Differentiation of Malignancy and Idiopathic Granulomatous Mastitis Presenting as Non-mass Lesions on MRI: Radiological, Clinical, Radiomics, and Clinical-Radiomics Models

Yasemin Kayadibi; Mehmet Sakıpcan Saracoglu; Seda Aladag Kurt; Enes Deger; Fatma Nur Soylu Boy; Nese Ucar; Gul Esen Icten

doi:10.1016/j.acra.2024.03.025

Differentiation of Malignancy and Idiopathic Granulomatous Mastitis Presenting as Non-mass Lesions on MRI: Radiological, Clinical, Radiomics, and Clinical-Radiomics Models

Acad Radiol. 2024 Apr 18:S1076-6332(24)00189-2. doi: 10.1016/j.acra.2024.03.025. Online ahead of print.

Authors

Yasemin Kayadibi¹, Mehmet Sakıpcan Saracoglu², Seda Aladag Kurt², Enes Deger², Fatma Nur Soylu Boy³, Nese Ucar⁴, Gul Esen Icten⁵

Affiliations

¹ Istanbul University-Cerrahpasa, Cerrahpasa Medical Faculty, Department of Radiology, Kocamustafapasa, Istanbul, Türkiye. Electronic address: yasemin.kayadibi@iuc.edu.tr.
² Istanbul University-Cerrahpasa, Cerrahpasa Medical Faculty, Department of Radiology, Kocamustafapasa, Istanbul, Türkiye.
³ Fatih Sultan Mehmet Education and Research Hospital, Department of Radiology, Atasehir, Istanbul, Türkiye.
⁴ Gaziosmanspasa Education and Research Hospital, Department of Radiology, Gaziosmanpasa, Istanbul, Türkiye.
⁵ Senology Research Institute, Acibadem Mehmet Ali Aydinlar University, Maslak, Istanbul, Türkiye.

PMID: 38641449
DOI: 10.1016/j.acra.2024.03.025

Abstract

Rationale and objectives: To investigate the effectiveness of machine learning-based clinical, radiomics, and combined models in differentiating idiopathic granulomatous mastitis (IGM) from malignancy, both presenting as non-mass enhancement (NME) lesions on magnetic resonance imaging (MRI), and to compare these models with radiological evaluation.

Material and methods: A total of 178 patients (69 IGM and 109 breast cancer patients) with NME on breast MRI evaluated between March 2018 and April 2022, were included in this two-center study. Age, skin changes, presence of fistula, and abscess were recorded from hospital records. Two experienced radiologists evaluated MRI images according to the breast imaging reporting and data system 2013 lexicon. Lesions were segmented independently on T2-weighted, apparent diffusion coefficient, and post-contrast-T1-weighted sequences. Data were split into training and external testing sets. Machine learning models were built using Light GBM (light gradient-boosting machine). Radiological, clinical, radiomics, and clinical-radiomics models were created and compared. Decision curve analysis was performed. Quality of reporting and that of methodology were evaluated using CLEAR and METRICS tools.

Results: IGM group was younger (p = 0.014). Abscesses (p < 0.001), fistulas (p < 0.001), and skin changes (p < 0.001) were significantly more common in the IGM group. No significant difference was detected in terms of lesion size (p = 0.213). In the evaluation of NME, the lowest performance belonged to the radiologists' evaluation (AUC for training, 0.740; for testing, 0.737), while the highest AUC was achieved by the model developed by combined clinical and radiomics features (AUC for training, 0.979; for testing, 0.942).

Conclusion: Our study has shown that the machine learning-based clinical-radiomics model might have the potential to accurately discriminate IGM and malignant lesions in evaluating NME areas.

Keywords: Breast cancer; Magnetic resonance imaging; Non-mass enhancement; Radiomics.