Lumbar Disease Classification Using an Involutional Neural Based VGG Nets (INVGG)

This study presents a novel approach for lumbar disease classification using an advanced convolutional neural network architecture, INVGG, which integrates involutional layers with a modified VGG network structure. The process begins with the preprocessing of input images, including resizing, denoising using adaptive median filtering, and various augmentation techniques such as flipping, rotating, and translating to enhance the dataset's diversity. The network architecture consists of multiple involutional layers designed to capture intricate features of lumbar images, followed by a global average pooling layer and a multi-layer perceptron (MLP) for classification. The model is trained using an Adam optimizer with specified hyperparameters, achieving notable performance in classifying lumbar images. Evaluation metrics, including accuracy, precision, recall, and F1 score, are computed through confusion matrix analysis, demonstrating the model's effectiveness in accurately classifying lumbar disease. This approach showcases the potential of combining involutional layers with traditional CNN structures to improve diagnostic accuracy in medical imaging.

Keywords: Lumbar Disease Dataset, Image Processing Techniques, Deep Learning Techniques, INVGG, MLP Classification, Accuracy.