Deep learning-based triage and analysis of lesion burden for COVID-19: a retrospective study with external validation

Abstract

Background Prompt identification of patients suspected to have COVID-19 is crucial for disease control. We aimed to develop a deep learning algorithm on the basis of chest CT for rapid triaging in fever clinics. Methods We trained a U-Net-based model on unenhanced chest CT scans obtained from 2447 patients admitted to Tongji Hospital (Wuhan, China) between Feb 1, 2020, and March 3, 2020 (1647 patients with RT-PCR-confirmed COVID-19 and 800 patients without COVID-19) to segment lung opacities and alert cases with COVID-19 imaging manifestations. The ability of artificial intelligence (AI) to triage patients suspected to have COVID-19 was assessed in a large external validation set, which included 2120 retrospectively collected consecutive cases from three fever clinics inside and outside the epidemic centre of Wuhan (Tianyou Hospital [Wuhan, China; area of high COVID-19 prevalence], Xianning Central Hospital [Xianning, China; area of medium COVID-19 prevalence], and The Second Xiangya Hospital [Changsha, China; area of low COVID-19 prevalence]) between Jan 22, 2020, and Feb 14, 2020. To validate the sensitivity of the algorithm in a larger sample of patients with COVID-19, we also included 761 chest CT scans from 722 patients with RT-PCR-confirmed COVID-19 treated in a makeshift hospital (Guanggu Fangcang Hospital, Wuhan, China) between Feb 21, 2020, and March 6, 2020. Additionally, the accuracy of AI was compared with a radiologist panel for the identification of lesion burden increase on pairs of CT scans obtained from 100 patients with COVID-19. Findings In the external validation set, using radiological reports as the reference standard, AI-aided triage achieved an area under the curve of 0·953 (95% CI 0·949–0·959), with a sensitivity of 0·923 (95% CI 0·914–0·932), specificity of 0·851 (0·842–0·860), a positive predictive value of 0·790 (0·777–0·803), and a negative predictive value of 0·948 (0·941–0·954). AI took a median of 0·55 min (IQR: 0·43–0·63) to flag a positive case, whereas radiologists took a median of 16·21 min (11·67–25·71) to draft a report and 23·06 min (15·67–39·20) to release a report. With regard to the identification of increases in lesion burden, AI achieved a sensitivity of 0·962 (95% CI 0·947–1·000) and a specificity of 0·875 (95 %CI 0·833–0·923). The agreement between AI and the radiologist panel was high (Cohen's kappa coefficient 0·839, 95% CI 0·718–0·940). Interpretation A deep learning algorithm for triaging patients with suspected COVID-19 at fever clinics was developed and externally validated. Given its high accuracy across populations with varied COVID-19 prevalence, integration of this system into the standard clinical workflow could expedite identification of chest CT scans with imaging indications of COVID-19. Funding Special Project for Emergency of the Science and Technology Department of Hubei Province, China.

Deep Learning Algorithm Trained with COVID-19 Pneumonia Also Identifies Immune Checkpoint Inhibitor Therapy-Related Pneumonitis

“…The output also includes the estimated risk probability for the diagnosis of COVID-19 pneumonia. The core algorithm is based on a deep convolutional neural network structure and uses the U-net network structure as the core segmentation network [ 27 ]. The model training process is shown in Figure 1 .…”

“…The model was developed initially after training on a population of patients diagnosed in Wuhan, China, and was later further developed by training on a larger population. Specifically, for the trained AI model, patients’ characteristics ( n = 2191 adult patients; Wuhan Chinese COVID-19) were mixed, including all stages and clinical presentation of the disease (e.g., symptoms could have been mild, moderate, or severe) [ 27 ]. In the Chinese training datasets, controls were 1000 adult patients without COVID-19, who were admitted to Tongji Hospital and had double negative RT-PCR test results.…”

A Survey of Artificial Intelligence and Internet of Things (IoT) based approaches against Covid-19

“…• Cao et al [6] and Huang et al [7] have come up with a model using CNNs as basis for CT image prediction. • The research work from [8] is focused on using CT imagery to develop segmentation models to detect abnormalities and lung diseases. Shan et al [9] introduces a deep learning (DL) based system using CT Scans for automatic segmentation and quantification of infected regions in lungs.…”

“…Goal Data source Results [1] disease CT scan 86.7 accuracy% classification [3] Covid-19 CT scan 0.96 AUC diagnosis [4], [8] lung image CT scan qualitative segmentation [6], [7] lung disease CT scan qualitative prediction [9] lung infection CT scan 91.6% accuracy segmentation [10] transmission confirmed 0.73% avg. forecasting cases error [11] transmission confirmed 93.4% accuracy forecasting cases [12] suspect IoT (mobile defining monitoring devices) roadmap [13] suspect mobile survey data collected monitoring [14] Covid-19 CCTV, mobile data collected monitoring care devices…”

Artificial Intelligence of COVID-19 Imaging: A Hammer in Search of a Nail

“…One such work showed little difference in performance by the different architectures ( 29 ). Example deep learning architectures proven successful for detecting COVID-19 include EfficientNet ( 6 ), U-Net ( 30 ), ResNet ( 31 ), and Inf-Net ( 32 ). Some studies preprocess the images to segment the lungs before analysis for pulmonary parenchymal opacities ( 5 ).…”