Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence.

Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses. However, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalised model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution under a federated learning framework (FL) without data sharing. Here we show that our FL model outperformed all the local models by a large yield (test sensitivity /specificity in China: 0.973/0.951, in the UK: 0.730/0.942), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals leaving out the FL) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK. Collectively, our work advanced the prospects of utilising federated learning for privacy-preserving AI in digital health.

From pathogenesis to treatment, a systemic review of cardiac lipoma.

Cardiac lipoma is an uncommon primary cardiac tumor. With the advancement of diagnostic methods and treatment techniques, more cases of cardiac lipomas have been reported and suggest that the entity previously widely thought to display classic features may also show atypical findings. A systemic review of the rare cardiac tumor was done by searching the literature of cardiac lipoma. We endeavor to summarize the clinical features of the rare disease from pathogenesis to treatment. Literature of cardiac lipoma was retrospectively searched through PubMed and 255 cases of cardiac lipoma were included into this analysis. Cardiac lipomas can occur anywhere within the heart, 53.1% were located within the cardiac chambers, 32.5% in the pericardium, 10,7% within the myocardium and 3.7% involved multiple structures. More than half of the reported cardiac lipomas (66%) may be clinically symptomatic, presenting with symptoms ranging from chest discomfort to syncope depending on their size and location as well as extent of myocardial involvement. Noninvasive cardiac imaging has replaced the role of autopsy and cardiothoracic surgery in detection and diagnosis of cardiac lipomas. Most symptomatic patients (83.7%) were treated by resection of cardiac lipomas and 68.3% of asymptomatic patients also underwentprophylactic resection. Overgrowth and myocardial infiltration of lipomas may result in unsuccessful resection. Recurrence of cardiac lipomas was rare but reported in a few cases. The early detection and accurate diagnosis of cardiac lipoma is of great significance in clinical management, to avoid an unfavourable outcome due to overgrowth.

A collaborative online AI engine for CT-based COVID-19 diagnosis.

Artificial intelligence can potentially provide a substantial role in streamlining chest computed tomography (CT) diagnosis of COVID-19 patients. However, several critical hurdles have impeded the development of robust AI model, which include deficiency, isolation, and heterogeneity of CT data generated from diverse institutions. These bring about lack of generalization of AI model and therefore prevent it from applications in clinical practices. To overcome this, we proposed a federated learning-based Unified CT-COVID AI Diagnostic Initiative (UCADI, http://www.ai-ct-covid.team/), a decentralized architecture where the AI model is distributed to and executed at each host institution with the data sources or client ends for training and inferencing without sharing individual patient data. Specifically, we firstly developed an initial AI CT model based on data collected from three Tongji hospitals in Wuhan. After model evaluation, we found that the initial model can identify COVID from Tongji CT test data at near radiologist-level (97.5% sensitivity) but performed worse when it was tested on COVID cases from Wuhan Union Hospital (72% sensitivity), indicating a lack of model generalization. Next, we used the publicly available UCADI framework to build a federated model which integrated COVID CT cases from the Tongji hospitals and Wuhan Union hospital (WU) without transferring the WU data. The federated model not only performed similarly on Tongji test data but improved the detection sensitivity (98%) on WU test cases. The UCADI framework will allow participants worldwide to use and contribute to the model, to deliver a real-world, globally built and validated clinic CT-COVID AI tool. This effort directly supports the United Nations Sustainable Development Goals' number 3, Good Health and Well-Being, and allows sharing and transferring of knowledge to fight this devastating disease around the world.