Deep Learning Model for Predicting the Pathological Complete Response to Neoadjuvant Chemoradiotherapy of Locally Advanced Rectal Cancer

Quantitative analysis of rectal cancer biopsies with the digital pathology segmentation algorithm QuantCRC associates with therapy response and recurrence

We examined whether QuantCRC, a digital pathology segmentation algorithm, on pre-therapy rectal cancer biopsies is associated with pathologic complete response (pCR) to neoadjuvant therapy, recurrence-free survival (RFS), and transcriptomic spatial profiling. QuantCRC was evaluated in an observational cohort of 288 pre-therapy biopsies and a separate validation cohort of 37 pre-therapy biopsies of rectal adenocarcinoma from patients undergoing neoadjuvant therapy. Associations between QuantCRC features and clinical outcomes, pCR, and RFS were analyzed using multivariable logistic regression and Cox proportional hazards modeling, respectively. QuantCRC variables were also correlated with transcriptomic digital spatial profiling of 37 pre-treatment biopsies of cT3N+ rectal cancer. QuantCRC-derived lymphocytes per mm2 of tumor epithelium (TILs) was significantly associated with pCR (multivariate OR 1.05, 95% CI 1.02-1.10, P=0.038). QuantCRC-derived TILs were significantly higher in pre-therapy biopsies with pCR (91.3 vs. 55.9 lymphocytes per mm2, P=0.004). The validation cohort confirmed that only QuantCRC-derived TILs in pre-therapy biopsies of rectal cancer were significantly associated with complete response to neoadjuvant therapy. QuantCRC %high tumor grade was independently associated with worse RFS (multivariate HR 1.27, 95% CI 1.09-1.47, P=0.002). Patients with ≥10.1% high tumor grade identified by QuantCRC had significantly reduced RFS (5-year RFS 69% vs 83%, log-rank p=0.007). Transcriptomic profiling identified high IL-6/JAK/STAT3 signaling within immune cells to be associated with worse RFS (adjusted P=0.01). Tumors with low IL-6/JAK/STAT3 expression within immune cells had significantly higher TILs compared to tumors with high expression (median 152 vs. 97 TILs per mm2, P=0.039). Biopsy-adapted QuantCRC in pre-therapy rectal cancer may be helpful in identifying patients who achieve pCR and are at risk for recurrence.

Response prediction for neoadjuvant treatment in locally advanced rectal cancer patients-improvement in decision-making: A systematic review

BACKGROUND

Predicting pathological complete response (pCR) from pre or post-treatment features could be significant in improving the process of making clinical decisions and providing a more personalized treatment approach for better treatment outcomes. However, the lack of external validation of predictive models, missing in several published articles, is a major issue that can potentially limit the reliability and applicability of predictive models in clinical settings. Therefore, this systematic review described different externally validated methods of predicting response to neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC) patients and how they could improve clinical decision-making.

METHOD

An extensive search for eligible articles was performed on PubMed, Cochrane, and Scopus between 2018 and 2023, using the keywords: (Response OR outcome) prediction AND (neoadjuvant OR chemoradiotherapy) treatment in 'locally advanced Rectal Cancer'.

INCLUSION CRITERIA

(i) Studies including patients diagnosed with LARC (T3/4 and N- or any T and N+) by pre-medical imaging and pathological examination or as stated by the author (ii) Standardized nCRT completed. (iii) Treatment with long or short course radiotherapy. (iv) Studies reporting on the prediction of response to nCRT with pathological complete response (pCR) as the primary outcome. (v) Studies reporting external validation results for response prediction. (vi) Regarding language restrictions, only articles in English were accepted.

EXCLUSION CRITERIA

(i) We excluded case report studies, conference abstracts, reviews, studies reporting patients with distant metastases at diagnosis. (ii) Studies reporting response prediction with only internally validated approaches.

DATA COLLECTION AND QUALITY ASSESSMENT

Three researchers (DC-D, FB, HT) independently reviewed and screened titles and abstracts of all articles retrieved after de-duplication. Possible disagreements were resolved through discussion among the three researchers. If necessary, three other researchers (LB, GC, MG) were consulted to make the final decision. The extraction of data was performed using the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) template and quality assessment was done using the Prediction model Risk Of Bias Assessment Tool (PROBAST).

