A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer.

Autor: Petrillo A; Radiology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy. a.petrillo@istitutotumori.na.it., Fusco R; Medical Oncology Division, Igea SpA, 80013, Naples, Italy., Petrosino T; Radiology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Vallone P; Radiology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Granata V; Radiology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Rubulotta MR; Radiology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Pariante P; Radiology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Raiano N; Radiology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Scognamiglio G; Pathology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Fanizzi A; Direzione Scientifica, IRCCS Istituto Tumori Giovanni Paolo II, Via Orazio Flacco 65, 70124, Bari, Italy., Massafra R; SSD Fisica Sanitaria, IRCCS Istituto Tumori Giovanni Paolo II, Via Orazio Flacco 65, 70124, Bari, Italy., Lafranceschina M; Struttura Semplice Dipartimentale Di Radiodiagnostica Senologica, IRCCS Istituto Tumori Giovanni Paolo II, Via Orazio Flacco 65, 70124, Bari, Italy., La Forgia D; Struttura Semplice Dipartimentale Di Radiodiagnostica Senologica, IRCCS Istituto Tumori Giovanni Paolo II, Via Orazio Flacco 65, 70124, Bari, Italy., Greco L; Radiology and Diagnostic Imaging, Istituto Di Ricovero E Cura a Carattere Scientifico (IRCCS) Regina Elena National Cancer Institute, Rome, Italy., Ferranti FR; Radiology and Diagnostic Imaging, Istituto Di Ricovero E Cura a Carattere Scientifico (IRCCS) Regina Elena National Cancer Institute, Rome, Italy., De Soccio V; Radiology and Diagnostic Imaging, Istituto Di Ricovero E Cura a Carattere Scientifico (IRCCS) Regina Elena National Cancer Institute, Rome, Italy., Vidiri A; Radiology and Diagnostic Imaging, Istituto Di Ricovero E Cura a Carattere Scientifico (IRCCS) Regina Elena National Cancer Institute, Rome, Italy., Botta F; Breast Imaging Division, IEO Istituto Europeo Di Oncologia, 20141, Milan, Italy., Dominelli V; Breast Imaging Division, IEO Istituto Europeo Di Oncologia, 20141, Milan, Italy., Cassano E; Breast Imaging Division, IEO Istituto Europeo Di Oncologia, 20141, Milan, Italy., Sorgente E; Radiation Protection and Innovative Technology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Pecori B; Radiation Protection and Innovative Technology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Cerciello V; Medical Physics, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy., Boldrini L; Dipartimento Di Diagnostica Per Immagini, Radioterapia Oncologica Ed Ematologia, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168, Rome, Italy.
Jazyk: angličtina
Zdroj: La Radiologia medica [Radiol Med] 2024 Jun; Vol. 129 (6), pp. 864-878. Date of Electronic Publication: 2024 May 17.
DOI: 10.1007/s11547-024-01817-8
Abstrakt: Objective: To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify luminal histotype of the breast cancer.
Methods: From four Italian centers were recruited 180 malignant lesions and 68 benign lesions. However, only the malignant lesions were considered for the analysis. All patients underwent contrast-enhanced mammography in cranium caudal (CC) and medium lateral oblique (MLO) view. Considering histological findings as the ground truth, four outcomes were considered: (1) G1 + G2 vs. G3; (2) HER2 + vs. HER2 - ; (3) HR + vs. HR - ; and (4) non-luminal vs. luminal A or HR + /HER2-  and luminal B or HR + /HER2 + . For multivariate analysis feature selection, balancing techniques and patter recognition approaches were considered.
Results: The univariate findings showed that the diagnostic performance is low for each outcome, while the results of the multivariate analysis showed that better performances can be obtained. In the HER2 + detection, the best performance (73% of accuracy and AUC = 0.77) was obtained using a linear regression model (LRM) with 12 features extracted by MLO view. In the HR + detection, the best performance (77% of accuracy and AUC = 0.80) was obtained using a LRM with 14 features extracted by MLO view. In grading classification, the best performance was obtained by a decision tree trained with three predictors extracted by MLO view reaching an accuracy of 82% on validation set. In the luminal versus non-luminal histotype classification, the best performance was obtained by a bagged tree trained with 15 predictors extracted by CC view reaching an accuracy of 94% on validation set.
Conclusions: The results suggest that radiomics analysis can be effectively applied to design a tool to support physician decision making in breast cancer classification. In particular, the classification of luminal versus non-luminal histotypes can be performed with high accuracy.
(© 2024. Italian Society of Medical Radiology.)
Databáze: MEDLINE
Externí odkaz: