No abstract

PurposeTo advance the usage of CXRs as a viable solution for efficient COVID-19 diagnostics by providing large-scale annotations of the abnormalities in frontal CXRs in BIMCV-COVID19+ database, and to provide a robust evaluation mechanism to facilitate its usage.Materials and MethodsWe provide the abnormality annotations in frontal CXRs by creating bounding boxes. The frontal CXRs are a part of the existing BIMCV-COVID19+ database. We also define four different protocols for robust evaluation of semantic segmentation and classification algorithms. Finally, we benchmark the defined protocols and report the results using popular deep learning models as a part of this study.ResultsFor semantic segmentation, Mask-RCNN performs the best among all the models with a DICE score of 0.43 ± 0.01. For classification, we observe that MobileNetv2 yields the best results for 2-class and 3-class classification. We also observe that deep models report a lower performance for classifying other classes apart from the COVID class.ConclusionBy making the annotated data and protocols available to the scientific community, we aim to advance the usage of CXRs as a viable solution for efficient COVID-19 diagnostics. This large-scale data will be useful for ML algorithms and can be used for learning radiological patterns observed in COVID-19 patients. Further, the protocols will facilitate ML practitioners for unified large-scale evaluation of their algorithms.Data Availability StatementThe data associated with this work is available here : Radiologists’ Annotations on COVID-19+ X-rays https://osf.io/b35xu/ via @OSFramework andhttp://covbase4all.igib.res.in/.

The objective of this study was to compare diagnostic accuracy of elastography point quantification (ElastPQ) with transient elastography (TE) and liver histology for measuring liver stiffness in patients with chronic viral hepatitis (CVH) and nonalcoholic fatty liver disease (NAFLD). Methods: Thirty-two patients with chronic liver disease (CVH and NAFLD) were evaluated by ElastPQ and TE within 7 days of liver biopsy. Within the CVH group, subgroup analysis was carried out in patients with end-stage renal disease (ESRD) and without ESRD. Area under the receiver operating characteristic (AUROC) curves were calculated for ElastPQ and TE. Results: There were 15 patients with CVH and 17 patients with NAFLD. In the CVH group, there were 8 patients with ESRD and 7 patients without ESRD. Taking liver histopathology as the gold standard, liver stiffness measurement by ElastPQ (r = 0.826;P < 0.0001) and TE (r = 0.649; P < 0.0001) correlated significantly with the stage of fibrosis. AUROCs of ElastPQ and TE for the diagnosis of any fibrosis (F $ 1), significant fibrosis (F $ 2), and advanced fibrosis (F $ 3) were 0.907, 0.959, 0.926 and 0.870, 0.770, 0.881, respectively, in both CVH and NAFLD groups. However, the accuracy of both these techniques was poor in patients with CVH and ESRD (AUROCs for ElastPQ and TE of 0.667 and 0.167 for the diagnosis of significant fibrosis, respectively, and 0.429 and 0.143 for the diagnosis of advanced fibrosis, respectively). The diagnostic accuracy of both ElastPQ and TE for detecting significant fibrosis was excellent in patients with NAFLD (AUROC of 1.000 and 0.936, respectively). ElastPQ was superior to TE in the diagnosis of significant fibrosis in the combined analysis (P = 0.0149) and in the CVH group (P = 0.0391), while both modalities were comparable in patients of the NAFLD group (P = 0.2539). Conclusion:ElastPQ may be equally accurate as Fibroscan, and large prospective studies are required to validate the same.

Consistent clinical observations of characteristic findings of COVID-19 pneumonia on chest X-rays have attracted the research community to strive to provide a fast and reliable method for screening suspected patients. Several machine learning algorithms have been proposed to find the abnormalities in the lungs using chest X-rays specific to COVID-19 pneumonia and distinguish them from other etiologies of pneumonia. However, despite the enormous magnitude of the pandemic, there are very few instances of public databases of COVID-19 pneumonia, and to the best of our knowledge, there is no database with annotation of abnormalities on the chest X-rays of COVID-19 affected patients. Annotated databases of X-rays can be of significant value in the design and development of algorithms for disease prediction. Further, explainability analysis for the performance of existing or new deep learning algorithms will be enhanced significantly with access to ground-truth abnormality annotations. The proposed COVID Abnormality Annotation for X-Rays (CAAXR) database is built upon the BIMCV-COVID19+ database which is a large-scale dataset containing COVID-19+ chest X-rays. The primary contribution of this study is the annotation of the abnormalities in over 1700 frontal chest X-rays. Further, we define protocols for semantic segmentation as well as classification for robust evaluation of algorithms. We provide benchmark results on the defined protocols using popular deep learning models such as DenseNet, ResNet, MobileNet, and VGG for classification, and UNet, SegNet, and Mask-RCNN for semantic segmentation. The classwise accuracy, sensitivity, and AUC-ROC scores are reported for the classification models, and the IoU and DICE scores are reported for the segmentation models.

Magnetic resonance spectroscopy (MRS) is a novel noninvasive approach to measuring important metabolites in living tissue. Its application to psychiatry is just beginning. In vivo MRS with 31P provides important information on brain phospholipid metabolism and energy production. In vivo 13C and 1H MRS can reveal information about carbohydrate, protein, and amino acid metabolism. In vivo 7Li and 19F MRS can be used to study the pharmacology of lithium and fluorinated psychopharmacological agents. MRS with 23Na can yield information about electrolyte balance. The limitations of in vivo MRS include poor sensitivity, poor resolution, and the fact that only highly mobile atomic nuclei can be detected. Future clinical application of MRS will benefit from improvements in the technology of localization, use of spectroscopy contrast agents, stronger magnets, and the merging of MRS and imaging technology.