RESULTS

A total of 4547 records were identified from the three databases. After excluding 392 duplicate results, 4155 records underwent title and abstract screening. Three thousand and eight hundred articles were excluded after title and abstract screening and 355 articles were retrieved. Out of the 355 retrieved articles, 51 studies were assessed for eligibility. Nineteen reports were then excluded due to lack of reports on external validation, while 4 were excluded due to lack of evaluation of pCR as the primary outcome. Only Twenty-eight articles were eligible and included in this systematic review. In terms of quality assessment, 89 % of the models had low concerns in the participants domain, while 11 % had an unclear rating. 96 % of the models were of low concern in both the predictors and outcome domains. The overall rating showed high applicability potential of the models with 82 % showing low concern, while 18 % were deemed unclear.

CONCLUSION

Most of the external validated techniques showed promising performances and the potential to be applied in clinical settings, which is a crucial step towards evidence-based medicine. However, more studies focused on the external validations of these models in larger cohorts is necessary to ensure that they can reliably predict outcomes in diverse populations.

Can Pretreatment MRI and Planning CT Radiomics Improve Prediction of Complete Pathological Response in Locally Advanced Rectal Cancer Following Neoadjuvant Treatment?

OBJECTIVE(S)

The treatment response to neoadjuvant chemoradiation (nCRT) differs largely in individuals treated for rectal cancer. In this study, we investigated the role of radiomics to predict the pathological response in locally advanced rectal cancers at different treatment time points: (1) before the start of any treatment using baseline T2-weighted MRI (T2W-MR) and (2) at the start of radiation treatment using planning CT.

METHODS

Patients on nCRT followed by surgery between June 2017 to December 2019 were included in the study. Histopathological tumour response grading (TRG) was used for classification, and gross tumour volume was defined by the radiation oncologists. Following resampling, 100 and 103 pyradiomic features were extracted from T2W-MR and planning CT images, respectively. Synthetic minority oversampling technique (SMOTE) was used to address class imbalance. Four machine learning classifiers built clinical, radiomic, and merged models. Model performances were evaluated on a held-out test dataset following 3-fold cross-validation using area under the receiver operator characteristic curves (AUC) with bootstrap 95% confidence intervals.

RESULTS

One hundred and fifty patients were included; 58/150 with TRG 1 were classified as complete responders, and rest were incomplete responders (IR). Clinical models performed better (AUC = 0.68) compared to radiomics models (AUC = 0.62). Overall, the clinical + T2W-MR model showed best performance (AUC = 0.72) in predicting the pathological response prior to therapy. Clinical + Planning CT-merged models could only achieve the highest AUC of 0.66.

CONCLUSION

Merging clinical and baseline T2W-MR radiomics enhances predicting pathological response in rectal cancer. Validation in larger cohorts is warranted, especially for watch and wait strategies.

Predicting the response to neoadjuvant chemoradiation for rectal cancer using nomograms based on MRI tumour regression grade

PURPOSE

This study aimed to develop nomograms that combine clinical factors and MRI tumour regression grade to predict the pathological response of mid-low locally advanced rectal cancer to neoadjuvant chemoradiotherapy.

METHODS

The retrospective study included 204 patients who underwent neoadjuvant chemoradiotherapy and surgery between January 2013 and December 2021. Based on pathological tumour regression grade, patients were categorized into four groups: complete pathological response (pCR, n=45), non-complete pathological response (non-pCR; n=159), good pathological response (pGR, n=119), and non-good pathological response (non-pGR, n=85). The patients were divided into a training set and a validation set in a 7:3 ratio. Based on the results of univariate and multivariate analyses in the training set, two nomograms were respectively constructed to predict complete and good pathological responses. Subsequently, these predictive models underwent validation in the independent validation set. The prognostic performances of the models were evaluated using the area under the curve (AUC).

