利用hnsc分类器提高数字化全切片组织学头颈癌检测的准确性:一种深度学习方法。

IF 3.9 3区 生物学 Q2 BIOCHEMISTRY & MOLECULAR BIOLOGY
Frontiers in Molecular Biosciences Pub Date : 2025-08-01 eCollection Date: 2025-01-01 DOI:10.3389/fmolb.2025.1652144
Haiyang Yu, Wang Yu, Yuan Enwu, Jun Ma, Xin Zhao, Linlin Zhang, Fang Yang
{"title":"利用hnsc分类器提高数字化全切片组织学头颈癌检测的准确性:一种深度学习方法。","authors":"Haiyang Yu, Wang Yu, Yuan Enwu, Jun Ma, Xin Zhao, Linlin Zhang, Fang Yang","doi":"10.3389/fmolb.2025.1652144","DOIUrl":null,"url":null,"abstract":"<p><p>Head and neck squamous cell carcinoma (HNSCC) represents the sixth most common cancer worldwide, with pathologists routinely analyzing histological slides to diagnose cancer by evaluating cellular heterogeneity, a process that remains time-consuming and labor-intensive. Although no previous studies have systematically applied deep learning techniques to automate HNSCC TNM staging and overall stage prediction from digital histopathology slides, we developed an inception-ResNet34 convolutional neural network model (HNSC-Classifier) trained on 791 whole slide images (WSIs) from 500 HNSCC patients sourced from The Cancer Genome Atlas (TCGA) Head and Neck Squamous Cell dataset. Our pipeline was designed to distinguish cancerous from normal tissue and to predict both tumor stage and TNM classification from histological images, with the dataset split at the patient level to ensure independence between training and testing sets and performance evaluated using comprehensive metrics including receiver operating characteristic (ROC) analysis, precision, recall, F1-score, and confusion matrices. The HNSC-Classifier demonstrated exceptional performance with areas under the ROC curves (AUCs) of 0.998 for both cancer/normal classification and TNM system stage prediction at the tile level, while cross-validation showed high precision, recall, and F1 scores (>0.99) across all classification tasks. Patient-level classification achieved AUCs of 0.998 for tumor/normal discrimination and 0.992 for stage prediction, significantly outperforming existing approaches for cancer stage detection. Our deep learning approach provides pathologists with a powerful computational tool that can enhance diagnostic efficiency and accuracy in HNSCC detection and staging, with the HNSC-Classifier having potential to improve clinical workflow and patient outcomes through more timely and precise diagnoses, serving as an automated decision support system for histopathological analysis of HNSCC.</p>","PeriodicalId":12465,"journal":{"name":"Frontiers in Molecular Biosciences","volume":"12 ","pages":"1652144"},"PeriodicalIF":3.9000,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12353728/pdf/","citationCount":"0","resultStr":"{\"title\":\"Enhancing head and neck cancer detection accuracy in digitized whole-slide histology with the HNSC-classifier: a deep learning approach.\",\"authors\":\"Haiyang Yu, Wang Yu, Yuan Enwu, Jun Ma, Xin Zhao, Linlin Zhang, Fang Yang\",\"doi\":\"10.3389/fmolb.2025.1652144\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Head and neck squamous cell carcinoma (HNSCC) represents the sixth most common cancer worldwide, with pathologists routinely analyzing histological slides to diagnose cancer by evaluating cellular heterogeneity, a process that remains time-consuming and labor-intensive. Although no previous studies have systematically applied deep learning techniques to automate HNSCC TNM staging and overall stage prediction from digital histopathology slides, we developed an inception-ResNet34 convolutional neural network model (HNSC-Classifier) trained on 791 whole slide images (WSIs) from 500 HNSCC patients sourced from The Cancer Genome Atlas (TCGA) Head and Neck Squamous Cell dataset. Our pipeline was designed to distinguish cancerous from normal tissue and to predict both tumor stage and TNM classification from histological images, with the dataset split at the patient level to ensure independence between training and testing sets and performance evaluated using comprehensive metrics including receiver operating characteristic (ROC) analysis, precision, recall, F1-score, and confusion matrices. The HNSC-Classifier demonstrated exceptional performance with areas under the ROC curves (AUCs) of 0.998 for both cancer/normal classification and TNM system stage prediction at the tile level, while cross-validation showed high precision, recall, and F1 scores (>0.99) across all classification tasks. Patient-level classification achieved AUCs of 0.998 for tumor/normal discrimination and 0.992 for stage prediction, significantly outperforming existing approaches for cancer stage detection. Our deep learning approach provides pathologists with a powerful computational tool that can enhance diagnostic efficiency and accuracy in HNSCC detection and staging, with the HNSC-Classifier having potential to improve clinical workflow and patient outcomes through more timely and precise diagnoses, serving as an automated decision support system for histopathological analysis of HNSCC.</p>\",\"PeriodicalId\":12465,\"journal\":{\"name\":\"Frontiers in Molecular Biosciences\",\"volume\":\"12 \",\"pages\":\"1652144\"},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2025-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12353728/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Molecular Biosciences\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.3389/fmolb.2025.1652144\",\"RegionNum\":3,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"BIOCHEMISTRY & MOLECULAR BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Molecular Biosciences","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.3389/fmolb.2025.1652144","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

