RESUMO
PURPOSE: Neoadjuvant chemoradiotherapy (nCRT) has become the standard treatment for locally advanced rectal cancer (LARC). However, the accuracy of traditional clinical indicators in predicting tumor response is poor. Recently, radiomics based on magnetic resonance imaging (MRI) has been regarded as a promising noninvasive assessment method. The present study was conducted to develop a model to predict the pathological response by analyzing the quantitative features of MRI and clinical risk factors, which might predict the therapeutic effects in patients with LARC as accurately as possible before treatment. PATIENTS AND METHODS: A total of 82 patients with LARC were enrolled as the training cohort and internal validation cohort. The pre-CRT MRI after pretreatment was acquired to extract texture features, which was finally selected through the minimum redundancy maximum relevance (mRMR) algorithm. A support vector machine (SVM) was used as a classifier to classify different tumor responses. A joint radiomics model combined with clinical risk factors was then developed and evaluated by receiver operating characteristic (ROC) curves. External validation was performed with 107 patients from another center to evaluate the applicability of the model. RESULTS: Twenty top image texture features were extracted from 6192 extracted-radiomic features. The radiomics model based on high-spatial-resolution T2-weighted imaging (HR-T2WI) and contrast-enhanced T1-weighted imaging (T1+C) demonstrated an area under the curve (AUC) of 0.8910 (0.8114-0.9706) and 0.8938 (0.8084-0.9792), respectively. The AUC value rose to 0.9371 (0.8751-0.9997) and 0.9113 (0.8449-0.9776), respectively, when the circumferential resection margin (CRM) and carbohydrate antigen 19-9 (CA19-9) levels were incorporated. Clinical usefulness was confirmed in an external validation cohort as well (AUC, 0.6413 and 0.6818). CONCLUSION: Our study indicated that the joint radiomics prediction model combined with clinical risk factors showed good predictive ability regarding the treatment response of tumors as accurately as possible before treatment.
RESUMO
PURPOSE: To investigate whether the apparent diffusion coefficient (ADC), intravoxel incoherent motion (IVIM), and stretched exponential model (SEM) based on histogram analyses derived from the whole-tumor volume combined with prognostic factors can be used to assess the response to chemotherapy and radiation therapy (CRT) in locally advanced rectal cancer (LARC). MATERIALS AND METHODS: This study included 60 patients with LARC who underwent diffusion-weighted imaging with 9b values (0-1000s/mm2) before CRT. Histograms derived from the whole-tumor volume were used to obtain the ADC, IVIM (Dslow, Dfast, and f), and SEM parameters (distributed diffusion coefficient (DDC) and α). The histogram metrics and prognostic factors before CRT were compared between pathological complete response (pCR) and non-pCR patients. The receiver operating characteristic (ROC) and the area under the ROC curve (AUC) were generated to analyze the histogram metrics and prognostic factors. RESULTS: A significant difference was only found in the tumor volume between the pCR and non-pCR groups (p = 0.033, AUC = 0.740). The ADC mean, DDC median, and most of the histogram metrics were significantly lower in the pCR group than the non-pCR group (p = 0.000-0.025), and AUC was highest for the ADC mean (0.890). Only the Dslow median differed significantly between the two groups (p = 0.023, AUC = 0.721). However, the Dfast, f, and α histogram metrics did not differ significantly between the pCR and non-pCR groups. The AUC for the ADC mean combined with the tumor volume was 0.908, with a sensitivity of 100% and specificity of 81%. The inter-observer agreements were good or excellent for the ADC and SEM histogram parameters but generally fair for IVIM. CONCLUSION: The whole-tumor ADC mean combined with the tumor volume was highly accurate for predicting pCR. The IVIM models were inferior to ADC and SEM at predicting pCR.