Scholarlink

Purpose <p>Large vision-language models (VLMs), such as GPT-4.1 and GPT-4o, have shown strong potential in medical tasks. However, their application in lossless 3D medical image analysis is still underexplored. This study proposes a GPT-based diagnostic approach that maintains voxel-level accuracy during data ingestion, structures multi-slice visual inputs for model interpretation, and integrates consensus guidelines to align predictions with clinical standards. In doing so, the approach may provide interpretable and guideline-consistent decision support even for less experienced clinicians.</p> Methods <p>We designed a novel approach that directly processes 3D chest CT scans in NIfTI format, maintains full voxel fidelity during data import and analysis, and is compatible with GPT-based workflows. For each lung nodule, we guided GPT in analyzing multi-slice visual inputs, including bounding annotations, segmentation overlays, and cropped views. Guidelines (Fleischner, BTS, ACCP) were embedded to promote standardized interpretation and guide reasoning from nodule-level characteristics to patient-level assessment. Three NIfTI-based input settings were used to test the method on the LIDC-IDRI dataset: (1) nodule coordinates only; (2) coordinates with guideline-based prompting; (3) segmentation overlays with guideline-based prompting. To evaluate the performance on external datasets, we performed external validation on the Lung Nodule Database (LNDb).</p> Results <p>GPT-4.1 outperformed GPT-4o overall, especially with full-context input, while GPT-4o had higher sensitivity with limited input. With segmentation and guideline-based prompting, GPT-4.1 achieved accuracy 0.722 and AUC 0.780 on LIDC-IDRI dataset. In external validation on LNDb dataset, it reached accuracy 0.767 and AUC 0.780. GPT-4.1 maintained its competitiveness when compared to representative deep-learning baselines and radiologist readers. It also provided stronger interpretability through guideline-grounded and patient-level reasoning with explicit textual justifications.</p> Conclusions <p>This study presents a clinically aligned and interpretable approach for GPT-based lung cancer diagnosis using lossless 3D CT images. The outcomes demonstrate the potential of combining large vision-language models with structured visual and guideline-based context in real-world diagnostic workflows.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A vision-language model–based approach for lung cancer diagnosis using lossless 3D CT images: evaluation of GPT-4.1 and GPT-4o for patient-level malignancy assessment

  • 期刊论文

  • 发表日期：

    2025年12月21日

查看全文
  • Ning Shi,
  • Zhenpeng Liu,
  • Zhenzhen Wan,
  • Guojie Yang,
  • Yasong Shi,
  • Peilin Wang,
  • Xiuling Liu

摘要

Purpose

Large vision-language models (VLMs), such as GPT-4.1 and GPT-4o, have shown strong potential in medical tasks. However, their application in lossless 3D medical image analysis is still underexplored. This study proposes a GPT-based diagnostic approach that maintains voxel-level accuracy during data ingestion, structures multi-slice visual inputs for model interpretation, and integrates consensus guidelines to align predictions with clinical standards. In doing so, the approach may provide interpretable and guideline-consistent decision support even for less experienced clinicians.

Methods

We designed a novel approach that directly processes 3D chest CT scans in NIfTI format, maintains full voxel fidelity during data import and analysis, and is compatible with GPT-based workflows. For each lung nodule, we guided GPT in analyzing multi-slice visual inputs, including bounding annotations, segmentation overlays, and cropped views. Guidelines (Fleischner, BTS, ACCP) were embedded to promote standardized interpretation and guide reasoning from nodule-level characteristics to patient-level assessment. Three NIfTI-based input settings were used to test the method on the LIDC-IDRI dataset: (1) nodule coordinates only; (2) coordinates with guideline-based prompting; (3) segmentation overlays with guideline-based prompting. To evaluate the performance on external datasets, we performed external validation on the Lung Nodule Database (LNDb).

Results

GPT-4.1 outperformed GPT-4o overall, especially with full-context input, while GPT-4o had higher sensitivity with limited input. With segmentation and guideline-based prompting, GPT-4.1 achieved accuracy 0.722 and AUC 0.780 on LIDC-IDRI dataset. In external validation on LNDb dataset, it reached accuracy 0.767 and AUC 0.780. GPT-4.1 maintained its competitiveness when compared to representative deep-learning baselines and radiologist readers. It also provided stronger interpretability through guideline-grounded and patient-level reasoning with explicit textual justifications.

Conclusions

This study presents a clinically aligned and interpretable approach for GPT-based lung cancer diagnosis using lossless 3D CT images. The outcomes demonstrate the potential of combining large vision-language models with structured visual and guideline-based context in real-world diagnostic workflows.