Related Experiment Video
Updated: Jan 14, 2026
Using Micro-computed Tomography for the Assessment of Tumor Development and Follow-up of Response to Treatment in a Mouse Model of Lung Cancer
Published on: May 20, 2016
Tumor rim-specific computed tomography radiomics improves prediction of pathological complete response to neoadjuvant
Jingyi Yang1, Fangyuan Qu1, Qiliang Wang1
1Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer/Tianjin's Clinical Research Center for Cancer/Key Laboratory of Cancer Immunology and Biotherapy, Tianjin, China.
Background:
Neoadjuvant immunotherapy has revolutionized the treatment of non-small cell lung cancer (NSCLC), highlighting the need for accurate predictors of pathological complete response (pCR). This study aims to enhance pCR prediction to neoadjuvant immunotherapy in NSCLC patients by using radiomics analysis across various volumes of interest (VOIs) of the primary tumor on computed tomography (CT) images.
Methods:
A total of 229 NSCLC patients who received neoadjuvant immunotherapy between August 2018 and May 2024 were retrospectively analyzed. Radiomics models were built using four VOIs: gross tumor volume (GTV), tumor rim volume (TRV) which included 3 mm inward contraction and 3 mm outward expansion of the tumor boundary, PTV3 (3 mm beyond the tumor margin), and PTV6 (6 mm beyond the tumor margin). The performances of prediction models were evaluated in terms of discrimination, calibration and clinical usefulness. An independent neoadjuvant chemotherapy cohort was included to assess model specificity. To explore the biological mechanisms linked to the radiomics score, a genetic analysis was performed on 36 patients from The Cancer Imaging Archive (TCIA) dataset with available RNA-sequencing data.
Results:
Ninety-seven patients (42.4%) achieve pCR after neoadjuvant immunotherapy. The TRV radiomics model demonstrated the highest accuracy for the prediction of pCR in the validation cohort, with an area under the curve (AUC) of 0.827 and a 95% confidence interval (CI) ranging from 0.742 to 0.913, significantly outperforming GTV (0.631, 95% CI: 0.516-0.746), PTV3 (0.658, 95% CI: 0.546-0.770), and PTV6 radiomics models (0.689, 95% CI: 0.580-0.798) (all P<0.05). The TRV model exhibited limited performance in the chemotherapy cohort (AUC =0.519), indicating treatment specificity. Further radiogenomic analysis revealed that higher TRV radiomics score correlated with increased antitumor immune cell infiltration and upregulation of immune regulatory and cellular metabolism pathways.
Conclusions:
The proposed TRV radiomics model provided effective predictive performance of pCR in NSCLC patients treated with neoadjuvant immunotherapy.
More Related Videos
04:04Endobronchial Ultrasound-guided Intratumoral Injection of Cisplatin for the Treatment of Isolated Mediastinal Recurrence of Lung Cancer
Published on: February 12, 2017
08:32Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
Published on: October 2, 2020