Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Background/Aims: Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1–3% of hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted a nationwide study to investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied to discriminate subjects who may fail to respond to DAA therapy. Methods: We analyzed the Taiwan HCV Registry Program database to explore predictors of DAA failure in HCV patients. Fifty-five host and virological features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and artificial neural network. The primary outcome was undetectable HCV RNA at 12 weeks after the end of treatment. Results: The training (n=23,955) and validation (n=10,346) datasets had similar baseline demographics, with an overall DAA failure rate of 1.6% (n=538). Multivariate logistic regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor DAA adherence, and higher hemoglobin A1c were significantly associated with virological failure. XGBoost outperformed the other algorithms and logistic regression models, with an area under the receiver operating characteristic curve of 1.000 in the training dataset and 0.803 in the validation dataset. The top five predictors of treatment failure were HCV RNA, body mass index, α-fetoprotein, platelets, and FIB-4 index. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model (cutoff value=0.5) were 99.5%, 69.7%, 99.9%, 97.4%, and 99.5%, respectively, for the entire dataset. Conclusions Machine learning algorithms effectively provide risk stratification for DAA failure and additional information on the factors associated with DAA failure.

Introduction: Psoriasis vulgaris has a significant association with obstructive sleep apnoea (OSA). The study intended to explore the relation between the severity of psoriasis vulgaris and OSA risk, and to identify the factors that are attributed to increased risk of OSA. Methods: A cross sectional, observational study was carried out from October 2020 until April 2021 at the dermatology clinic of Hospital Tengku Ampuan Rahimah, Malaysia. All study participants were evaluated for OSA risk using the STOP-Bang and Epworth Sleepiness Scale questionnaires. Results: Our study recruited 237 participants and the results revealed a higher percentage of moderate to severe psoriasis participants with intermediate to high risk of OSA than participants with mild psoriasis (35.3% versus 17.7%, respectively). There was also a 2.3 times higher incidence of daytime sleepiness among participants with moderate to severe psoriasis as opposed to participants with mild psoriasis (44.1% versus 19.2%, respectively). We have also detected a significantly higher probability for OSA in psoriasis patients with diabetes mellitus versus those without (odds ratio: 2.09). We also noticed that for every unit rise in body mass index (BMI), there seemed to be a 1.06 times higher risk of OSA. Furthermore, patients with moderate to severe psoriasis were found to possess 3.32 times increased odds to have OSA. Conclusion: Our results suggest that psoriasis severity and the existence of comorbidities i.e. diabetes mellitus and high BMI are linked with an enhanced risk of OSA in adults with psoriasis.

Summary Sporotrichosis is a rare and chronic granulomatous subcutaneous mycotic infection caused by a dimorphic fungus, Sporothrix schenckii. We describe a patient with disseminated cutaneous sporotrichosis who was later diagnosed with myeloproliferative neoplasm and discuss the challenges and importance in diagnosing this rare condition.
Sporotrichosis ; Granulomatous Disease, Chronic ; Myeloproliferative Disorders

Summary Eosinophilic granulomatosis with polyangiitis (EGPA), or Churg-Strauss Syndrome (CSS) is a rare granulomatous necrotizing vasculitic disease characterized by the presence of asthma, sinusitis, and hypereosinophilia. We describe a patient who was initially diagnosed with tuberculous lymphadenitis and later diagnosed with EGPA.
Granulomatosis with Polyangiitis ; Tuberculosis, Cutaneous ; Tuberculosis, Lymph Node

Human pluripotent stem cells (hPSCs), including embryonic stem cells (ESCs) and induced PSCs (iPSCs), represent potentially unlimited cell sources for clinical applications. Previous studies have suggested that hPSCs may benefit from immune privilege and limited immunogenicity, as reflected by the reduced expression of major histocompatibility complex class-related molecules. Here we investigated the global immune-related gene expression profiles of human ESCs, hiPSCs and somatic cells and identified candidate immune-related genes that may alter their immunogenicity. The expression levels of global immune-related genes were determined by comparing undifferentiated and differentiated stem cells and three types of human somatic cells: dermal papilla cells, ovarian granulosa cells and foreskin fibroblast cells. We identified the differentially expressed genes CD24, GATA3, PROM1, THBS2, LY96, IFIT3, CXCR4, IL1R1, FGFR3, IDO1 and KDR, which overlapped with selected immune-related gene lists. In further analyses, mammalian target of rapamycin complex (mTOR) signaling was investigated in the differentiated stem cells following treatment with rapamycin and lentiviral transduction with specific short-hairpin RNAs. We found that the inhibition of mTOR signal pathways significantly downregulated the immunogenicity of differentiated stem cells. We also tested the immune responses induced in differentiated stem cells by mixed lymphocyte reactions. We found that CD24- and GATA3-deficient differentiated stem cells including neural lineage cells had limited abilities to activate human lymphocytes. By analyzing the transcriptome signature of immune-related genes, we observed a tendency of the hPSCs to differentiate toward an immune cell phenotype. Taken together, these data identify candidate immune-related genes that might constitute valuable targets for clinical applications.
Embryonic Stem Cells ; Female ; Fibroblasts ; Foreskin ; Granulosa Cells ; Humans* ; Induced Pluripotent Stem Cells ; Lymphocyte Culture Test, Mixed ; Lymphocytes* ; Major Histocompatibility Complex ; Phenotype ; Pluripotent Stem Cells* ; RNA ; Signal Transduction ; Sirolimus ; Stem Cells ; Transcriptome