Image-intensity normalization approaches on T1-weighted MRI images for lipomatous soft tissue tumors
Issued Date
2026-01-01
Resource Type
eISSN
24058440
Scopus ID
2-s2.0-105024872684
Journal Title
Heliyon
Volume
12
Issue
1
Rights Holder(s)
SCOPUS
Bibliographic Citation
Heliyon Vol.12 No.1 (2026)
Suggested Citation
Sudjai N., Siriwanarangsun P., Lektrakul N., Saiviroonporn P., Maungsomboon S., Phimolsarnti R., Asavamongkolkul A., Chandhanayingyong C. Image-intensity normalization approaches on T1-weighted MRI images for lipomatous soft tissue tumors. Heliyon Vol.12 No.1 (2026). doi:10.1016/j.heliyon.2025.e44320 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/114695
Title
Image-intensity normalization approaches on T1-weighted MRI images for lipomatous soft tissue tumors
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Purpose To propose new image-intensity normalization approaches to overcome image-intensity variations on magnetic resonance imaging (MRI) and compare the effects of these approaches on radiomic feature reproducibility. Material and method This retrospective study included 70 patients diagnosed with intramuscular lipoma and atypical lipomatous tumors/well-differentiated liposarcoma, confirmed via histopathology, who underwent preoperative MRI examinations between 2010 and 2020. Two observers segmented the region of interest for all tumors on T1-weighted images (T1WIs) and extracted radiomic features from the normalized images using four different methods (I<inf>Z</inf>, I<inf>NIV</inf>, I<inf>M</inf>, and I<inf>FM</inf>). We evaluated the performance of the methods in terms of the stable feature rate and the area under the receiver operating characteristic curve (AUC) of the machine-learning model on the reproducible features. We compared the stable feature rates and the AUCs between the models using the chi-squared test and the Delong's test, respectively. Results The extraction process yielded a total of 107 radiomic features, including 14 shape, 18 first-order, and 75 texture features. The proposed method I<inf>FM</inf> exhibited a higher stable feature rate than the other methods (I<inf>FM</inf>, 86.0 % vs. I<inf>Z</inf>, 26.2 %; I<inf>NIV</inf>, 74.8 %; and I<inf>M</inf>, 49.5 %; all P < 0.05). The AUC of the model for the I<inf>FM</inf> method was 0.95 (0.86–1), higher than that for the other methods. Conclusions The proposed method I<inf>FM</inf> can reduce T1WI intensity variations. This approach should be evaluated in future multicenter studies to develop the machine-learning model in predicting intramuscular lipomas and atypical lipomatous tumors/well-differentiated liposarcomas.