Objective: To identify predictors of pulmonary fibrosis development by combining follow-up thin-section CT findings and clinical features in patients discharged after treatment for COVID-19. Materials and Methods: This retrospective study involved 32 confirmed COVID-19 patients who were divided into two groups according to the evidence of fibrosis on their latest follow-up CT imaging. Clinical data and CT imaging features of all the patients in different stages were collected and analyzed for comparison. Results: The latest follow-up CT imaging showed fibrosis in 14 patients (male, 12; female, 2) and no fibrosis in 18 patients (male, 10; female, 8). Compared with the non-fibrosis group, the fibrosis group was older (median age: 54.0 years vs. 37.0 years, p = 0.008), and the median levels of C-reactive protein (53.4 mg/L vs. 10.0 mg/L, p = 0.002) and interleukin-6 (79.7 pg/L vs. 11.2 pg/L, p = 0.04) were also higher. The fibrosis group had a longer-term of hospitalization (19.5 days vs. 10.0 days, p = 0.001), pulsed steroid therapy (11.0 days vs. 5.0 days, p < 0.001), and antiviral therapy (12.0 days vs. 6.5 days, p = 0.012). More patients on the worst-state CT scan had an irregular interface (59.4% vs. 34.4%, p = 0.045) and a parenchymal band (71.9% vs. 28.1%, p < 0.001). On initial CT imaging, the irregular interface (57.1%) and parenchymal band (50.0%) were more common in the fibrosis group. On the worst-state CT imaging, interstitial thickening (78.6%), air bronchogram (57.1%), irregular interface (85.7%), coarse reticular pattern (28.6%), parenchymal band (92.9%), and pleural effusion (42.9%) were more common in the fibrosis group. Conclusion: Fibrosis was more likely to develop in patients with severe clinical conditions, especially in patients with high inflammatory indicators. Interstitial thickening, irregular interface, coarse reticular pattern, and parenchymal band manifested in the process of the disease may be predictors of pulmonary fibrosis. Irregular interface and parenchymal band could predict the formation of pulmonary fibrosis early.

Recently, the coronavirus disease 2019 (COVID-19) has caused a pandemic disease in over 200 countries, influencing billions of humans. To control the infection, identifying and separating the infected people is the most crucial step. The main diagnostic tool is the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. Still, the sensitivity of the RT-PCR test is not high enough to effectively prevent the pandemic. The chest CT scan test provides a valuable complementary tool to the RT-PCR test, and it can identify the patients in the early-stage with high sensitivity. However, the chest CT scan test is usually time-consuming, requiring about 21.5 minutes per case. This paper develops a novel Joint Classification and Segmentation (JCS) system to perform real-time and explainable COVID-19 chest CT diagnosis. To train our JCS system, we construct a large scale COVID-19 Classification and Segmentation (COVID-CS) dataset, with 144,167 chest CT images of 400 COVID-19 patients and 350 uninfected cases. 3,855 chest CT images of 200 patients are annotated with fine-grained pixel-level labels of opacifications, which are increased attenuation of the lung parenchyma. We also have annotated lesion counts, opacification areas, and locations and thus benefit various diagnosis aspects. Extensive experiments demonstrate that the proposed JCS diagnosis system is very efficient for COVID-19 classification and segmentation. It obtains an average sensitivity of 95.0% and a specificity of 93.0% on the classification test set, and 78.5% Dice score on the segmentation test set of our COVID-CS dataset. The COVID-CS dataset and code are available at https://github.com/yuhuan-wu/JCS.

Hip Osteoarthritis (OA) is a common disease among the middle-aged and elderly people. Conventionally, hip OA is diagnosed by manually assessing X-ray images. This study took the hip joint as the object of observation and explored the diagnostic value of deep learning in hip osteoarthritis. A deep convolutional neural network (CNN) was trained and tested on 420 hip X-ray images to automatically diagnose hip OA. This CNN model achieved a balance of high sensitivity of 95.0% and high specificity of 90.7%, as well as an accuracy of 92.8% compared to the chief physicians. The CNN model performance is comparable to an attending physician with 10 years of experience. The results of this study indicate that deep learning has promising potential in the field of intelligent medical image diagnosis practice.

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.

Non-invasive prediction of isocitrate dehydrogenase (IDH) genotype plays an important role in tumor glioma diagnosis and prognosis. Recently, research has shown that radiology images can be a potential tool for genotype prediction, and fusion of multi-modality data by deep learning methods can further provide complementary information to enhance prediction accuracy. However, it still does not have an effective deep learning architecture to predict IDH genotype with three-dimensional (3D) multimodal medical images. In this paper, we proposed a novel multimodal 3D DenseNet (M3D-DenseNet) model to predict IDH genotypes with multimodal magnetic resonance imaging (MRI) data. To evaluate its performance, we conducted experiments on the BRATS-2017 and The Cancer Genome Atlas breast invasive carcinoma (TCGA-BRCA) dataset to get image data as input and gene mutation information as the target, respectively. We achieved 84.6% accuracy (area under the curve (AUC) = 85.7%) on the validation dataset. To evaluate its generalizability, we applied transfer learning techniques to predict World Health Organization (WHO) grade status, which also achieved a high accuracy of 91.4% (AUC = 94.8%) on validation dataset. With the properties of automatic feature extraction, and effective and high generalizability, M3D-DenseNet can serve as a useful method for other multimodal radiogenomics problems and has the potential to be applied in clinical decision making.