Kidney Stone Detection

• Tech Stack:
• Language: Python
• Libraries: Pandas, Numpy, Scikit-Learn
• Notebook: Google Colab
• Github URL: Project Link
• Video Demonstration: Video Link

In this project, I utilized the pre-trained VGG16 model, a deep convolutional neural network, to classify the presence of kidney stones in medical imaging data, achieving an accuracy of approximately 60% on the test set. I fine-tuned the VGG16 architecture by adapting its fully connected layers to the binary classification task, using a dataset of renal ultrasound and CT scan images that I preprocessed for consistency. The model was trained with a binary cross-entropy loss function and evaluated using standard metrics to assess its performance in supporting diagnostic decisions.