Fully Automated Pipeline for the Detection and Segmentation of Non-Small Cell Lung Cancer (NSCLC) on CT Images

Detection Clinical Trial

Official title:

Fully Automated Pipeline for the Detection and Segmentation of Non-Small Cell Lung Cancer (NSCLC) on CT Images: Quantitative and Qualitative Evaluation

Clinical Trial Details — Status: Active, not recruiting

Administrative data

• NCT number: NCT04164186
• Other study ID #: ALSP
• Status: Active, not recruiting
• Start date: March 10, 2019
• Est. completion date: October 31, 2020

Study information

• Verified date: November 2019
• Source: Maastricht University
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Accurate segmentation of lung tumor is essential for treatment planning, as well as for monitoring response to therapy. It is well-known that segmentation of the lung tumour by different radiologists gives different results (inter-observer variance). Moreover, if the same radiologist is asked to repeat the segmentation after several weeks, these two segmentations are not identical (intra-observer variance). In this study we aim to develop an automated pipeline that can produce swift, accurate and reproducible lung tumor segmentations.

Description:

In this study, we aim to develop and test an automated deep learning detection and segmentation software for non-small cell lung cancer (NSCLC) that can automatically detect and segment tumors on CT scans and thus reduce the human variation. We will assess the level of agreement between a group of radiologists, performing manual versus semi-automatic tumour segmentation. To do so, we will provide radiologists with two sets of CT scans. The first set will be segmented manually; the second one will be segmented using the automated software program.

Subsequently, we will use the inter- and intra-observer variance from the clinical study in a simulation or modeling study. We also compare the time needed and the consistency in segmentations by the software to medical doctors performance.

Reliability and Agreement study:

Primary tumours of 25 lung cancer patients will be delineated by 6 segmentation experts.

1. Assess agreement between automatic segmentation and radiologists' segmentation The primary tumours of 25 patients will be manually segmented by the radiologists and automatically by the the tool. The time needed to perform this task and the reproducibility of the segmentation will be recorded. The degree of overlap between the ROs and the automatic contour will be assessed pairwise using the Dice coefficient.

2. Delination of tumours by the experts, assisted by the software tool For another 25 patients, the experts will be provided with an automatic delineation, performed by the tool. They have the possibility to adjust and validate it. The time needed will be recorded. The difference between the mean overlap fraction in the first situation (manual delineation of experts) and the second situation (delineation of experts+ software tool) will be assessed, using a multi-observer Dice coefficient.

3. Assessment of intra-observer variance The experts will repeat the segmentation of the lung tumours after 2 weeks. They will repeat the manual segmentation (n=25) and the semi-automatic segmentation (n=25). This will make it possible to assess the intra-observer variance in both situations.

4. Qualitative assessment of the experts' preferences using an in-house developed visualization toolbox.

Recruitment information / eligibility

• Status: Active, not recruiting
• Enrollment: 1043
• Est. completion date: October 31, 2020
• Est. primary completion date: November 7, 2019
• Accepts healthy volunteers: No
• Gender: All
• Age group: N/A and older

Eligibility

Inclusion Criteria:

• Availability of CT scans

• Availability of definite diagnosis

Exclusion Criteria:

• Lack of segmentations

Related Conditions & MeSH terms

• Carcinoma, Non-Small-Cell Lung
• Detection
• Segmentation

Intervention

Other:
• Automatic detection and segmentation of NSCLC tumors
an automated deep learning detection and segmentation software for non-small cell lung cancer (NSCLC) that can automatically detect and segment tumors on CT scans and thus reduce the human variation.

Locations

Country	Name	City	State
Netherlands	Maastricht University	Maastricht	Limburg

Sponsors (5)

Lead Sponsor	Collaborator
Maastricht University	Affiliated Zhongshan Hospital of Dalian University, 6 Jiefang street, Dalian 116001, China, Hospital Center Universitaire De Liege, Liege, Belgium., University Hospital RWTH Aachen University, Aachen, Germany., University of California San Francisco, San Francisco, California, CA.

Country where clinical trial is conducted

Netherlands, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Detection of NSCLC on CT scans	Automatic detection of NSCLC tumors	November, 2019
Primary	Segmentation of NSCLC scans	Automatic segmentation of NSCLC tumors	November, 2019