SOLVE: Spatially Optimized Lung Volume Evidence Model for Efficient Nodule Malignancy Classification

Abstract

Lung cancer diagnosis remains a critical challenge in personalized medicine, demanding novel approaches for efficient and accurate prediction. In this context, we propose the Spatially Optimized Lung Volume Evidence (SOLVE) framework, which is a novel lung malignancy prediction model developed by integrating principles from brain-inspired evidence accumulation and retina-inspired data processing. SOLVE introduces spatial scale optimization in Computed Tomography (CT) scan analysis, integrating evidence accumulation concepts to enhance decision-making. Mimicking the retina’s ability to process images across various spatial scales, SOLVE applies a series of filters and progressively captures features from coarse to fine details within each CT slice that may not be apparent when analyzed at a single resolution. Such an approach allows for a more discriminating feature representation, improving the richness of available information for analysis and reducing the reliance on large datasets. Addressing the challenge of limited medical image resources, SOLVE effectively decreases computational complexity via the use of its evidence-based mechanism. Through experiments conducted on an in-house dataset of 114 subjects, SOLVE demonstrated a marked improvement in prediction accuracy, outperforming traditional methods with far less training data.