Morphologic predictors of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer

Radiomics Approaches for the Prediction of Pathological Complete Response after Neoadjuvant Treatment in Locally Advanced Rectal Cancer: Ready for Prime Time?

In recent years, neoadjuvant therapy of locally advanced rectal cancer has seen tremendous modifications. Adding neoadjuvant chemotherapy before or after chemoradiotherapy significantly increases loco-regional disease-free survival, negative surgical margin rates, and complete response rates. The higher complete rate is particularly clinically meaningful given the possibility of organ preservation in this specific sub-population, without compromising overall survival. However, all locally advanced rectal cancer most likely does not benefit from total neoadjuvant therapy (TNT), but experiences higher toxicity rates. Diagnosis of complete response after neoadjuvant therapy is a real challenge, with a risk of false negatives and possible under-treatment. These new therapeutic approaches thus raise the need for better selection tools, enabling a personalized therapeutic approach for each patient. These tools mostly focus on the prediction of the pathological complete response given the clinical impact. In this article, we review the place of different biomarkers (clinical, biological, genomics, transcriptomics, proteomics, and radiomics) as well as their clinical implementation and discuss the most recent trends for future steps in prediction modeling in patients with locally advanced rectal cancer.

Three perspectives: the approach to neoadjuvant treatment of rectal cancer according to medical oncologists, radiation oncologists, and surgeons

Background: Two treatment options considered for radiotherapy are short-course radiotherapy and immediate surgery, or chemoradiation with 5-Fluorouracil based chemotherapy and delayed surgery. Aim of the study: Evaluate the real-life treatment approaches of medical, radiation, and surgical oncologists, to neoadjuvant treatment of rectal cancers. Material and methods: An online survey was established via Google Forms. The survey was taken voluntarily by medical oncologists, radiation oncologists, surgical oncologists, and general surgeons. Results: Of those who participated, 183 were medical oncologists, 36 were radiotherapists, and 36 were surgeons. Most of the study population preferred long-course radiation therapy and chemotherapy (85%). Meanwhile, two-thirds of the participants preferred chemotherapy prior to operating. The most frequent chemotherapy cycles for the pre-operative setting were ‘three’ and ‘four-or-more’ (27.8% and 25.1%, respectively). Medical oncologists had a significantly higher tendency to offer chemotherapy between radiation therapy and surgery compared to the other groups. Optimal time of surgery was different between groups, but there was no difference among groups between surgery and the ‘watch & wait’ strategy. Neoadjuvant chemotherapy regimens were significantly different between groups. Conclusions: We found that the new pre-operative chemotherapy regimen with short-course radiotherapy was slowly adopted into current practice. Also, medical oncologists tended to prefer pre-operative chemotherapy in comparison to the other groups.

Predicting Response to Total Neoadjuvant Treatment (TNT) in Locally Advanced Rectal Cancer Based on Multiparametric Magnetic Resonance Imaging: A Retrospective Study

Purpose

To investigate the potential value of magnetic resonance imaging (MRI) in predicting response relevance to total neoadjuvant treatment (TNT) in locally advanced rectal cancer.

Methods

We analyzed MRI of 71 patients underwent TNT from 2015 to 2017 retrospectively. We categorized the response of TNT as CR (complete response) vs non-CR, and high vs moderate vs low sensitivity. Logistic regression analysis was used to identify the best predictors of response. Diagnostic performance was assessed using receiver operating characteristic curve analysis.

Results

Post-ICT (induction chemotherapy) ∆TL (tumor length), post-CRT (concurrent chemoradiotherapy) ∆LNN (the numbers of lymph node metastases), post-CCT (consolidation chemotherapy) ∆S_DWI (maximum cross-sectional area of tumor on diffusion-weighted imaging), post-CCT ADC_T (the mean apparent diffusion coefficient values of tumor) and post-CCT ∆LNV (volume of lymph node) were the best CR predictors. Post-ICT ∆TL, post-CRT EMVI (extramural vascular invasion) and post-CCT ∆S_T2 (S on T2-weight) were the best significant factors for high sensitivity.

Conclusion

Post-ICT ∆TL may be an early predictor of CR and high sensitivity to TNT. Dynamic analysis based on MRI between baseline and post-CCT could provide the most valuable prediction of CR. The grouping modality of CR vs non-CR may be more suitable for treatment response prediction than high vs moderate vs low sensitivity.

