Neoplasms

Respiratory Tract (Lung and Bronchial) Diseases

All Conditions

Lung Neoplasms

Adenocarcinoma

Multiple Pulmonary Nodules

Adenocarcinoma in Situ

Carcinoma

Neoplasms, Glandular and Epithelial

Neoplasms by Histologic Type

Carcinoma in Situ

All Drugs and Chemicals

Immunomodulating Agents

The internal cohort was retrospective enrolled in Guangdong Provincial People's hospital from March 1, 2015 to December 31,2019. Patients with single pulmonary lesion underwent preoperative chest CT scan and histologically confirmed precancerous lesions or early stage lung adenocarcinoma after thoracic surgery was included.

The same inclusion/exclusion criteria were applied for another independent centers, Sun Yat-sen Memorial Hospital ,Guangdong Province, China, forming an external validation cohort of 73 patients

The same inclusion/exclusion criteria were applied for another independent centers, Zhoushan Lung Cancer Institution, Zhejiang Province, China, forming second external validation cohort of 30 patients

The internal cohort was retrospective enrolled in Guangdong Provincial People's hospital from March 1, 2015 to May 31,2020. Patients with advanced lung cancer underwent preoperative chest CT scan and histologically confirmed NSCLC before receiving immunotherapy was included.

Different radiomic and machine learning strategies for radiomic features extraction, sorting features and model constriction

Radiomic Algorithm

Haiyu Zhou, PhD

Luyu Huang

Herui Yao, PhD

Yufang Yu

Hanbo Cao, PhD

Yunfang Yu

The purpose of this study was to investigate whether the combined radiomic model based on radiomic features extracted from focus and perifocal area (5mm) can effectively improve prediction performance of distinguishing precancerous lesions from early-stage lung adenocarcinoma, which could assist clinical decision making for surgery indication. Besides, response and long term clinical benefit of immunotherapy of advanced NSCLC lung cancer patients could also be predicted by this strategy.

Early detection and diagnosis of pulmonary nodules is clinically significant regarding optimal treatment selection and avoidance of unnecessary surgical procedures. Deferential pathology results causes widely different prognosis after standard surgery among pulmonary precancerous lesion, atypical adenomatous hyperplasia (AAH) as well as adenocarcinoma in situ (AIS), and early stage invasive adenocarcinoma (IAC). The micro-invasion of pulmonary perifocal interstitium is difficult to identify from AIS unless pathology immunohistochemical study was implemented after operation，which may causes prolonged procedure time and inappropriate surgical decision-making. Key feature-derived variables screened from CT scans via statistics and machine learning algorithms, could form a radiomics signature for disease diagnosis, tumor staging, therapy response adn patient prognosis. The purpose of this study was to investigate whether the combined radiomic signature based on the focal and perifocal（5mm）radiomic features can effectively improve predictive performance of distinguishing precancerous lesions from early stage lung adenocarcinoma. Besides, immunotherapy response is various among patients and no more than 20% of patients could benefit from it. None reliable biomarker has been found yet expect Programmed death-ligand 1 (PD-L1) expression, the only approved biomarker for immunotherapy. However recent reports suggested that patients could benefit from immunotherapy regardless of PD-L1 positive or negative. On the contrast, radiomics has show it advantages of non-invasiveness, easy-acquired and no limitation of sampling. Therefore, we applied this strategy in prediction for the immunotherapy response of advanced NSCLC lung cancer patients receiving immune checkpoint inhibitors (ICIs), which would prevent some non-benefit patient from the adverse effect of ICIs.

CT-based Radiomic Algorithm for Assisting Surgery Decision and Predicting Immunotherapy Response of NSCLC

The datasets used or analysed during the current study are available from the corresponding author on reasonable request.

Rate of ORR in all subjects for the patients who receiving immunotherapy

From enrollment to progression or death (for any reason) in immunotherapy cohort

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization	Link
CT-based Radiomic Algorithm for Assisting Surgery Decision and Predicting Immunotherapy Response of NSCLC	NCT04452058	Predictive Canc... Lung Cancer Preinvasive Ade...	Radiomic Algori...	18 Years -	Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
CT-based Radiomic Algorithm for Assisting Surgery Decision and Predicting Immunotherapy Response of NSCLC	NCT04452058	Predictive Canc... Lung Cancer Preinvasive Ade...	Radiomic Algori...	18 Years -	Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

Spots Global Cancer Trial Database for pericancerous tissue