Classification of Benign and Malignant Lung Nodules Based on CT Raw Data

Comparison and Analysis of Predictive Performance of CT and Raw Data in Benign and Malignant Classification of Pulmonary Nodules

The employ of medical images combined with deep neural networks to assist in clinical diagnosis, therapeutic effect, and prognosis prediction is nowadays a hotspot. However, all the existing methods are designed based on the reconstructed medical images rather than the lossless raw data. Considering that medical images are intended for human eyes rather than the AI, we try to use raw data to predict the malignancy of pulmonary nodules and compared the predictive performance with CT. Experiments will prove the feasibility of diagnosis by CT raw data. We believe that the proposed method is promising to change the current medical diagnosis pipeline since it has the potential to free the radiologists.

Study Overview

• Status: Completed
• Conditions: Lung Cancer; Image, Body
• Intervention / Treatment: Other: No interventions

Detailed Description

The routinely used diagnostic scheme of cancers follows the process of signal-to-image-to-diagnosis. It is essential to reconstruct the visible images from the signal of medical device so that the human doctor can perform diagnosis. However, the huge amount of information inside the signal is not optimally mined, which causes the current unsatisfactory performance of image based diagnosis.

In this clinical trial, we will develop an AI based diagnostic scheme for lung nodules directly from the signal (raw data) to diagnosis, skipping the reconstruction step. In this trial, we will focus on the discrimination of malignant from benign lung nodules. We will collect a dataset of patients who are screened out lung nodules. All patients undergo preoperative CT scan (raw data and CT images available) and have pathologically confirmed result of the nodules. We will build a model using only raw data for diagnosis of the lung nodules. Moreover, another model from CT image will be built for comparison.

Furthermore, we will perform follow-up on these patients and build a model based on CT raw data for prognosis analysis of lung cancer.

• Study Type: Observational
• Enrollment (Actual): 626

Contacts and Locations

Study Locations

• China
  • Jilin
    • Changchun, Jilin, China, 130021
      • The First Hospital of Ji Lin University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

Patients who are screened out lung nodules by CT will be included in this study. The golden standard is the pathologically confirmed malignance of the nodule.

Description

Inclusion Criteria:

1. Patients who are screened out lung nodule.
2. The CT data and corresponding CT raw data are available before the surgery.
3. Final pathology diagnosis of the malignancy of the nodule is available.

Exclusion Criteria:

1. Previous history of lung malignancies.
2. Artifacts on CT images seriously deteriorating the observation of the lesion.
3. The time interval between CT scan and pathology diagnosis is more than 4 weeks.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
The First Hospital of Ji Lin University; CT data and corresponding CT raw data of patients with lung nodule will be collected.	Other: No interventions; No interventions

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area under the receiver operating characteristic curve (ROC)	Area under curve (AUC) of raw data in discriminating malignant nodules from benign nodules.	8 months
Disease free survival	The association between raw data and disease free survival (DFS), which defined as the time from the beginning of diagnosis of lung cancer to the confirmed time of recurrence or metastatic disease, or death occurred.	5 years
Overal survival	The association between raw data and overall survival (OS), which defined as the time from the beginning of diagnosis of lung cancer to the death with any causes.	5 years

Collaborators and Investigators

• Sponsor: Chinese Academy of Sciences
• Collaborators: The First Hospital of Jilin University; Neusoft Medical Systems Co., Ltd.
• Investigators: Study Director: Yali Zang, Ph.D., Institute of Automation, Chinese Academy of Sciences

Publications and helpful links

General Publications

• Kalra M, Wang G, Orton CG. Radiomics in lung cancer: Its time is here. Med Phys. 2018 Mar;45(3):997-1000. doi: 10.1002/mp.12685. Epub 2017 Dec 12. No abstract available.

Helpful Links

• Lung Cancer
• LUNA2016

Study record dates

Study Major Dates

• Study Start (ACTUAL): April 15, 2019
• Primary Completion (ACTUAL): June 30, 2022
• Study Completion (ACTUAL): June 30, 2022

Study Registration Dates

• First Submitted: January 23, 2020
• First Submitted That Met QC Criteria: January 23, 2020
• First Posted (ACTUAL): January 27, 2020

Study Record Updates

• Last Update Posted (ACTUAL): June 30, 2022
• Last Update Submitted That Met QC Criteria: June 29, 2022
• Last Verified: June 1, 2022

More Information

Terms related to this study

• Keywords: lung cancer; CT; classification; radiomics; raw data
• Additional Relevant MeSH Terms: Respiratory Tract Diseases; Neoplasms; Lung Diseases; Neoplasms by Site; Respiratory Tract Neoplasms; Thoracic Neoplasms; Lung Neoplasms
• Other Study ID Numbers: CASMI001

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

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