Artificial intelligence, BI-RADS evaluation and morphometry: A novel combination to diagnose breast cancer using ultrasonography, results from multi-center cohorts.

PURPOSE: To develop and validate a machine learning (ML) model for the classification of breast lesions on ultrasound images. METHOD: In the present study, three separate data cohorts containing 1288 breast lesions from three countries (Malaysia, Iran, and Turkey) were utilized for MLmodel development and external validation. The model was trained on ultrasound images of 725 breast lesions, and validation was done separately on the remaining data. An expert radiologist and a radiology resident classified the lesions based on the BI-RADS lexicon. Thirteen morphometric features were selected from a contour of the lesion and underwent a three-step feature selection process. Five features were chosen to be fed into the model separately and combined with the imaging signs mentioned in the BI-RADS reference guide. A support vector classifier was trained and optimized. RESULTS: The diagnostic profile of the model with various input data was compared to the expert radiologist and radiology resident. The agreement of each approach with histopathologic specimens was also determined. Based on BI-RADS and morphometric features, the model achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.885, which is higher than the expert radiologist and radiology resident performances with AUC of 0.814 and 0.632, respectively in all cohorts. DeLong's test also showed that the AUC of the ML protocol was significantly different from that of the expert radiologist (ΔAUCs = 0.071, 95%CI: (0.056, 0.086), P = 0.005). CONCLUSIONS: These results support the possible role of morphometric features in enhancing the already well-excepted classification schemes.

Accurate automated diagnosis of carpal tunnel syndrome using radiomics features with ultrasound images: A comparison with radiologists' assessment.

PURPOSE: Ultrasonography is the most common imaging modality used to diagnose carpal tunnel syndrome (CTS). Recently artificial intelligence algorithms have been used to diagnose musculoskeletal diseases accurately without human errors using medical images. In this work, a computer-aided diagnosis (CAD) system is developed using radiomics features extracted from median nerves (MN) to diagnose CTS accurately. METHOD: This study is performed on 228 wrists from 65 patients and 57 controls, with an equal number of control and CTS wrists. Nerve conduction study (NCS) is considered as the gold standard in this study. Two radiologists used two guides to evaluate and categorize the pattern and echogenicity of MNs. Radiomics features are extracted from B-mode ultrasound images (Ultrasomics), and the robust features are fed into support vector machine classifier for automated classification. The diagnostic performances of two radiologists and the CAD system are evaluated using ROC analysis. RESULTS: The agreement of two radiologists was excellent for both guide 1 and 2. The honey-comb pattern clearly appeared in control wrists (based on guide 1). In addition, CTS wrists indicated significantly lower number of fascicles in MNs (based on guide 2). The area under ROC curve (AUC) of the radiologist 1 and 2 are 0.658 and 0.667 based on guide 1 and 0.736 and 0.721 based on guide 2, respectively. The CAD system indicated higher performance than two radiologists with AUC of 0.926. CONCLUSION: The proposed CAD system shows the benefit of using ultrasomics features and can assist radiologists to diagnose CTS accurately.