A data fusion deep learning approach for accurate organelle-based classification of cancer cells

Microscopy-based cancer cell classification traditionally relies on cell-based morphological features, while subcellular organelle organization remains underutilized. Existing machine learning methods often require manual preprocessing and handcrafted feature extraction, limiting scalability and introducing user bias. This study proposes an automated, interpretable, and organelle-focused deep learning framework for classifying breast cancer cell lines from high-resolution fluorescence microscopy images. We developed an end-to-end framework that incorporates patch-based sampling, sparsity filtering, and a channel-wise intermediate fusion strategy to independently extract and integrate organelle-specific features. Model interpretability was assessed using Grad-CAM visualizations and single-organelle classifier analyses. The framework was evaluated on fluorescence microscopy images from six breast cancer cell lines using 5-fold cross-validation. The proposed framework achieved a classification accuracy of $$97.1 \pm 1.1$$ %, performing comparably to or exceeding conventional handcrafted feature-based approaches while eliminating the need for manual segmentation and 3D rendering steps. Interpretability and classifier analyses revealed inter-organelle dependencies and mitochondria as the most informative contributors to classification decisions. Organelle morphology and spatial organization provide strong discriminative signals for cancer cell classification. The proposed framework offers a scalable, automated, and interpretable deep learning solution that advances microscopy-based phenotyping and supports broader applications in computational pathology and cellular informatics.