Machine Learning Applied to Pre-Operative Computed-Tomography-Based Radiomic Features Can Accurately Differentiate Uterine Leiomyoma from Leiomyosarcoma: A Pilot Study

• Published in: Cancers 2024-04, Vol.16 (8), p.1570
• Main Authors: Santoro, Miriam, Zybin, Vladislav, Coada, Camelia Alexandra, Mantovani, Giulia, Paolani, Giulia, Di Stanislao, Marco, Modolon, Cecilia, Di Costanzo, Stella, Lebovici, Andrei, Ravegnini, Gloria, De Leo, Antonio, Tesei, Marco, Pasquini, Pietro, Lovato, Luigi, Morganti, Alessio Giuseppe, Pantaleo, Maria Abbondanza, De Iaco, Pierandrea, Strigari, Lidia, Perrone, Anna Myriam
• Format: Article
• Language: English
• Subjects: Abdomen; Archives & records; Computed tomography; Decision making; Differential diagnosis; Fibroids; Gynecology; Hysterectomy; Image processing; Laparotomy; Learning algorithms; Machine learning; Medical imaging; Patients; Pilot projects; Radiomics; Sarcoma; Software; Surgery; Tomography; Tumors; Ultrasonic imaging; Uterus
• ISSN: 2072-6694; 2072-6694
• DOI: 10.3390/cancers16081570

The accurate discrimination of uterine leiomyosarcomas and leiomyomas in a pre-operative setting remains a current challenge. To date, the diagnosis is made by a pathologist on the excised tumor. The aim of this study was to develop a machine learning algorithm using radiomic data extracted from contrast-enhanced computed tomography (CECT) images that could accurately distinguish leiomyosarcomas from leiomyomas. Pre-operative CECT images from patients submitted to surgery with a histological diagnosis of leiomyoma or leiomyosarcoma were used for the region of interest identification and radiomic feature extraction. Feature extraction was conducted using the PyRadiomics library, and three feature selection methods combined with the general linear model (GLM), random forest (RF), and support vector machine (SVM) classifiers were built, trained, and tested for the binary classification task (malignant vs. benign). In parallel, radiologists assessed the diagnosis with or without clinical data. A total of 30 patients with leiomyosarcoma (mean age 59 years) and 35 patients with leiomyoma (mean age 48 years) were included in the study, comprising 30 and 51 lesions, respectively. Out of nine machine learning models, the three feature selection methods combined with the GLM and RF classifiers showed good performances, with predicted area under the curve (AUC), sensitivity, and specificity ranging from 0.78 to 0.97, from 0.78 to 1.00, and from 0.67 to 0.93, respectively, when compared to the results obtained from experienced radiologists when blinded to the clinical profile (AUC = 0.73 95%CI = 0.62-0.84), as well as when the clinical data were consulted (AUC = 0.75 95%CI = 0.65-0.85). CECT images integrated with radiomics have great potential in differentiating uterine leiomyomas from leiomyosarcomas. Such a tool can be used to mitigate the risks of eventual surgical spread in the case of leiomyosarcoma and allow for safer fertility-sparing treatment in patients with benign uterine lesions.