Predicting treatment response to neoadjuvant chemoradiotherapy in local advanced rectal cancer by biopsy digital pathology image features.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhang F
PROVIDER: S-EPMC7403709 | biostudies-literature | 2020 Jun
REPOSITORIES: biostudies-literature
Publications
Predicting treatment response to neoadjuvant chemoradiotherapy in local advanced rectal cancer by biopsy digital pathology image features.
Zhang Fang F Yao Su S Li Zhi Z Liang Changhong C Zhao Ke K Huang Yanqi Y Gao Ying Y Qu Jinrong J Li Zhenhui Z Liu Zaiyi Z
Clinical and translational medicine 20200628 2
Quantitative features extracted from biopsy digital pathology images can provide predictive information for neoadjuvant chemoradiotherapy (nCRT) in local advanced rectal cancer (LARC) Machine learning technologies are applied to build the digital-pathology-based pathology signature The pathology signature is an independent predictor of treatment response to nCRT in LARC. ...[more]
Similar Datasets
Project description:ObjectiveTo evaluate the predictive value of the apparent diffusion coefficient (ADC) for pathologic complete response (pCR) to neoadjuvant chemoradiotherapy (NCRT) in locally advanced rectal cancer.MethodsA total of 265 patients with rectal adenocarcinoma, whole Diffusion-Weighted MRI (DWI-MRI) images, clinically stage II to III (cT3-4 and/or cN+) and treated with NCRT followed by TME were screened. Fifty patients with pCR and another 50 patients without pCR with similar clinical charcacters and treatment regimens were selected for statistical analysis. All the patients' pre-CRT and post-CRT average ADC values were calculated from the coefficient maps created by DWI-MRI and recorded independently. The difference in the ADC values between the pCR and non-pCR was analyzed by the Mann-Whitney U test. The cut-off ADC value of the receiver operating characteristic (ROC) curve with pCR was then established.ResultsThe mean pre- and post-ADC values in all patients, and in pCR patients and non-pCR patients were 0.879±0.06 and 1.383±0.11, 0.859±0.04 and 1.440±0.10, 0.899±0.07 and 1.325±0.09 (×10(-3) mm(2)/s), respectively. The difference between the pre- and post-ADC values in all patients, pCR patients, and non-pCR patients were considered to be statistically significant. The pre-ADC value was significantly lower in the pCR patients than in the non-pCR patients (p = 0.003), whereas the post-ADC values were significantly higher in the pCR patients than in the non-pCR patients. The percentage increase of the ADC value (?ADC%) in the pCR and non-pCR patients were 68% and 48% respectively (p<0.001). The ROC curves of the cut-off value of the pre-CRT patient ADC value was 0.866×10(-3) mm(2)/s. The AUC, sensitivity, specificity, PPV, NPV, and accuracy of diagnosing pCR were 0.670 (95% CI 0.563-0.777), 0.600, 0.640, 60%, 60%, and 60%, respectively. The cut-off value of ?ADC% was 58%. The corresponding AUC, sensitivity, specificity, PPV, NPV, and accuracy of diagnosing pCR were 0.856 (95% CI 0.783-0.930), 0.800, 0.760, 76.9%, 79.2%, and 78%, respectively.ConclusionsDWI-MRI technology can be efficient for predicting pCR for LARC after NCRT. Although the mean pre-CRT ADC value and the ?ADC% are moderate predictors for pCR, the latter would be more accurate.
| S-EPMC4839695 | biostudies-literature
Project description:The development of deep learning (DL) models to predict the consensus molecular subtypes (CMS) from histopathology images (imCMS) is a promising and cost-effective strategy to support patient stratification. Here, we investigate whether imCMS calls generated from whole slide histopathology images (WSIs) of rectal cancer (RC) pre-treatment biopsies are associated with pathological complete response (pCR) to neoadjuvant long course chemoradiotherapy (LCRT) with single agent fluoropyrimidine. DL models were trained to classify WSIs of colorectal cancers stained with hematoxylin and eosin into one of the four CMS classes using a multi-centric dataset of resection and biopsy specimens (n = 1057 WSIs) with paired transcriptional data. Classifiers were tested on a held out RC biopsy cohort (ARISTOTLE) and correlated with pCR to LCRT in an independent dataset merging two RC cohorts (ARISTOTLE, n = 114 and SALZBURG, n = 55 patients). DL models predicted CMS with high classification performance in multiple comparative analyses. In the independent cohorts (ARISTOTLE, SALZBURG), cases with WSIs classified as imCMS1 had a significantly higher likelihood of achieving pCR (OR = 2.69, 95% CI 1.01-7.17, p = 0.048). Conversely, imCMS4 was associated with lack of pCR (OR = 0.25, 95% CI 0.07-0.88, p = 0.031). Classification maps demonstrated pathologist-interpretable associations with high stromal content in imCMS4 cases, associated with poor outcome. No significant association was found in imCMS2 or imCMS3. imCMS classification of pre-treatment biopsies is a fast and inexpensive solution to identify patient groups that could benefit from neoadjuvant LCRT. The significant associations between imCMS1/imCMS4 with pCR suggest the existence of predictive morphological features that could enhance standard pathological assessment.
