Evaluating treatment response to neoadjuvant chemoradiotherapy in rectal cancer using various MRI-based radiomics models

Abstract

Background To validate and compare various MRI-based radiomics models to evaluate treatment response to neoadjuvant chemoradiotherapy (nCRT) of rectal cancer. Methods A total of 80 patients with locally advanced rectal cancer (LARC) who underwent surgical resection after nCRT were enrolled retrospectively. Rectal MR images were scanned pre- and post-nCRT. The radiomics features were extracted from T2-weighted images, then reduced separately by least absolute shrinkage and selection operator (LASSO) and principal component analysis (PCA). Four classifiers of Logistic Regression, Random Forest (RF), Decision Tree and K-nearest neighbor (KNN) models were constructed to assess the tumor regression grade (TRG) and pathologic complete response (pCR), respectively. The diagnostic performances of models were determined with leave-one-out cross-validation by generating receiver operating characteristic curves and decision curve analysis. Results Three features related to the TRG and 11 features related to the pCR were obtained by LASSO. Top five principal components representing a cumulative contribution of 80% to overall features were selected by PCA. For TRG, the area under the curve (AUC) of RF model was 0.943 for LASSO and 0.930 for PCA, higher than other models (P < 0.05 for both). As for pCR, the AUCs of KNN for LASSO and PCA were 0.945 and 0.712, higher than other models (P < 0.05 for both). The DCA showed that LASSO algorithm was clinically superior to PCA. Conclusion MRI-based radiomics models demonstrated good performance for evaluating the treatment response of LARC after nCRT and LASSO algorithm yielded more clinical benefit.

A radiomics-based nomogram for preoperative T staging prediction of rectal cancer

“…Radiomics can extract large amounts of quantified features from medical imaging data to provide mineable highdimensional data. It deeply analyzes the clinicopathological information contained in large amounts of data [9,10] and has been applied to tumor staging [11][12][13], predicting treatment response [14][15][16][17], and assessing the efficacy after chemoradiotherapy [18][19][20] in rectal cancer patients. Although some studies have explored the application of radiomics in T staging of rectal cancer, most of these studies used radiomics features alone; few have incorporated the clinical factors with the radiomics features and lack preoperative experimental validation.…”

Analysis of MRI and CT-based radiomics features for personalized treatment in locally advanced rectal cancer and external validation of published radiomics models

“…All identified studies were performed on patients with LARC that were treated with nCRT followed by surgery with the aim of predicting tumour response using radiomics. 23 studies were excluded after full text review due to following reasons: 3 studies used contrast enhanced CT data that was not available in our dataset 21 , 45 , 46 , 4 studies used both pre and\or post treatment data 47 – 50 , 5 studies used pre-treatment multiparametric MRI (mpMRI) to develop a final signature with no standalone T2w MRI signature being reported 17 , 18 , 51 – 53 , 2 studies did not report any final signature 22 , 30 , 3 studies could not be reproduced as the radiomics workflow or feature definition was not clearly explained 25 , 54 , 55 , 1 study was excluded as the considered ROI was not the primarytumour 56 , 3 studies were excluded as authors reported failure of radiomics to predict the outcome of interest 57 – 59 , 2 studies were excluded as the reported signature was computed from feature maps, which are currently not supported by MIRP 28 , 60 . Finally, eleven studies were included for external validation analysis.…”

RadCloud—An Artificial Intelligence-Based Research Platform Integrating Machine Learning-Based Radiomics, Deep Learning, and Data Management

“…MR radiomics models with different ML classifiers (such as MLP, LR, SVM, DT, RF, and KNN, etc.) were developed for predicting tumor stages simplified as T(T1-T2) and N(N1-N2) stages [28], and tumor regression grades (TRGs) for evaluating the treatment response of LARC after neoadjuvant chemoradiotherapy (nCRT) of RC [29].…”