{"title":"Explainable rotation-invariant self-supervised representation learning","authors":"","doi":"10.1016/j.mex.2024.102959","DOIUrl":null,"url":null,"abstract":"<div><p>This paper describes a method that can perform robust detection and classification in out-of-distribution rotated images in the medical domain. In real-world medical imaging tools, noise due to the rotation of the body part is frequently observed. This noise reduces the accuracy of AI-based classification and prediction models. Hence, it is important to develop models which are rotation invariant. To that end, the proposed method - RISC (rotation invariant self-supervised vision framework) addresses this issue of rotational corruption. We present state-of-the-art rotation-invariant classification results and provide explainability for the performance in the domain. The evaluation of the proposed method is carried out on real-world adversarial examples in Medical Imagery-OrganAMNIST, RetinaMNIST and PneumoniaMNIST. It is observed that RISC outperforms the rotation-affected benchmark methods by obtaining 22\\%, 17\\% and 2\\% accuracy boost on OrganAMNIST, PneumoniaMNIST and RetinaMNIST rotated baselines respectively. Further, explainability results are demonstrated.</p><p>This methods paper describes:</p><ul><li><span>•</span><span><p>a representation learning approach that can perform robust detection and classification in out-of-distribution rotated images in the medical domain.</p></span></li><li><span>•</span><span><p>It presents a method that incorporates self-supervised rotation invariance for correcting rotational corruptions.</p></span></li><li><span>•</span><span><p>GradCAM-based explainability for the rotational SSL pretext task and the downstream classification outcomes for the three benchmark datasets are presented</p></span></li></ul></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2215016124004102/pdfft?md5=960ede7733b4b76435ee298fd9a1d9b1&pid=1-s2.0-S2215016124004102-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"MethodsX","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2215016124004102","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
This paper describes a method that can perform robust detection and classification in out-of-distribution rotated images in the medical domain. In real-world medical imaging tools, noise due to the rotation of the body part is frequently observed. This noise reduces the accuracy of AI-based classification and prediction models. Hence, it is important to develop models which are rotation invariant. To that end, the proposed method - RISC (rotation invariant self-supervised vision framework) addresses this issue of rotational corruption. We present state-of-the-art rotation-invariant classification results and provide explainability for the performance in the domain. The evaluation of the proposed method is carried out on real-world adversarial examples in Medical Imagery-OrganAMNIST, RetinaMNIST and PneumoniaMNIST. It is observed that RISC outperforms the rotation-affected benchmark methods by obtaining 22\%, 17\% and 2\% accuracy boost on OrganAMNIST, PneumoniaMNIST and RetinaMNIST rotated baselines respectively. Further, explainability results are demonstrated.
This methods paper describes:
•
a representation learning approach that can perform robust detection and classification in out-of-distribution rotated images in the medical domain.
•
It presents a method that incorporates self-supervised rotation invariance for correcting rotational corruptions.
•
GradCAM-based explainability for the rotational SSL pretext task and the downstream classification outcomes for the three benchmark datasets are presented