arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.04294eess.IVcs.CV
收藏

PELE scores:通过骨盆提取与增强进行骨盆 X 射线关键点检测

PELE scores: Pelvic X-ray Landmark Detection by Pelvis Extraction and Enhancement

Zhen Huang, Han Li, Shitong Shao, Heqin Zhu, Huijie Hu, Zhiwei Cheng, Jianji Wang, S. Kevin Zhou

AI总结:

针对骨盆 X 射线中组织叠加干扰关键点检测的问题,提出利用 CT 三维解剖先验的 PELE 骨盆提取模块,并在 850 张图像上验证其达到最先进性能。

摘要:

骨盆是躯干的下部,支撑并平衡躯干。从骨盆 X 射线(PXR)中检测关键点有助于下游分析以及骨盆疾病的计算机辅助诊断和治疗。尽管与计算机断层扫描(CT)图像相比,PXR 具有辐射低、成本低的优势,但其三维结构的二维骨盆—组织叠加会干扰临床决策。本文提出一种 PELvis Extraction(PELE,骨盆提取)模块,利用 CT 中的三维先验解剖知识来引导并很好地将骨盆从 PXR 中分离出来,从而消除软组织的影响。我们基于两个公开数据集和一个私有数据集(共 850 张 PXR)开展了广泛评估。实验结果表明,所提出的 PELE 模块显著提高了 PXR 关键点检测的准确率,并在多项基准指标上取得了最先进性能,从而更好地服务于下游任务。

英文摘要:

The pelvis, the lower part of the trunk, supports and balances the trunk. Landmark detection from a pelvic X-ray (PXR) facilitates downstream analysis and computer-assisted diagnosis and treatment of pelvic diseases. Although PXRs have the advantages of low radiation and reduced cost compared to computed tomography (CT) images, their 2D pelvis-tissue superposition of 3D structures confuses clinical decision-making. In this paper, we propose a PELvis Extraction (PELE) module that utilizes 3D prior anatomical knowledge in CT to guide and well isolate the pelvis from PXRs, thereby eliminating the influence of soft tissue. We conduct an extensive evaluation based on two public datasets and one private dataset, totaling 850 PXRs. The experimental results show that the proposed PELE module significantly improves the accuracy of PXRs landmark detection and achieves state-of-the-art performances in several benchmark metrics, thus better serving downstream tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