| S-EPMC11003957 | biostudies-literature
Project description:ImportancePreviously, it was shown in patients with low rectal cancer that a short-axis (SA) lateral node size of 7 mm or greater on primary magnetic resonance imaging (MRI) resulted in a high lateral local recurrence (LLR) rate after chemoradiotherapy or radiotherapy ([C]RT) with total mesorectal excision (TME) and that this risk was lowered by a lateral lymph node dissection (LLND). The role of restaging MRI after (C)RT with regard to LLR risk and which specific patients might benefit from an LLND is not fully understood.ObjectiveTo determine the factors on primary and restaging MRI that are associated with LLR in low rectal cancer after (C)RT and to formulate specific guidelines on which patients might benefit from an LLND.Design, setting, and participantsIn this retrospective, multicenter, pooled cohort study, patients who underwent surgery for cT3 or cT4 low rectal cancer with a curative intent from 12 centers in 7 countries from January 2009 to December 2013 were included. All patients' MRIs were rereviewed according to a standardized protocol, with specific attention to lateral nodal features. The original cohort included 1216 patients. For this study, patients who underwent (C)RT and had a restaging MRI were selected, leaving 741 for analyses across 10 institutions, including 651 who underwent (C)RT with TME and 90 who underwent (C)RT with TME and LLND.Main outcomes and measuresThe main purpose was to identify the factors on primary and restaging MRI associated with LLR after (C)RT with TME. Whether high-risk patients might benefit in terms of LLR reduction from an LLND was also studied.ResultsOf the 741 included patients, 480 (64.8%) were male, and the mean (SD) age was 60.4 (12.0) years. An SA lateral node size of 7 mm or greater on primary MRI resulted in a 5-year LLR rate of 17.9% after (C)RT with TME. At 3 years, there were no LLRs in 28 patients (29.2%) with lateral nodes that were 4 mm or less on restaging MRI. Nodes that were 7 mm or greater on primary MRI and greater than 4 mm on restaging MRI in the internal iliac compartment resulted in a 5-year LLR rate of 52.3%, significantly higher compared with nodes in the obturator compartment of that size (9.5%; hazard ratio, 5.8; 95% CI, 1.6-21.3; P = .003). Compared with (C)RT with TME alone, treatment with (C)RT with TME and LLND in these unresponsive internal nodes resulted in a significantly lower LLR rate of 8.7% (hazard ratio, 6.2; 95% CI, 1.4-28.5; P = .007).Conclusions and relevanceRestaging MRI is important in clinical decision making in lateral nodal disease. In patients with shrinkage of lateral nodes from an SA node size of 7 mm or greater on primary MRI to an SA node size of 4 mm or less on restaging MRI, which occurs in about 30% of cases, LLND can be avoided. However, persistently enlarged nodes in the internal iliac compartment indicate an extremely high risk of LLR, and an LLND lowered LLR in these cases.
| S-EPMC6613303 | biostudies-literature
Project description:The treatment strategy of rectal cancer has substantially changed in recent decades. Historically postoperative chemoradiotherapy (CRT) was considered to be the first-line therapy for stage II and III rectal cancers. However, the preoperative CRT is now considered to be the optimal therapy regimen for locally advanced rectal ancer due to its improved local control, reduced toxicity, and increased rate of sphincter preservation. Our study established a clinically practical multi-class prediction model by adopting a novel strategy that applies two separate prediction models (MI and TO predictor) sequentially to a patient to predict the response. For promising clinical practice, we validated our model in a published dataset, which is completely independent dataset from ours. This study suggests a clinically plausible prediction model that correctly infers the preoperative CRT response of patients with high accuracy based on 163 gene signatures we identified. Total RNAs were isolated from primary rectal tumor tissues of 69 patients who underwent chemoradiation therapy (CRT). These patients are classified into four different CRT responses: minimal response (MI), moderate response (MO), near total response (NT) and total response (TO). All the RNAs were subjected to microarray analysis using Affymetrix GenChip arrays.
