Adapting Classification Neural Network Architectures for Medical Image Segmentation Using Explainable AI

Simple item page
dc.contributor.authorNikulins, Arturs
dc.contributor.authorEdelmers, Edgars
dc.contributor.authorSudars, Kaspars
dc.contributor.authorPolaka, Inese
dc.contributor.institutionFaculty of Medicine
dc.date.accessioned2025-03-17T08:15:01Z
dc.date.available2025-03-17T08:15:01Z
dc.date.issued2025-02-13
dc.descriptionPublisher Copyright: © 2025 by the authors.
dc.description.abstractSegmentation neural networks are widely used in medical imaging to identify anomalies that may impact patient health. Despite their effectiveness, these networks face significant challenges, including the need for extensive annotated patient data, time-consuming manual segmentation processes and restricted data access due to privacy concerns. In contrast, classification neural networks, similar to segmentation neural networks, capture essential parameters for identifying objects during training. This paper leverages this characteristic, combined with explainable artificial intelligence (XAI) techniques, to address the challenges of segmentation. By adapting classification neural networks for segmentation tasks, the proposed approach reduces dependency on manual segmentation. To demonstrate this concept, the Medical Segmentation Decathlon ‘Brain Tumours’ dataset was utilised. A ResNet classification neural network was trained, and XAI tools were applied to generate segmentation-like outputs. Our findings reveal that GuidedBackprop is among the most efficient and effective methods, producing heatmaps that closely resemble segmentation masks by accurately highlighting the entirety of the target object.en
dc.description.statusPeer reviewed
dc.format.extent816869
dc.identifier.citationNikulins, A, Edelmers, E, Sudars, K & Polaka, I 2025, 'Adapting Classification Neural Network Architectures for Medical Image Segmentation Using Explainable AI', Journal of Imaging, vol. 11, no. 2, 55. https://doi.org/10.3390/jimaging11020055
dc.identifier.doi10.3390/jimaging11020055
dc.identifier.issn2313-433X
dc.identifier.urihttps://dspace.rsu.lv/jspui/handle/123456789/17178
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85219579496&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofJournal of Imaging
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectmedical imaging
dc.subjectclassification models
dc.subjectimage segmentation
dc.subjectexplainable artificial intelligence
dc.subjectneural networks
dc.subject1.2 Computer and information sciences
dc.subject2.6 Medical engineering
dc.subject1.1. Scientific article indexed in Web of Science and/or Scopus database
dc.titleAdapting Classification Neural Network Architectures for Medical Image Segmentation Using Explainable AIen
dc.type/dk/atira/pure/researchoutput/researchoutputtypes/contributiontojournal/article

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
jimaging-11-00055.pdf
Size:
797.72 KB
Format:
Adobe Portable Document Format
Download

Collections

Research outputs from Pure / Zinātniskās darbības rezultāti no ZDIS Pure