Saved in:
Bibliographic Details
Main Authors: Chen, Huangwei, Chen, Yifei, Yan, Zhenyu, Ding, Mingyang, Li, Chenlei, Zhu, Zhu, Qin, Feiwei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.12927
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913744395698176
author Chen, Huangwei
Chen, Yifei
Yan, Zhenyu
Ding, Mingyang
Li, Chenlei
Zhu, Zhu
Qin, Feiwei
author_facet Chen, Huangwei
Chen, Yifei
Yan, Zhenyu
Ding, Mingyang
Li, Chenlei
Zhu, Zhu
Qin, Feiwei
contents Neuroblastoma (NB), a leading cause of childhood cancer mortality, exhibits significant histopathological variability, necessitating precise subtyping for accurate prognosis and treatment. Traditional diagnostic methods rely on subjective evaluations that are time-consuming and inconsistent. To address these challenges, we introduce MMLNB, a multi-modal learning (MML) model that integrates pathological images with generated textual descriptions to improve classification accuracy and interpretability. The approach follows a two-stage process. First, we fine-tune a Vision-Language Model (VLM) to enhance pathology-aware text generation. Second, the fine-tuned VLM generates textual descriptions, using a dual-branch architecture to independently extract visual and textual features. These features are fused via Progressive Robust Multi-Modal Fusion (PRMF) Block for stable training. Experimental results show that the MMLNB model is more accurate than the single modal model. Ablation studies demonstrate the importance of multi-modal fusion, fine-tuning, and the PRMF mechanism. This research creates a scalable AI-driven framework for digital pathology, enhancing reliability and interpretability in NB subtyping classification. Our source code is available at https://github.com/HovChen/MMLNB.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MMLNB: Multi-Modal Learning for Neuroblastoma Subtyping Classification Assisted with Textual Description Generation
Chen, Huangwei
Chen, Yifei
Yan, Zhenyu
Ding, Mingyang
Li, Chenlei
Zhu, Zhu
Qin, Feiwei
Computer Vision and Pattern Recognition
Artificial Intelligence
Neuroblastoma (NB), a leading cause of childhood cancer mortality, exhibits significant histopathological variability, necessitating precise subtyping for accurate prognosis and treatment. Traditional diagnostic methods rely on subjective evaluations that are time-consuming and inconsistent. To address these challenges, we introduce MMLNB, a multi-modal learning (MML) model that integrates pathological images with generated textual descriptions to improve classification accuracy and interpretability. The approach follows a two-stage process. First, we fine-tune a Vision-Language Model (VLM) to enhance pathology-aware text generation. Second, the fine-tuned VLM generates textual descriptions, using a dual-branch architecture to independently extract visual and textual features. These features are fused via Progressive Robust Multi-Modal Fusion (PRMF) Block for stable training. Experimental results show that the MMLNB model is more accurate than the single modal model. Ablation studies demonstrate the importance of multi-modal fusion, fine-tuning, and the PRMF mechanism. This research creates a scalable AI-driven framework for digital pathology, enhancing reliability and interpretability in NB subtyping classification. Our source code is available at https://github.com/HovChen/MMLNB.
title MMLNB: Multi-Modal Learning for Neuroblastoma Subtyping Classification Assisted with Textual Description Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.12927