RESUMO
BACKGROUND: Mitral regurgitation (MR) is the most common valve lesion worldwide. However, the quantitative assessment of MR severity based on current guidelines is challenging and time-consuming; strict adherence to applying these guidelines is therefore relatively infrequent. We aimed to develop an automatic, reliable and reproducible artificial intelligence (AI) diagnostic system to assist physicians in grading MR severity based on color video Doppler echocardiography via a self-supervised learning (SSL) algorithm. METHODS: We constructed a retrospective cohort of 2,766 consecutive echocardiographic studies of patients with MR diagnosed based on clinical criteria from two hospitals in China. One hundred and forty-eight studies with reference standards were selected in the main analysis and also served as the test set for the AI segmentation model. Five hundred and ninety-two and 148 studies were selected with stratified random sampling as the training and validation datasets, respectively. The self-supervised algorithm captures features and segments the MR jet and left atrium (LA) area, and the output is used to assist physicians in MR severity grading. The diagnostic performance of physicians without and with the support from AI was estimated and compared. RESULTS: The performance of SSL algorithm yielded 89.2% and 85.3% average segmentation dice similarity coefficient (DICE) on the validation and test datasets, which achieved 6.2% and 8.1% improvement compared to Residual U-shape Network (ResNet-UNet), respectively. When physicians were provided the output of algorithm for grading MR severity, the sensitivity increased from 77.0% (95% CI: 70.9-82.1%) to 86.7% (95% CI: 80.3-91.2%) and the specificity was largely unchanged: 91.5% (95% CI: 87.8-94.1%) vs. 90.5% (95% CI: 86.7-93.2%). CONCLUSIONS: This study provides a new, practical, accurate, plug-and-play AI-assisted approach for assisting physicians in MR severity grading that can be easily implemented in clinical practice.
RESUMO
Due to the development of deep learning, an increasing number of research works have been proposed to establish automated analysis systems for 3D volumetric medical data to improve the quality of patient care. However, it is challenging to obtain a large number of annotated 3D medical data needed to train a neural network well, as such manual annotation by physicians is time consuming and laborious. Self-supervised learning is one of the potential solutions to mitigate the strong requirement of data annotation by deeply exploiting raw data information. In this paper, we propose a novel self-supervised learning framework for volumetric medical data. Specifically, we propose a pretext task, i.e., Rubik's cube+, to pre-train 3D neural networks. The pretext task involves three operations, namely cube ordering, cube rotating and cube masking, forcing networks to learn translation and rotation invariant features from the original 3D medical data, and tolerate the noise of the data at the same time. Compared to the strategy of training from scratch, fine-tuning from the Rubik's cube+ pre-trained weights can remarkablely boost the accuracy of 3D neural networks on various tasks, such as cerebral hemorrhage classification and brain tumor segmentation, without the use of extra data.