2013-05-14 | E-GEOD-46862 | biostudies-arrayexpress
Project description:The treatment strategy of rectal cancer has substantially changed in recent decades. Historically postoperative chemoradiotherapy (CRT) was considered to be the first-line therapy for stage II and III rectal cancers. However, the preoperative CRT is now considered to be the optimal therapy regimen for locally advanced rectal ancer due to its improved local control, reduced toxicity, and increased rate of sphincter preservation. Our study established a clinically practical multi-class prediction model by adopting a novel strategy that applies two separate prediction models (MI and TO predictor) sequentially to a patient to predict the response. For promising clinical practice, we validated our model in a published dataset, which is completely independent dataset from ours. This study suggests a clinically plausible prediction model that correctly infers the preoperative CRT response of patients with high accuracy based on 163 gene signatures we identified.
2013-05-14 | GSE46862 | GEO
Project description:ObjectiveTo build and validate an MRI-based radiomics nomogram to predict the therapeutic response to neoadjuvant chemoradiotherapy (nCRT) in rectal mucinous adenocarcinoma (RMAC).MethodsTotally, 92 individuals with pathologically confirmed RMAC administered surgical resection upon nCRT in two different centers were assessed retrospectively (training set, n = 52, validation set, n = 40). Rectal MRI was performed pre-nCRT. Radiomics parameters were obtained from high-resolution T2-weighted images and selected to construct a radiomics signature. Then, radiomics nomogram construction integrated patient variables and the radiomics signature. The resulting radiomics nomogram was utilized to assess the tumor regression grade (TRG). Diagnostic performance was determined by generating receiver operating characteristic (ROC) curves and decision curve analysis (DCA).ResultsSix optimal features related to TRG were obtained to construct a radiomics signature. The nomogram combining the radiomics signature with age and mucin deposit outperformed the radiomics signature alone in the training (AUC, 0.950 vs 0.843, p < 0.05) and validation (AUC, 0.868 vs 0.719, p < 0.05) cohorts. DCA demonstrated a clinical utility for the radiomics nomogram model.ConclusionsThe established quantitative MRI-based radiomics nomogram is effective in predicting treatment response to neoadjuvant therapy in patients with RMAC.
| S-EPMC8181148 | biostudies-literature
Project description:ImportanceNeoadjuvant chemoradiotherapy (CRT) is the standard of care for advanced rectal cancer. Yet, estimating response to CRT remains an unmet clinical challenge.ObjectiveTo investigate and better understand the transcriptomic factors associated with response to neoadjuvant CRT and survival in patients with advanced rectal cancer.Design, setting, and participantsA single-center, retrospective, case series was conducted at a comprehensive cancer center. Pretreatment biopsies from 298 patients with rectal cancer who were later treated with neoadjuvant CRT between April 1, 2004, and September 30, 2020, were analyzed by RNA sequencing. Data analysis was performed from July 1, 2021, to May 31, 2022.ExposuresChemoradiotherapy followed by total mesorectal excision or watch-and-wait management.Main outcomes and measuresTranscriptional subtyping was performed by consensus molecular subtype (CMS) classification. Immune cell infiltration was assessed using microenvironment cell populations-counter (MCP-counter) scores and single-sample gene set enrichment analysis (ssGSEA). Patients with surgical specimens of tumor regression grade 3 to 4 or whose care was managed by the watch-and-wait approach for more than 3 years were defined as good responders.ResultsOf the 298 patients in the study, 205 patients (68.8%) were men, and the median age was 61 (IQR, 52-67) years. Patients classified as CMS1 (6.4%) had a significantly higher rate of good response, albeit survival was comparable among the 4 subtypes. Good responders exhibited an enrichment in various immune-related pathways, as determined by ssGSEA. Microenvironment cell populations-counter scores for cytotoxic lymphocytes were significantly higher for good responders than nonresponders (median, 0.76 [IQR, 0.53-1.01] vs 0.58 [IQR, 0.43-0.83]; P < .001). Cytotoxic lymphocyte MCP-counter score was independently associated with response to CRT, as determined in the multivariable analysis (odds ratio, 3.81; 95% CI, 1.82-7.97; P < .001). Multivariable Cox proportional hazards regression analysis, including postoperative pathologic factors, revealed the cytotoxic lymphocyte MCP-counter score to be independently associated with recurrence-free survival (hazard ratio [HR], 0.38; 95% CI, 0.16-0.92; P = .03) and overall survival (HR, 0.16; 95% CI, 0.03-0.83; P = .03).Conclusions and relevanceIn this case series of patients with rectal cancer treated with neoadjuvant CRT, the cytotoxic lymphocyte score in pretreatment biopsy samples, as computed by RNA sequencing, was associated with response to CRT and survival. This finding suggests that the cytotoxic lymphocyte score might serve as a biomarker in personalized multimodal rectal cancer treatment.
