Cargando…

An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images

BACKGROUND: Determining the origin of bone metastatic cancer (OBMC) is of great significance to clinical therapeutics. It is challenging for pathologists to determine the OBMC with limited clinical information and bone biopsy. METHODS: We designed a regional multiple-instance learning algorithm to p...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhu, Lianghui, Shi, Huijuan, Wei, Huiting, Wang, Chengjiang, Shi, Shanshan, Zhang, Fenfen, Yan, Renao, Liu, Yiqing, He, Tingting, Wang, Liyuan, Cheng, Junru, Duan, Hufei, Du, Hong, Meng, Fengjiao, Zhao, Wenli, Gu, Xia, Guo, Linlang, Ni, Yingpeng, He, Yonghong, Guan, Tian, Han, Anjia
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9803701/
https://www.ncbi.nlm.nih.gov/pubmed/36577348
http://dx.doi.org/10.1016/j.ebiom.2022.104426
_version_ 1784861943545200640
author Zhu, Lianghui
Shi, Huijuan
Wei, Huiting
Wang, Chengjiang
Shi, Shanshan
Zhang, Fenfen
Yan, Renao
Liu, Yiqing
He, Tingting
Wang, Liyuan
Cheng, Junru
Duan, Hufei
Du, Hong
Meng, Fengjiao
Zhao, Wenli
Gu, Xia
Guo, Linlang
Ni, Yingpeng
He, Yonghong
Guan, Tian
Han, Anjia
author_facet Zhu, Lianghui
Shi, Huijuan
Wei, Huiting
Wang, Chengjiang
Shi, Shanshan
Zhang, Fenfen
Yan, Renao
Liu, Yiqing
He, Tingting
Wang, Liyuan
Cheng, Junru
Duan, Hufei
Du, Hong
Meng, Fengjiao
Zhao, Wenli
Gu, Xia
Guo, Linlang
Ni, Yingpeng
He, Yonghong
Guan, Tian
Han, Anjia
author_sort Zhu, Lianghui
collection PubMed
description BACKGROUND: Determining the origin of bone metastatic cancer (OBMC) is of great significance to clinical therapeutics. It is challenging for pathologists to determine the OBMC with limited clinical information and bone biopsy. METHODS: We designed a regional multiple-instance learning algorithm to predict the OBMC based on hematoxylin-eosin (H&E) staining slides alone. We collected 1041 cases from eight different hospitals and labeled 26,431 regions of interest to train the model. The performance of the model was assessed by ten-fold cross validation and external validation. Under the guidance of top3 predictions, we conducted an IHC test on 175 cases of unknown origins to compare the consistency of the results predicted by the model and indicated by the IHC markers. We also applied the model to identify whether there was tumor or not in a region, as well as distinguishing squamous cell carcinoma, adenocarcinoma, and neuroendocrine tumor. FINDINGS: In the within-cohort, our model achieved a top1-accuracy of 91.35% and a top3-accuracy of 97.75%. In the external cohort, our model displayed a good generalizability with a top3-accuracy of 97.44%. The top1 consistency between the results of the model and the immunohistochemistry markers was 83.90% and the top3 consistency was 94.33%. The model obtained an accuracy of 98.98% to identify whether there was tumor or not and an accuracy of 93.85% to differentiate three types of cancers. INTERPRETATION: Our model demonstrated good performance to predict the OBMC from routine histology and had great potential for assisting pathologists with determining the OBMC accurately. FUNDING: 10.13039/501100001809National Science Foundation of China (61875102 and 61975089), Natural Science Foundation of Guangdong province (2021A15-15012379 and 2022A1515 012550), Science and Technology Research Program of Shenzhen City (JCYJ20200109110606054 and WDZC20200821141349001), and 10.13039/501100004147Tsinghua University Spring Breeze Fund (2020Z99CFZ023).