Association Between Pathological Complete Response and Tumor Location in Patients with Rectal Cancer After Neoadjuvant Chemoradiotherapy, a Prospective Cohort Study

Background: Colorectal cancers are the third common malignancies after lung and breast neoplasms. Some contributing factors for pathological complete response (pCR) to neoadjuvant therapy of rectal cancer have been defined. Despite various studies in this era, there are few studies on the location of tumors. Objectives: Regarding the high prevalence of colorectal cancer in Iran and the importance of neoadjuvant chemoradiation for survival and morbidity, this study was carried out to determine the association between pathologic complete response and tumor location in patients with rectal cancer after neoadjuvant chemoradiotherapy. Methods: In this prospective cohort, 100 cases with rectal adenocarcinoma from 2017 to 2019 were enrolled. Distance between anal verge and tumor was measured by clinical examination, colonoscopy, endo-sonography, and MRI. Tumors were defined as distal (less than 5 cm from the anal verge) and none distal (more than 5 cm from the anal verge). Another subdivision was inferior (0 - 4.99 cm), middle (5 - 9.99 cm), and superior (10 - 15 cm). The pathological response was compared across the groups. Results: In this study, the pCR was seen in 30%. In univariate analysis body mass index (BMI), grade, N-stage, and distance from anal verge were related to pCR. In cases with BMI over 25 kg/m2 and in tumors with low to medium grade N0/N1, and distance less than 5 cm from the anal verge (low lying tumors) the pCR to neoadjuvant treatment was higher. In multivariate analysis tumor grade, N stage, and distance from anal verge were still related to pCR. Conclusions: According to the obtained results in this study, there may be some association between rectal tumor location and pathologic complete response.

MRI Evaluation of Complete Response of Locally Advanced Rectal Cancer After Neoadjuvant Therapy: Current Status and Future Trends

Complete tumor response can be achieved in a certain proportion of patients with locally advanced rectal cancer, who achieve maximal response to neoadjuvant therapy (NAT). For these patients, a watch-and-wait (WW) or nonsurgical strategy has been proposed and is becoming widely practiced in order to avoid unnecessary surgical complications. Therefore, a non-invasive, reliable diagnostic tool for accurately evaluating complete tumor response is needed. Magnetic resonance imaging (MRI) plays a crucial role in both primary staging and restaging tumor response to NAT in rectal cancer without relying on resected specimen. In recent years, numerous efforts have been made to research the value of MRI in predicting and evaluating complete response in rectal cancer. Current MRI evaluation is mainly based on morphological and functional images. Morphologic MRI yields high soft tissue resolution, multiplanar images, and provides detailed depictions of rectal cancer and its surrounding structures. Functional MRI may help to distinguish residual tumor from fibrosis, therefore improving the diagnostic performance of morphologic MRI in identifying complete tumor response. Both morphologic and functional MRI have several promising parameters that may help accurately evaluate and/or predict complete response of rectal cancer. However, these parameters still have limitations and the results remain inconsistent. Recent development of new techniques, such as textural analysis, radiomics analysis and deep learning, demonstrate great potential based on MRI-derived parameters. This article aimed to review and help better understand the strengths, limitations, and future trends of these MRI-derived methods in evaluating complete response in rectal cancer.

MRI radiomics in the prediction of therapeutic response to neoadjuvant therapy for locoregionally advanced rectal cancer: a systematic review

Introduction: The standard of care for locoregionally advanced rectal cancer is neoadjuvant therapy (NA CRT) prior to surgery, of which 10-30% experience a complete pathologic response (pCR). There has been interest in using imaging features, also known as radiomics features, to predict pCR and potentially avoid surgery. This systematic review aims to describe the spectrum of MRI studies examining high-performing radiomic features that predict NA CRT response.Areas covered: This article reviews the use of pre-therapy MRI in predicting NA CRT response for patients with locoregionally advanced rectal cancer (T3/T4 and/or N1+). The primary outcome was to identify MRI radiomic studies; secondary outcomes included the power and the frequency of use of radiomic features.Expert opinion: Advanced models incorporating multiple radiomics categories appear to be the most promising. However, there is a need for standardization across studies with regards to; the definition of NA CRT response, imaging protocols, and radiomics features incorporated. Further studies are needed to validate current radiomics models and to fully ascertain the value of MRI radiomics in the response prediction for locoregionally advanced rectal cancer.

3.0 T MRI IVIM-DWI for predicting the efficacy of neoadjuvant chemoradiation for locally advanced rectal cancer

Purpose

The purpose of this study was to determine the diagnostic performance of intravoxel incoherent motion (IVIM) on assessing response to neoadjuvant chemoradiation (nCRT) in patients with Locally Advanced Rectal Cancer (LARC).

