Singpath-VL Technical Report

TL;DR

Singpath-VL is a specialized vision-language large model for cervical cytology, developed using a novel synthetic dataset and fine-tuning strategy, achieving improved cell morphology understanding and diagnostic accuracy.

Contribution

We created a large-scale synthetic dataset and fine-tuned a vision-language model specifically for cervical cytology, addressing data scarcity in computational pathology.

Findings

Superior performance in cell-level diagnostic classification

Enhanced fine-grained morphological perception

Open-sourced synthetic dataset and benchmark

Abstract

We present Singpath-VL, a vision-language large model, to fill the vacancy of AI assistant in cervical cytology. Recent advances in multi-modal large language models (MLLMs) have significantly propelled the field of computational pathology. However, their application in cytopathology, particularly cervical cytology, remains underexplored, primarily due to the scarcity of large-scale, high-quality annotated datasets. To bridge this gap, we first develop a novel three-stage pipeline to synthesize a million-scale image-description dataset. The pipeline leverages multiple general-purpose MLLMs as weak annotators, refines their outputs through consensus fusion and expert knowledge injection, and produces high-fidelity descriptions of cell morphology. Using this dataset, we then fine-tune the Qwen3-VL-4B model via a multi-stage strategy to create a specialized cytopathology MLLM. The resulting model, named Singpath-VL, demonstrates superior performance in fine-grained morphological perception and cell-level diagnostic classification. To advance the field, we will open-source a portion of the synthetic dataset and benchmark.