Related Experiment Video
Updated: Jul 6, 2025
09:31
In Vivo, Percutaneous, Needle Based, Optical Coherence Tomography of Renal Masses
Published on: March 30, 2015
8.9K
Cystic renal mass screening: machine-learning-based radiomics on unenhanced computed tomography
Lesheng Huang1, Yongsong Ye2, Jun Chen1,2
1Guangdong Provincial Hospital of Chinese Medicine, Department of Radiology, Zhuhai, China
Diagnostic and Interventional Radiology (Ankara, Turkey)
|January 2, 2024
Summary
Unenhanced CT radiomics and machine learning (ML) classifiers show promise in diagnosing cystic renal masses (CRMs). These ML models, particularly k-nearest neighbor (KNN), may assist in CRM screening.
Area of Science:
- Radiology
- Artificial Intelligence
- Oncology
Background:
- Cystic renal masses (CRMs) require accurate differentiation between benign and malignant types.
- Diagnostic performance of unenhanced computed tomography (CT) radiomics-based machine learning (ML) classifiers and radiologists is compared for CRMs.
Purpose of the Study:
- To compare the diagnostic performance of unenhanced CT radiomics-based ML classifiers against a radiologist for CRMs.
- To evaluate the potential of ML models in aiding the screening of CRMs.
Main Methods:
- Radiomic features were extracted from unenhanced CT scans of 207 patients with pathologically diagnosed CRMs.
- Machine learning models (random forest, decision tree, k-nearest neighbor) were constructed using selected features.
- External validation was performed, and ML model performance was assessed using calibration curves, decision curves, and ROC curves.
Main Results:
- The radiologist's diagnostic accuracy, sensitivity, and specificity were 85.5%, 84.2%, and 91.1% respectively (AUC, 0.87).
- ML classifiers demonstrated high performance in the training set (accuracy, sensitivity, specificity: 94.3%-100%).
- In the validation set, k-nearest neighbor (KNN) showed superior sensitivity and accuracy compared to other ML models.
Conclusions:
- Unenhanced CT radiomics-based ML classifiers show comparable or superior performance to radiologists in diagnosing CRMs.
- ML models, especially KNN, may serve as valuable tools for screening CRMs, potentially improving diagnostic accuracy and efficiency.
Related Concept Videos
01:10Computed Tomography
4.5K
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...
4.5K
01:30Radiological Investigation I: X-ray and CT
241
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
241