S3F-Net: A Multi-Modal Approach to Medical Image Classification via Spatial-Spectral Summarizer Fusion Network

Convolutional Neural Networks have become a cornerstone of medical image analysis due to their proficiency in learning hierarchical spatial features. However, this focus on a single domain is inefficient at capturing global, holistic patterns and fails to explicitly model an image's frequency-domain characteristics. To address these challenges, we propose the Spatial-Spectral Summarizer Fusion Network (S3F-Net), a dual-branch framework that learns from both spatial and spectral representations simultaneously. The S3F-Net performs a fusion of a deep spatial CNN with our proposed shallow spectral encoder, SpectraNet. SpectraNet features the proposed SpectralFilter layer, which leverages the Convolution Theorem by applying a bank of learnable filters directly to an image's full Fourier spectrum via a computation-efficient element-wise multiplication. This allows the SpectralFilter layer to attain a global receptive field instantaneously, with its output being distilled by a lightweight summarizer network. We evaluate S3F-Net across four medical imaging datasets spanning different modalities to validate its efficacy and generalizability. Our framework consistently and significantly outperforms its strong spatial-only baseline in all cases, with accuracy improvements of up to 5.13%. With a powerful Bilinear Fusion, S3F-Net achieves a SOTA competitive accuracy of 98.76% on the BRISC2025 dataset. Concatenation Fusion performs better on the texture-dominant Chest X-Ray Pneumonia dataset, achieving 93.11% accuracy, surpassing many top-performing, much deeper models. Our explainability analysis also reveals that the S3F-Net learns to dynamically adjust its reliance on each branch based on the input pathology. Our source code and pre-trained model weights are publicly available on GitHub at: https://github.com/Saiful185/S3F-Net.