Methods

50 patients with rectal cancer who underwent magnetic resonance (MR) imaging before and after nCRT, the values of pre-nCRT and post-nCRT IVIM-DWI parameters apparent diffusion coefficient (ADC), diffusion coefficient (D), false diffusion coefficient (D*), and perfusion fraction (f), together with the percentage changes (∆% parametric value) induced by nCRT were calculated. According to the patient's response to nCRT, the patients were divided into pathological complete response (pCR) and non-pCR groups, Good Response (GR) group and Poor Response (PR) group, and the above values were compared between different groups. Univariate and multiple logistic regression analysis were done to investigate the relation between different parameters and patient nCRT. Draw ROC curve according to sensitivity and specificity, and compare its diagnostic efficacy.

Results

There were no significant differences in the baseline data of 50 patients. After nCRT, the ADC and D values for LARC increased significantly (all p < 0.05). The pCR group (n = 9) had higher preD*, pref, postD*, ∆%ADC and ∆%D values than the non-pCR group (n = 41) (all p < 0.05). The GR group (n = 17) exhibited higher post D, ∆%ADC and ∆%D values than the PR group (n = 33) (all p < 0.05). From the results of Logistic regression analysis found that ∆%ADC and ∆%D were significantly correlated with patients' response to nCRT. Based on ROC analysis, ∆%D had a higher area under the curve value than ∆%ADC (p = 0.009) in discriminating the pCR from non-pCR groups.

Conclusions

IVIM-DWI technology may be helpful in identifying the pCR and GR patients to nCRT for LARC.

Machine learning for predicting pathological complete response in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy

For patients with locally advanced rectal cancer (LARC), achieving a pathological complete response (pCR) after neoadjuvant chemoradiotherapy (CRT) provides them with the optimal prognosis. However, no reliable prediction model is presently available. We evaluated the performance of an artificial neural network (ANN) model in pCR prediction in patients with LARC. Predictive accuracy was compared between the ANN, k-nearest neighbor (KNN), support vector machine (SVM), naïve Bayes classifier (NBC), and multiple logistic regression (MLR) models. Data from two hundred seventy patients with LARC were used to compare the efficacy of the forecasting models. We trained the model with an estimation data set and evaluated model performance with a validation data set. The ANN model significantly outperformed the KNN, SVM, NBC, and MLR models in pCR prediction. Our results revealed that the post-CRT carcinoembryonic antigen is the most influential pCR predictor, followed by intervals between CRT and surgery, chemotherapy regimens, clinical nodal stage, and clinical tumor stage. The ANN model was a more accurate pCR predictor than other conventional prediction models. The predictors of pCR can be used to identify which patients with LARC can benefit from watch-and-wait approaches.

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.

Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI

PURPOSE

To predict the neoadjuvant chemoradiation therapy (CRT) response in patients with locally advanced rectal cancer (LARC) using radiomics and deep learning based on pre-treatment MRI and a mid-radiation follow-up MRI taken 3-4 weeks after the start of CRT.

METHODS

A total of 51 patients were included, 45 with pre-treatment, 41 with mid-radiation therapy (RT), and 35 with both MRI sets. The multi-parametric MRI protocol included T2, diffusion weighted imaging (DWI) with b-values of 0 and 800 s/mm², and dynamic-contrast-enhanced (DCE) MRI. After completing CRT and surgery, the specimen was examined to determine the pathological response based on the tumor regression grade. The tumor ROI was manually drawn on the post-contrast image and mapped to other sequences. The total tumor volume and mean apparent diffusion coefficient (ADC) were measured. Radiomics using GLCM texture and histogram parameters, and deep learning using a convolutional neural network (CNN), were performed to differentiate pathologic complete response (pCR) vs. non-pCR, and good response (GR) vs. non-GR.

RESULTS

Tumor volume decreased and ADC increased significantly in the mid-RT MRI compared to the pre-treatment MRI. For predicting pCR vs. non-pCR, combining ROI and radiomics features achieved an AUC of 0.80 for pre-treatment, 0.82 for mid-RT, and 0.86 for both MRI together. For predicting GR vs. non-GR, the AUC was 0.91 for pre-treatment, 0.92 for mid-RT, and 0.93 for both MRI together. In deep learning using CNN, combining pre-treatment and mid-RT MRI achieved a higher accuracy compared to using either dataset alone, with AUC of 0.83 for predicting pCR vs. non-pCR.

CONCLUSION

Radiomics based on pre-treatment and early follow-up multi-parametric MRI in LARC patients receiving CRT could extract comprehensive quantitative information to predict final pathologic response.