1. Clinical value of radiomics and machine learning in breast ultrasound: a multicenter study for differential diagnosis of benign and malignant lesions
- Author
-
Simone Maurea, Luigi Insabato, Massimo Imbriaco, Francesco Verde, Renato Cuocolo, M. Amitrano, Valeria Romeo, Roberta Apolito, Annalisa Vitale, Anna Maria Cascone, Antonello Accurso, Maria Rosaria Argenzio, Arnaldo Stanzione, Annarita Gencarelli, Antonio Ventimiglia, Arturo Brunetti, Roberta Buonocore, Romeo, Valeria, Cuocolo, Renato, Apolito, Roberta, Stanzione, Arnaldo, Ventimiglia, Antonio, Vitale, Annalisa, Verde, Francesco, Accurso, Antonello, Amitrano, Michele, Insabato, Luigi, Gencarelli, Annarita, Buonocore, Roberta, Argenzio, Maria Rosaria, Cascone, Anna Maria, Imbriaco, Massimo, Maurea, Simone, and Brunetti, Arturo
- Subjects
medicine.medical_specialty ,education ,Machine learning ,computer.software_genre ,030218 nuclear medicine & medical imaging ,Diagnosis, Differential ,Machine Learning ,03 medical and health sciences ,0302 clinical medicine ,McNemar's test ,Breast cancer ,Diagnosis ,Ultrasound ,Medicine ,Humans ,Radiology, Nuclear Medicine and imaging ,Breast ,Breast ultrasound ,Neuroradiology ,Retrospective Studies ,Ultrasonography ,Mammary ,medicine.diagnostic_test ,business.industry ,General Medicine ,medicine.disease ,Confidence interval ,Random forest ,Female ,Ultrasonography, Mammary ,030220 oncology & carcinogenesis ,Test set ,Differential ,Radiology ,Artificial intelligence ,business ,computer - Abstract
Objectives We aimed to assess the performance of radiomics and machine learning (ML) for classification of non-cystic benign and malignant breast lesions on ultrasound images, compare ML’s accuracy with that of a breast radiologist, and verify if the radiologist’s performance is improved by using ML. Methods Our retrospective study included patients from two institutions. A total of 135 lesions from Institution 1 were used to train and test the ML model with cross-validation. Radiomic features were extracted from manually annotated images and underwent a multistep feature selection process. Not reproducible, low variance, and highly intercorrelated features were removed from the dataset. Then, 66 lesions from Institution 2 were used as an external test set for ML and to assess the performance of a radiologist without and with the aid of ML, using McNemar’s test. Results After feature selection, 10 of the 520 features extracted were employed to train a random forest algorithm. Its accuracy in the training set was 82% (standard deviation, SD, ± 6%), with an AUC of 0.90 (SD ± 0.06), while the performance on the test set was 82% (95% confidence intervals (CI) = 70–90%) with an AUC of 0.82 (95% CI = 0.70–0.93). It resulted in being significantly better than the baseline reference (p = 0.0098), but not different from the radiologist (79.4%, p = 0.815). The radiologist’s performance improved when using ML (80.2%), but not significantly (p = 0.508). Conclusions A radiomic analysis combined with ML showed promising results to differentiate benign from malignant breast lesions on ultrasound images. Key Points • Machine learning showed good accuracy in discriminating benign from malignant breast lesions • The machine learning classifier’s performance was comparable to that of a breast radiologist • The radiologist’s accuracy improved with machine learning, but not significantly
- Published
- 2021