头颈部鳞状细胞癌(HNSCC)是全球第六大常见癌症,病理学家通常通过评估细胞异质性来分析组织学切片来诊断癌症,这一过程仍然是耗时和劳动密集型的。尽管之前没有研究系统地应用深度学习技术来自动化HNSCC TNM分期和数字组织病理学切片的总体分期预测,但我们开发了一个初始- resnet34卷积神经网络模型(HNSC-Classifier),该模型对来自癌症基因组图谱(TCGA)头颈部鳞状细胞数据集的500名HNSCC患者的791张全切片图像(wsi)进行了训练。我们的管道设计用于区分癌组织和正常组织,并从组织学图像中预测肿瘤分期和TNM分类,数据集在患者水平上进行分割,以确保训练集和测试集之间的独立性,并使用综合指标进行性能评估,包括受试者工作特征(ROC)分析、精度、召回率、f1评分和混淆矩阵。HNSC-Classifier在癌症/正常分类和TNM系统阶段预测方面表现出色,ROC曲线下面积(auc)均为0.998,而交叉验证显示,在所有分类任务中,准确率、召回率和F1分数(>0.99)都很高。患者水平分类的肿瘤/正常区分auc为0.998,分期预测auc为0.992,明显优于现有的癌症分期检测方法。我们的深度学习方法为病理学家提供了一个强大的计算工具,可以提高HNSCC检测和分期的诊断效率和准确性,HNSC-Classifier有可能通过更及时和准确的诊断改善临床工作流程和患者预后,作为HNSCC组织病理学分析的自动化决策支持系统。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Enhancing head and neck cancer detection accuracy in digitized whole-slide histology with the HNSC-classifier: a deep learning approach.

Head and neck squamous cell carcinoma (HNSCC) represents the sixth most common cancer worldwide, with pathologists routinely analyzing histological slides to diagnose cancer by evaluating cellular heterogeneity, a process that remains time-consuming and labor-intensive. Although no previous studies have systematically applied deep learning techniques to automate HNSCC TNM staging and overall stage prediction from digital histopathology slides, we developed an inception-ResNet34 convolutional neural network model (HNSC-Classifier) trained on 791 whole slide images (WSIs) from 500 HNSCC patients sourced from The Cancer Genome Atlas (TCGA) Head and Neck Squamous Cell dataset. Our pipeline was designed to distinguish cancerous from normal tissue and to predict both tumor stage and TNM classification from histological images, with the dataset split at the patient level to ensure independence between training and testing sets and performance evaluated using comprehensive metrics including receiver operating characteristic (ROC) analysis, precision, recall, F1-score, and confusion matrices. The HNSC-Classifier demonstrated exceptional performance with areas under the ROC curves (AUCs) of 0.998 for both cancer/normal classification and TNM system stage prediction at the tile level, while cross-validation showed high precision, recall, and F1 scores (>0.99) across all classification tasks. Patient-level classification achieved AUCs of 0.998 for tumor/normal discrimination and 0.992 for stage prediction, significantly outperforming existing approaches for cancer stage detection. Our deep learning approach provides pathologists with a powerful computational tool that can enhance diagnostic efficiency and accuracy in HNSCC detection and staging, with the HNSC-Classifier having potential to improve clinical workflow and patient outcomes through more timely and precise diagnoses, serving as an automated decision support system for histopathological analysis of HNSCC.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Frontiers in Molecular Biosciences
Frontiers in Molecular Biosciences Biochemistry, Genetics and Molecular Biology-Biochemistry
CiteScore
7.20
自引率
4.00%
发文量
1361
审稿时长
14 weeks
期刊介绍: Much of contemporary investigation in the life sciences is devoted to the molecular-scale understanding of the relationships between genes and the environment — in particular, dynamic alterations in the levels, modifications, and interactions of cellular effectors, including proteins. Frontiers in Molecular Biosciences offers an international publication platform for basic as well as applied research; we encourage contributions spanning both established and emerging areas of biology. To this end, the journal draws from empirical disciplines such as structural biology, enzymology, biochemistry, and biophysics, capitalizing as well on the technological advancements that have enabled metabolomics and proteomics measurements in massively parallel throughput, and the development of robust and innovative computational biology strategies. We also recognize influences from medicine and technology, welcoming studies in molecular genetics, molecular diagnostics and therapeutics, and nanotechnology. Our ultimate objective is the comprehensive illustration of the molecular mechanisms regulating proteins, nucleic acids, carbohydrates, lipids, and small metabolites in organisms across all branches of life. In addition to interesting new findings, techniques, and applications, Frontiers in Molecular Biosciences will consider new testable hypotheses to inspire different perspectives and stimulate scientific dialogue. The integration of in silico, in vitro, and in vivo approaches will benefit endeavors across all domains of the life sciences.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信