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.

An integrated framework to evaluate and improve the performance of emergency departments during the COVID-19 pandemic: A mathematical programing approach.

The emergency department (ED) is one of the most critical and high-risk sections of the health system. Providing quality services at a fast pace is vital in this ward since it directly affects people's lives. The COVID-19 pandemic has turned into a serious challenge for physicians and emergency departments (EDs). The growing number of patients who refer to EDs creates congestion, which will reduce the quality of services. Consequently, managing and operating EDs will be more urgent during this pandemic. Considering this problem, we first used data envelopment analysis (DEA) to evaluate the performance of EDs in the central provinces of Iran. Then, sensitivity analysis was used to determine the main factors affecting the efficiency of this ward. Accordingly, the high number of admitted patients, the congestion of the ward, and the long time required to report the COVID-19 test results were found to be the most influential factors. Finally, drawing on the results of sensitivity analysis, we advance a number of measures to improve these three and other related indicators. Furthermore, appropriate strategies were presented for improving health, COVID-19 management, key performance indicators, and safety indicators in accordance with the results of strengths-weaknesses-opportunity-threat (SWOT) analysis.

Designing humanitarian logistics network for managing epidemic outbreaks in disasters using Internet-of-Things. A case study: An earthquake in Salas-e-Babajani city.

Along with the destructive effects of catastrophes throughout the world, the COVID-19 outbreak has intensified the severity of disasters. Although the global aid organizations and philanthropists aim to alleviate the adverse impacts, many employed actions are not impactful in dealing with the epidemic outbreak in disasters. However, there is a gap in controlling the epidemic outbreak in the aftermath of disasters. Therefore, this paper proposes a novel humanitarian location-allocation-inventory model by focusing on preventing COVID-19 outbreaks with IoT-based technology in the response phase of disasters. In this study, IoT-based systems enable aid and health-related organizations to monitor people remotely, suspect detection, surveillance, disinfection, and transportation of relief items. The presented model consists of two stages; the first is defining infected cases, transferring patients to temporary hospitals promptly, and accommodating people in evacuation centers. Next, distribution centers are located in the second stage, and relief items are transferred to temporary hospitals and evacuation centers equally regarding shortage minimization. The model is solved by the LP-metric method and applied in a real case study in Salas-e-Babajani city, Kermanshah province. Then, sensitivity analysis on significant model parameters pertaining to the virus, relief items, and capacity has been conducted. Using an IoT-based system in affected areas and evacuation centers reduces the number of infected cases and relief item's shortages. Finally, several managerial insights are obtained from sensitivity analyses provided for healthcare managers.

Automatic detection of active and inactive multiple sclerosis plaques using the Bayesian approach in susceptibility-weighted imaging.

BACKGROUND: Susceptibility-weighted imaging (SWI) is efficient in detecting multiple sclerosis (MS) plaques and evaluating the level of disease activity. PURPOSE: To automatically detect active and inactive MS plaques in SWI images using a Bayesian approach. MATERIAL AND METHODS: A 1.5-T scanner was used to evaluate 147 patients with MS. The area of the plaques along with their active or inactive status were automatically identified using a Bayesian approach. Plaques were given an orange color if they were active and a blue color if they were inactive, based on the preset signal intensity. RESULTS: Experimental findings show that the proposed method has a high accuracy rate of 91% and a sensitivity rate of 76% for identifying the type and area of plaques. Inactive plaques were properly identified in 87% of cases, and active plaques in 76% of cases. The Kappa analysis revealed an 80% agreement between expert diagnoses based on contrast-enhanced and FLAIR images and Bayesian inferences in SWI. CONCLUSION: The results of our study demonstrated that the proposed method has good accuracy for identifying the MS plaque area as well as for identifying the types of active or inactive plaques in SWI. Therefore, it might be helpful to use the proposed method as a supplemental tool to accelerate the specialist's diagnosis.

Comparison of susceptibility weighted imaging with conventional MRI sequences in multiple sclerosis plaque assessment: A cross-sectional study.

