Medical Imaging (Lab Report Sample)

I was tasked with choosing a disease to study, selecting a relevant paper, and analyzing the techniques and methodologies used. The disease under study is Diabetic Retinopathy, and the chosen paper is "Diabetic Retinopathy Techniques in Retinal Images: A Review" (link: here). The datasets used include DRIVE, STARE, DIARETDB1, DIARETDB0, and MESSIDOR, with preprocessing steps such as resizing, normalization, handling missing values, noise reduction, and contrast enhancement. Feature extraction methods employed are texture analysis, edge detection, and wavelet transformation, each chosen for their ability to capture critical aspects of retinal images. For algorithm implementation in the context of breast cancer detection, Support Vector Machines (SVM), Random Forest, and Convolutional Neural Networks (CNN) were discussed. The dataset was divided into training and testing sets, and performance was evaluated using metrics like accuracy, precision, recall, and F1-score, with cross-validation to ensure robustness. A comparative analysis revealed that CNN outperforms SVM and Random Forest, highlighting its effectiveness in image analysis despite higher computational demands. A detailed report summarizing these findings emphasized the strengths and weaknesses of each method, with visualizations such as bar charts and confusion matrices to illustrate performance. source..