NodMAISI: Nodule-Oriented Medical AI for Synthetic Imaging

2025-12-19

AI Summary

To address the scarcity, inconsistency, and insufficiency of annotated pulmonary nodules in lung cancer screening CT data, this paper proposes an anatomy-constrained and nodule-guided CT image synthesis and augmentation framework. Methodologically, it introduces a novel nodule-mask-controllable shrinkage augmentation strategy and a ControlNet-rectified flow generative model to jointly ensure structural fidelity of thoracic organs and morphological realism of nodules; it further integrates a multi-level organ/nodule mask annotation pipeline with lesion-aware perturbation augmentation. Experiments demonstrate that the method achieves significantly lower FID than MAISI-v2, improves nodule detection sensitivity by 0.3–0.43, and boosts classification AUC by up to 0.21 under low-data regimes—effectively alleviating the data bottleneck in pulmonary nodule analysis.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Search and Optimization: Mixed Discrete/Continuous Search
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Objective: Although medical imaging datasets are increasingly available, abnormal and annotation-intensive findings critical to lung cancer screening, particularly small pulmonary nodules, remain underrepresented and inconsistently curated. Methods: We introduce NodMAISI, an anatomically constrained, nodule-oriented CT synthesis and augmentation framework trained on a unified multi-source cohort (7,042 patients, 8,841 CTs, 14,444 nodules). The framework integrates: (i) a standardized curation and annotation pipeline linking each CT with organ masks and nodule-level annotations, (ii) a ControlNet-conditioned rectified-flow generator built on MAISI-v2's foundational blocks to enforce anatomy- and lesion-consistent synthesis, and (iii) lesion-aware augmentation that perturbs nodule masks (controlled shrinkage) while preserving surrounding anatomy to generate paired CT variants. Results: Across six public test datasets, NodMAISI improved distributional fidelity relative to MAISI-v2 (real-to-synthetic FID range 1.18 to 2.99 vs 1.69 to 5.21). In lesion detectability analysis using a MONAI nodule detector, NodMAISI substantially increased average sensitivity and more closely matched clinical scans (IMD-CT: 0.69 vs 0.39; DLCS24: 0.63 vs 0.20), with the largest gains for sub-centimeter nodules where MAISI-v2 frequently failed to reproduce the conditioned lesion. In downstream nodule-level malignancy classification trained on LUNA25 and externally evaluated on LUNA16, LNDbv4, and DLCS24, NodMAISI augmentation improved AUC by 0.07 to 0.11 at <=20% clinical data and by 0.12 to 0.21 at 10%, consistently narrowing the performance gap under data scarcity.

Problem

• Addresses underrepresentation of small pulmonary nodules in medical imaging datasets
• Improves synthetic CT image fidelity for lung cancer screening applications
• Enhances nodule detection and malignancy classification under data scarcity

Innovation

• ControlNet-conditioned rectified-flow generator for anatomy-consistent synthesis
• Lesion-aware augmentation with controlled shrinkage of nodule masks
• Standardized curation pipeline linking CTs with organ and nodule annotations