Dataset Information

Predictive models of response to neoadjuvant chemotherapy in muscle-invasive bladder cancer using nuclear morphology and tissue architecture.

ABSTRACT: Characterizing likelihood of response to neoadjuvant chemotherapy (NAC) in muscle-invasive bladder cancer (MIBC) is an important yet unmet challenge. In this study, a machine-learning framework is developed using imaging of biopsy pathology specimens to generate models of likelihood of NAC response. Developed using cross-validation (evaluable N = 66) and an independent validation cohort (evaluable N = 56), our models achieve promising results (65%-73% accuracy). Interestingly, one model-using features derived from hematoxylin and eosin (H&E)-stained tissues in conjunction with clinico-demographic features-is able to stratify the cohort into likely responders in cross-validation and the validation cohort (response rate of 65% for predicted responder compared with the 41% baseline response rate in the validation cohort). The results suggest that computational approaches applied to routine pathology specimens of MIBC can capture differences between responders and non-responders to NAC and should therefore be considered in the future design of precision oncology for MIBC.

SUBMITTER: Mi H

PROVIDER: S-EPMC8484511 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictive models of response to neoadjuvant chemotherapy in muscle-invasive bladder cancer using nuclear morphology and tissue architecture.

Mi Haoyang H Bivalacqua Trinity J TJ Kates Max M Seiler Roland R Black Peter C PC Popel Aleksander S AS Baras Alexander S AS

Cell reports. Medicine 20210827 9

Characterizing likelihood of response to neoadjuvant chemotherapy (NAC) in muscle-invasive bladder cancer (MIBC) is an important yet unmet challenge. In this study, a machine-learning framework is developed using imaging of biopsy pathology specimens to generate models of likelihood of NAC response. Developed using cross-validation (evaluable N = 66) and an independent validation cohort (evaluable N = 56), our models achieve promising results (65%-73% accuracy). Interestingly, one model-using fe ...[more]

PMID: 34622225

Similar Datasets

Project description:IntroductionIdentifying neoadjuvant chemotherapy (NAC) response in patients with muscle invasive bladder cancer (MIBC) has had limited success based on clinicopathological features and molecular subtyping. Identification of chemotherapy responsive cohorts would facilitate delivery to those most likely to benefit.ObjectiveDevelop a molecular signature that can identify MIBC NAC responders (R) and non-responders (NR) using a cohort of known NAC response phenotypes, and better understand differences in molecular pathways and subtype classifications between NAC R and NR.Materials and methodsPresented are the messenger RNA (mRNA) and microRNA (miRNA) differential expression profiles from initial transurethral resection of bladder tumor (TURBT) specimens of a discovery cohort of MIBC patients consisting of 7 known NAC R and 11 NR, and a validation cohort consisting of 3 R and 5 NR. Pathological response at time of cystectomy after NAC was used to classify initial TURBT specimens as R (pT0) versus NR (≥pT2). RNA and miRNA from FFPE blocks were sequenced using RNAseq and qPCR, respectively.ResultsThe discovery cohort had 2309 genes, while the validation cohort had 602 genes and 13 miRNA differentially expressed between R and NR. Gene set enrichment analysis identified mitochondrial gene expression, DNA replication initiation, DNA unwinding in the R discovery cohort and positive regulation of vascular associated smooth muscle cell proliferation in the NR discovery cohort. Canonical correlation (CC) analysis was applied to differentiate R versus NR. 3 CCs (CC13, CC16, and CC17) had an AUC >0.65 in the discovery and validation dataset. Gene ontology enrichment showed CC13 as nucleoside triphosphate metabolic process, CC16 as cell cycle and cellular response to DNA damage, CC17 as DNA packaging complex. All patients were classified using established molecular subtypes: Baylor, UNC, CIT, Lund, MD Anderson, TCGA, and Consensus Class. The MD Anderson p53-like subtype, CIT MC4 subtype and Consensus Class stroma rich subtype had the strongest correlation with a NR phenotype, while no subtype had a strong correlation with the R phenotype.ConclusionsOur results identify molecular signatures that can be used to differentiate MIBC NAC R versus NR, salient molecular pathway differences, and highlight the utility of molecular subtyping in relation to NAC response.

