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

Abstract

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.

Studying local tumour heterogeneity on MRI and FDG-PET/CT to predict response to neoadjuvant chemoradiotherapy in rectal cancer

“…In rectal cancer, there are multiple previous reports correlating image texture features with response to neoadjuvant treatment [7,[13][14][15][16][17][18][19][20][35][36][37][38][39][40][41][42][43][44][45][46][47]. Some of these studies focused on relatively simple first-and second-order features derived from histogram analysis and grey-level co-occurrence matrices (GLCM) [7,13,40,41,45], while others assessed advanced features by applying more sophisticated radiomics modelling [14-20, 37-39, 42-44, 46-49].…”

Treatment response prediction using MRI‐based pre‐, post‐, and delta‐radiomic features and machine learning algorithms in colorectal cancer

“…Patients with pathologic complete response, with no viable cancer cells, with single or small group of cancer cells, with residual cancer outgrown by fibrosis, with fibrosis outgrown by residual cancer, and finally with fibrotic mass without tumor cells were included in grade 0 to grade 4, respectively 41–43 . Subsequently, the patients were divided into two classes: responders (Grade 0 or Grade 1) and non‐responders (Grade 2, Grade 3 or Grade 4) 37,38,44 …”

“…The training and validation datasets were acquired 2 weeks before and 4 weeks after nCRT using 3T (Tesla‐Trio, Siemens Healthcare, Germany) and 1.5 T (Philips Healthcare, Best, the Netherlands) MRI systems, respectively. T2W MR images were acquired using a fast spine echo sequence on a 32‐channel pelvic phased array coil, with repetition time/echo (msec) 4800/97, 3 number of excitations (NEX), 256 × 248 matrix size, phase resolution of 70, 0.8 mm interslice gap and 35 cm field‐of‐view 37,38 …”

“…T2W MR images were acquired using a fast spine echo sequence on a 32-channel pelvic phased array coil, with repetition time/echo (msec) 4800/97, 3 number of excitations (NEX), 256 × 248 matrix size, phase resolution of 70, 0.8 mm interslice gap and 35 cm field-of-view. 37,38 2.B. Image processing…”

“…[41][42][43] Subsequently, the patients were divided into two classes: responders (Grade 0 or Grade 1) and non-responders (Grade 2, Grade 3 or Grade 4). 37,38,44…”