format Online
Article
Text
id pubmed-9803701
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-98037012023-01-01 An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images Zhu, Lianghui Shi, Huijuan Wei, Huiting Wang, Chengjiang Shi, Shanshan Zhang, Fenfen Yan, Renao Liu, Yiqing He, Tingting Wang, Liyuan Cheng, Junru Duan, Hufei Du, Hong Meng, Fengjiao Zhao, Wenli Gu, Xia Guo, Linlang Ni, Yingpeng He, Yonghong Guan, Tian Han, Anjia eBioMedicine Articles BACKGROUND: Determining the origin of bone metastatic cancer (OBMC) is of great significance to clinical therapeutics. It is challenging for pathologists to determine the OBMC with limited clinical information and bone biopsy. METHODS: We designed a regional multiple-instance learning algorithm to predict the OBMC based on hematoxylin-eosin (H&E) staining slides alone. We collected 1041 cases from eight different hospitals and labeled 26,431 regions of interest to train the model. The performance of the model was assessed by ten-fold cross validation and external validation. Under the guidance of top3 predictions, we conducted an IHC test on 175 cases of unknown origins to compare the consistency of the results predicted by the model and indicated by the IHC markers. We also applied the model to identify whether there was tumor or not in a region, as well as distinguishing squamous cell carcinoma, adenocarcinoma, and neuroendocrine tumor. FINDINGS: In the within-cohort, our model achieved a top1-accuracy of 91.35% and a top3-accuracy of 97.75%. In the external cohort, our model displayed a good generalizability with a top3-accuracy of 97.44%. The top1 consistency between the results of the model and the immunohistochemistry markers was 83.90% and the top3 consistency was 94.33%. The model obtained an accuracy of 98.98% to identify whether there was tumor or not and an accuracy of 93.85% to differentiate three types of cancers. INTERPRETATION: Our model demonstrated good performance to predict the OBMC from routine histology and had great potential for assisting pathologists with determining the OBMC accurately. FUNDING: 10.13039/501100001809National Science Foundation of China (61875102 and 61975089), Natural Science Foundation of Guangdong province (2021A15-15012379 and 2022A1515 012550), Science and Technology Research Program of Shenzhen City (JCYJ20200109110606054 and WDZC20200821141349001), and 10.13039/501100004147Tsinghua University Spring Breeze Fund (2020Z99CFZ023). Elsevier 2022-12-26 /pmc/articles/PMC9803701/ /pubmed/36577348 http://dx.doi.org/10.1016/j.ebiom.2022.104426 Text en © 2022 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Articles
Zhu, Lianghui
Shi, Huijuan
Wei, Huiting
Wang, Chengjiang
Shi, Shanshan
Zhang, Fenfen
Yan, Renao
Liu, Yiqing
He, Tingting
Wang, Liyuan
Cheng, Junru
Duan, Hufei
Du, Hong
Meng, Fengjiao
Zhao, Wenli
Gu, Xia
Guo, Linlang
Ni, Yingpeng
He, Yonghong
Guan, Tian
Han, Anjia
An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images
title An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images
title_full An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images
title_fullStr An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images
title_full_unstemmed An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images
title_short An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images
title_sort accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images
topic Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9803701/
https://www.ncbi.nlm.nih.gov/pubmed/36577348
http://dx.doi.org/10.1016/j.ebiom.2022.104426
work_keys_str_mv AT zhulianghui anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT shihuijuan anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT weihuiting anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT wangchengjiang anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT shishanshan anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT zhangfenfen anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT yanrenao anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT liuyiqing anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT hetingting anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT wangliyuan anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT chengjunru anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT duanhufei anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT duhong anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT mengfengjiao anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT zhaowenli anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT guxia anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT guolinlang anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT niyingpeng anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT heyonghong anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT guantian anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT hananjia anaccuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT zhulianghui accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT shihuijuan accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT weihuiting accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT wangchengjiang accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT shishanshan accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT zhangfenfen accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT yanrenao accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT liuyiqing accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT hetingting accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT wangliyuan accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT chengjunru accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT duanhufei accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT duhong accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT mengfengjiao accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT zhaowenli accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT guxia accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT guolinlang accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT niyingpeng accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT heyonghong accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT guantian accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages
AT hananjia accuratepredictionoftheoriginforbonemetastaticcancerusingdeeplearningondigitalpathologicalimages