BACKGROUND: The current study was performed to compare susceptibility-weighted imaging (SWI) with magnetic resonance imaging (MRI) methods of T2-weighted (T2W) and fluid-attenuated inversion recovery (FLAIR) imaging in multiple sclerosis (MS) plaque assessment. MATERIALS AND METHODS: This cross-sectional study was conducted among 50 MS patients referred to Shafa Imaging Center, Isfahan, Iran. Patients who fulfilled McDonald criteria and were diagnosed with MS by a professional neurologist at least 1 year before the study initiation were included in the study. Eligible patients underwent brain scans using SWI, T2W imaging, and FLAIR. Plaques' number and volume were detected separately for each imaging sequence. Moreover, identified lesions in SWI sequence were evaluated in terms of iron deposition and central veins. RESULTS: Totally 50 patients (10 males and 40 females) with a mean age of 28.48 ± 5.25 years were included in the current study. Majority of patients (60%) had a disease duration of >5 years, and mean expanded disability status score was 2.56 ± 1.32. There was no significant difference between different imaging modalities in terms of plaques' number and volume (P > 0.05). It was also found that there was a high correlation between SWI and conventional imaging techniques of T2W (r = 0.97, 0.91, P < 0.001) and FLAIR (r = 0.99, 0.99, P < 0.001) in the estimation of both the number and volume of plaques (P < 0.001). CONCLUSION: The results of the present study indicated that SWI and conventional MRI sequences have similar efficiency for plaque assessment in MS patients.

Integrated locating of helicopter stations and helipads for wounded transfer under demand location uncertainty.

Health emergency medical service (HEMS) plays an important role in reducing injuries by providing advanced medical care in the shortest time and reducing the transfer time to advanced treatment centers. In the regions without ground relief coverage, it would be faster to transfer emergency patients to the hospital by a helicopter. In this paper, an integer nonlinear programming model is presented for the integrated locating of helicopter stations and helipads by considering uncertainty in demand points. We assume three transfer modes: (1) direct transfer by an ambulance, (2) transfer by an ambulance to a helicopter station and then to the hospital by a helicopter, (3) transfer by an ambulance to a predetermined point and then to the hospital by a helicopter. We also assume that demands occur in a square-shaped area, in which each side follows a uniform distribution. It is also assumed that demands in an area decrease errors in the distances between each two cities. The purpose of this model is to minimize the transfer time from demand points to the hospital by considering different modes. The proposed model is examined in terms of validity and applicability in Lorestan Province and a sensitivity analysis is also conducted on the total allocated budget.

Computed tomography-guided percutaneous core needle biopsy for diagnosis of mediastinal mass lesions: Experience with 110 cases in two university hospitals in Isfahan, Iran.

BACKGROUND: Computed tomography-guided percutaneous core needle biopsy (PCNB) is a diagnostic technique for initial assessment of mediastinal mass lesions. This study was conducted to evaluate its diagnostic yield and its complication rate. MATERIALS AND METHODS: We reviewed the records of CT-guided PCNB in 110 patients with mediastinal mass lesions performed in Kashani and Alzahra Hospitals, Isfahan, from 2006 to 2012. Gender, age at biopsy, size, and anatomic location of the lesion, number of passes, site of approach, complications, and final diagnosis were extracted. RESULTS: Our series encompasses 52 (47.2%) females and 58 (52/7%) males with mean age of 41 ± 8 years. The most common site of involvement was the anterior mediastinum (91.8% of cases). An average of 3/5 passes per patient has been taken for tissue sampling. Parasternal site was the most frequent approach taken for PCNB (in 78.1% of cases). Diagnostic tissue was obtained in 99 (90%) biopsies while, in 11 (10%) cases, specimen materials were inadequate. Lymphoma (49.5%) and bronchogenic carcinoma (33.3%) were the most frequent lesions in our series. The overall complication rate was 17.2% from which 10.9% was pneumothorax, 5.4% was hemoptysis, and 0.9% was vasovagal reflex. CONCLUSION: CT-guided PCNB is a safe and reliable procedure that can provide a precise diagnosis for patients with both benign and malignant mediastinal masses, and it is considered the preferred first diagnostic procedure use for this purpose.

Congenital nasal pyriform aperture stenosis: A case with accompanying short lingual frenulum.

Congenital nasal pyriform aperture stenosis (CNPAS) is a rare cause of nasal obstruction. We presented a case of CNPAS with accompanying short lingual frenulum. Surgical dilatation without osteotomy was used, and the infant had normal growth and development. In these cases, the less invasive surgical methods can be effective.