Newest papers

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

Iori Azuma, Hiroyuki Kusuhara, Tadahaya Mizuno · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.24023 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Глубокое обучение присвоило сильную производительность в вычислительной патологии, но объяснение предсказаний всего слайда (WSI) остается сложной задачей. Существующие методы объяснения часто подчеркивают важные регионы без идентификации их морфологических паттернов, оставляя разрыв между вычислительными доказательствами на уровне патча и контекстной интерпретацией на уровне слайда. Мы предлагаем ProtoGTX, графическую структуру, которая сочетает пространственную контекстуализацию с гибким морфологическим прототипом словаря. ProtoGTX отделяет референтные прототипы, используемые для определения морфологических концепций, от предсказательной модели: референтная лексика на уровне слайда может быть генерирована из учебных данных путем не

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Vocabulary, Artificial intelligence, Contextualization, Classifier (UML), Cluster analysis

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange