TRAITER: transformer-guided diagnosis and prognosis of heart failure using cell nuclear morphology and DNA damage marker.

Bioinformatics (Oxford, England) Pub Date : 2024-11-01 DOI:10.1093/bioinformatics/btae610

Hiromu Hayashi, Toshiyuki Ko, Zhehao Dai, Kanna Fujita, Seitaro Nomura, Hiroki Kiyoshima, Shinya Ishihara, Momoko Hamano, Issei Komuro, Yoshihiro Yamanishi

{"title":"TRAITER: transformer-guided diagnosis and prognosis of heart failure using cell nuclear morphology and DNA damage marker.","authors":"Hiromu Hayashi, Toshiyuki Ko, Zhehao Dai, Kanna Fujita, Seitaro Nomura, Hiroki Kiyoshima, Shinya Ishihara, Momoko Hamano, Issei Komuro, Yoshihiro Yamanishi","doi":"10.1093/bioinformatics/btae610","DOIUrl":null,"url":null,"abstract":"Motivation: Heart failure (HF), a major cause of morbidity and mortality, necessitates precise diagnostic and prognostic methods.Results: This study presents a novel deep learning approach, Transformer-based Analysis of Images of Tissue for Effective Remedy (TRAITER), for HF diagnosis and prognosis. Using image segmentation techniques and a Vision Transformer, TRAITER predicts HF likelihood from cardiac tissue cell nuclear morphology images and the potential for left ventricular reverse remodeling (LVRR) from dual-stained images with cell nuclei and DNA damage markers. In HF prediction using 31 158 images from 9 patients, TRAITER achieved 83.1% accuracy. For LVRR prediction with 231 840 images from 46 patients, TRAITER attained 84.2% accuracy for individual images and 92.9% for individual patients. TRAITER outperformed other neural network models in terms of receiver operating characteristics, and precision-recall curves. Our method promises to advance personalized HF medicine decision-making.Availability and implementation: The source code and data are available at the following link: https://github.com/HamanoLaboratory/predict-of-HF-and-LVRR.","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11552630/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioinformatics (Oxford, England)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/bioinformatics/btae610","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Motivation: Heart failure (HF), a major cause of morbidity and mortality, necessitates precise diagnostic and prognostic methods.

Results: This study presents a novel deep learning approach, Transformer-based Analysis of Images of Tissue for Effective Remedy (TRAITER), for HF diagnosis and prognosis. Using image segmentation techniques and a Vision Transformer, TRAITER predicts HF likelihood from cardiac tissue cell nuclear morphology images and the potential for left ventricular reverse remodeling (LVRR) from dual-stained images with cell nuclei and DNA damage markers. In HF prediction using 31 158 images from 9 patients, TRAITER achieved 83.1% accuracy. For LVRR prediction with 231 840 images from 46 patients, TRAITER attained 84.2% accuracy for individual images and 92.9% for individual patients. TRAITER outperformed other neural network models in terms of receiver operating characteristics, and precision-recall curves. Our method promises to advance personalized HF medicine decision-making.

Availability and implementation: The source code and data are available at the following link: https://github.com/HamanoLaboratory/predict-of-HF-and-LVRR.

查看原文本刊更多论文

TRAITER：利用细胞核形态学和 DNA 损伤标记物进行心力衰竭的变构指导诊断和预后。

动机：心力衰竭（HF）是发病和死亡的主要原因，需要精确的诊断和预后方法：心力衰竭（HF）是发病和死亡的主要原因，需要精确的诊断和预后方法：本研究提出了一种新颖的深度学习方法--基于变换器的组织图像有效补救分析（TRAITER），用于心力衰竭的诊断和预后。TRAITER 采用图像分割技术和视觉变换器，从心脏组织细胞核形态图像预测高频的可能性，并从细胞核和 DNA 损伤标记的双重染色图像预测左心室反向重塑（LVRR）的可能性。在使用 9 名患者的 31,158 张图像进行高频预测时，TRAITER 的准确率达到了 83.1%。在使用 46 名患者的 231,840 张图像进行 LVRR 预测时，TRAITER 对单张图像的准确率达到 84.2%，对单个患者的准确率达到 92.9%。TRAITER 在接收者操作特征和精确度-召回曲线方面的表现优于其他神经网络模型。我们的方法有望推动个性化高频医学决策：源代码和数据可从以下链接获取：Https://github.com/HamanoLaboratory/predict-of-HF-and-LVRR.Supplementary information：补充数据可在 Bioinformatics online 上获取。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Bioinformatics (Oxford, England)

自引率

0.00%

发文量