Multimodality radiomics prediction of radiotherapy-induced the early proctitis and cystitis in rectal cancer patients: a machine learning study.

Purpose.This study aims to predict radiotherapy-induced rectal and bladder toxicity using computed tomography (CT) and magnetic resonance imaging (MRI) radiomics features in combination with clinical and dosimetric features in rectal cancer patients.Methods.A total of sixty-three patients with locally advanced rectal cancer who underwent three-dimensional conformal radiation therapy (3D-CRT) were included in this study. Radiomics features were extracted from the rectum and bladder walls in pretreatment CT and MR-T2W-weighted images. Feature selection was performed using various methods, including Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-square (Chi2), Analysis of Variance (ANOVA), Recursive Feature Elimination (RFE), and SelectPercentile. Predictive modeling was carried out using machine learning algorithms, such as K-nearest neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Gradient Boosting (XGB), and Linear Discriminant Analysis (LDA). The impact of the Laplacian of Gaussian (LoG) filter was investigated with sigma values ranging from 0.5 to 2. Model performance was evaluated in terms of the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, and specificity.Results.A total of 479 radiomics features were extracted, and 59 features were selected. The pre-MRI T2W model exhibited the highest predictive performance with an AUC: 91.0/96.57%, accuracy: 90.38/96.92%, precision: 90.0/97.14%, sensitivity: 93.33/96.50%, and specificity: 88.09/97.14%. These results were achieved with both original image and LoG filter (sigma = 0.5-1.5) based on LDA/DT-RF classifiers for proctitis and cystitis, respectively. Furthermore, for the CT data, AUC: 90.71/96.0%, accuracy: 90.0/96.92%, precision: 88.14/97.14%, sensitivity: 93.0/96.0%, and specificity: 88.09/97.14% were acquired. The highest values were achieved using XGB/DT-XGB classifiers for proctitis and cystitis with LoG filter (sigma = 2)/LoG filter (sigma = 0.5-2), respectively. MRMR/RFE-Chi2 feature selection methods demonstrated the best performance for proctitis and cystitis in the pre-MRI T2W model. MRMR/MRMR-Lasso yielded the highest model performance for CT.Conclusion.Radiomics features extracted from pretreatment CT and MR images can effectively predict radiation-induced proctitis and cystitis. The study found that LDA, DT, RF, and XGB classifiers, combined with MRMR, RFE, Chi2, and Lasso feature selection algorithms, along with the LoG filter, offer strong predictive performance. With the inclusion of a larger training dataset, these models can be valuable tools for personalized radiotherapy decision-making.

Non-alcoholic fatty liver disease and compromised endothelial function in people with type 2 diabetes.

INTRODUCTION: Nonalcoholic fatty liver disease (NAFLD) frequently coexists with type 2 diabetes mellitus (T2DM) and synergistically contributes to the development of atherosclerosis. Flow-mediated dilation (FMD) is a commonly used noninvasive test for assessing endothelial function. The main objective of this study was to explore FMD in patients with T2DM with and without NAFLD. METHODS: In this cross-sectional study, conducted on people with T2DM, NAFLD was defined as controlled attenuation parameter (CAP) score > 302 dB/m. Endothelial dysfunction was detected when arterial FMD of brachial artery was equal or less than 0.7%. Regression analyses were applied to assess factors associated with impaired FMD. RESULT: A total of 147 patients (72 with NAFLD and 75 without NAFLD) were included in the final analysis. Patients with NAFLD were more likely to develop FMD ≤ 7% (77.8% vs. 58.7%, P = 0.01). In multivariate analysis, NAFLD (OR = 2.581, 95% CI (1.18-5.62), P = 0.017) and hypertension (HTN) (OR = 3.114, 95% CI (1.31-7.35), P = 0.010) were associated with an increased risk of impaired FMD. However, female sex was associated with a decreased risk of impaired FMD (OR = 0.371, 95% CI (0.15-0.87), P = 0.024). CONCLUSION: NAFLD is associated with endothelial dysfunction in people with T2DM. This risk is comparable with the risk imposed by HTN, highlighting the importance of screening and management of NAFLD in these patients.

A Novel Method for Investigating the Role of Reflux Pattern in Color Doppler Ultrasound for Grading of Varicocele.

Varicocele is the most common correctable cause of infertility. Color Doppler Ultrasound (CDUS) has a sensitivity of 97% and specificity of 94% for diagnosing this condition. This study aimed to propose a new pattern of scrotal Doppler for predicting the severity of varicocele. An observational study was conducted from January 2016 to January 2017 on 120 testes units in 60 patients. Scrotal CDUS and semen analysis were done in all participants. Patients were evaluated for reflux pattern, pampiniform venous plexus diameter, and venous reflux time. The ultrasonography parameters and semen analysis data were compared to assess the correlations between the results. The reflux pattern and vein diameters had a significant correlation. Also, a significant correlation was detected between the reflux pattern and reflux time. There was a significant correlation between the reflux pattern and two parameters of semen analysis namely sperm count and its motility. In conclusion, the reflux pattern classification suggested in this study can be used as a useful predictor of varicocele severity and sperm parameters in patients with varicocele.

Comparison of Diagnostic Value of Sonourethrography with Retrograde Urethrography in Diagnosis of Anterior Urethral Stricture.

BACKGROUND: In spite of the advanced imaging methods, MRI and CT-Scan, the role of ultrasonography is still unique in some fields of genitourinary tract diseases. AIM: This study was aimed at assessing this role in the evaluation of male urinary stricture, and comparison with standard retrograde urethrography (SUG). METHODS: This was a cross-sectional study. The patients include those who were suspected of anterior urethral stricture and were introduced assessed with imaging techniques (RUG). The patient underwent ultrasonography too. The results of both methods were compared. RUG was considered as the gold standard for this comparison. RESULT: Ninety-seven patients were studied. The mean age was 46.9 ± 11.7 years (range 21-88 years), in RUG, 22 patients (22.8%) and SUG 23 patients (23.7%) had a stricture, 3 cases with a stricture in RUG had not evidenced of stenosis in SUG. The mean length of urethral stricture in RUG was 12.9 ± 8.1 mm and in SUG was 8.1 ± 7.3 mm. The estimated length in RUG way was significantly higher than SUG way (P=0.025). The sensitivity and specificity in using of SUG were 86.6% and 94.6%, respectively. CONCLUSION: The result of this study showed stricture length measured by ultrasound is shorter than the length measured by RUG and the sensitivity and specificity in using of SUG was 86.6% and 94.6% respectively that due to the advantages it is an acceptable way.