从研究前沿到实验室实践：多模态医学图像智能诊断四层实验教学系统设计

arXiv cs.AI 论文
medical-ai multimodal-imaging educational-curriculum deep-learning laboratory-teaching experimental-design

摘要

本文设计了一个用于多模态医学图像智能诊断的四层实验教学系统，将研究成果转化为本科实验室教学，以解决临床人工智能教育中的空白。

arXiv:2609.22790v1 Announce Type: new Abstract: Undergraduate programmes in intelligent medical engineering are expanding, yet laboratory curricula lag behind the multimodal, long-tailed, and distributionally shifting realities of clinical AI. This design paper presents an advanced experimental teaching system that translates an ongoing multimodal deep learning research project on endometrial carcinoma into a structured undergraduate lab sequence. We identify three educational gaps (modality, authenticity, and deployment) and derive four pedagogical principles from constructive alignment, experiential learning, the research teaching nexus, and the CDIO framework. The curriculum comprises four progressive tiers plus an engineering layer, with 32 laboratory units over 64 contact hours, delivered via a custom virtual clinical workstation using de-identified multi-institutional data. Each tier maps to a specific technical bottleneck, prerequisite coursework, and criterion-referenced deliverables. Data governance, safety, and assessment protocols are specified. Learning outcome data will be collected across two implementation cycles.
查看原文
查看缓存全文

缓存时间: 2026/09/23 09:16 

# From Research Frontier to Laboratory Bench: Design of a Four-Tier Experimental Teaching System for Multimodal Medical Image Intelligent Diagnosis
Source: [https://arxiv.org/abs/2609.22790](https://arxiv.org/abs/2609.22790)
[View PDF](https://arxiv.org/pdf/2609.22790)

> Abstract:Undergraduate programmes in intelligent medical engineering are expanding, yet laboratory curricula lag behind the multimodal, long\-tailed, and distributionally shifting realities of clinical AI\. This design paper presents an advanced experimental teaching system that translates an ongoing multimodal deep learning research project on endometrial carcinoma into a structured undergraduate lab sequence\. We identify three educational gaps \(modality, authenticity, and deployment\) and derive four pedagogical principles from constructive alignment, experiential learning, the research teaching nexus, and the CDIO framework\. The curriculum comprises four progressive tiers plus an engineering layer, with 32 laboratory units over 64 contact hours, delivered via a custom virtual clinical workstation using de\-identified multi\-institutional data\. Each tier maps to a specific technical bottleneck, prerequisite coursework, and criterion\-referenced deliverables\. Data governance, safety, and assessment protocols are specified\. Learning outcome data will be collected across two implementation cycles\.

## Submission history

From: Dongjing Shan \[[view email](https://arxiv.org/show-email/0f14f24e/2609.22790)\] **\[v1\]**Sat, 19 Sep 2026 05:40:57 UTC \(248 KB\)

相似文章

MedAction：迈向主动式多轮临床诊断大语言模型

arXiv cs.CL

本文介绍了 MedAction 框架，该框架通过模拟迭代式的检查开具与假设更新，训练大语言模型（LLM）进行主动的多轮临床诊断。文章提出了一个新的数据集 MedAction-32K，并展示了开源模型在医学基准测试上的最先进水平（SOTA）性能。

AutoMedBench：迈向基于智能体AI模型的医学自动研究

Hugging Face Daily Papers

AutoMedBench是一个面向自主医学AI研究工作流的基准测试，评估智能体在五个阶段中处理多种医学影像任务的表现。阶段级评分显示，验证阶段最弱，凸显了智能体工作流中可靠验证的必要性。