Project description:BackgroundBladder-sparing chemoradiation therapy is a definitive first-line treatment option for muscle-invasive bladder cancer. Randomized trials have demonstrated that the addition of neoadjuvant chemotherapy to radical cystectomy or radiation monotherapy results in a survival benefit. Whether neoadjuvant chemotherapy improves outcomes when used with definitive chemoradiation is unknown.Patients and methodsWe identified 2566 patients in the National Cancer Data Base with cT2-4N0M0 urothelial cell carcinoma of the bladder treated with definitive intent concurrent chemoradiation from 2004 to 2015. The exposure of interest was receipt of neoadjuvant chemotherapy versus those without neoadjuvant chemotherapy. The primary outcome was overall survival defined from the time of diagnosis. Kaplan-Meier and multivariable Cox proportional hazard analyses were used to compare survival between groups. Sensitivity analyses tested (1) an interaction term for clinical T stage and (2) defining survival from start of radiation (as opposed to time of diagnosis) to address potential leading time bias.ResultsWe identified 462 patients treated with neoadjuvant chemotherapy followed by chemoradiation and 2104 patients treated with chemoradiation alone. With a median follow-up of 6.2 years, we found no difference in survival between groups: 5-year or 10-year overall survival of 30.6% (95% confidence interval [CI], 28.4%-32.9%) in the neoadjuvant group versus 31.8% (95% CI, 27.0%-36.8%) in the standard chemoradiation therapy group and 13.3% (95% CI, 11.2%-15.5%) in the neoadjuvant group versus 13.0% (95% CI, 8.4%-18.7%) in the standard chemoradiation therapy group, respectively (log-rank P = .19). On multivariable analysis we found no association between receipt of neoadjuvant chemotherapy and overall survival (hazard ratio, 1.01; 95% CI, 0.88-1.15; P = .921). The sensitivity analyses did not identify any differential effect by clinical T stage nor by defining survival from start of radiation.ConclusionThese results do not support the routine addition of neoadjuvant chemotherapy to definitive chemoradiation for bladder cancer, and optimizing the chemotherapy sequencing and regimens for bladder-preserving approaches to muscle invasive bladder cancer should continue to be studied under prospective clinical trials.

Project description:Background and objectiveNeoadjuvant chemotherapy (NAC) followed by cystectomy is the standard of care in muscle-invasive bladder cancer (MIBC). Pathological response has been associated with longer survival, but no currently available clinicopathological variables can identify patients likely to respond, highlighting the need for predictive biomarkers. We sought to identify a predictive signature of response to NAC integrating clinical score, taxonomic subtype, and gene expression.Material and methodsFrom 1994 to 2014, pre-treatment tumor samples were collected from MIBC patients (stage T2-4N0/+M0) at two Spanish hospitals. A clinical score was determined based on stage, hydronephrosis and histology. Taxonomic subtypes (BASQ, luminal, and mixed) were identified by immunohistochemistry. A custom set of 41 genes involved in DNA damage repair and immune response was analyzed in 84 patients with the NanoString nCounter platform. Genes related to pathological response were identified by LASSO penalized logistic regression. NAC consisted of cisplatin/methotrexate/vinblastine until 2000, after which most patients received cisplatin/gemcitabine. The capacity of the integrated signature to predict pathological response was assessed with AUC. Overall survival (OS) and disease-specific survival (DSS) were analyzed with the Kaplan-Meier method.ResultsLASSO selected eight genes to be included in the signature (RAD51, IFNγ, CHEK1, CXCL9, c-MET, KRT14, HERC2, FOXA1). The highest predictive accuracy was observed with the inclusion in the model of only three genes (RAD51, IFNɣ, CHEK1). The integrated clinical-taxonomic-gene expression signature including these three genes had a higher predictive ability (AUC=0.71) than only clinical score plus taxonomic subtype (AUC=0.58) or clinical score alone (AUC=0.56). This integrated signature was also significantly associated with OS (p=0.02) and DSS (p=0.02).ConclusionsWe have identified a predictive signature for response to NAC in MIBC patients that integrates the expression of three genes with clinicopathological characteristics and taxonomic subtypes. Prospective studies to validate these results are ongoing.

