Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Kidney Structure01:45

Kidney Structure

68.3K
The kidneys are two large bean-shaped organs located in the upper abdomen. They filter the blood several times a day to remove toxins and rebalance water and electrolytes of the circulatory system via the renal veins. The kidneys receive blood directly from the heart via the renal arteries. These arteries enter the kidney at the hilum, the concave surface of the bean, where they branch and divide into smaller vessels and capillaries.
68.3K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Multi-Task and Federated Learning for Breast and Lung Cancer Screening and Diagnosis: A Survey and Future Research Directions.

Journal of imaging·2026
Same author

An efficient YOLOv12-based framework for detecting extremely small-scale objects.

Scientific reports·2025
Same author

Optimized car parts detection with advanced feature fusion and attention modules.

Scientific reports·2025
Same author

An Explainable Deep Learning-Based Predictive Maintenance Solution for Air Compressor Condition Monitoring.

Sensors (Basel, Switzerland)·2025
Same author

A Method for Assessing the Reliability of the Pepper Robot in Handling Office Documents: A Case Study.

Biomimetics (Basel, Switzerland)·2024
Same author

A reliable anchor regenerative-based transformer model for x-small and dense objects recognition.

Neural networks : the official journal of the International Neural Network Society·2023

相关实验视频

Updated: May 21, 2025

Unilateral Ureteral Obstruction Model for Investigating Kidney Interstitial Fibrosis
04:57

Unilateral Ureteral Obstruction Model for Investigating Kidney Interstitial Fibrosis

Published on: April 25, 2025

372

使用高效的RT-DETR模型预测多重结石.

Ponduri Vasanthi1, Lingamallu Naga Srinivasu2, Ventrapragada Teju3

  • 1Eswar College of Engineering, India.

Computers in biology and medicine
|March 19, 2025
PubMed
概括

该RT-DETR模型提供了高效和准确的结石检测,在CT扫描中超越现有方法识别多个石头. 这一进步提高了诊断能力和患者治疗策略.

关键词:
跨尺度的特征融合.内尺度特征相互作用的作用.检测结石 检测结石的检测实时检测变压器小规模的物体检测检测小规模的物体检测.

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K
5/6 Nephrectomy Using Sharp Bipolectomy Via Midline Laparotomy in Rats
05:34

5/6 Nephrectomy Using Sharp Bipolectomy Via Midline Laparotomy in Rats

Published on: April 4, 2025

427

相关实验视频

Last Updated: May 21, 2025

Unilateral Ureteral Obstruction Model for Investigating Kidney Interstitial Fibrosis
04:57

Unilateral Ureteral Obstruction Model for Investigating Kidney Interstitial Fibrosis

Published on: April 25, 2025

372
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K
5/6 Nephrectomy Using Sharp Bipolectomy Via Midline Laparotomy in Rats
05:34

5/6 Nephrectomy Using Sharp Bipolectomy Via Midline Laparotomy in Rats

Published on: April 4, 2025

427

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 腎臟病學 (nephrology) 是一種醫學專業.

背景情况:

  • 结石检测 (KSD) 对于医学成像中的有效治疗计划至关重要.
  • 目前的模型在CT切片中的多个石头上扎,预测时间缓慢.
  • 精确识别石类型对于量身定制的治疗方法至关重要.

研究的目的:

  • 介绍RT-DETR模型,以高效准确地检测多结石.
  • 解决现有模型在处理多块石头和预测速度方面的局限性.
  • 提高诊断能力,识别结石.

主要方法:

  • 使用了带有基于注意力的尺度内特征交互 (AIFI) 和跨尺度特征融合模块 (CSFM) 的混合编码器的RT-DETR.
  • 整合了一个交叉在欧盟 (IoU) 意识到的查询选择机制,以改进异质结石检测.
  • 在注释CT图像的数据集上评估模型性能.

主要成果:

  • RT-DETR实现了74.3%的精度,91%的回忆,73.3%的mAP和82.65%的准确性.
  • 小型结石的检测时间为1.043秒.
  • 在统计测试中,RT-DETR显著优于现有模型 (OF,KC,ED19,DL,EL,YOLOv5,YOLOv8).

结论:

  • RT-DETR模型显著提高了结石检测的效率和准确性.
  • 有效管理多尺度特征和IOU-aware查询可以提高诊断能力.
  • 通过精确及时诊断,有可能简化临床工作流程并改善患者的治疗结果.