相关实验视频

Updated: Sep 10, 2025

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

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

Published on: August 16, 2020

用"海优化增强ResNet-50"进行人工智能驱动的脏恶性病预测

Sabura Banu Urundai Meeran¹

¹Department of Electrical and Electronics Engineering, Saveetha Engineering College, Saveetha Nagar, Thandalam, Chennai, 602105, Tamilnadu, India.

Asian Pacific journal of cancer prevention : APJCP

|August 24, 2025

概括

这项研究使用Walrus优化算法 (WaOA) 优化了ResNet-50,以提高CT扫描中的瘤检测. 通过WaOA优化模型显著提高了分类准确性和可解释性,为医学诊断提供了有希望的AI工具.

科学领域:

医学成像
人工智能
深度学习

背景情况:

检测脏恶性瘤对于患者的结果至关重要.
传统的深度学习模型需要优化复杂的医学图像分析.
在人工智能驱动的医学诊断中,解释性和透明度是关键的挑战.

研究的目的:

使用海象优化算法 (WaOA) 优化ResNet-50的超参数,以改善瘤检测.
与传统深度学习模型对比 WaOA 优化的 ResNet-50 的性能.
通过封闭敏感性分析提高模型的可解释性和透明度.

主要方法:

使用了12446张腹部CT图像的数据集,分为囊,正常,石头和瘤.
进行了ResNet-50,AlexNet,GoogLeNet和Inception V3模型的训练和评估.
在ResNet-50的超参数调整中使用了Walrus优化算法 (WaOA).
进行了封闭灵敏度分析以确定模型的可解释性.

主要成果:

优化了 WaOA 的 ResNet-50 实现了 94.53% 的精度,在精度,回忆,F1 评分和 AUC-ROC 方面超过了其他模型.
该模型具有高可靠性,MCC为0.9038和低日志损失为0.1597.
封闭敏感性分析提供了对影响分类决策的关键图像区域的见解.

结论:

基于元听觉的超参数调对于医学成像中的深度学习是有效的.
通过WaOA优化的ResNet-50显示出精确可靠的脏恶性瘤检测的巨大潜力.
整合闭塞敏感性分析可确保人工智能辅助医疗诊断的透明度和可靠性.

关键词:

计算机辅助诊断深度学习超参数优化超听觉算法绩效评估

更多相关视频

In Vivo, Percutaneous, Needle Based, Optical Coherence Tomography of Renal Masses

In Vivo, Percutaneous, Needle Based, Optical Coherence Tomography of Renal Masses

Published on: March 30, 2015

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

相关概念视频

Receiver Operating Characteristic Plot

Receiver Operating Characteristic Plot

A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...

Renal Drug Clearance: Overview

Renal Drug Clearance: Overview

Renal clearance is a crucial parameter in pharmacokinetics that quantifies the rate at which the kidneys excrete a drug. It represents a constant fraction of the central volume of distribution containing the drug that the kidney eliminates per unit of time.
Renal clearance can be calculated using different methods. One approach is to divide the urinary drug excretion rate by the plasma drug concentration. This method directly measures renal clearance, indicating the kidneys' efficiency in...