A novel deep learning model for breast lesion classification using ultrasound Images: A multicenter data evaluation.

PURPOSE: Breast cancer is one of the major reasons of death due to cancer in women. Early diagnosis is the most critical key for disease screening, control, and reducing mortality. A robust diagnosis relies on the correct classification of breast lesions. While breast biopsy is referred to as the "gold standard" in assessing both the activity and degree of breast cancer, it is an invasive and time-consuming approach. METHOD: The current study's primary objective was to develop a novel deep-learning architecture based on the InceptionV3 network to classify ultrasound breast lesions. The main promotions of the proposed architecture were converting the InceptionV3 modules to residual inception ones, increasing their number, and altering the hyperparameters. In addition, we used a combination of five datasets (three public datasets and two prepared from different imaging centers) for training and evaluating the model. RESULTS: The dataset was split into the train (80%) and test (20%) groups. The model achieved 0.83, 0.77, 0.8, 0.81, 0.81, 0.18, and 0.77 for the precision, recall, F1 score, accuracy, AUC, Root Mean Squared Error, and Cronbach's α in the test group, respectively. CONCLUSIONS: This study illustrates that the improved InceptionV3 can robustly classify breast tumors, potentially reducing the need for biopsy in many cases.

Automatic fetal biometry prediction using a novel deep convolutional network architecture.

PURPOSE: Fetal biometric measurements face a number of challenges, including the presence of speckle, limited soft-tissue contrast and difficulties in the presence of low amniotic fluid. This work proposes a convolutional neural network for automatic segmentation and measurement of fetal biometric parameters, including biparietal diameter (BPD), head circumference (HC), abdominal circumference (AC), and femur length (FL) from ultrasound images that relies on the attention gates incorporated into the multi-feature pyramid Unet (MFP-Unet) network. METHODS: The proposed approach, referred to as Attention MFP-Unet, learns to extract/detect salient regions automatically to be treated as the object of interest via the attention gates. After determining the type of anatomical structure in the image using a convolutional neural network, Niblack's thresholding technique was applied as pre-processing algorithm for head and abdomen identification, whereas a novel algorithm was used for femur extraction. A publicly-available dataset (HC18 grand-challenge) and clinical data of 1334 subjects were utilized for training and evaluation of the Attention MFP-Unet algorithm. RESULTS: Dice similarity coefficient (DSC), hausdorff distance (HD), percentage of good contours, the conformity coefficient, and average perpendicular distance (APD) were employed for quantitative evaluation of fetal anatomy segmentation. In addition, correlation analysis, good contours, and conformity were employed to evaluate the accuracy of the biometry predictions. Attention MFP-Unet achieved 0.98, 1.14 mm, 100%, 0.95, and 0.2 mm for DSC, HD, good contours, conformity, and APD, respectively. CONCLUSIONS: Quantitative evaluation demonstrated the superior performance of the Attention MFP-Unet compared to state-of-the-art approaches commonly employed for automatic measurement of fetal biometric parameters.

Accuracy of diffusion-weighted imaging in discriminating atypical vertebral haemangiomas from malignant masses in patients with vertebral lesions: a cross-sectional study.

PURPOSE: Vertebral haemangiomas are incidental findings in imaging modalities. Atypical haemangiomas are haeman-giomas rich in vascular tissue, and they are found to be hypointense in T1 sequences and hyperintense in T2 sequences, mimicking the findings of metastatic lesions. In the present study we aim to evaluate the ability of diffusion- weighted imaging to differentiate these two groups of vertebral lesions. MATERIAL AND METHODS: In the present cross-sectional study, a total of 23 lesions were included, including 10 haemangiomas and 13 malignant lesions. Diffusion-weighted imaging was used to compare atypical haemangiomas and metastatic lesions. The apparent diffusion co-efficient was determined for each lesion, and then the mean of each group was calculated. The means were then compared. Receiver operating characteristic analysis was used to determine a cut-off ADC value to differentiate these lesions. RESULTS: The difference between the mean age of the two groups was not significant. The mean ADC value for atypical haemangiomas was 1884 ± 74 × 10-6 mm2/s and 1008 ± 81 × 10-6 mm2/s for the malignant lesions. The difference between the two groups was statistically significant (p < 10-3). ROC curve analysis determined an ADC value of 958 × 10-6 mm2/s to be able to differentiate between atypical haemangiomas and malignant lesions. CONCLUSIONS: Diffusion-weighted MRI could be used to differentiate between atypical haemangiomas and malignant metastatic lesions.