炎性乳腺癌的病理影像和临床特征：诊断和预后模型的发展

IF 3.4 2区工程技术 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Displays Pub Date : 2025-08-30 DOI:10.1016/j.displa.2025.103204

Mengmeng Zhang , Yalan Hu , Duanyang Zhai , Tiantian Zhen , Sihua Liu , Yuxuan Gao , Yawei Shi , Huijuan Shi , Ying Lin

{"title":"炎性乳腺癌的病理影像和临床特征：诊断和预后模型的发展","authors":"Mengmeng Zhang , Yalan Hu , Duanyang Zhai , Tiantian Zhen , Sihua Liu , Yuxuan Gao , Yawei Shi , Huijuan Shi , Ying Lin","doi":"10.1016/j.displa.2025.103204","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Inflammatory breast cancer (IBC) is recognized as a lethal and aggressive subtype of breast cancer. However, in current clinical practice, there is a lack of precise and objective diagnostic criteria for IBC. Here, we aim to apply deep learning algorithms to integrate digitized whole slide images (WSIs) from tumor biopsies with clinical characteristics of patients with inflammatory breast cancer (IBC) and locally advanced breast cancer (LABC) to develop diagnostic and prognostic models.</div></div><div><h3>Method</h3><div>Models based solely on pathology signatures or incorporating clinicopathological characteristics were developed using a training dataset (IBC, n = 28; LABC, n = 24) and validated on a separate validation dataset (IBC, n = 7; LABC, n = 6). They were subsequently tested on a prospective testing dataset (IBC, n = 5; LABC, n = 4). Based on pathological IBC scores (PIBCS) output by the deep learning pathology model and the clinicopathological characteristics, a prognostic model for 3-year progression-free survival (PFS) was constructed using Least absolute shrinkage and selection operator(LASSO)-cox regression. Additionally, 55 cases of non-inflammatory breast cancer (non-IBC) were included for validation of the prognostic model.</div></div><div><h3>Results</h3><div>The model that integrated pathology signatures and clinicopathological characteristics demonstrated superior performance, with the area under the receiver operating characteristic curve (AUC) consistently above 0.900, in contrast to the model based solely on pathology signatures. The prognostic model, which combined PIBCS, age, and ER/PR status, showed good predictive capability for 3-year PFS of breast cancer patients, achieving AUC values of 0.858 in the training dataset and 0.841 in the test dataset.</div></div><div><h3>Conclusion</h3><div>The models have the potential to be employed in clinical settings for the unbiased diagnosis of IBC and the prediction of breast cancer prognosis.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103204"},"PeriodicalIF":3.4000,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pathological imaging and clinical features of inflammatory breast cancer: Development of diagnostic and prognostic models\",\"authors\":\"Mengmeng Zhang , Yalan Hu , Duanyang Zhai , Tiantian Zhen , Sihua Liu , Yuxuan Gao , Yawei Shi , Huijuan Shi , Ying Lin\",\"doi\":\"10.1016/j.displa.2025.103204\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Inflammatory breast cancer (IBC) is recognized as a lethal and aggressive subtype of breast cancer. However, in current clinical practice, there is a lack of precise and objective diagnostic criteria for IBC. Here, we aim to apply deep learning algorithms to integrate digitized whole slide images (WSIs) from tumor biopsies with clinical characteristics of patients with inflammatory breast cancer (IBC) and locally advanced breast cancer (LABC) to develop diagnostic and prognostic models.</div></div><div><h3>Method</h3><div>Models based solely on pathology signatures or incorporating clinicopathological characteristics were developed using a training dataset (IBC, n = 28; LABC, n = 24) and validated on a separate validation dataset (IBC, n = 7; LABC, n = 6). They were subsequently tested on a prospective testing dataset (IBC, n = 5; LABC, n = 4). Based on pathological IBC scores (PIBCS) output by the deep learning pathology model and the clinicopathological characteristics, a prognostic model for 3-year progression-free survival (PFS) was constructed using Least absolute shrinkage and selection operator(LASSO)-cox regression. Additionally, 55 cases of non-inflammatory breast cancer (non-IBC) were included for validation of the prognostic model.</div></div><div><h3>Results</h3><div>The model that integrated pathology signatures and clinicopathological characteristics demonstrated superior performance, with the area under the receiver operating characteristic curve (AUC) consistently above 0.900, in contrast to the model based solely on pathology signatures. The prognostic model, which combined PIBCS, age, and ER/PR status, showed good predictive capability for 3-year PFS of breast cancer patients, achieving AUC values of 0.858 in the training dataset and 0.841 in the test dataset.</div></div><div><h3>Conclusion</h3><div>The models have the potential to be employed in clinical settings for the unbiased diagnosis of IBC and the prediction of breast cancer prognosis.</div></div>\",\"PeriodicalId\":50570,\"journal\":{\"name\":\"Displays\",\"volume\":\"91 \",\"pages\":\"Article 103204\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2025-08-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Displays\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0141938225002410\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Displays","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0141938225002410","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}

