Mix-and-Interpolate: A Training Strategy to Deal With Source-Biased Medical Data.

Till March 31st, 2021, the coronavirus disease 2019 (COVID-19) had reportedly infected more than 127 million people and caused over 2.5 million deaths worldwide. Timely diagnosis of COVID-19 is crucial for management of individual patients as well as containment of the highly contagious disease. Having realized the clinical value of non-contrast chest computed tomography (CT) for diagnosis of COVID-19, deep learning (DL) based automated methods have been proposed to aid the radiologists in reading the huge quantities of CT exams as a result of the pandemic. In this work, we address an overlooked problem for training deep convolutional neural networks for COVID-19 classification using real-world multi-source data, namely, the data source bias problem. The data source bias problem refers to the situation in which certain sources of data comprise only a single class of data, and training with such source-biased data may make the DL models learn to distinguish data sources instead of COVID-19. To overcome this problem, we propose MIx-aNd-Interpolate (MINI), a conceptually simple, easy-to-implement, efficient yet effective training strategy. The proposed MINI approach generates volumes of the absent class by combining the samples collected from different hospitals, which enlarges the sample space of the original source-biased dataset. Experimental results on a large collection of real patient data (1,221 COVID-19 and 1,520 negative CT images, and the latter consisting of 786 community acquired pneumonia and 734 non-pneumonia) from eight hospitals and health institutions show that: 1) MINI can improve COVID-19 classification performance upon the baseline (which does not deal with the source bias), and 2) MINI is superior to competing methods in terms of the extent of improvement.

Anatomic Repair of Left Main Coronary Artery Atresia: Coronary Ostioplasty With Autologous Pulmonary Artery.

BACKGROUND: Left main coronary arterial (LMCA) atresia is a rare coronary arterial anomaly with extremely limited data on the optimal management. We aimed to report our single-surgeon experience of the ostioplasty in patients with LMCA atresia. METHODS: From July 2018 to December 2019, pediatric patients who presented with LMCA atresia and subsequently underwent surgical coronary ostioplasty were recruited into this retrospective study. Concomitant mitral repair was applied when the regurgitation was moderate or more severe. RESULTS: A total of 9 patients diagnosed with LMCA atresia were included. Mitral regurgitation was found in all of them, including 6 (66.7%) severe, 1 (11.1%) moderate, and 2 (22.2%) mild. In addition to ischemic lesions, which were found in 7 (77.8%) patients, structural mitral problems were also common (presented in 7 [77.8%] patients). All the patients underwent coronary ostioplasty with autologous pulmonary arterial patch augmenting the anterior wall of the neo-ostium. Mean aortic cross clamp time and cardiopulmonary bypass time was 88.1 ± 18.9 and 124.6 ± 23.6 minutes, respectively. During a median of 10.9 (range: 3.3 to 17.2) months' follow-up, there was only 1 death at 5 months after surgery. All survivors were recovered uneventfully with normal left-ventricular function; however, with 4 (50.0%) having significant recurrence of mitral regurgitation. CONCLUSIONS: With favourable surgical outcomes, coronary ostioplasty for LMCA atresia may be an option of revascularization. Structural mitral problems presented in majority patients, resulting in the requirement of concomitant mitral repair. However, the optimal technique of mitral repair remains unclear.

Efficient and Effective Training of COVID-19 Classification Networks With Self-Supervised Dual-Track Learning to Rank.

Coronavirus Disease 2019 (COVID-19) has rapidly spread worldwide since first reported. Timely diagnosis of COVID-19 is crucial both for disease control and patient care. Non-contrast thoracic computed tomography (CT) has been identified as an effective tool for the diagnosis, yet the disease outbreak has placed tremendous pressure on radiologists for reading the exams and may potentially lead to fatigue-related mis-diagnosis. Reliable automatic classification algorithms can be really helpful; however, they usually require a considerable number of COVID-19 cases for training, which is difficult to acquire in a timely manner. Meanwhile, how to effectively utilize the existing archive of non-COVID-19 data (the negative samples) in the presence of severe class imbalance is another challenge. In addition, the sudden disease outbreak necessitates fast algorithm development. In this work, we propose a novel approach for effective and efficient training of COVID-19 classification networks using a small number of COVID-19 CT exams and an archive of negative samples. Concretely, a novel self-supervised learning method is proposed to extract features from the COVID-19 and negative samples. Then, two kinds of soft-labels ('difficulty' and 'diversity') are generated for the negative samples by computing the earth mover's distances between the features of the negative and COVID-19 samples, from which data 'values' of the negative samples can be assessed. A pre-set number of negative samples are selected accordingly and fed to the neural network for training. Experimental results show that our approach can achieve superior performance using about half of the negative samples, substantially reducing model training time.