Project description:BackgroundThis prospective study tested the hypothesis that the apparent diffusion coefficient (ADC) value and tumor volume (TV) measured in diffusion-weighted magnetic resonance imaging (DW-MRI) before, during, and after the treatment are quantitative imaging markers to assess tumor response in muscle-invasive bladder cancer (MIBC) patients undergoing neoadjuvant chemotherapy (NAC).MethodsMulti-parametric MRI was prospectively done for MIBC patients at 3 time points. Pre-treatment ADC value, pre-treatment TV, as well as, percent of changes (ΔADC%, and ΔTV%) in these parameters at mid- and post-treatment relative to baseline were calculated and compared between the patients with and without clinical complete response (CR). Also, further analysis was carried out based on the groups of patients with and without overall response (OR). Two different methods of ADC estimation including single-slice ADC measurement (ADCsingle-slice) and whole-lesion ADC measurement (ADCwhole-lesion) were used.ResultsA total of 50 eligible patients were included in the analysis. Of these, 20 patients (40%) showed clinical CR to treatment, while 30 (60%) did not. Our results showed that although there was no significant difference between the two groups of patients with and without CR in terms of mid-treatment ΔADC% and mid-treatment ΔTV%, significant differences were observed in terms of the pre-treatment ADC (p < 0.01), pre-treatment TV (p < 0.001), post-treatment ΔADC% (p < 0.05), and post-treatment ΔTV% (p < 0.05). The results of the OR-based analysis were in line with the CR-based results. There was also a strong and significant correlation between ADCsingle-slice and ADCwhole-lesion measurements (r > 0.9, P < 0.001).ConclusionPre-treatment ADC, pre-treatment TV, post-treatment ΔADC%, and post-treatment ΔTV% could be considered as promising quantitative imaging markers of tumor response in MIBC patients undergoing NAC. Moreover, mid-treatment ΔADC% and mid-treatment ΔTV% should not be used as predictors of tumor response in these patients. Further larger studies are required to confirm these results.

Project description:Background and Objective: Neoadjuvant chemotherapy (NAC) followed by cystectomy is the standard of care in muscle-invasive bladder cancer (MIBC). Pathological response has been associated with longer survival, but no currently available clinicopathological variables can identify patients likely to respond, highlighting the need for predictive biomarkers. We sought to identify a predictive signature of response to NAC integrating clinical score, taxonomic subtype, and gene expression. Material and Methods: From 1994 to 2014, pre-treatment tumor samples were collected from MIBC patients (stage T2-4N0/+M0) at two Spanish hospitals. A clinical score was determined based on stage, hydronephrosis and histology. Taxonomic subtypes (BASQ, luminal, and mixed) were identified by immunohistochemistry. A custom set of 41 genes involved in DNA damage repair and immune response was analyzed in 84 patients with the NanoString nCounter platform. Genes related to pathological response were identified by LASSO penalized logistic regression. NAC consisted of cisplatin/methotrexate/vinblastine until 2000, after which most patients received cisplatin/gemcitabine. The capacity of the integrated signature to predict pathological response was assessed with AUC. Overall survival (OS) and disease-specific survival (DSS) were analyzed with the Kaplan-Meier method. Results: LASSO selected eight genes to be included in the signature (RAD51, IFNγ, CHEK1, CXCL9, c-MET, KRT14, HERC2, FOXA1). The highest predictive accuracy was observed with the inclusion in the model of only three genes (RAD51, IFNɣ, CHEK1). The integrated clinical-taxonomic-gene expression signature including these three genes had a higher predictive ability (AUC=0.71) than only clinical score plus taxonomic subtype (AUC=0.58) or clinical score alone (AUC=0.56). This integrated signature was also significantly associated with OS (p=0.02) and DSS (p=0.02). Conclusions: We have identified a predictive signature for response to NAC in MIBC patients that integrates the expression of three genes with clinicopathological characteristics and taxonomic subtypes. Prospective studies to validate these results are ongoing.

Dataset Information

Predictive models of response to neoadjuvant chemotherapy in muscle-invasive bladder cancer using nuclear morphology and tissue architecture.

Publications

Predictive models of response to neoadjuvant chemotherapy in muscle-invasive bladder cancer using nuclear morphology and tissue architecture.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets