Cross-modality white matter lesion segmentation by modality de-indentification

Preložnik, Domen (author), Špiclin, Žiga (author)

Multiple sclerosis (MS) diagnosis and prognosis relies heavily on the accurate detection and segmentation of white matter lesions (WML) in magnetic resonance imaging (MRI). Different MRI sequences, particularly Fluid-Attenuated Inversion Recovery (FLAIR) and Double Inversion Recovery (DIR), offer complementary information about lesions but are rarely simultaneously acquired in clinical imaging protocols. We introduce a novel self-supervised modality sequential unlearning (SSMSU) adaptation technique that employs modality de-identification to extract modality-invariant features from MRI images, improving WML segmentation regardless of the input modality. Building upon the public nnU-Net framework, we introduce auxiliary modality classifiers at each resolution level and utilize confusion loss to explicitly suppress the modality-specific features while training on alternating modality inputs. We evaluated the approach on in-house dataset of 28 MS patients with paired FLAIR and DIR, MSSEG 2016 dataset of 53 subjects with paired FLAIR and proton density (DP), and 22 FLAIR test cases of MSLesSeg 2024. All cases had expert-annotated WML segmentation as reference. Experiments involved within- and between-dataset validation, comparing performances of single- and multi-modality single-channel, and multi-modality multi-channel training strategies based on Dice Similarity Coefficient (DSC), Lesion-wise True Positive Rate (LTPR), and Lesion-wise False Discovery Rate (LFDR). On in-house and MSSEG 2016 the SSMSU achieved best DSC and LTPR among single-channel models, with LFDR levels comparable to best values, while it attained the same level of performance to multi-channel models that required paired FLAIR/DIR or FLAIR/DP modalities. It ranked 2nd among single-channel methods on MSLesSeg 2024. Effectively suppressing modality-related information resulted in a technique that is cross-modal and delivers a flexible and robust automated WML segmentation tool.

• Language: English
• Keywords: magnetic resonance imaging, white-matter lesions, multimodal images, image segmentation, deep learning, self-supervised learning, validation
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Author Accepted Manuscript
• Year: 2026
• Number of pages: Str. 120-127
• Numbering: Vol. 199
• PID: 20.500.12556/RUL-180172
• UDC: 004.93
• ISSN on article: 0167-8655
• DOI: 10.1016/j.patrec.2025.11.020
• COBISS.SI-ID: 257288963
• Publication date in RUL: 04.03.2026

Record is a part of a journal

• Title: Pattern recognition letters : an official publication of the International Association for Pattern Recognition
• Shortened title: Pattern recogn. lett.
• Publisher: North-Holland
• ISSN: 0167-8655
• COBISS.SI-ID: 26103296

Licences

• License: CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
• Link: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Description: The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.

Secondary language

• Language: Slovenian
• Keywords: magnetnoresonančno slikanje, lezije v beli možganovini, večmodalne slike, segmentacija slik, globoko učenje, samonadzorovano učenje, validacija

Projects

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P2-0232
• Name: Analiza biomedicinskih slik in signalov

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: J2-3059
• Name: Sprotno prilagajanje načrta protonske in radioterapije