Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution.

PURPOSE: The purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations. MATERIALS AND METHODS: Using a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio. RESULTS: Quantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850-0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810-0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668-0.760) and of 0.723 (95% CI: 0.668-0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set. CONCLUSION: This study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.

Synthetic MR image generation of macrotrabecular-massive hepatocellular carcinoma using generative adversarial networks.

PURPOSE: The purpose of this study was to develop a method for generating synthetic MR images of macrotrabecular-massive hepatocellular carcinoma (MTM-HCC). MATERIALS AND METHODS: A set of abdominal MR images including fat-saturated T1-weighted images obtained during the arterial and portal venous phases of enhancement and T2-weighted images of 91 patients with MTM-HCC, and another set of MR abdominal images from 67 other patients were used. Synthetic images were obtained using a 3-step pipeline that consisted in: (i), generating a synthetic MTM-HCC tumor on a neutral background; (ii), randomly selecting a background among the 67 patients and a position inside the liver; and (iii), merging the generated tumor in the background at the specified location. Synthetic images were qualitatively evaluated by three radiologists and quantitatively assessed using a mix of 1-nearest neighbor classifier metric and Fréchet inception distance. RESULTS: A set of 1000 triplets of synthetic MTM-HCC images with consistent contrasts were successfully generated. Evaluation of selected synthetic images by three radiologists showed that the method gave realistic, consistent and diversified images. Qualitative and quantitative evaluation led to an overall score of 0.64. CONCLUSION: This study shows the feasibility of generating realistic synthetic MR images with very few training data, by leveraging the wide availability of liver backgrounds. Further studies are needed to assess the added value of those synthetic images for automatic diagnosis of MTM-HCC.

Breast nodule classification with two-dimensional ultrasound using Mask-RCNN ensemble aggregation.

PURPOSE: The purpose of this study was to create a deep learning algorithm to infer the benign or malignant nature of breast nodules using two-dimensional B-mode ultrasound data initially marked as BI-RADS 3 and 4. MATERIALS AND METHODS: An ensemble of mask region-based convolutional neural networks (Mask-RCNN) combining nodule segmentation and classification were trained to explicitly localize the nodule and generate a probability of the nodule to be malignant on two-dimensional B-mode ultrasound. These probabilities were aggregated at test time to produce final results. Resulting inferences were assessed using area under the curve (AUC). RESULTS: A total of 460 ultrasound images of breast nodules classified as BI-RADS 3 or 4 were included. There were 295 benign and 165 malignant breast nodules used for training and validation, and another 137 breast nodules images used for testing. As a part of the challenge, the distribution of benign and malignant breast nodules in the test database remained unknown. The obtained AUC was 0.69 (95% CI: 0.57-0.82) on the training set and 0.67 on the test set. CONCLUSION: The proposed deep learning solution helps classify benign and malignant breast nodules based solely on two-dimensional ultrasound images initially marked as BIRADS 3 and 4.

Optimization of Fetal Biometry With 3D Ultrasound and Image Recognition (EPICEA): protocol for a prospective cross-sectional study.

CONTEXT: Variability in 2D ultrasound (US) is related to the acquisition of planes of reference and the positioning of callipers and could be reduced in combining US volume acquisitions and anatomical structures recognition. OBJECTIVES: The primary objective is to assess the consistency between 3D measurements (automated and manual) extracted from a fetal US volume with standard 2D US measurements (I). Secondary objectives are to evaluate the feasibility of the use of software to obtain automated measurements of the fetal head, abdomen and femur from US acquisitions (II) and to assess the impact of automation on intraobserver and interobserver reproducibility (III). METHODS AND ANALYSIS: 225 fetuses will be measured at 16-30 weeks of gestation. For each fetus, six volumes (two for head, abdomen and thigh, respectively) will be prospectively acquired after performing standard 2D biometry measurements (head and abdominal circumference, femoral length). Each volume will be processed later by both a software and an operator to extract the reference planes and to perform the corresponding measurements. The different sets of measurements will be compared using Bland-Altman plots to assess the agreement between the different processes (I). The feasibility of using the software in clinical practice will be assessed through the failure rate of processing and the score of quality of measurements (II). Interclass correlation coefficients will be used to evaluate the intraobserver and interobserver reproducibility (III). ETHICS AND DISSEMINATION: The study and related consent forms were approved by an institutional review board (CPP SUD-EST 3) on 2 October 2018, under reference number 2018-033 B. The study has been registered in https://clinicaltrials.gov registry on 23 January 2019, under the number NCT03812471. This study will enable an improved understanding and dissemination of the potential benefits of 3D automated measurements and is a prerequisite for the design of intention to treat randomised studies assessing their impact. TRIAL REGISTRATION NUMBER: NCT03812471; Pre-results.