| S-EPMC9860531 | biostudies-literature
Project description:Background: Neoadjuvant chemoradiotherapy (NCRT) is the treatment of choice in advanced rectal cancer, even though there are many patients who will not benefit from it. There are still no effective methods for predicting which patients will respond or not. The present study aimed to define the genomic profile of rectal tumors and to identify alterations that are predictive of response in order to optimize therapeutic strategies. Methods: Forty-eight candidates for NCRT were recruited and their pretherapy biopsies analyzed by array Comparative Genomic Hybridization (aCGH). Pathologic response was evaluated by tumor regression grade (TRG).Results: Both Smoothing and Hidden Markov Model (HMM) approaches identified similar alterations, with a prevalence of DNA gains. Non responsive patients had a different alteration profile from responsive ones, with a higher number of genome changes mainly located on 2q21, 7q21, 7q36, 13q12, 13q32-34, 16p13, 17p12 chromosomal regions. Conclusion: This exploratory study suggests that an in depth characterization of chromosomal alterations by aCGH would provide useful predictive information about response to NCRT and help to optimize therapy in rectal cancer patients. 48 samples included in the study were analyzed on whole genome BAC arrays with the aim to characterize genomic alterations and correlate them with the tumor response to therapy. The case series was composed by 15%,81% and 4% of uT2, uT3 and uT4 tumors, respectively. At the diagnosis 56% of patients had uN0 tumors and 44% uN+. 30%,13%, 23% and 34% of patients reached/mantained respectively ypT0, ypT1, ypT2 and ypT3. With regard to response to NCRT, according to TRG criteria proposed by Dworak, two group were defined: non responders (TRG0-2= 56%) and responders (TRG3-4=44%). Clinical and pathological parameters: uT: pre-therapy stage determined by ultrasounds techniques uN: pre-therapy lymph node status determined by ultrasounds techniques ypT: pathologic stage after a neoadjuvant treatment ypN: pathologic lymph node status after a neoadjuvant treatment
2011-11-17 | E-GEOD-25885 | biostudies-arrayexpress
Project description:BackgroundThe purpose of this study was to investigate and validate multiparametric magnetic resonance imaging (MRI)-based machine learning classifiers for early identification of poor responders after neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC).MethodsPatients with LARC who underwent nCRT were included in this retrospective study (207 patients). After preprocessing of multiparametric MRI, radiomics features were extracted and four feature selection methods were used to select robust features. The selected features were used to build five machine learning classifiers, and 20 (four feature selection methods × five machine learning classifiers) predictive models for the screening of poor responders were constructed. The predictive models were evaluated according to the area under the curve (AUC), F1 score, accuracy, sensitivity, and specificity.ResultsEighty percent of all predictive models constructed achieved an AUC of more than 0.70. A predictive model using a support vector machine classifier with the minimum redundancy maximum relevance (mRMR) selection method followed by the least absolute shrinkage and selection operator (LASSO) selection method showed superior prediction performance, with an AUC of 0.923, an F1 score of 88.14%, and accuracy of 91.03%. The predictive performance of the constructed models was not improved by ComBat compensation.ConclusionsIn rectal cancer patients who underwent neoadjuvant chemoradiotherapy, machine learning classifiers with radiomics features extracted from multiparametric MRI were able to accurately discriminate poor responders from good responders. The techniques should provide additional information to guide patient-tailored treatment.
| S-EPMC9017030 | biostudies-literature
Project description:Objective This study aimed to develop an artificial intelligence model for predicting the pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) of locally advanced rectal cancer (LARC) using digital pathological images. Background nCRT followed by total mesorectal excision (TME) is a standard treatment strategy for patients with LARC. Predicting the PCR to nCRT of LARC remine difficulty. Methods 842 LARC patients treated with standard nCRT from three medical centers were retrospectively recruited and subgrouped into the training, testing and external validation sets. Treatment response was classified as pCR and non-pCR based on the pathological diagnosis after surgery as the ground truth. The hematoxylin & eosin (H&E)-stained biopsy slides were manually annotated and used to develop a deep pathological complete response (DeepPCR) prediction model by deep learning. Results The proposed DeepPCR model achieved an AUC-ROC of 0.710 (95% CI: 0.595, 0.808) in the testing cohort. Similarly, in the external validation cohort, the DeepPCR model achieved an AUC-ROC of 0.723 (95% CI: 0.591, 0.844). The sensitivity and specificity of the DeepPCR model were 72.6% and 46.9% in the testing set and 72.5% and 62.7% in the external validation cohort, respectively. Multivariate logistic regression analysis showed that the DeepPCR model was an independent predictive factor of nCRT (P=0.008 and P=0.004 for the testing set and external validation set, respectively). Conclusions The DeepPCR model showed high accuracy in predicting pCR and served as an independent predictive factor for pCR. The model can be used to assist in clinical treatment decision making before surgery.
| S-EPMC9214314 | biostudies-literature