相关实验视频

Updated: Jan 20, 2026

3-D Cell Culture System for Studying Invasion and Evaluating Therapeutics in Bladder Cancer

3-D Cell Culture System for Studying Invasion and Evaluating Therapeutics in Bladder Cancer

Published on: September 13, 2018

使用CT放射学的可解释机器学习预测了非肌肉侵入性膀癌中二次切除后的病理升级

Xue Peng Rao¹, Xin Chang Zou¹, Zhan Jiang Yu¹

¹The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330008, China.

|January 18, 2026

概括

这项研究开发了一种可解释的CT放射学机器学习模型,用于预测在接受反复穿尿道切除 (ReTUR) 的非肌肉侵入性膀癌 (NMIBC) 患者的病理升级风险. 该模型准确识别高风险患者,帮助个性化治疗决策.

科学领域:

在瘤学瘤学.
放射学放射学是一门学科.
机器学习机器学习
医疗信息学医疗信息学

背景情况:

重复通过尿道切除 (ReTUR) 对于管理非肌肉侵入性膀癌 (NMIBC) 至关重要.
在ReTUR后的病态升级显著影响患者的预后.
准确预测升级风险对于指导治疗策略至关重要.

研究的目的:

使用CT放射学开发一种可解释的机器学习模型.
预测ReTUR后NMIBC患者病理升级的风险.
整合临床和成像功能,以提高预测准确度.

主要方法:

对104名接受ReTUR.UR的NMIBC患者进行了回顾性分析.
从手术前的CT扫描中提取放射性特征.
使用LASSO和后勤回归的机器学习模型 (XGBoost,GBDT,RF,LDA) 的开发和验证.
使用SHAP分析解释最佳模型.

主要成果:

瘤等级,大小和数量是升级阶段的独立风险因素.
在内部验证中,XGBoost模型取得了0.804的AUC,并在外部验证中证明了稳定性.
通过SHAP分析确定的关键预测因素包括特定的放射性特征和瘤等级.
该模型表现出良好的校准和临床效用.

结论:

一个基于CT放射学的可解释的机器学习模型可以准确地预测在NMIBC中ReTUR后的病态升级风险.
这种预测工具可以支持个性化治疗的临床决策.
建议进行多中心验证,以确认模型的通用性.

关键词:

可解释的机器学习非肌肉侵袭性膀癌是一种非肌肉侵袭性膀癌.病理升级病理升级无线电学 (Radiomics) 是一种无线电学.重复通过尿道切除.

更多相关视频

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

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

3-D Cell Culture System for Studying Invasion and Evaluating Therapeutics in Bladder Cancer

3-D Cell Culture System for Studying Invasion and Evaluating Therapeutics in Bladder Cancer

The processes governing bladder cancer invasion represent opportunities for biomarker and therapeutic development. Here we present a bladder cancer invasion model which incorporates 3-D culture of tumor spheroids, time-lapse imaging and confocal microscopy. This technique is useful for defining the features of the invasive process and for screening therapeutic...

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

This protocol was designed to train a machine learning algorithm to use a combination of imaging parameters derived from magnetic resonance imaging (MRI) and positron emission tomography/computed tomography (PET/CT) in a rat model of breast cancer bone metastases to detect early metastatic disease and predict subsequent progression to...

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

Intra-arterial therapies are the standard of care for patients with hepatocellular carcinoma who cannot undergo surgical resection. A method for predicting response to these therapies is proposed. The technique uses pre-procedural clinical, demographic, and imaging information to train machine learning models capable of predicting response prior to...

Guidelines and Experience Using Imaging Biomarker Explorer (IBEX) for Radiomics

Guidelines and Experience Using Imaging Biomarker Explorer (IBEX) for Radiomics

We describe IBEX, an open-source tool designed for medical imaging radiomics studies, and how to use this tool. In addition, some published works that have used IBEX for uncertainty analysis and model building are...

Minimally Invasive Establishment of Murine Orthotopic Bladder Xenografts

Minimally Invasive Establishment of Murine Orthotopic Bladder Xenografts

The established technique to inoculate primary invasive orthotopic bladder cancer xenografts requires laparotomy and mobilization of the bladder. This procedure inflicts significant morbidity on the mice, is technically challenging and time-consuming. We therefore developed a high-precision, percutaneous approach utilizing ultrasound...

RNA Secondary Structure Prediction Using High-throughput SHAPE

RNA Secondary Structure Prediction Using High-throughput SHAPE

High-throughput selective 2' hydroxyl acylation analyzed by primer extension (SHAPE) utilizes a novel chemical probing technology, reverse transcription, capillary electrophoresis and secondary structure prediction software to determine the structures of RNAs from several hundred to several thousand nucleotides at single nucleotide...