IEEE Journal on Emerging and Selected Topics in Circuits and Systems

SN - 2156-3357

IS - 4

M1 - 8892562

ER -