Balancing Performance and Interpretability in Medical Image Analysis: Case study of Osteopenia.

Autor: Mikulić M; University of Rijeka, Faculty of Engineering, Department of Computer Engineering, Vukovarska 58, Rijeka, 51000, Croatia., Vičević D; University of Rijeka, Faculty of Engineering, Department of Computer Engineering, Vukovarska 58, Rijeka, 51000, Croatia., Nagy E; Medical University of Graz, Department of Radiology, Division of Pediatric Radiology, Graz, 8036, Austria., Napravnik M; University of Rijeka, Faculty of Engineering, Department of Computer Engineering, Vukovarska 58, Rijeka, 51000, Croatia., Štajduhar I; University of Rijeka, Faculty of Engineering, Department of Computer Engineering, Vukovarska 58, Rijeka, 51000, Croatia.; University of Rijeka, Center for Artificial Intelligence and Cybersecurity, Radmile Matejčić 2, Rijeka, 51000, Croatia., Tschauner S; Medical University of Graz, Department of Radiology, Division of Pediatric Radiology, Graz, 8036, Austria., Hržić F; University of Rijeka, Faculty of Engineering, Department of Computer Engineering, Vukovarska 58, Rijeka, 51000, Croatia. franko.hrzic@uniri.hr.; University of Rijeka, Center for Artificial Intelligence and Cybersecurity, Radmile Matejčić 2, Rijeka, 51000, Croatia. franko.hrzic@uniri.hr.
Jazyk: angličtina
Zdroj: Journal of imaging informatics in medicine [J Imaging Inform Med] 2024 Jul 17. Date of Electronic Publication: 2024 Jul 17.
DOI: 10.1007/s10278-024-01194-8
Abstrakt: Multiple studies within the medical field have highlighted the remarkable effectiveness of using convolutional neural networks for predicting medical conditions, sometimes even surpassing that of medical professionals. Despite their great performance, convolutional neural networks operate as black boxes, potentially arriving at correct conclusions for incorrect reasons or areas of focus. Our work explores the possibility of mitigating this phenomenon by identifying and occluding confounding variables within images. Specifically, we focused on the prediction of osteopenia, a serious medical condition, using the publicly available GRAZPEDWRI-DX dataset. After detection of the confounding variables in the dataset, we generated masks that occlude regions of images associated with those variables. By doing so, models were forced to focus on different parts of the images for classification. Model evaluation using F1-score, precision, and recall showed that models trained on non-occluded images typically outperformed models trained on occluded images. However, a test where radiologists had to choose a model based on the focused regions extracted by the GRAD-CAM method showcased different outcomes. The radiologists' preference shifted towards models trained on the occluded images. These results suggest that while occluding confounding variables may degrade model performance, it enhances interpretability, providing more reliable insights into the reasoning behind predictions. The code to repeat our experiment is available on the following link: https://github.com/mikulicmateo/osteopenia .
(© 2024. The Author(s) under exclusive licence to Society for Imaging Informatics in Medicine.)
Databáze: MEDLINE
Externí odkaz: