Search

A brain tumor is the most common primary brain malignancy. Delaying in brain tumor diagnosis is a primary cause of death in affected individuals. Therefore, early diagnosis of a brain tumor is essential for treatment planning and prognosis. In this study, the multilevel dilated convolutional neural network (MLDCNN) model is used for brain tumor segmentation. MLDCNN model is implemented independently for five MLDC blocks with a different combination of dilation rates to analyze their impact on brain tumor segmentation. For each segmentation model, overall survival time prediction is performed independently. An automated system is proposed for the overall survival time prediction of patients suffering from a brain tumor. First, shape and multiscale texture‐based features are extracted from LoG filtered and wavelet decomposed images of the magnetic resonance imaging scans. The proposed model utilizes 3D information by extracting radiomic features from axial, coronal, and sagittal views. These features are reduced using an extra tree classifier to avoid overfitting. Random forest algorithms are applied on selected feature sets to predict overall survival time in days. Extensive experimentation is performed for the segmentation and survival time prediction on the publicly available BraTS2019 and BraTS 2020 datasets. Results demonstrate that the proposed approach achieved the least mean squared error value in the survival time prediction task. [ABSTRACT FROM AUTHOR]

Objectives: To compare the diagnostic accuracy of transabdominal ultrasonography and contrast enhanced magnetic resonance imaging, in the differentiation of benign and malignant adnexal masses. Study Design: A prospective comparative study. Place and Duration of Study: Armed Forces Institute of Radiology and Imaging (AFIRI), Rawalpindi from 16 Jun 2015 to 15 Jun 2016. Methodology: 61 female patients with adnexal masses, irrespective of age, were evaluated with transabdominal ultrasonography and contrast enhanced magnetic resonance imaging (MRI). This was followed by surgery (either laporotomy or laproscopy) or ultrasound guided biopsy and then histopathology to characterize them as benign or malignant masses. Results: Diagnostic accuracy of contrast enhanced MRI for characterization of adnexal masses was 90.1%, while that of transabdominal ultrasonography was 72.1 %. Sensitivity and specificity of transabdominal ultrasonography was 100 % and 54 % respectively while positive predictive value was 58.5 % and negative predictive value was 100 %. Sensitivity and specificity of MRI was 95.8 % and 86.4 % respectively while positive predictive value was 82.1% while negative predictive value was 96.9 %. Conclusion: Contrast enhanced MRI has a superior diagnostic accuracy as compared to transabdominal ultrasonography in the characterization of adnexal masses into benign and malignant, which influences the mode of treatment and clinical outcome. [ABSTRACT FROM AUTHOR]

Objective: To determine the diagnostic accuracy of CT scan in staging of colorectal carcinoma among biopsy proven patients of colorectal carcinoma by taking histopathological finding as gold standard. Study Design: Cross-sectional validation study. Place and Duration of Study: Combined Military Hospital Rawalpindi, Six months, from Jul 2015 to Dec 2015. Material and Methods: A total of 176 cases of 15-70 years of age, diagnosed of colorectal carcinoma oncolonoscopic biopsy, were included in the study. Patients with previous malignancies other than colorectal carcinoma, allergy to the contrast agent and pregnant patients were excluded from the study. All the patients then underwent CT scan for detection of the stage of cancer. After surgery, histopathology of the resected specimen was compared with the findings on CT scan. Results: Mean age was 50.27 ± 14.50 years. Out of these 176 patients, 113 (64.20%) were male and 63 (35.80%) were females with ratio of 1.8:1. Among CT positive, 80 were true positive while 11 were false positive. Among, CT negative patients, 12 were false negative while 73 were true negative. Overall sensitivity, specificity, positive predictive value, negative predictive value and diagnostic accuracy of CT in staging colorectal carcinoma taking histopathology as gold standard was 87.91%, 85.88%, 86.96%, 86.90% and 86.93% respectively. Conclusion: This study concluded that CT scan is a highly sensitive and accurate modality for pre-operative detection of stage of colorectal carcinoma. [ABSTRACT FROM AUTHOR]