AUTHOR=Shen Leilei , Fu Hongchao , Tao Guangyu , Liu Xuemei , Yuan Zheng , Ye Xiaodan 

TITLE=Pre-Immunotherapy Contrast-Enhanced CT Texture-Based Classification: A Useful Approach to Non-Small Cell Lung Cancer Immunotherapy Efficacy Prediction

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.591106

DOI=10.3389/fonc.2021.591106

ISSN=2234-943X

ABSTRACT=Objective To investigate the utility of the pre-immunotherapy contrast-enhanced CT-based texture classification in predicting response to non-small cell lung cancer immunotherapy treatment.
Methods Sixty-three patients with 72 lesions received immunotherapy were enrolled in this study. We extracted textures that including histogram, absolute gradient, run-length matrix, gray-level co-occurrence matrix, autoregressive model and wavelet transform from pre-immunotherapy contrast-enhanced CT by using MaZda software. Three different methods, named Fisher coefficient, mutual information measure (MI) and minimization of classification error probability combined average correlation coefficients (POE+ACC), were performed to select ten optimal texture features set, respectively. The patients were divided into non-progressive disease (non-PD) and progressive disease (PD) groups. T-test or Mann-Whitney U test were performed to tested the differences in each texture features set between the above two groups. Each texture features set was analyzed by principal component analysis (PCA), linear discriminant analysis (LDA) and nonlinear discriminant analysis (NDA). The area under the curve (AUC) was used to quantify the predictive accuracy of the above three analysis models for each texture features set, and the sensitivity, specificity, accuracy, positive-predictive value (PPV) and negative-predictive value (NPV) were also calculated, respectively.
Results Among the three texture features sets, the texture parameters differences of Kurtosis（2.12±3.92 vs. 0.78±1.10，p=0.047）、"S(2,2)SumEntrp"（1.14±0.31 vs. 1.24±0.12，p=0.036）and "S(1,0)SumEntrp"（1.18±0.27 vs. 1.28±0.11，p=0.046）between non-PD and PD group. were statistically significant (all P<0.05). The classification result of texture features set selected by POE+ACC and analyzed by NDA was identified as the best model (AUC =0.812, 95% CI:0.706-0.919) with the sensitivity, specificity, accuracy, PPV and NPV were 88.2%, 76.3% , 81.9%, 76.9%, and 87.9%, respectively.
Conclusion Pre-immunotherapy contrast-enhanced CT-based texture provides a new method for clinical evaluation of the NSCLC immunotherapy efficacy prediction.