DeepPulmoTB: A benchmark dataset for multi-task learning of tuberculosis lesions in lung computerized tomography (CT).

Tuberculosis (TB) remains a significant global health challenge, characterized by high incidence and mortality rates on a global scale. With the rapid advancement of computer-aided diagnosis (CAD) tools in recent years, CAD has assumed an increasingly crucial role in supporting TB diagnosis. Nonetheless, the development of CAD for TB diagnosis heavily relies on well-annotated computerized tomography (CT) datasets. Currently, the available annotations in TB CT datasets are still limited, which in turn restricts the development of CAD tools for TB diagnosis to some extent. To address this limitation, we introduce DeepPulmoTB, a CT multi-task learning dataset explicitly designed for TB diagnosis. To demonstrate the advantages of DeepPulmoTB, we propose a novel multi-task learning model, DeepPulmoTBNet (DPTBNet), for the joint segmentation and classification of lesion tissues in CT images. The architecture of DPTBNet comprises two subnets: SwinUnetR for the segmentation task, and a lightweight multi-scale network for the classification task. Furthermore, to enhance the model's capacity to capture TB lesion features, we introduce an improved iterative optimization algorithm that refines feature maps by integrating probability maps obtained in previous iterations. Extensive experiments validate the effectiveness of DPTBNet and the practicality of the DeepPulmoTB dataset.

Prevalence of Ultrasound-diagnosed Non Alcoholic Fatty Liver Disease Among Rural Indigenous Population in Malaysian and Its Association With Biochemical and Anthropometric Measures

@#Introduction: Non-alcoholic fatty liver disease (NAFLD) is the most common cause of chronic liver disease worldwide, especially in the Western world and Asia-Pacific regions. This study was designed to determine the prevalence of NAFLD detected by sonographic assessment among the rural indigenous population in Peninsula Malaysia and its association with anthropometric and biochemical factors. Methods: A cross-sectional survey was carried out from January 2014-February 2016. Subjects were recruited among indigenous peninsula Malaysia population in rural villages, aged ≥18 years old. The survey was questionnaire-based followed by anthropometric and blood parameters measurements. All subjects underwent abdominal ultrasound assessment to screen for the presence of NAFLD. Semi-quantitative visual grading was performed to assess for mild, moderate or severe NAFLD. Results: A total of 270 subjects underwent the screening program (mean age 43.3 ±14.0 years). Approximately 53 subjects (19.6 %) were identified with NAFLD. Of those with NAFLD, approximately 83% had moderate grade of fatty liver and the remainder were diagnosed with mild grade. NAFLD was closely associated with age, body mass index (BMI), central obesity, hypertension, total cholesterol (TC), triglyceride/high density lipoprotein-cholesterol (TG/HDL-C) ratio. On multivariate logistic regression, a high BMI (≥23.0 kg/m2), central obesity, and raised TG/HDL-C ratio were independent risk factors for developing NAFLD. Conclusion: This pioneer study defines the prevalence of NAFLD among rural indigenous population in Peninsula Malaysia. Lifestyle-related diseases, such as NAFLD can affect both rural and urban communities with equal severity. High BMI, central obesity, and elevated TG/HDL-C ratio were independent risk factors for developing NAFLD.

Tuberculous Myelopathy Associated with Longitudinally Extensive Lesion:A Clinicoradiological Review of Reported Cases

Acute transverse myelitis is an inflammatory disorder of the spinal cord in which there is no evidence of spinal cord compression. Longitudinally extensive transverse myelitis (LETM) is a specific subtype of acute transverse myelitis that usually affects three or more vertebral levels and produces marked neurological deficits. While the most-common cause of LETM is neuromyelitis optica or neuromyelitis optica spectrum disorder, there are rare cases of other causes mimicking this condition, including tuberculosis (TB). We sought to review the clinicoradiological features of TB myelopathy associated with longitudinally extensive lesion, which may mimic LETM, in the English literature. We searched the PubMed, Google Scholar, Web of Science, and Scopus databases for relevant articles using search terms including “longitudinally extensive transverse myelitis,” “tuberculosis,” “TB spinal cord,” and various combinations of these expressions. Full-text papers were selected without limiting the publication year. We also examined the reference lists of key papers to identify further articles that are potentially relevant. We found 10 cases in 7 papers describing TB myelopathy associated with longitudinally extensive lesion. The demographics, clinical features, relevant cerebrospinal fluid findings, and radiological findings were compiled and summarized. TB myelopathy associated with longitudinally extensive lesion is very rare, with no documented prevalence. Early and accurate diagnosis is important since the condition is potentially treatable.