发表机构
Gdańsk University of Technology; NASK National Research Institute; Medical University of Gdańsk（格但斯克工业大学; 国家信息与通信技术研究所; 格但斯克医科大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对冠状动脉造影像素级分类缺标准化评估协议的问题，构建CARDIAG基准，涵盖24种架构。通过实验选出最佳模型并集成提升性能，展示架构校准等情况，强调高低分辨率特征重要性，为未来相关研究提供评估基准。
AI 中文摘要
准确的冠状动脉造影像素级分类对心血管疾病评估至关重要，但该领域缺乏标准化评估协议。本文展示了一个用于评估深度学习模型的新基准，该模型将冠状动脉造影像素密集分类为SYNTAX类别之一（或背景）。评估涵盖24种不同架构。我们发布了CARDIAG多中心、多标签数据集，并仔细拆分以可靠计算指标。从众多算法中，选出最佳性能的ConvNeXt V2编码器与DeepLab V3 Plus解码器，经集成后F1值提高。还展示了架构的校准情况等，强调了编码中高低分辨率特征的重要性。该基准能让未来研究稳健严格地评估相关方案。
英文摘要
Accurate pixel-level classification of coronary angiograms is critical for cardiovascular disease assessment, yet the field lacks standardized evaluation protocols. In this work we demonstrate a new benchmark for the assessment of deep learning models which densely classify pixels of coronary angiograms to one of SYNTAX classes (or background). The evaluation covers 24 distinct architectures starting with classic convnets to recent state-space-based vision algorithms. We release CARDIAG - a multi-center, multi-label dataset which we carefully split to reliably compute metrics, accounting for diameter error, overlap, centerline quality and calibration. The data contains SYNTAX labels, binary, uncertainty and segmentation masks as well as intermediate frames together with the selected non-sensitive DICOM metadata. From the multitude of algorithms, we nominate ConvNeXt V2 encoder with DeepLab V3 Plus decoder as the best performing, achieving macro $F_1=0.456$, which we then ensemble with Mamba U-Net and Feature Pyramid Network, for an increased $F_1=0.479$. We demonstrate all the architectures to be well calibrated and determine the generalization of the top 5 methods, together with the data efficiency of these architectures. We highlight the importance of both high-resolution and low-resolution features in encoding. We also demonstrate the model correctness in the context of patient demographic, vessel sides and projection angle configurations. Overall the released benchmark allows for future studies to robustly and rigorously assess the proposals, not only for SYNTAX segmentation, but lesion detection and many more.
Comments19 pages, 12 figures, 3 tables, dataset available on Zenodo at https://zenodo.org/records/19958730, code available at https://github.com/cvlab-ai/cardiag-benchmark
