Shree-L۱: A dynamic CNN architecture for efficient tumor classification in medical imaging

Brain tumor classification is a crucial task in medical imaging for early diagnosis. In this paper, we propose a novel deep learning architecture, Shree-L۱, designed for efficient brain tumor classification. Our architecture utilizes dynamic downscaling and upscaling blocks for enhanced feature extraction and regularization. We evaluate the model on a publicly available brain tumor dataset, achieving state-of-the-art results in terms of classification accuracy and computational efficiency. Our method provides an effective approach for tumor detection, with potential applications in clinical settings.

کلیدواژه ها:

Shree-L۱ ، Deep Learning ، LSTM ، CNN ، Neural Network