Atypical Lipomatous Tumours vs. Lipomas: A Multimodal Diagnostic Approach.

Abstract

Background/Objectives: This study aimed to develop a reliable scoring system combining clinical and radiological parameters to distinguish atypical lipomatous tumours (ALTs) from lipomas, improving diagnostic accuracy and reducing expensive molecular pathology testing. Methods: A retrospective analysis of 188 patients who underwent surgery for lipomatous tumours was conducted. Patient data, including medical history, pathology, and MRI imaging results, were reviewed. Four predictive models were developed using various clinical and imaging parameters, including age, tumour size, location, and MRI characteristics (homogeneity, contrast enhancement). Statistical analysis, including ROC curve analysis and logistic regression, was performed to assess the accuracy of these models. Results: The highest predictive accuracy was achieved with Model 1, which included seven parameters, yielding an AUC of 0.952. This model achieved a sensitivity of 96.4% and a negative predictive value (NPV) of 97.2%. Reducing the number of parameters lowered the accuracy, with contrast enhancement playing a significant role in Model 1. A risk calculator based on the optimal model was developed, offering an effective tool for clinical use that can be provided. Notably, 21 out of 37 ALTs lacked atypia and would have been missed without molecular testing. Conclusions: The developed scoring system, based on clinical and imaging parameters, accurately distinguishes ALTs from lipomas, offering a practical alternative to molecular pathology testing. This multi-parameter approach significantly improves diagnostic reliability, reducing the risk of misclassification and false negatives, while also potentially lowering healthcare costs.