Balancing Performance and Interpretability in Medical Image Analysis: Case study of Osteopenia.
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 b...
| Publicado en: | Journal of Imaging Informatics in Medicine Vol. 38; no. 1; pp. 177 - 191 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | diagnostic images pictorial tables/charts Journal Article |
| Publicado: |
Springer Nature
Feb2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=184471482&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 184471482 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 29482925 NR3A jtl: Journal of Imaging Informatics in Medicine issn: 29482925 maglogo: N pubinfo: dt: Feb2025 vid: 38 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 184471482 184471482 184471482 10.1007/s10278-024-01194-8 184471482 ppf: 177 ppct: 14 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Balancing Performance and Interpretability in Medical Image Analysis: Case study of Osteopenia. aug: au: Mikulić, Mateo Vičević, Dominik Nagy, Eszter Napravnik, Mateja Štajduhar, Ivan Tschauner, Sebastian Hržić, Franko affil: https://ror.org/05r8dqr10 University of Rijeka, Faculty of Engineering, Department of Computer Engineering, Vukovarska 58, 51000, Rijeka, Croatia sug: subj: Bone Diseases, Metabolic Risk Factors Artificial Intelligence Image Processing, Computer Assisted Image Interpretation, Computer Assisted Access to Information Human Algorithms Funding Source Prediction Algorithms ab: 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. pubtype: Academic Journal doctype: diagnostic images pictorial tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|