Tokensome: Towards a Genetic Vision-Language GPT for Explainable and Cognitive Karyotyping

TL;DR

Tokensome is a novel vision-language model that enhances explainability and cognitive reasoning in automatic karyotype analysis by integrating domain knowledge and reasoning capabilities.

Contribution

It introduces a chromosome tokenization approach and elevates analysis from perception to cognition, enabling explainability and abnormality detection.

Findings

Improved interpretability of karyotype analysis

Enhanced abnormality detection accuracy

Integration of knowledge graphs and LLMs for reasoning

Abstract

Automatic karyotype analysis is often defined as a visual perception task focused solely on chromosomal object-level modeling. This definition has led most existing methods to overlook componential and holistic information, significantly constraining model performance. Moreover, the lack of interpretability in current technologies hinders clinical adoption. In this paper, we introduce Tokensome, a novel vision-language model based on chromosome tokenization for explainable and cognitive karyotyping. Tokensome elevates the method from the conventional visual perception layer to the cognitive decision-making layer. This elevation enables the integration of domain knowledge and cognitive reasoning via knowledge graphs and LLMs, markedly enhancing model's explainability and facilitating abnormality detection.