RESULTS

The nomogram predicting complete pathological response incorporates tumour length, post-treatment mesorectal fascia involvement, white blood cell count, and MRI tumour regression grade. It yielded an AUC of 0.787 in the training set and 0.716 in the validation set, surpassing the performance of the model relying solely on MRI tumour regression grade (AUCs of 0.649 and 0.530, respectively). Similarly, the nomogram predicting good pathological response includes the distance of the tumour's lower border from the anal verge, post-treatment mesorectal fascia involvement, platelet/lymphocyte ratio, and MRI tumour regression grade. It achieved an AUC of 0.754 in the training set and 0.719 in the validation set, outperforming the model using MRI tumour regression grade alone (AUCs of 0.629 and 0.638, respectively).

CONCLUSIONS

Nomograms combining MRI tumour regression grade with clinical factors may be useful for predicting pathological response of mid-low locally advanced rectal cancer to neoadjuvant chemoradiotherapy. The proposed models could be applied in clinical practice after validation in large samples.

Artificial Intelligence in Colorectal Cancer: From Patient Screening over Tailoring Treatment Decisions to Identification of Novel Biomarkers

BACKGROUND

Artificial intelligence (AI) is increasingly entering and transforming not only medical research but also clinical practice. In the last 10 years, new AI methods have enabled computers to perform visual tasks, reaching high performance and thereby potentially supporting and even outperforming human experts. This is in particular relevant for colorectal cancer (CRC), which is the 3rd most common cancer type in general, as along the CRC patient journey many complex visual tasks need to be performed: from endoscopy over imaging to histopathology; the screening, diagnosis, and treatment of CRC involve visual image analysis tasks.

SUMMARY

In all these clinical areas, AI models have shown promising results by supporting physicians, improving accuracy, and providing new biological insights and biomarkers. By predicting prognostic and predictive biomarkers from routine images/slides, AI models could lead to an improved patient stratification for precision oncology approaches in the near future. Moreover, it is conceivable that AI models, in particular together with innovative techniques such as single-cell or spatial profiling, could help identify novel clinically as well as biologically meaningful biomarkers that could pave the way to new therapeutic approaches.

KEY MESSAGES

Here, we give a comprehensive overview of AI in colorectal cancer, describing and discussing these developments as well as the next steps which need to be taken to incorporate AI methods more broadly into the clinical care of CRC.

Digitally assessed lymphocyte infiltration in rectal cancer biopsies is associated with pathological response to neoadjuvant therapy

A frequently used treatment strategy in locally advanced rectal cancer (RC) is neoadjuvant therapy followed by surgery. Patients treated with neoadjuvant therapy achieve varying pathological response, and currently, predicting the degree of response is challenging. This study examined the association between digitally assessed histopathological features in the diagnostic biopsies and pathological response to neoadjuvant therapy, aiming to find potential predictive biomarkers. 50 patients with RC treated with neoadjuvant chemotherapy and/or radiotherapy followed by surgery were included. Deep learning-based digital algorithms were used to assess the epithelium tumor area percentage (ETP) based on H&E-stained slides, and to quantify the density of CD3+ and CD8+ lymphocytes, as well as the CD8+/CD3+ lymphocyte percentage, based on immunohistochemically stained slides, from the diagnostic tumor biopsies. Pathological response was assessed according to the Mandard method. A good pathological response was defined as tumor regression grade (TRG) 1-2, and a complete pathological response was defined as Mandard TRG 1. Associations between the ETP and lymphocyte densities in the diagnostic biopsies and the pathological response were examined. The density of CD8+ lymphocytes, and the CD8+/CD3+ lymphocyte percentage, were associated with both good and complete response to neoadjuvant therapy, while the density of CD3+ lymphocytes was associated with complete response. The ETP did not correlate with response to neoadjuvant therapy. It is well-known that infiltration of lymphocytes in colorectal cancer is a prognostic biomarker. However, assessment of CD8+ and CD3+ lymphocytes in the diagnostic tumor biopsies of patients with RC may also be useful in predicting response to neoadjuvant therapy.

