Back to all papers

High Accuracy but Low Explainability: The Challenge of XAI in Multiple Sclerosis Assessment from MRI Radiology Reports.

January 30, 2026pubmed logopapers

Authors

Martín-Noguerol T,López-Úbeda P,Escartin J,Mohan S,Luna A

Affiliations (5)

  • MRI unit, Radiology department. HT medica, Jaén, SPAIN. Electronic address: [email protected].
  • NLP department. HT medica. Jaén, SPAIN. Electronic address: [email protected].
  • Diagnostic and Interventional Neuroradiology Unit. HT medica, Ávila. SPAIN. Electronic address: [email protected].
  • Division of Neuroradiology, Hospital of the University of Pennsylvania, Philadelphia, PA, USA. Electronic address: [email protected].
  • MRI unit, Radiology department. HT medica, Jaén, SPAIN. Electronic address: [email protected].

Abstract

Timely identification of disease progression and/or active lesions in multiple sclerosis (MS) is essential for clinical management. Radiology reports often contain complex language, making consistent interpretation challenging. We developed a natural language processing (NLP)-based tool to assist radiologists in detecting MS-related changes and evaluated its explainability. To assess the performance and interpretability of NLP algorithms in identifying disease progression and/or active lesions in MRI reports of MS patients. A retrospective study included 600 MRI reports labeled for MS progression and/or active lesions (January 2013-July 2022). Five hundred reports were used to fine-tune RoBERTa-based models; 100 served as the test set. A prospective evaluation was conducted on 122 reports. Explainability was assessed using the LIME tool and radiologist feedback. Retrospective accuracy was 87% for new/enlarged lesions and 96% for active lesions. Prospective accuracy improved to 94.26% and 99.18%, respectively. LIME-based interpretability yielded radiologist agreement rates of 53.2% (new/enlarged lesions) and 52.5% (active lesions). Our NLP tools demonstrated high accuracy in detecting MS-related MRI findings. However, explainability remains limited, underscoring the need for more intuitive interpretability methods to support clinical integration.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 9,300+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.