{"title":"Ensembled YOLO for multiorgan detection in chest x-rays.","authors":"Sivaramakrishnan Rajaraman, Zhaohui Liang, Zhiyun Xue, Sameer Antani","doi":"10.1117/12.3047210","DOIUrl":null,"url":null,"abstract":"<p><p>Chest radiographs are a vital tool for identifying pathological changes within the thoracic cavity. Artificial intelligence (AI) and machine learning (ML) driven screening or diagnostic applications require accurate detection of anatomical structures within the Chest X-ray (CXR) image. The You Only Look Once (YOLO) object detection models have recently gained prominence for their efficacy in detecting anatomical structures in medical images. However, state-of-the-art results using it are typically for single anatomical organ detection. Advanced image analysis would benefit from simultaneous detection more than one anatomical organ. In this work we propose a multi-organ detection technique through two recent YOLO versions and their sub-variants. We evaluate their effectiveness in detecting lung and heart regions in CXRs simultaneously. We used the JSRT CXR dataset for internal training, validation, and testing. Further, the generalizability of the models is evaluated using two external test sets, viz., the Montgomery CXR dataset and a subset of the RSNA CXR dataset against available annotations therein. Our evaluation demonstrates that YOLOv9 models notably outperform YOLOv8 variants. We demonstrated further improvements in detection performance through ensemble approaches.</p>","PeriodicalId":74505,"journal":{"name":"Proceedings of SPIE--the International Society for Optical Engineering","volume":"13407 ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11996225/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of SPIE--the International Society for Optical Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.3047210","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/4/4 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Chest radiographs are a vital tool for identifying pathological changes within the thoracic cavity. Artificial intelligence (AI) and machine learning (ML) driven screening or diagnostic applications require accurate detection of anatomical structures within the Chest X-ray (CXR) image. The You Only Look Once (YOLO) object detection models have recently gained prominence for their efficacy in detecting anatomical structures in medical images. However, state-of-the-art results using it are typically for single anatomical organ detection. Advanced image analysis would benefit from simultaneous detection more than one anatomical organ. In this work we propose a multi-organ detection technique through two recent YOLO versions and their sub-variants. We evaluate their effectiveness in detecting lung and heart regions in CXRs simultaneously. We used the JSRT CXR dataset for internal training, validation, and testing. Further, the generalizability of the models is evaluated using two external test sets, viz., the Montgomery CXR dataset and a subset of the RSNA CXR dataset against available annotations therein. Our evaluation demonstrates that YOLOv9 models notably outperform YOLOv8 variants. We demonstrated further improvements in detection performance through ensemble approaches.
胸片是鉴别胸腔内病变的重要工具。人工智能(AI)和机器学习(ML)驱动的筛查或诊断应用需要准确检测胸部x光片(CXR)图像中的解剖结构。You Only Look Once (YOLO)目标检测模型最近因其在检测医学图像中的解剖结构方面的有效性而获得了突出的地位。然而,使用它的最先进的结果通常用于单个解剖器官检测。先进的图像分析将受益于同时检测多个解剖器官。在这项工作中,我们通过两个最新的YOLO版本及其子变体提出了一种多器官检测技术。我们评估了它们在cxr中同时检测肺和心脏区域的有效性。我们使用JSRT CXR数据集进行内部训练、验证和测试。此外,使用两个外部测试集(即Montgomery CXR数据集和RSNA CXR数据集的一个子集)对其中的可用注释评估模型的泛化性。我们的评估表明,YOLOv9模型明显优于YOLOv8变体。我们展示了通过集成方法进一步改进检测性能。