Amino Acid Profiles in the Biological Fluids and Tumor Tissue of CRC Patients

Amino acids are the building blocks of proteins and essential players in pathways such as the citric acid and urea cycle, purine and pyrimidine biosynthesis, and redox cell signaling. Therefore, it is unsurprising that these molecules have a significant role in cancer metabolism and its metabolic plasticity. As one of the most prevalent malign diseases, colorectal cancer needs biomarkers for its early detection, prognostic, and prediction of response to therapy. However, the available biomarkers for this disease must be more powerful and present several drawbacks, such as high costs and complex laboratory procedures. Metabolomics has gathered substantial attention in the past two decades as a screening platform to study new metabolites, partly due to the development of techniques, such as mass spectrometry or liquid chromatography, which have become standard practice in diagnostic procedures for other diseases. Extensive metabolomic studies have been performed in colorectal cancer (CRC) patients in the past years, and several exciting results concerning amino acid metabolism have been found. This review aims to gather and present findings concerning alterations in the amino acid plasma pool of colorectal cancer patients.

Validated Pretreatment Prediction Models for Response to Neoadjuvant Therapy in Patients with Rectal Cancer: A Systematic Review and Critical Appraisal

Pretreatment response prediction is crucial to select those patients with rectal cancer who will benefit from organ preservation strategies following (intensified) neoadjuvant therapy and to avoid unnecessary toxicity in those who will not. The combination of individual predictors in multivariable prediction models might improve predictive accuracy. The aim of this systematic review was to summarize and critically appraise validated pretreatment prediction models (other than radiomics-based models or image-based deep learning models) for response to neoadjuvant therapy in patients with rectal cancer and provide evidence-based recommendations for future research. MEDLINE via Ovid, Embase.com, and Scopus were searched for eligible studies published up to November 2022. A total of 5006 studies were screened and 16 were included for data extraction and risk of bias assessment using Prediction model Risk Of Bias Assessment Tool (PROBAST). All selected models were unique and grouped into five predictor categories: clinical, combined, genetics, metabolites, and pathology. Studies generally included patients with intermediate or advanced tumor stages who were treated with neoadjuvant chemoradiotherapy. Evaluated outcomes were pathological complete response and pathological tumor response. All studies were considered to have a high risk of bias and none of the models were externally validated in an independent study. Discriminative performances, estimated with the area under the curve (AUC), ranged per predictor category from 0.60 to 0.70 (clinical), 0.78 to 0.81 (combined), 0.66 to 0.91 (genetics), 0.54 to 0.80 (metabolites), and 0.71 to 0.91 (pathology). Model calibration outcomes were reported in five studies. Two collagen feature-based models showed the best predictive performance (AUCs 0.83-0.91 and good calibration). In conclusion, some pretreatment models for response prediction in rectal cancer show encouraging predictive potential but, given the high risk of bias in these studies, their value should be evaluated in future, well-designed studies.

Total neoadjuvant therapy for locally advanced rectal cancer: a narrative review

Locally advanced rectal cancer has traditionally been treated with chemoradiotherapy (CRT) followed by surgery and adjuvant chemotherapy. However, a new strategy, total neoadjuvant therapy, involves the administration of CRT and neoadjuvant chemotherapy with the aim of eradicating micrometastases earlier and achieving greater control of the disease. The use of total neoadjuvant therapy has shown higher rates of pathological complete response and resectability compared with CRT, including improved survival. Nevertheless, distant relapse is the main cause of morbidity and mortality in locally advanced rectal cancer. To address this, new biomarkers are being developed to predict disease response.

Role of artificial intelligence in risk prediction, prognostication, and therapy response assessment in colorectal cancer: current state and future directions

Artificial Intelligence (AI) is a branch of computer science that utilizes optimization, probabilistic and statistical approaches to analyze and make predictions based on a vast amount of data. In recent years, AI has revolutionized the field of oncology and spearheaded novel approaches in the management of various cancers, including colorectal cancer (CRC). Notably, the applications of AI to diagnose, prognosticate, and predict response to therapy in CRC, is gaining traction and proving to be promising. There have also been several advancements in AI technologies to help predict metastases in CRC and in Computer-Aided Detection (CAD) Systems to improve miss rates for colorectal neoplasia. This article provides a comprehensive review of the role of AI in predicting risk, prognosis, and response to therapies among patients with CRC.

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.