Pilot Study to Develop a Deep Learning Algorithm for Identification & Scoring of Terminal Ileal Crohn's Disease in Magnetic Resonance Enterography Images.
试验速览
- 阶段
- 不适用
- 状态
- 进行中（未招募）
- 入组人数
- 226
- 试验地点
- 2
- 主要终点
- Machine learning algorithm's ability to accurately localize the terminal ileum.
研究概览
简要总结
Crohn's disease affects 200,000 people in the UK (~1 in 500), most are young (diagnosed < 35 years) with costs of direct medical care exceeding £500 million.
Crohn's disease is caused by an auto-immune response and affects any part of the digestive tract, most commonly the last segment of the small bowel (the terminal ileum).
Magnetic resonance imaging (MRI) plays a role in 3 areas: Crohn's disease diagnosis , monitoring treatment response & assessing development of complications.
To evaluate the small bowel using MRI, Radiologists visually examine the scan slice-by-slice. The interpretation is time consuming and error-prone because of disease presentation variability and differentiation of diseased segments from collapsed segments.
Deep learning for image analysis is based on a computer algorithm "learning" from human (Radiologist) generated training data.
This method has been successfully applied to medical imaging, for example computer detection of lung cancer on chest X-rays.
This pilot study investigates if a deep learning algorithm can identify and score segments of inflamed terminal ileum affected by Crohn's disease.
To our knowledge this is the first project attempting to develop such an algorithm.The study will retrospectively review MR images obtained as part of standard care from patients being investigated for, Crohn's or being followed up with Crohn's disease. 226 patients' images will be used for the study.
On fully anonymised images two Radiologists working at Northwick Park Hospital will score and outline normal and abnormal loops of terminal ileum. Imperial College computer science department will then develop a deep learning algorithm from imaging features of normal and abnormal loops.
The study end-point is algorithm performance vs. images labelled by Radiologists.
The eventual aim is to develop an algorithm that assists Radiologists in the accurate diagnosis and follow-up of patients with Crohn's disease.
详细描述
Introduction.
The principal aim of the study is evaluating the accuracy of deep learning algorithm in differentiating between normal and abnormal terminal ileum against experienced Radiologists on MR Enterography images.
The study builds on existing research, which has shown statistical methods can identify sites of small bowel Crohn's disease. However the process was time consuming >1hr and not fully automatic. Our project investigates if cutting edge "deep learning" algorithm (based on neural networks) coupled with increased computing power can provide accurate and timely information.
The project has been designed jointly by Specialist Radiologists in Gastrointestinal imaging (who are aware of the challenges in imaging Crohn's disease accurately) and Imperial College Computer Science Department (who are experienced in developing neural networks for medical imaging). Input and review from London North-West Research and Development department is also acknowledged.
Study design.
研究设计
- 研究类型
- Interventional
- 分配方式
- Randomized
- 干预模型
- Single Group
- 主要目的
- Diagnostic
- 盲法
- None
盲法说明
Neither the Radiologists nor the Computer scientists/outcomes assessors will be masked to the image labels or if a given MR Enterography has been used in the training or validation dataset.
入排标准
- 年龄范围
- 16 Years 至 —（Child, Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •for all cases:
- •Patient's age >16 years of age, (this age cut off has been used in the recent METRIC trial investigating imaging in Crohn's disease)
- •MRI sequences obtained include axial T2 weighted images; coronal T2 weighted images and axial post contrast MRI images.
- •Inclusion criteria for normal MR Enterography cases:
- •Normal MR Enterography studies reviewed in consensus by two Radiologists (UP & PL). Normal is defined as no sites of small or large bowel Crohn's disease.
- •Inclusion criteria for terminal ileal Crohn's cases:
- •MR Enterography studies reviewed in consensus by two Radiologists shows terminal ileal Crohn's disease. Patients with more than one segment of small bowel Crohn's disease including terminal ileum are eligible. Patients with terminal ileal Crohn's disease continuous with large bowel are eligible.
- •Diagnosis of Crohn's disease of terminal ileum based on endoscopic, histological and radiological findings. (This criteria has been used in the recent METRIC trial investigating imaging in Crohn's disease).
排除标准
- •for all cases:
- •Poor quality MRI images as judged by consensus Radiologist opinion.
- •No more than 3 MRI scans will come from the same patient.
- •Exclusion criteria for terminal ileal Crohn's cases:
- •MR Enterography shows any bowel abnormality not due to Crohn's.
- •Patient has undergone previous small or large bowel resection (this will distort anatomy and is beyond the scope of the present project). Patients' with other previous surgeries are eligible.
- •Patients with large bowel Crohn's disease not continuous with the terminal ileum.
研究组 & 干预措施
Training of machine learning algorithm
113 MR Enterography images labelled by Radiologists will be used to develop a machine learning algorithm to (1) localise the terminal ileum, (2) classify the terminal ileum as normal or abnormal.
干预措施: Machine learning algorithm (Other)
Testing of machine learning algorithm
113 MR Enterography images labelled by Radiologists will be used to test the accuracy of the machine learning algorithm to (1) localise the terminal ileum, (2) classify the terminal ileum as normal or abnormal compared to Radiologists opinion.
Cross Validation analysis will be used for data analysis.
干预措施: Machine learning algorithm (Other)
结局指标
主要结局
Machine learning algorithm's ability to accurately localize the terminal ileum.
时间窗: 24 months
Study will compare manually segmented regions of interest by Radiologists with predictions by machine learning localisation algorithm.
次要结局
- Data processing time until a diagnosis reported by algorithm.(24 months)
- Machine learning algorithm's ability to accurately distinguish abnormal and normal terminal ileum.(24 months)