Deep learning for discrimination of active and inactive lesions in multiple sclerosis using non-contrast FLAIR MRI: A multicenter study.

BACKGROUND: Within the domain of multiple sclerosis (MS), the precise discrimination between active and inactive lesions bears immense significance. Active lesions are enhanced on T1-weighted MRI images after administration of gadolinium-based contrast agents, which brings about associated complexities. This study investigates the potential of deep learning to differentiate between active and inactive lesions in MS using non-contrast FLAIR-type MRI data, presenting a non-invasive alternative to conventional gadolinium-based MRI methods. METHODS: The dataset encompasses 9097 lesion images collected from 130 MS patients across four distinct imaging centers, with post-contrast T1-weighted images as the benchmark reference. We initially identified and labeled the lesions and carefully selected corresponding regions of interest (ROIs). These ROIs were employed as inputs for a convolutional neural network (CNN) to predict lesion status. Also, transfer learning was utilized, incorporating 12 pre-trained CNN models. Subsequently, an ensemble technique was applied to 3 of best models, followed by a systematic comparison of the results. RESULTS: Through a 5-fold cross-validation, our custom designed network exhibited an average accuracy of 85 %, a sensitivity of 95 %, a specificity of 75 %, and an AUC value of 0.90. Among the pre-trained models, ResNet50 emerged as the most effective, achieving a specificity of 58 %, an accuracy of 75 %, a sensitivity of 91 %, and an AUC value of 0.81. Our comprehensive evaluations encompassed the receiver operating characteristic curve, precision-recall curve, and confusion matrix analyses. CONCLUSION: The findings underscore the efficacy of the proposed CNN, trained on FLAIR MRI data ROIs, in accurately discerning active and inactive lesions without reliance on contrast agents. Our multicenter study of 130 patients with diverse imaging devices outperforms the other single-center studies, achieving superior sensitivity and specificity. Unlike studies using multiple modalities, our exclusive use of FLAIR images streamlines the process, and our streamlined approach, excluding conventional pre-processing, demonstrates efficiency. The external validation conducted on diverse datasets, coupled with the analysis of dilated masks, underscores the adaptability and efficacy of our custom CNN model in discerning between active and inactive lesions.

The effect of trunk-stabilizing muscle training in women with stress urinary incontinence: A randomized controlled trial.

INTRODUCTION: There is little evidence regarding the effect of trunk-stabilizing muscle training on the improvement of stress urinary incontinence (SUI) symptoms. OBJECTIVE: To investigate the effect of trunk-stabilizing muscle training on transabdominal ultrasonography (TAUS) and clinical urological indices, and on the quality of life (QoL) in women with SUI. DESIGN: Randomized controlled trial. SETTING: A university hospital. PARTICIPANTS: Forty-six women with SUI, ages 20-55 years, were randomly assigned to an experimental (n = 23) and control group (n = 23). INTERVENTIONS: The experimental group performed trunk-stabilization exercises according to the Sapsford protocol, whereas the control group performed pelvic floor muscle (PFM) exercises for 8 weeks. MAIN OUTCOME MEASURES: The primary outcome measure was bladder base displacement (BBD), assessed by TAUS during PFM contraction (PFMC), Valsalva, and abdominal curl. The secondary outcome measures were PFM strength, the severity of urinary incontinence (UI), voiding diary, and QoL, assessed by the Modified Oxford Grading System, the severity index, frequency chart, and lower urinary tract symptoms-QoL questionnaire, respectively. All variables were assessed at baseline and after 8 weeks of intervention. RESULTS: The interaction of group and time was not significant for BBD during PFMC (p = .98), Valsalva (p = .28), abdominal curl (p = .34), and secondary variables (p > .05). The main effect of time was significant in both groups for BBD during PFMC, PFM strength, the severity of UI, voiding diary, and QoL (p < .001), with effect size (d) of 0.30, 0.80, 2.05, 1.07, and 1.03 in the control; and 0.49, 0.52, 1.75, 0.66, and 0.88 in the experimental group, respectively. The main effect of the group was not significant for BBD during PFMC (p = .68), Valsalva (p = .22), abdominal curl (p = .53), and secondary variables (p > .05). CONCLUSIONS: Trunk-stabilizing muscle training and PFM exercise are equally effective in the improvement of PFM function, UI symptoms, and QoL in women with SUI. Both methods can be used interchangeably by physical therapists.

Transabdominal Ultrasound Imaging of Pelvic Floor Muscle Activity in Women With and Without Stress Urinary Incontinence: A Case-Control Study.

OBJECTIVE: Transabdominal ultrasound (TAU) is an easy and noninvasive way to evaluate and retrain pelvic floor muscle (PFM) function. The purpose of this study was to compare PFM activity in women with and without urinary incontinence (UI) by measuring bladder base displacement (as a marker for PFM activity) using TAU during PFM contraction, Valsalva's maneuver, and abdominal curl. METHODS: Sixty-three women, aged 20-55 years, volunteered to participate in this cross-sectional study: 21 were continent and 42 had UI (21 stress urinary incontinence [SUI] and 21 mixed urinary incontinence [MUI]). Mean bladder base displacement in millimeters was measured to evaluate differences between the three groups (continent, SUI, and MUI) and also between the continent and UI groups during the performance of each maneuver. RESULTS: No significant differences were seen between the three groups in bladder base elevation during PFM contraction (P > 0.05). Descent of the bladder base during Valsalva's maneuver and abdominal curl was significantly greater in women with SUI and MUI than in women in the continent group (P < 0.05). Comparison of the continent and UI groups showed no significant differences in elevation of the bladder base during PFM contraction, while descent of the bladder base was significantly greater in women with UI than in women in the continent group during Valsalva's maneuver and abdominal curl (P < 0.05). CONCLUSION: TAU indicated that bladder base descent was greater in women with SUI and MUI than those in the continent group during the performance of maneuvers that increased intra-abdominal pressure. This effect may be due to decreased PFM performance in women with urinary incontinence.

The effect of aerobic exercises among women with mild and moderate irritable bowel syndrome: A pilot study.

BACKGROUND: Irritable Bowel Syndrome (IBS) is a functional bowel disorder characterized by abdominal pain or discomfort. Although patients with IBS are commonly recommended to increase their physical activity, after reviewing the literature, it was found that no study has assessed the effect of aerobic exercises on the severity of symptoms and quality of life in patients with IBS. Therefore the aim of the present study was to evaluate the effect of aerobic exercises with treadmill on the severity of symptoms and quality of life among women with mild and moderate IBS. METHODS: Twenty women with mild and moderate IBS were randomly assigned into two groups of treadmill exercise (10 participants) and control (10 participants). The treadmill group had six weeks (30 min, three sessions per week) of aerobic exercises on treadmill. The control group continued their usual daily activities. RESULTS: After six weeks of aerobic exercises on a treadmill a significant improvement was observed in the severity of IBS symptoms (p ≤ 0.001) and IBS quality of life (p = 0.001) in the treadmill group compared to the control group. Also in the treadmill group, the severity of symptoms and quality of life demonstrated a significant improvement after the intervention compared to before the intervention (p ≤ 0.001). No significant difference was observed in the severity of symptoms and quality of life in the control group before and after the study (p > 0.05).