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.

Objective: To quantitatively assess the pulmonary vasculature using non-contrast computed tomography (CT) in patients with chronic thromboembolic pulmonary hypertension (CTEPH) pre- and post-treatment and correlate CT-based parameters with right heart catheterization (RHC) hemodynamic and clinical parameters. Materials and Methods: A total of 30 patients with CTEPH (mean age, 57.9 years; 53% female) who received multimodal treatment, including riociguat for ≥ 16 weeks with or without balloon pulmonary angioplasty and underwent both noncontrast CT for pulmonary vasculature analysis and RHC pre- and post-treatment were included. The radiographic analysis included subpleural perfusion parameters, including blood volume in small vessels with a cross-sectional area ≤ 5 mm 2 (BV5) and total blood vessel volume (TBV) in the lungs. The RHC parameters included mean pulmonary artery pressure (mPAP), pulmonary vascular resistance (PVR), and cardiac index (CI). Clinical parameters included the World Health Organization (WHO) functional class and 6-minute walking distance (6MWD). Results: The number, area, and density of the subpleural small vessels increased after treatment by 35.7% (P < 0.001), 13.3% (P = 0.028), and 39.3% (P < 0.001), respectively. The blood volume shifted from larger to smaller vessels, as indicated by an 11.3% increase in the BV5/TBV ratio (P = 0.042). The BV5/TBV ratio was negatively correlated with PVR (r = -0.26; P = 0.035) and positively correlated with CI (r = 0.33; P = 0.009). The percent change across treatment in the BV5/TBV ratio correlated with the percent change in mPAP (r = -0.56; P = 0.001), PVR (r = -0.64; P < 0.001), and CI (r = 0.28; P = 0.049).Furthermore, the BV5/TBV ratio was inversely associated with the WHO functional classes I–IV (P = 0.004) and positively associated with 6MWD (P = 0.013). Conclusion Non-contrast CT measures could quantitatively assess changes in the pulmonary vasculature in response to treatment and were correlated with hemodynamic and clinical parameters.

Objective: The impact of serotonergic system on obsessive-compulsive disorder (OCD) is well studied. However, the correlation between OC presentations and autonomic nervous system (ANS) is still unclear. Furthermore, whether the correlation might be modulated by serotonin is also uncertain. Methods: We recruited eighty-nine healthy subjects. Serotonin transporter (SERT) availability by [ 123 I]ADAM and heart rate variability (HRV) tests were measured. Symptoms checklist-90 was measured for the OC presentations. The interaction between HRV and SERT availability were calculated and the correlation between HRV and OC symptoms were analyzed after stratified SERT level into two groups, split at medium. Results: The interactions were significant in the factors of low frequency (LF), high frequency (HF), and root mean square of successive differences (RMSSD). Furthermore, the significantly negative correlations between OC symptoms and the above HRV indexes existed only in subjects with higher SERT availability. Conclusion OC symptoms might be correlated with ANS regulations in subjects with higher SERT availability.

Objective: The characteristics of patients with metachronous breast and ovarian malignancies and the pathogenic role of BRCA1/2 mutations remain poorly understood. We investigated these issues through a review of hospital records and nationwide Taiwanese registry data, followed by BRCA1/2 mutation analysis in hospital-based cases. Methods: We retrospectively retrieved consecutive clinical records of Taiwanese patients who presented with these malignancies to our hospital between 2001 and 2017. We also collected information from the Data Science Center of the Taiwan Cancer Registry (TCR) between 2007 and 2015. Next-generation sequencing and multiplex ligation-dependent probe amplification were used to identify BRCA1/2 mutations and large genomic rearrangements, respectively. When BRCA1/2 mutations were identified in index cases, pedigrees were reconstructed and genetic testing was offered to family members. Results: A total of 12,769 patients with breast cancer and 1,537 with ovarian cancer were retrieved from our hospital records. Of them, 28 had metachronous breast and ovarian malignancies. We also identified 113 cases from the TCR dataset. Eighteen hospital-based cases underwent BRCA1/2 sequencing and germline pathogenic mutations were detected in 7 patients (38.9%, 5 in BRCA1 and 2 in BRCA2). All BRCA1/2 mutation carriers had ovarian high-grade serous carcinomas. Of the 12 patients who were alive at the time of analysis, 5 were BRCA1/2 mutation carriers. All of them had family members with BRCA1/2-associated malignancies. Conclusions Our results provide pilot evidence that BRCA1/2 mutations are common in Taiwanese patients with metachronous breast and ovarian malignancies, supporting the clinical utility of genetic counseling.

PURPOSE: The main objective of this study was to investigate the relationship among the clinical characteristics and the frequency of T790M mutation in advanced epidermal growth factor receptor (EGFR)–mutant lung adenocarcinoma patients with acquired resistance after firstline EGFR–tyrosine kinase inhibitor (TKI) treatment. MATERIALS AND METHODS: We enrolled EGFR-mutant stage IIIB-IV lung adenocarcinoma patients, who had progressed to prior EGFR-TKI therapy, and evaluated their rebiopsy EGFR mutation status. RESULTS: A total of 205 patients were enrolled for analysis. The overall T790M mutation rate of rebiopsy was 46.3%. The T790M mutation rates among patients with exon 19 deletion mutation, exon 21 L858R point mutation, and other mutations were 55.0%, 37.3%, and 27.3%, respectively. Baseline exon 19 deletion was associated with a significantly higher frequency of T790M mutation (adjusted odds ratio, 2.14; 95% confidence interval [CI], 1.20 to 3.83; p=0.010). In the exon 19 deletion subgroup, there was a greater prevalence of T790M mutation than other exon 19 deletion subtypes in patients with the Del E746-A750 mutation (61.6% vs. 40.6%; odds ratio, 2.35; 95% CI, 1.01 to 5.49; p=0.049). The progression-free survival (PFS) of first-line TKI treatment > 11 months was also associated with a higher T790M mutation rate (54.1% vs. 39.3%; adjusted odds ratio, 1.82; 95% CI, 1.02 to 3.25; p=0.044). Patients who underwent rebiopsy at metastatic sites had more chance to harbor T790M mutation (52.6% vs. 33.8%; adjusted odds ratio, 1.97; 95% CI, 1.06 to 3.67; p=0.032). CONCLUSION: PFS of first-line EGFR-TKI, rebiopsy site, EGFR exon 19 deletion and its subtype Del E746-A750 mutation are associated with the frequency of T790M mutation.
Adenocarcinoma* ; Disease-Free Survival ; Epidermal Growth Factor* ; Exons ; Humans ; Lung Neoplasms ; Lung* ; Mutation Rate ; Odds Ratio ; Phosphotransferases ; Point Mutation ; Prevalence ; Receptor, Epidermal Growth Factor* ; Sequence Deletion