Salvatore Gitto1, Renato Cuocolo2, Domenico Albano3, Vito Chianca4, Carmelo Messina5, Angelo Gambino4, Lorenzo Ugga2, Maria Cristina Cortese6, Angelo Lazzara7, Domenico Ricci8, Riccardo Spairani9, Edoardo Zanchetta10, Alessandro Luzzati4, Arturo Brunetti2, Antonina Parafioriti11, Luca Maria Sconfienza5. 1. Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milano, Italy. Electronic address: sal.gitto@gmail.com. 2. Dipartimento di Scienze Biomediche Avanzate, Università degli Studi di Napoli Federico II, Napoli, Italy. 3. IRCCS Istituto Ortopedico Galeazzi, Milano, Italy; Sezione di Scienze Radiologiche, Dipartimento di Biomedicina, Neuroscienze e Diagnostica Avanzata, Università degli Studi di Palermo, Palermo, Italy. 4. IRCCS Istituto Ortopedico Galeazzi, Milano, Italy. 5. Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milano, Italy; IRCCS Istituto Ortopedico Galeazzi, Milano, Italy. 6. Istituto di Radiologia, Fondazione Policlinico A. Gemelli IRCCS - Università Cattolica Sacro Cuore, Roma, Italy. 7. Dipartimento di Radiologia e Neuroradiologia Pediatrica, Ospedale dei Bambini "V. Buzzi", Milano, Italy. 8. AUSL Romagna, Ospedale Santa Maria Delle Croci, Ravenna, Italy. 9. IRCCS Policlinico San Donato, San Donato Milanese, Italy. 10. ASST Santi Paolo e Carlo, Milano, Italy. 11. Pathology Department, ASST Pini-CTO, Milano, Italy.
Abstract
PURPOSE: To evaluate the diagnostic performance of machine learning for discrimination between low-grade and high-grade cartilaginous bone tumors based on radiomic parameters extracted from unenhanced magnetic resonance imaging (MRI). METHODS: We retrospectively enrolled 58 patients with histologically-proven low-grade/atypical cartilaginous tumor of the appendicular skeleton (n = 26) or higher-grade chondrosarcoma (n = 32, including 16 appendicular and 16 axial lesions). They were randomly divided into training (n = 42) and test (n = 16) groups for model tuning and testing, respectively. All tumors were manually segmented on T1-weighted and T2-weighted images by drawing bidimensional regions of interest, which were used for first order and texture feature extraction. A Random Forest wrapper was employed for feature selection. The resulting dataset was used to train a locally weighted ensemble classifier (AdaboostM1). Its performance was assessed via 10-fold cross-validation on the training data and then on the previously unseen test set. Thereafter, an experienced musculoskeletal radiologist blinded to histological and radiomic data qualitatively evaluated the cartilaginous tumors in the test group. RESULTS: After feature selection, the dataset was reduced to 4 features extracted from T1-weighted images. AdaboostM1 correctly classified 85.7 % and 75 % of the lesions in the training and test groups, respectively. The corresponding areas under the receiver operating characteristic curve were 0.85 and 0.78. The radiologist correctly graded 81.3 % of the lesions. There was no significant difference in performance between the radiologist and machine learning classifier (P = 0.453). CONCLUSIONS: Our machine learning approach showed good diagnostic performance for classification of low-to-high grade cartilaginous bone tumors and could prove a valuable aid in preoperative tumor characterization.
PURPOSE: To evaluate the diagnostic performance of machine learning for discrimination between low-grade and high-grade cartilaginous bone tumors based on radiomic parameters extracted from unenhanced magnetic resonance imaging (MRI). METHODS: We retrospectively enrolled 58 patients with histologically-proven low-grade/atypical cartilaginous tumor of the appendicular skeleton (n = 26) or higher-grade chondrosarcoma (n = 32, including 16 appendicular and 16 axial lesions). They were randomly divided into training (n = 42) and test (n = 16) groups for model tuning and testing, respectively. All tumors were manually segmented on T1-weighted and T2-weighted images by drawing bidimensional regions of interest, which were used for first order and texture feature extraction. A Random Forest wrapper was employed for feature selection. The resulting dataset was used to train a locally weighted ensemble classifier (AdaboostM1). Its performance was assessed via 10-fold cross-validation on the training data and then on the previously unseen test set. Thereafter, an experienced musculoskeletal radiologist blinded to histological and radiomic data qualitatively evaluated the cartilaginous tumors in the test group. RESULTS: After feature selection, the dataset was reduced to 4 features extracted from T1-weighted images. AdaboostM1 correctly classified 85.7 % and 75 % of the lesions in the training and test groups, respectively. The corresponding areas under the receiver operating characteristic curve were 0.85 and 0.78. The radiologist correctly graded 81.3 % of the lesions. There was no significant difference in performance between the radiologist and machine learning classifier (P = 0.453). CONCLUSIONS: Our machine learning approach showed good diagnostic performance for classification of low-to-high grade cartilaginous bone tumors and could prove a valuable aid in preoperative tumor characterization.
Authors: Claudio E von Schacky; Nikolas J Wilhelm; Valerie S Schäfer; Yannik Leonhardt; Matthias Jung; Pia M Jungmann; Maximilian F Russe; Sarah C Foreman; Felix G Gassert; Florian T Gassert; Benedikt J Schwaiger; Carolin Mogler; Carolin Knebel; Ruediger von Eisenhart-Rothe; Marcus R Makowski; Klaus Woertler; Rainer Burgkart; Alexandra S Gersing Journal: Eur Radiol Date: 2022-04-09 Impact factor: 7.034
Authors: Anna Castaldo; Davide Raffaele De Lucia; Giuseppe Pontillo; Marco Gatti; Sirio Cocozza; Lorenzo Ugga; Renato Cuocolo Journal: Diagnostics (Basel) Date: 2021-06-30