Genomic predictor of complete response after chemoradiotherapy in rectal cancer

Intratumoral HLA-DR-/CD33+/CD11b+ Myeloid-Derived Suppressor Cells Predict Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer

Capecitabine-based neoadjuvant chemoradiation therapy (nCRT) is currently the mainstay of treatment for locally advanced rectal cancer (LARC), prior to surgical tumor removal. While response to this treatment is partial, it carries significant risk of side effects. As of today, there is no accepted model to predict tumor response, and allow for patient stratification. The level of circulating Myeloid-derived suppressor cells (MDSCs), a subpopulation of early myeloid cells (EMCs), has been shown to correlate with prognosis and response to therapy in advanced colon cancer, but their role in LARC is not clear. We sought to study the effect of intratumoral and circulating levels of different EMCs subpopulations including MDSCs on response to nCRT. We analyzed tumor, normal mucosa, and peripheral blood samples from 25 LARC patients for their different EMCs subpopulation before and after nCRT, and correlated them with degree of pathologic response, as determined postoperatively. In addition, we compared LARC patient to 10 healthy donors and 6 metastatic patients. CD33⁺HLA-DR⁻CD16⁻CD11b⁺EMCs in the circulation of LARC patients were found to inhibit T-cell activation. Furthermore, elevated levels of CD33⁺HLA-DR⁻ myeloid cells were found in the tumor relative to normal mucosa, but not in the circulation when compared to healthy subjects. Moreover, intratumoral, but not circulating levels of MDSCs correlated with clinical stage and response to therapy in patients treated with nCRT, with high levels of MDSCs significantly predicting poor response to nCRT. Importantly, therapy by itself, had significant differential effects on MDSC levels, leading to increased circulating MDSCs, concomitantly with decreasing intratumoral MDSCs. Our results suggest that high levels of intratumoral, but not circulating MDSCs may confer drug resistance due to immunomodulatory effects, and serve as a biomarker for patient stratification and decision-making prior to nCRT.

Prediction of Response to Neoadjuvant Chemoradiotherapy by MRI-Based Machine Learning Texture Analysis in Rectal Cancer Patients

INTRODUCTION

Neoadjuvant chemoradiotherapy (nCRT) followed by surgical resection is the standard treatment for locally advanced rectal cancer (LARC). Radiomics can be used as noninvasive biomarker for prediction of response to therapy. The main aim of this study was to evaluate the association of MRI texture features of LARC with nCRT response and the effect of Laplacian of Gaussian (LoG) filter and feature selection algorithm in prediction process improvement.

METHODS

All patients underwent MRI with a 3T clinical scanner, 1 week before nCRT. For each patient, intensity, shape, and texture-based features were derived from MRI images with LoG filter using the IBEX software and without preprocessing. We identified responder from a non-responder group using 9 machine learning classifiers. Then, the effect of preprocessing LoG filters with 0.5, 1 and 1.5 value on these classification algorithms' performance was investigated. Eventually, classification algorithm's results were compared in different feature selection methods.

RESULT

Sixty-seven patients with LARC were included in the study. Patients' nCRT responses included 11 patients with Grade 0, 19 with Grade 1, 26 with Grade 2, and 11 with Grade 3 according to AJCC/CAP pathologic grading. In MR Images which were not preprocessed, the best performance was for Ada boost classifier (AUC = 74.8) with T2W MR Images. In T1W MR Images, the best performance was for aba boost classifier (AUC = 78.1) with a σ = 1 preprocessing LoG filter. In T2W MR Images, the best performance was for naive Bayesian network classifier (AUC = 85.1) with a σ = 0.5 preprocessing LoG filter. Also, performance of machine learning models with CfsSubsetEval (CF SUB E) feature selection algorithm was better than others.

CONCLUSION

Machine learning can be used as a response predictor model in LARC patients, but its performance should be improved. A preprocessing LoG filter can improve the machine learning methods performance and at the end, the effect of feature selection algorithm on model's performance is clear.