Differentiation and risk stratification of basal cell carcinoma with deep learning on histopathologic images and measuring nuclei and tumor microenvironment features

Author:

Lan Xuemei1ORCID,Guo Guanchen2,Wang Xiaopo1ORCID,Yan Qiao3,Xue Ruzeng4,Li Yufen1,Zhu Jiaping1,Dong Zhengbang3,Wang Fei3,Li Guomin4,Wang Xiangxue2,Xu Jun2,Jiang Yiqun1

Affiliation:

1. Department of Dermatopathology Hospital for Skin Diseases Institute of Dermatology Chinese Academy of Medical Sciences & Peking Union Medical College, Nanjing Jiangsu China

2. lnstitute for Al in Medicine School of Artificial lntelligence Nanjing University of Information Science and Technology Nanjing China

3. Department of Dermatology School of Medicine Zhong Da Hospital Southeast University Nanjing China

4. Dermatology Hospital Southern Medical University Guangzhou China

Abstract

AbstractBackgroundNuclear pleomorphism and tumor microenvironment (TME) play a critical role in cancer development and progression. Identifying most predictive nuclei and TME features of basal cell carcinoma (BCC) may provide insights into which characteristics pathologists can use to distinguish and stratify this entity.ObjectivesTo develop an automated workflow based on nuclei and TME features from basaloid cell tumor regions to differentiate BCC from trichoepithelioma (TE) and stratify BCC into high‐risk (HR) and low‐risk (LR) subtypes, and to identify the nuclear and TME characteristics profile of different basaloid cell tumors.MethodsThe deep learning systems were trained on 161 H&E ‐stained sections which contained 51 sections of HR‐BCC, 50 sections of LR‐BCC and 60 sections of TE from one institution (D1), and externally and independently validated on D2 (46 sections) and D3 (76 sections), from 2015 to 2022. 60%, 20% and 20% of D1 data were randomly splitted for training, validation and testing, respectively. The framework comprised four stages: tumor regions identification by multi‐head self‐attention (MSA) U‐Net, nuclei segmentation by HoVer‐Net, quantitative feature by handcrafted extraction, and differentiation and risk stratification classifier construction. Pixel accuracy, precision, recall, dice score, intersection over union (IoU) and area under the curve (AUC) were used to evaluate the performance of tumor segmentation model and classifiers.ResultsMSA‐U‐Net model detected tumor regions with 0.910 precision, 0.869 recall, 0.889 dice score and 0.800 IoU. The differentiation classifier achieved 0.977 ± 0.0159, 0.955 ± 0.0181, 0.885 ± 0.0237 AUC in D1, D2 and D3, respectively. The most discriminative features between BCC and TE contained Homogeneity, Elongation, T‐T_meanEdgeLength, T‐T_Nsubgraph, S‐T_HarmonicCentrality, S‐S_Degrees. The risk stratification model can well predict HR‐BCC and LR‐BCC with 0.920 ± 0.0579, 0.839 ± 0.0176, 0.825 ± 0.0153 AUC in D1, D2 and D3, respectively. The most discriminative features between HR‐BCC and LR‐BCC comprised IntensityMin, Solidity, T‐T_minEdgeLength, T‐T_Coreness, T‐T_Degrees, T‐T_Betweenness, S‐T_Degrees.ConclusionsThis framework hold potential for future use as a second opinion helping inform diagnosis of BCC, and identify nuclei and TME features related with malignancy and tumor risk stratification.

Funder

National Natural Science Foundation of China

Publisher

Wiley

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Innovations in Skin Diagnostic Technologies: Utilizing a DenseNet201 Deep Learning Model for the Early Detection of Skin Cancer;2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS);2024-06-28

2. Extracellular matrix in leg basal cell carcinoma: Possible pathogenetic role of chronic venous insufficiency;Skin Research and Technology;2024-06

3. Cutting-edge Dermatological Advances using Deep Learning for Precise Skin Cancer Classification;2024 International Conference on Smart Systems for applications in Electrical Sciences (ICSSES);2024-05-03

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3