ProtoGTX: Prototype-Aligned Graph Transformer for Explainable Whole-Slide Image Analysis

Abstract

Deep learning has achieved strong performance in computational pathology, but explaining whole-slide image (WSI) predictions remains challenging. Existing explanation methods often highlight important regions without identifying their morphological patterns, leaving a gap between patch-level computational evidence and slide-level pathological interpretation. We propose ProtoGTX, a graph-based framework that combines spatial contextualization with a flexible morphological prototype vocabulary. ProtoGTX separates the reference prototypes used to define morphological concepts from the predictive model: the reference vocabulary can be generated from training data by unsupervised clustering or supplied externally, and remains fixed during classifier training. Patch features are first contextualized over a spatial graph, after which learnable prototypes representing morphological concepts are optimized through cross-attention. Their slide-level activation profile is aligned with the morphological composition induced by the fixed reference prototype bank. On the CPTAC and BRACS datasets, ProtoGTX outperforms the evaluated MIL, prototype-based, and graph-based baselines, with particularly pronounced improvements on BRACS. Qualitative analyses further show that spatial contextualization transforms fragmented patch-level prototype assignments into more coherent tissue regions. In BRACS, prototype maps also co-localize with pathologist annotations and regions relevant to slide-level prediction. These results demonstrate that ProtoGTX provides complementary semantic and spatial explanations while retaining a prototype vocabulary that can be defined independently of the predictive model. Code is available at https://github.com/mizuno-group/ProtoGTX.