Computer-aided diagnosis of chest X-ray for COVID-19 diagnosis in external validation study by radiologists with and without deep learning system.

To evaluate the diagnostic performance of our deep learning (DL) model of COVID-19 and investigate whether the diagnostic performance of radiologists was improved by referring to our model. Our datasets contained chest X-rays (CXRs) for the following three categories: normal (NORMAL), non-COVID-19 pneumonia (PNEUMONIA), and COVID-19 pneumonia (COVID). We used two public datasets and private dataset collected from eight hospitals for the development and external validation of our DL model (26,393 CXRs). Eight radiologists performed two reading sessions: one session was performed with reference to CXRs only, and the other was performed with reference to both CXRs and the results of the DL model. The evaluation metrics for the reading session were accuracy, sensitivity, specificity, and area under the curve (AUC). The accuracy of our DL model was 0.733, and that of the eight radiologists without DL was 0.696 ± 0.031. There was a significant difference in AUC between the radiologists with and without DL for COVID versus NORMAL or PNEUMONIA (p = 0.0038). Our DL model alone showed better diagnostic performance than that of most radiologists. In addition, our model significantly improved the diagnostic performance of radiologists for COVID versus NORMAL or PNEUMONIA.

Improved diagnosis of histological capsule in hepatocallular carcinoma by using nonenhancing capsule appearance in addition to enhancing capsule appearance in gadoxetic acid-enhanced MRI.

To assess the value of nonenhancing capsule by adding to enhancing capsule in gadoxetic acid-enhanced MRI (EOB-MRI) in comparison with contrast-enhanced CT (CE-CT) for diagnosing histological capsule in hepatocellular carcinoma (HCC). One-hundred fifty-one patients with HCC who underwent both CE-CT and EOB-MRI were retrospectively reviewed. Liver Imaging-Reporting and Data System (LI-RADS) v2018 imaging features, including enhancing and nonenhancing capsule were evaluated by two readers in CE-CT and EOB-MRI. Frequencies of each imaging feature were compared between CE-CT and EOB-MRI. The area under the receiver operating characteristic (AUC) curve for the diagnosis of histological capsule was compared across the following three imaging criteria: (1) enhancing capsule in CE-CT, (2) enhancing capsule in EOB-MRI, and (3) enhancing/nonenhancing capsule in EOB-MRI. Enhancing capsule in EOB-MRI was significantly less frequently depicted than that in CE-CT (p < 0.001 and = 0.016 for reader 1 and 2). Enhancing/nonenhancing capsule in EOB-MRI achieved a similar frequency of enhancing in CE-CT (p = 0.590 and 0.465 for reader 1 and 2). Adding nonenhancing capsule to enhancing capsule in EOB-MRI significantly increased AUCs (p < 0.001 for both readers) and achieved similar AUCs compared with enhancing capsule in CE-CT (p = 0.470 and 0.666 for reader 1 and 2). Adding nonenhancing capsule to the definition of capsule appearance can improve the diagnosis of capsule in EOB-MRI for the diagnosis of histological capsule in HCC and decrease discordance of capsule appearance between EOB-MRI and CE-CT.

Bayesian multidimensional nominal response model for observer study of radiologists.

PURPOSE: This study proposes a Bayesian multidimensional nominal response model (MD-NRM) to statistically analyze the nominal response of multiclass classifications. MATERIALS AND METHODS: First, for MD-NRM, we extended the conventional nominal response model to achieve stable convergence of the Bayesian nominal response model and utilized multidimensional ability parameters. We then applied MD-NRM to a 3-class classification problem, where radiologists visually evaluated chest X-ray images and selected their diagnosis from one of the three classes. The classification problem consisted of 150 cases, and each of the six radiologists selected their diagnosis based on a visual evaluation of the images. Consequently, 900 (= 150 × 6) nominal responses were obtained. In MD-NRM, we assumed that the responses were determined by the softmax function, the ability of radiologists, and the difficulty of images. In addition, we assumed that the multidimensional ability of one radiologist were represented by a 3 × 3 matrix. The latent parameters of the MD-NRM (ability parameters of radiologists and difficulty parameters of images) were estimated from the 900 responses. To implement Bayesian MD-NRM and estimate the latent parameters, a probabilistic programming language (Stan, version 2.21.0) was used. RESULTS: For all parameters, the Rhat values were less than 1.10. This indicates that the latent parameters of the MD-NRM converged successfully. CONCLUSION: The results show that it is possible to estimate the latent parameters (ability and difficulty parameters) of the MD-NRM using Stan. Our code for the implementation of the MD-NRM is available as open source.

