Harnessing ensemble deep learning models for precise detection of gynaecological cancers

IF 2.3 Q2 PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH

Clinical Epidemiology and Global Health Pub Date : 2025-02-11 DOI:10.1016/j.cegh.2025.101956

Chetna Vaid Kwatra , Harpreet Kaur , Saiprasad Potharaju , Swapnali N. Tambe , Devyani Bhamare Jadhav , Sagar B. Tambe

{"title":"Harnessing ensemble deep learning models for precise detection of gynaecological cancers","authors":"Chetna Vaid Kwatra , Harpreet Kaur , Saiprasad Potharaju , Swapnali N. Tambe , Devyani Bhamare Jadhav , Sagar B. Tambe","doi":"10.1016/j.cegh.2025.101956","DOIUrl":null,"url":null,"abstract":"<div><h3>Problem considered</h3><div>The accurate and timely identification of gynaecological cancers is critical for improving patient outcomes and increasing survival rates. However, diagnostic imaging for these conditions is complex and prone to human error, necessitating advanced computational methods to enhance diagnostic reliability.</div></div><div><h3>Methods</h3><div>This study proposes an ensemble framework combining two state-of-the-art deep learning models, ResNet50 and Inception V3, for robust gynaecological malignancy detection. The synergistic integration of these models aims to leverage their strengths, significantly improving diagnostic performance. The models were trained and validated on a comprehensive dataset of medical images, including histopathology slides and radiological scans. The ensemble model's performance was rigorously evaluated using key metrics, including sensitivity, specificity, and overall diagnostic accuracy.</div></div><div><h3>Results</h3><div>The ensemble model achieved remarkable diagnostic accuracy, with results showing 99.8 % accuracy, 99.6 % sensitivity, and 99.9 % specificity. In comparison, the individual performance of ResNet50 and Inception V3 models was substantially lower. This demonstrates the effectiveness of the ensemble approach in detecting a wide range of gynaecological cancers, including ovarian and cervical malignancies.</div></div>","PeriodicalId":46404,"journal":{"name":"Clinical Epidemiology and Global Health","volume":"32 ","pages":"Article 101956"},"PeriodicalIF":2.3000,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Epidemiology and Global Health","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2213398425000454","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH","Score":null,"Total":0}

引用次数: 0

Abstract

Problem considered

The accurate and timely identification of gynaecological cancers is critical for improving patient outcomes and increasing survival rates. However, diagnostic imaging for these conditions is complex and prone to human error, necessitating advanced computational methods to enhance diagnostic reliability.

Methods

This study proposes an ensemble framework combining two state-of-the-art deep learning models, ResNet50 and Inception V3, for robust gynaecological malignancy detection. The synergistic integration of these models aims to leverage their strengths, significantly improving diagnostic performance. The models were trained and validated on a comprehensive dataset of medical images, including histopathology slides and radiological scans. The ensemble model's performance was rigorously evaluated using key metrics, including sensitivity, specificity, and overall diagnostic accuracy.

Results

The ensemble model achieved remarkable diagnostic accuracy, with results showing 99.8 % accuracy, 99.6 % sensitivity, and 99.9 % specificity. In comparison, the individual performance of ResNet50 and Inception V3 models was substantially lower. This demonstrates the effectiveness of the ensemble approach in detecting a wide range of gynaecological cancers, including ovarian and cervical malignancies.

查看原文本刊更多论文

利用集成深度学习模型精确检测妇科癌症

准确和及时地识别妇科癌症对于改善患者预后和提高生存率至关重要。然而，对这些疾病的诊断成像是复杂的，容易出现人为错误，需要先进的计算方法来提高诊断的可靠性。本研究提出了一个集成框架，结合两种最先进的深度学习模型，ResNet50和Inception V3，用于强大的妇科恶性肿瘤检测。这些模型的协同整合旨在利用它们的优势，显著提高诊断性能。这些模型在医学图像的综合数据集上进行了训练和验证，包括组织病理学切片和放射学扫描。使用关键指标对集成模型的性能进行严格评估，包括敏感性、特异性和总体诊断准确性。结果集合模型的诊断准确率为99.8%，灵敏度为99.6%，特异度为99.9%。相比之下，ResNet50和Inception V3模型的单个性能要低得多。这表明综合方法在检测各种妇科癌症，包括卵巢癌和子宫颈恶性肿瘤方面的有效性。

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

Clinical Epidemiology and Global Health PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH-

CiteScore

4.60

自引率

7.70%

发文量

218

审稿时长

66 days

期刊介绍： Clinical Epidemiology and Global Health (CEGH) is a multidisciplinary journal and it is published four times (March, June, September, December) a year. The mandate of CEGH is to promote articles on clinical epidemiology with focus on developing countries in the context of global health. We also accept articles from other countries. It publishes original research work across all disciplines of medicine and allied sciences, related to clinical epidemiology and global health. The journal publishes Original articles, Review articles, Evidence Summaries, Letters to the Editor. All articles published in CEGH are peer-reviewed and published online for immediate access and citation.