Assessment of Intratumoral and Peritumoral Computed Tomography Radiomics for Predicting Pathological Complete Response to Neoadjuvant Chemoradiation in Patients With Esophageal Squamous Cell Carcinoma

Abstract

Key Points Question Are peritumoral radiomics features extracted from pretreatment computed tomography images predictive of pathological complete response following neoadjuvant chemoradiation in patients with esophageal squamous cell carcinoma? Findings In this diagnostic study of 231 patients, the developed model integrating intratumoral and peritumoral radiomics features achieved improvement of predictive performance (area under the receiver operating characteristic curve, 0.852) compared with the conventionally constructed model merely using intratumoral radiomics features (area under the receiver operating characteristic curve, 0.730). Meaning Peritumoral radiomics may provide additional predictive value for treatment response estimation in esophageal squamous cell carcinoma and thus benefit individualized therapeutic strategies.

A Meta-Analysis for Using Radiomics to Predict Complete Pathological Response in Esophageal Cancer Patients Receiving Neoadjuvant Chemoradiation

“…Three articles were conducted by Beukinga et al (14)(15)(16), therefore we only chose one of these for further analysis. Two articles were conducted by Hu et al (17,18), therefore we selected only one of them for the subsequent analysis. As a result, seven articles were chosen for quantitative meta-analysis.…”

“…The second-order class includes the graylevel (GL) co-occurrence matrix, GL run-length matrix, GL size-zone matrix, GL distance-zone matrix, neighborhood gray tone difference matrix, and neighboring GL dependence matrix (8). We reviewed the radiomics feature type used and other types of features of the selected articles, and the results are provided in Table III (19), four studies used the first-order feature (17,(20)(21)(22), and five studies used the second-order feature (14,17,(21)(22)(23).…”

“…The details of the algorithms used in the selected studies are provided in Table IV. Of the selected studies, three used machine learning algorithms (LASSO and SVM) (14,17,21), while the others used traditional biostatistical methods (19,20,22,23).…”

Machine Learning and Radiomics Applications in Esophageal Cancers Using Non-Invasive Imaging Methods—A Critical Review of Literature

“…Most published studies ( n = 12) focused on the prediction of treatment response for patients receiving chemoradiotherapy or nCRT [ 83 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 ]. The ML algorithms achieved an AUC of 0.78–1.00.…”

“…Yang et al [ 102 ] developed three predictive models for treatment response after nCRT and noted that overfitting was a problem for small sample size studies. Hu et al [ 101 ] found that a combination of peritumoral radiomics features appeared to improve the predictive performance of intratumoral radiomics for pre-treatment prediction of pCR (AUC = 0.85, 95% CI, 0.75–0.95) for nCRT using CT radiomics features, with a cohort of 231 patients and external validation of the results. The same cohort of patients was used for the exploration of the transfer learning approach and the results showed that ResNet50-based deep learning features had the predictive ability for treatment response in esophageal SCC [ 83 ].…”