Artificial intelligence for stepwise diagnosis and monitoring of COVID-19

Abstract

Background Main challenges for COVID-19 include the lack of a rapid diagnostic test, a suitable tool to monitor and predict a patient’s clinical course and an efficient way for data sharing among multicenters. We thus developed a novel artificial intelligence system based on deep learning (DL) and federated learning (FL) for the diagnosis, monitoring, and prediction of a patient’s clinical course. Methods CT imaging derived from 6 different multicenter cohorts were used for stepwise diagnostic algorithm to diagnose COVID-19, with or without clinical data. Patients with more than 3 consecutive CT images were trained for the monitoring algorithm. FL has been applied for decentralized refinement of independently built DL models. Results A total of 1,552,988 CT slices from 4804 patients were used. The model can diagnose COVID-19 based on CT alone with the AUC being 0.98 (95% CI 0.97–0.99), and outperforms the radiologist’s assessment. We have also successfully tested the incorporation of the DL diagnostic model with the FL framework. Its auto-segmentation analyses co-related well with those by radiologists and achieved a high Dice’s coefficient of 0.77. It can produce a predictive curve of a patient’s clinical course if serial CT assessments are available. Interpretation The system has high consistency in diagnosing COVID-19 based on CT, with or without clinical data. Alternatively, it can be implemented on a FL platform, which would potentially encourage the data sharing in the future. It also can produce an objective predictive curve of a patient’s clinical course for visualization. Key Points • CoviDet could diagnose COVID-19 based on chest CT with high consistency; this outperformed the radiologist’s assessment. Its auto-segmentation analyses co-related well with those by radiologists and could potentially monitor and predict a patient’s clinical course if serial CT assessments are available. It can be integrated into the federated learning framework. • CoviDet can be used as an adjunct to aid clinicians with the CT diagnosis of COVID-19 and can potentially be used for disease monitoring; federated learning can potentially open opportunities for global collaboration. Supplementary Information The online version contains supplementary material available at 10.1007/s00330-021-08334-6.

The Artificial Intelligence in Digital Radiology: Part 2: Towards an Investigation of acceptance and consensus on the Insiders

“…We are undoubtedly about to face another important change in the world of digital radiology [ 14 ]: the introduction of AI in clinical practice. During the pandemic, the importance and potential of AI clearly emerged in two sectors of digital radiology: chest CT and chest radiography [ 15 , 16 , 17 , 18 , 43 ]. However, even before the pandemic, we were already talking about this phenomenon affecting the health domain, especially the sectors where the conversion to digital health has been heavy, such as the DR [ 27 , 28 ], thanks to the DICOM standardization process.…”

“…An important engine in this context is represented by the research efforts during the COVID-19 pandemic. For example, research on chest CT/radiography has opened important discussions and scenarios [15][16][17][18]. AI, a field of computer science [19], when used in the health domain is considered a tool able to perform tasks normally requiring human intelligence [20][21][22][23] that in recent years have been applied in various health-related areas, such as cancer detection [24], dementia classification [25], and drug design [26], to name a few.…”

“…An important engine in this context is represented by the research efforts during the COVID-19 pandemic. For example, research on chest CT/radiography has opened important discussions and scenarios [ 15 , 16 , 17 , 18 ].…”

COVID-19 focused series: diagnosis and forecast of COVID-19

“…During the current COVID-19 pandemic, there has been growing interest in using reverse-transcription loop-mediated isothermal amplification (RT-LAMP) and clustered regularly interspaced short palindromic repeats (CRISPR)-based diagnostic techniques to develop rapid and accurate assays for detecting SARS-CoV-2. In addition to these detection methods, artificial intelligence (AI)-assisted diagnosis based on lung CT scan images is also actively under development ( 9 ).…”

Disorder-Free Data are All You Need: Inverse Supervised Learning for Broad-Spectrum Head Disorder Detection

“…In the medical field, the accumulation of medical image data has enabled many AI diagnostic techniques to achieve radiologist-level performance in recognizing, classifying, and quantifying specific diseases. For example, AI has been used for cerebral hemorrhage recognition 1 and COVID-19 recognition 2 from CT images. These breakthroughs have led us to envision that AI diagnostic techniques can assist in clinical decision-making from medical images and alleviate the severe shortage of expert radiologists in many areas and hospitals.…”