引用次数: 0

摘要

背景：炎症性乳腺癌（IBC）被认为是一种致死性和侵袭性的乳腺癌亚型。然而，在目前的临床实践中，缺乏准确、客观的IBC诊断标准。在这里，我们的目标是应用深度学习算法，将肿瘤活检的数字化全幻灯片图像（wsi）与炎性乳腺癌（IBC）和局部晚期乳腺癌（LABC）患者的临床特征相结合，以开发诊断和预后模型。方法使用训练数据集（IBC, n = 28； LABC, n = 24）开发仅基于病理特征或结合临床病理特征的模型，并在单独的验证数据集（IBC, n = 7； LABC, n = 6）上进行验证。随后在前瞻性测试数据集（IBC, n = 5； LABC, n = 4）上对他们进行测试。基于深度学习病理模型输出的病理IBC评分（PIBCS）和临床病理特征，采用最小绝对收缩和选择算子(LASSO)-cox回归构建3年无进展生存期（PFS）的预后模型。此外，55例非炎性乳腺癌（非ibc）被纳入预后模型验证。结果综合病理特征和临床病理特征的模型优于单纯基于病理特征的模型，受试者工作特征曲线下面积（AUC）始终在0.900以上。结合PIBCS、年龄和ER/PR状态的预后模型对乳腺癌患者3年PFS的预测能力较好，在训练数据集中AUC值为0.858，在测试数据集中AUC值为0.841。结论该模型具有临床应用价值，可用于IBC的无偏诊断和乳腺癌预后预测。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Pathological imaging and clinical features of inflammatory breast cancer: Development of diagnostic and prognostic models

Background

Inflammatory breast cancer (IBC) is recognized as a lethal and aggressive subtype of breast cancer. However, in current clinical practice, there is a lack of precise and objective diagnostic criteria for IBC. Here, we aim to apply deep learning algorithms to integrate digitized whole slide images (WSIs) from tumor biopsies with clinical characteristics of patients with inflammatory breast cancer (IBC) and locally advanced breast cancer (LABC) to develop diagnostic and prognostic models.

Method

Models based solely on pathology signatures or incorporating clinicopathological characteristics were developed using a training dataset (IBC, n = 28; LABC, n = 24) and validated on a separate validation dataset (IBC, n = 7; LABC, n = 6). They were subsequently tested on a prospective testing dataset (IBC, n = 5; LABC, n = 4). Based on pathological IBC scores (PIBCS) output by the deep learning pathology model and the clinicopathological characteristics, a prognostic model for 3-year progression-free survival (PFS) was constructed using Least absolute shrinkage and selection operator(LASSO)-cox regression. Additionally, 55 cases of non-inflammatory breast cancer (non-IBC) were included for validation of the prognostic model.

Results

The model that integrated pathology signatures and clinicopathological characteristics demonstrated superior performance, with the area under the receiver operating characteristic curve (AUC) consistently above 0.900, in contrast to the model based solely on pathology signatures. The prognostic model, which combined PIBCS, age, and ER/PR status, showed good predictive capability for 3-year PFS of breast cancer patients, achieving AUC values of 0.858 in the training dataset and 0.841 in the test dataset.

Conclusion

The models have the potential to be employed in clinical settings for the unbiased diagnosis of IBC and the prediction of breast cancer prognosis.

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

Displays 工程技术-工程：电子与电气

CiteScore

4.60

自引率

25.60%

发文量

138

审稿时长

92 days

期刊介绍： Displays is the international journal covering the research and development of display technology, its effective presentation and perception of information, and applications and systems including display-human interface. Technical papers on practical developments in Displays technology provide an effective channel to promote greater understanding and cross-fertilization across the diverse disciplines of the Displays community. Original research papers solving ergonomics issues at the display-human interface advance effective presentation of information. Tutorial papers covering fundamentals intended for display technologies and human factor engineers new to the field will also occasionally featured.