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

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

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.

Study Overview

• Status: Unknown
• Conditions: Detection; Segmentation
• Intervention / Treatment: Other: Automatic detection and segmentation of NSCLC tumors

Detailed 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.

• Study Type: Observational
• Enrollment (Actual): 1043

Contacts and Locations

Study Locations

• Netherlands
  • Limburg
    • Maastricht, Limburg, Netherlands, 6229ER
      • Maastricht University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: ADULT; OLDER_ADULT; CHILD
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

CT scans of 1043 patients diagnosed with NSCLC at one of the 8 centers (Netherlands, USA, China, Belgium) were collected retrospectively. All patients had a biopsy to confirm the diagnosis

Description

Inclusion Criteria:

• Availability of CT scans
• Availability of definite diagnosis

Exclusion Criteria:

• Lack of segmentations

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Detection of NSCLC on CT scans	Automatic detection of NSCLC tumors	November, 2019
Segmentation of NSCLC scans	Automatic segmentation of NSCLC tumors	November, 2019

Collaborators and Investigators

• Sponsor: Maastricht University
• Collaborators: University of California, San Francisco; Centre Hospitalier Universitaire de Liege; University Hospital RWTH Aachen University, Aachen, Germany.; Affiliated Zhongshan Hospital of Dalian University, 6 Jiefang street, Dalian 116001, China

Study record dates

Study Major Dates

• Study Start (ACTUAL): March 10, 2019
• Primary Completion (ACTUAL): November 7, 2019
• Study Completion (ANTICIPATED): October 31, 2020

Study Registration Dates

• First Submitted: November 12, 2019
• First Submitted That Met QC Criteria: November 12, 2019
• First Posted (ACTUAL): November 15, 2019

Study Record Updates

• Last Update Posted (ACTUAL): April 6, 2020
• Last Update Submitted That Met QC Criteria: April 3, 2020
• Last Verified: November 1, 2019

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Respiratory Tract Diseases; Neoplasms; Lung Diseases; Neoplasms by Site; Respiratory Tract Neoplasms; Thoracic Neoplasms; Carcinoma, Bronchogenic; Bronchial Neoplasms; Lung Neoplasms; Carcinoma, Non-Small-Cell Lung
• Other Study ID Numbers: ALSP

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Currently, there is no plan to make it public

Study Data/Documents

1. Individual Participant Data Set
   Information identifier: NSCLC Radiomics Interobserver
2. Individual Participant Data Set
   Information identifier: NSCLC Radiomics
3. Individual Participant Data Set
   Information identifier: NSCLC Radiogenomics

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No