通过使用CNN和视觉变换器在全景放射图中自动检测和分类骨解质病变
Niels van Nistelrooij1,2, Iman Ghanad2, Amir K Bigdeli3
1Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, P.O. Box 9101, Nijmegen, 6500 HB, the Netherlands.
BMC oral health
|June 21, 2025
概括
深度学习模型在从全景放射图中检测下骨解病变方面表现有前途. 基于视觉变压器的模型,如Mask R-CNN与Swin-Tiny,为早期诊断提供了卓越的性能.
科学领域:
- 口腔和面放射学 口腔和面放射学
- 人工智能在医学中的应用
- 医学图像分析 医学图像分析
背景情况:
- 骨解性病变的特点是骨吸收,通常是无症状的,延迟了诊断.
- 在全景放射图 (PRs) 中早期检测明确的 (良性) 和不明确的 (恶性/传染性) 病变对于牙医来说至关重要但具有挑战性.
- 这项研究解决了改善诊断工具的需求,以支持牙医识别这些病变.
研究的目的:
- 开发和评估深度学习 (DL) 模型,用于在全景放射图 (PRs) 中自动检测骨解病变.
- 为了比较不同DL架构的有效性,包括那些具有视觉变压器组件的架构,用于病变识别.
主要方法:
- 一组676个PR的数据集被策划,骨解病变按像素细分,并将其分类为明确或不明确的.
- 四个实例细分模型 (Mask R-CNN与Swin-Tiny/ResNet-50,Mask DINO,YOLOv5) 被训练并使用五倍交叉验证进行评估.
- 性能指标包括灵敏度,特异性,F1得分和曲线下的面积 (AUC);分析了故障病例.
主要成果:
- 使用Swin-Tiny骨干的R-CNN口罩表现出最高的有效性,F1得分分为0.784 (定义良好) 和0.904 (定义不良),AUC分别为0.881和0.971.
- 整合视觉变压器组件的模型通常表现优于没有的模型.
- 常见的故障点包括大鼻腔,拔牙部位和放射性带.
结论:
- 深度学习模型,特别是那些使用视觉转换器 (Mask R-CNN与Swin-Tiny,Mask DINO) 的模型,显示出在PRs中检测骨解性病变的巨大潜力.
- 这些先进的DL模型比传统的自动化病变检测方法有了显著的改进.
- 这些发现强调了视觉变换器在提高牙科放射学诊断准确性的价值.
相关概念视频
01:18Classification of Bones
7.0K
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
7.0K
01:10Computed Tomography
6.1K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
6.1K