Cargando…

A multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study

Neoadjuvant therapy (NAT) is a major treatment option for locally advanced rectal cancer. With recent advancement of machine/deep learning algorithms, predicting the treatment response of NAT has become possible using radiological and/or pathological images. However, programs reported thus far are l...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Yihan, Liu, Xiaohua, Liu, Fang, Li, Yi, Xiong, Xiaomin, Sun, Hao, Lin, Bo, Li, Yu, Xu, Bo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10269576/
https://www.ncbi.nlm.nih.gov/pubmed/37334122
http://dx.doi.org/10.7717/peerj.15408
_version_ 1785059200759496704
author Wu, Yihan
Liu, Xiaohua
Liu, Fang
Li, Yi
Xiong, Xiaomin
Sun, Hao
Lin, Bo
Li, Yu
Xu, Bo
author_facet Wu, Yihan
Liu, Xiaohua
Liu, Fang
Li, Yi
Xiong, Xiaomin
Sun, Hao
Lin, Bo
Li, Yu
Xu, Bo
author_sort Wu, Yihan
collection PubMed
description Neoadjuvant therapy (NAT) is a major treatment option for locally advanced rectal cancer. With recent advancement of machine/deep learning algorithms, predicting the treatment response of NAT has become possible using radiological and/or pathological images. However, programs reported thus far are limited to binary classifications, and they can only distinguish the pathological complete response (pCR). In the clinical setting, the pathological NAT responses are classified as four classes: (TRG0-3), with 0 as pCR, 1 as moderate response, 2 as minimal response and 3 as poor response. Therefore, the actual clinical need for risk stratification remains unmet. By using ResNet (Residual Neural Network), we developed a multi-class classifier based on Hematoxylin-Eosin (HE) images to divide the response to three groups (TRG0, TRG1/2, and TRG3). Overall, the model achieved the AUC 0.97 at 40× magnification and AUC 0.89 at 10× magnification. For TRG0, the model under 40× magnification achieved a precision of 0.67, a sensitivity of 0.67, and a specificity of 0.95. For TRG1/2, a precision of 0.92, a sensitivity of 0.86, and a specificity of 0.89 were achieved. For TRG3, the model obtained a precision of 0.71, a sensitivity of 0.83, and a specificity of 0.88. To find the relationship between the treatment response and pathological images, we constructed a visual heat map of tiles using Class Activation Mapping (CAM). Notably, we found that tumor nuclei and tumor-infiltrating lymphocytes appeared to be potential features of the algorithm. Taken together, this multi-class classifier represents the first of its kind to predict different NAT responses in rectal cancer.
format Online
Article
Text
id pubmed-10269576
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-102695762023-06-16 A multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study Wu, Yihan Liu, Xiaohua Liu, Fang Li, Yi Xiong, Xiaomin Sun, Hao Lin, Bo Li, Yu Xu, Bo PeerJ Computational Biology Neoadjuvant therapy (NAT) is a major treatment option for locally advanced rectal cancer. With recent advancement of machine/deep learning algorithms, predicting the treatment response of NAT has become possible using radiological and/or pathological images. However, programs reported thus far are limited to binary classifications, and they can only distinguish the pathological complete response (pCR). In the clinical setting, the pathological NAT responses are classified as four classes: (TRG0-3), with 0 as pCR, 1 as moderate response, 2 as minimal response and 3 as poor response. Therefore, the actual clinical need for risk stratification remains unmet. By using ResNet (Residual Neural Network), we developed a multi-class classifier based on Hematoxylin-Eosin (HE) images to divide the response to three groups (TRG0, TRG1/2, and TRG3). Overall, the model achieved the AUC 0.97 at 40× magnification and AUC 0.89 at 10× magnification. For TRG0, the model under 40× magnification achieved a precision of 0.67, a sensitivity of 0.67, and a specificity of 0.95. For TRG1/2, a precision of 0.92, a sensitivity of 0.86, and a specificity of 0.89 were achieved. For TRG3, the model obtained a precision of 0.71, a sensitivity of 0.83, and a specificity of 0.88. To find the relationship between the treatment response and pathological images, we constructed a visual heat map of tiles using Class Activation Mapping (CAM). Notably, we found that tumor nuclei and tumor-infiltrating lymphocytes appeared to be potential features of the algorithm. Taken together, this multi-class classifier represents the first of its kind to predict different NAT responses in rectal cancer. PeerJ Inc. 2023-06-12 /pmc/articles/PMC10269576/ /pubmed/37334122 http://dx.doi.org/10.7717/peerj.15408 Text en ©2023 Wu et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited.
spellingShingle Computational Biology
Wu, Yihan
Liu, Xiaohua
Liu, Fang
Li, Yi
Xiong, Xiaomin
Sun, Hao
Lin, Bo
Li, Yu
Xu, Bo
A multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study
title A multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study
title_full A multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study
title_fullStr A multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study
title_full_unstemmed A multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study
title_short A multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study
title_sort multi-class classification algorithm based on hematoxylin-eosin staining for neoadjuvant therapy in rectal cancer: a retrospective study
topic Computational Biology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10269576/
https://www.ncbi.nlm.nih.gov/pubmed/37334122
http://dx.doi.org/10.7717/peerj.15408
work_keys_str_mv AT wuyihan amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT liuxiaohua amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT liufang amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT liyi amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT xiongxiaomin amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT sunhao amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT linbo amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT liyu amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT xubo amulticlassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT wuyihan multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT liuxiaohua multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT liufang multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT liyi multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT xiongxiaomin multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT sunhao multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT linbo multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT liyu multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy
AT xubo multiclassclassificationalgorithmbasedonhematoxylineosinstainingforneoadjuvanttherapyinrectalcanceraretrospectivestudy