Comparison of Conventional Imaging and 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in the Diagnostic Accuracy of Staging in Patients with Intrahepatic Cholangiocarcinoma.

We aimed to examine the accuracy of tumor staging of intrahepatic cholangiocarcinoma (ICC) by using 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET-CT). From January 2001 to December 2021, 202 patients underwent PET-CT, CT, and MRI for the initial staging of ICC in two institutions. Among them, 102 patients had undergone surgical treatment. Ninety patients who had a histopathological diagnosis of ICC were retrospectively reviewed. The sensitivity and specificity of 18F-FDG PET-CT, CT, and magnetic resonance imaging (MRI) in detecting tumors, satellite focus, vascular invasion, and lymph node metastases were analyzed. Ninety patients with histologically diagnosed ICC were included. PET-CT demonstrated no statistically significant advantage over CT and MR in the diagnosis of multiple tumors and macrovascular invasion, and bile duct invasion. The overall sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of PET-CT in lymph node metastases were 84%, 86%, 91%, 84%, and 86%, respectively. PET-CT revealed a significantly higher accuracy compared to CT or MRI (86%, 67%, and 76%, p < 0.01, respectively) in the diagnosis of regional lymph node metastases. The accuracy of tumor staging by PET-CT was higher than that by CT/MRI (PET-CT vs. CT vs. MRI: 68/90 vs. 47/90 vs. 51/90, p < 0.05). 18F-FDG PET-CT had sensitivity and specificity values for diagnosing satellite focus and vascular and bile duct invasion similar to those of CT or MRI; however, PET-CT showed higher accuracy in diagnosing regional lymph node metastases. 18F-FDG PET-CT exhibited higher tumor staging accuracy than that of CT/MRI. Thus, 18FDG PET-CT may support tumor staging in ICC.

Deep learning model for the automatic classification of COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy: a multi-center retrospective study.

This retrospective study aimed to develop and validate a deep learning model for the classification of coronavirus disease-2019 (COVID-19) pneumonia, non-COVID-19 pneumonia, and the healthy using chest X-ray (CXR) images. One private and two public datasets of CXR images were included. The private dataset included CXR from six hospitals. A total of 14,258 and 11,253 CXR images were included in the 2 public datasets and 455 in the private dataset. A deep learning model based on EfficientNet with noisy student was constructed using the three datasets. The test set of 150 CXR images in the private dataset were evaluated by the deep learning model and six radiologists. Three-category classification accuracy and class-wise area under the curve (AUC) for each of the COVID-19 pneumonia, non-COVID-19 pneumonia, and healthy were calculated. Consensus of the six radiologists was used for calculating class-wise AUC. The three-category classification accuracy of our model was 0.8667, and those of the six radiologists ranged from 0.5667 to 0.7733. For our model and the consensus of the six radiologists, the class-wise AUC of the healthy, non-COVID-19 pneumonia, and COVID-19 pneumonia were 0.9912, 0.9492, and 0.9752 and 0.9656, 0.8654, and 0.8740, respectively. Difference of the class-wise AUC between our model and the consensus of the six radiologists was statistically significant for COVID-19 pneumonia (p value = 0.001334). Thus, an accurate model of deep learning for the three-category classification could be constructed; the diagnostic performance of our model was significantly better than that of the consensus interpretation by the six radiologists for COVID-19 pneumonia.

Ruptured gastric artery aneurysm: an uncommon manifestation of microscopic polyangiitis.

Gastric artery aneurysm is a rare and lethal condition, and is caused by inflammatory or degenerative vasculopathies. We describe herein the clinical course of a patient with a ruptured gastric artery aneurysm associated with microscopic polyangiitis. Absence of vasculitic changes in the aneurysm resected and negative results of autoantibodies interfered with our diagnostic process. We should have adopted an interventional radiology and initiated steroid therapy promptly to rescue the patient.