Classification of Non-small Cell Lung Carcinoma Using Machine Learning Methods Based on CT Radiomic Features
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 发起方
- 入组人数
- 114
- 试验地点
- 1
- 主要终点
- The machine learning methods based on CT radiomic features can be used to classify Non-Small Cell Lung Carcinoma subtypes using a simple, non-invasive, and cost-effective diagnostic approach
研究概览
简要总结
57 of Squamous Cell carcinoma and Adenocarcinoma will be included in the study. Patients with CT imaging Characteristics of Squamous Cell Carcinoma and Adenocarcinoma will be selected for the study. Data will be collected from patients undergoing CT Contrast Thorax considering inclusion and exclusion criteria using convenience sampling technique. Post contrast images will be acquired using Philips Incisive 128 slice Ct and Philips Brilliance 16 Slice Big Bore CT (Philips Health Care) will be used for extracting the radiomic features from the tumor volume. Machine learning models will be are validated using prospective data.
研究设计
- 研究类型
- Observational
入排标准
- 年龄范围
- 18.00 Year(s) 至 90.00 Year(s)（—）
- 性别
- All
入选标准
- •Patients with CT imaging features of Squamous cell carcinoma and Adenocarcinoma.
排除标准
- •Patients with histopathologic diagnosis of small cell carcinoma.
结局指标
主要结局
The machine learning methods based on CT radiomic features can be used to classify Non-Small Cell Lung Carcinoma subtypes using a simple, non-invasive, and cost-effective diagnostic approach
时间窗: Scan will be performed after biopsy
次要结局
- Machine learning methods based on CT radiomic features can provide non-invasive diagnosis of classification of Non-Small Cell Lung Carcinoma.
研究者
Kaushik Nayak
Kasturba medical College and Hospital