View in EDS

Integrative radiomics analysis of peri-tumoral and habitat zones for predicting major pathological response to neoadjuvant immunotherapy and chemotherapy in non-small cell lung cancer

Saved in:
Bibliographic Details
Title: Integrative radiomics analysis of peri-tumoral and habitat zones for predicting major pathological response to neoadjuvant immunotherapy and chemotherapy in non-small cell lung cancer
Authors: Han, Dan, Zhao, Junfeng, Hao, Shaoyu, Fu, Shenbo, Wei, Ran, Zheng, Xin, Zhao, Qian, Liu, Chengxin, Sun, Hongfu, Fu, Chengrui, Wang, Zhongtang, Huang, Wei, Li, Baosheng
Source: Transl Lung Cancer Res
Publisher Information: AME Publishing Company, 2025.
Publication Year: 2025
Subject Terms: Original Article
Description: It is crucial for clinical decision-making to identify non-small cell lung cancer (NSCLC) patients who are likely to achieve major pathological response (MPR) following neoadjuvant immunotherapy and chemotherapy (NICT). This study conducted a thorough analysis of the regions surrounding and within resectable NSCLC tumors, creating an integrative tumor microenvironment model that encompasses features of both the peri-tumoral areas and habitat-based subregions, aiming at enhancing accurate predictions and supporting clinical decision-making processes.Our study involved an analysis of 243 NSCLC patients from three centers, treated with NICT and surgery and categorized into training, validation, and test cohorts. We conducted an extensive analysis of the tumor area, examining the intra-tumoral zone and the surrounding peri-tumoral regions at 2 mm, 4 mm and 6 mm, developing an algorithm for delineating tumor habitats. Features were standardized with Z-scores and de-duplicated by retaining one from each highly correlated pair. We finalized the feature set using least absolute shrinkage and selection operator (LASSO) regression and 10-fold cross-validation, forming a robust radiomics signature for machine learning models. Clinical features underwent univariable and multivariable analyses, combining with peri-tumoral and habitat signatures in a nomogram, of which its diagnostic accuracy and clinical utility were evaluated using receiver operating characteristic (ROC), calibration curves, and decision curve analysis (DCA).The cohort showed a 68% MPR rate, with histology identified as a key predictor. An integrated nomogram including histology, Peri6mm and habitat signatures outperformed individual models with an area under the curve (AUC) of 0.894 in the training cohort, 0.831 in validation and 0.799 in testing. The nomogram demonstrated a clear advantage in predictive probabilities, as evidenced by DCA curve results.Our study's development of a predictive model using a nomogram integrating clinical and radiomics features significantly improved MPR prediction in NSCLC patients undergoing NICT, enhancing clinical decision-making.
Document Type: Article
Other literature type
ISSN: 2226-4477
2218-6751
DOI: 10.21037/tlcr-2024-1131
Access URL: https://pubmed.ncbi.nlm.nih.gov/40386728
Rights: CC BY NC ND
Accession Number: edsair.doi.dedup.....f91b37809052fc7ed3f7b9458dda3bbe
Database: OpenAIRE
Description
Abstract:It is crucial for clinical decision-making to identify non-small cell lung cancer (NSCLC) patients who are likely to achieve major pathological response (MPR) following neoadjuvant immunotherapy and chemotherapy (NICT). This study conducted a thorough analysis of the regions surrounding and within resectable NSCLC tumors, creating an integrative tumor microenvironment model that encompasses features of both the peri-tumoral areas and habitat-based subregions, aiming at enhancing accurate predictions and supporting clinical decision-making processes.Our study involved an analysis of 243 NSCLC patients from three centers, treated with NICT and surgery and categorized into training, validation, and test cohorts. We conducted an extensive analysis of the tumor area, examining the intra-tumoral zone and the surrounding peri-tumoral regions at 2 mm, 4 mm and 6 mm, developing an algorithm for delineating tumor habitats. Features were standardized with Z-scores and de-duplicated by retaining one from each highly correlated pair. We finalized the feature set using least absolute shrinkage and selection operator (LASSO) regression and 10-fold cross-validation, forming a robust radiomics signature for machine learning models. Clinical features underwent univariable and multivariable analyses, combining with peri-tumoral and habitat signatures in a nomogram, of which its diagnostic accuracy and clinical utility were evaluated using receiver operating characteristic (ROC), calibration curves, and decision curve analysis (DCA).The cohort showed a 68% MPR rate, with histology identified as a key predictor. An integrated nomogram including histology, Peri6mm and habitat signatures outperformed individual models with an area under the curve (AUC) of 0.894 in the training cohort, 0.831 in validation and 0.799 in testing. The nomogram demonstrated a clear advantage in predictive probabilities, as evidenced by DCA curve results.Our study's development of a predictive model using a nomogram integrating clinical and radiomics features significantly improved MPR prediction in NSCLC patients undergoing NICT, enhancing clinical decision-making.
ISSN:22264477
22186751
DOI:10.21037/tlcr-2024-1131