Association of collagen deep learning classifier with prognosis and chemotherapy benefits in stage II-III colon cancer.
Ontology highlight
ABSTRACT:
SUBMITTER: Jiang W
PROVIDER: S-EPMC10189440 | biostudies-literature | 2023 May
REPOSITORIES: biostudies-literature
Publications
Association of collagen deep learning classifier with prognosis and chemotherapy benefits in stage II-III colon cancer.
Jiang Wei W Wang Huaiming H Chen Weisheng W Zhao Yandong Y Yan Botao B Chen Dexin D Dong Xiaoyu X Cheng Jiaxin J Lin Zexi Z Zhuo Shuangmu S Wang Hui H Yan Jun J
Bioengineering & translational medicine 20230417 3
The current tumor-node-metastasis staging system does not provide sufficient prognostic prediction or adjuvant chemotherapy benefit information for stage II-III colon cancer (CC) patients. Collagen in the tumor microenvironment affects the biological behaviors and chemotherapy response of cancer cells. Hence, in this study, we proposed a collagen deep learning (collagen<sup>DL</sup>) classifier based on the 50-layer residual network model for predicting disease-free survival (DFS) and overall su ...[more]
Similar Datasets
Project description:ImportanceThe current TNM staging system may not provide adequate information for prognostic purposes and to assess the potential benefits of chemotherapy for patients with stage III colon cancer.ObjectiveTo develop and validate a pathomics signature to estimate prognosis and benefit from chemotherapy using hematoxylin-eosin (H-E)-stained slides.Design, setting, and participantsThis retrospective prognostic study used data from consecutive patients with histologically confirmed stage III colon cancer at 2 medical centers between January 2012 and December 2015. A total of 114 pathomics features were extracted from digital H-E-stained images from Nanfang Hospital of Southern Medical University, Guangzhou, China, and a pathomics signature was constructed using a least absolute shrinkage and selection operator Cox regression model in the training cohort. The associations of the pathomics signature with disease-free survival (DFS) and overall survival (OS) were evaluated. Patients at the Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China, formed the validation cohort. Data analysis was conducted from September 2022 to March 2023.Main outcomes and measuresThe prognostic accuracy of the pathomics signature as well as its association with chemotherapy response were evaluated.ResultsThis study included 785 patients (mean [SD] age, 62.7 [11.1] years; 437 [55.7%] male). A pathomics signature was constructed based on 4 features. Multivariable analysis revealed that the pathomics signature was an independent factor associated with DFS (hazard ratio [HR], 2.46 [95% CI, 2.89-4.13]; P < .001) and OS (HR, 2.78 [95% CI, 2.34-3.31]; P < .001) in the training cohort. Incorporating the pathomics signature into pathomics nomograms resulted in better performance for the estimation of prognosis than the traditional model in a concordance index comparison in the training cohort (DFS: HR, 0.88 [95% CI, 0.86-0.89] vs HR, 0.73 [95% CI, 0.71-0.75]; P < .001; OS: HR, 0.85 [95% CI, 0.84-0.86] vs HR, 0.74 [95% CI, 0.72-0.76]; P < .001) and validation cohort (DFS: HR, 0.83 [95% CI, 0.82-0.85] vs HR, 0.70 [95% CI, 0.67-0.72]; P < .001; OS: HR, 0.80 [95% CI, 0.78-0.82] vs HR, 0.69 [0.67-0.72]; P < .001). Further analysis revealed that patients with a low pathomics signature were more likely to benefit from chemotherapy (eg, combined cohort: DFS: HR, 0.44 [95% CI, 0.28-0.69]; P = .001; OS: HR, 0.43 [95% CI, 0.29-0.64]; P < .001).Conclusions and relevanceThese findings suggest that a pathomics signature could help identify patients most likely to benefit from chemotherapy in stage III colon cancer.
| S-EPMC10902777 | biostudies-literature
Project description:Cancer metastases accounts for most cancer deaths. The secreting glycoprotein Wnt5a impairs tumor cell migration and reduces invasiveness and metastasis. High Wnt5a expression in tumor cells is correlated to better outcomes in patients with breast, prostate and epithelial ovarian cancer. We aimed to investigate the association between the Wnt5a expression and outcomes in patients with colon cancer (CC) stage II/III. We performed a retrospective single-center study evaluating 345 patients with radical resection for primary CC, stage II/III, who started 6 months of adjuvant chemotherapy with 5-FU or capecitabine ± oxaliplatin between 2001 and 2015. Archived formalin-fixed paraffin embedded tumor tissue from resection specimens were stained with Wnt5a antibody using immunohistochemistry. Cytoplasmatic Wnt5a staining was assessed according to intensity and percentage of stained cells. Patients were divided in groups depending on high (n = 230) or low (n = 115) Wnt5a expression. Disease free survival (DFS) and overall survival (OS) were analyzed for the two groups using Kaplan-Meier plots and Long rank test. Patients with Wnt5a-negative tumors had significantly poorer performance status (PS) than patients with high Wnt5a expression (p = 0.046). No significant difference was seen between patients with low and high Wnt5a expression in terms of 5-year DFS (p = 0.517) or 5-year OS (p = 0.415). Poor PS was associated with lower DFS (p = 0.002) and OS (p < 0.001). In conclusion, we found no significant difference in prognosis for patients with stage II/III CC depending on their Wnt5a expression. Patients with Wnt5a-negative tumors had significant poorer PS than patients with higher levels. Poor PS was associated with lower DFS and OS.
| S-EPMC7553443 | biostudies-literature
Project description:Background. To explore preferred and actual involvement in chemotherapy decision making among stage II and III colon cancer (CC) patients by sociodemographic, interpersonal, and intrapersonal communication factors. Methods. Cross-sectional exploratory study collecting self-reported survey data from stage II and III CC patients from 2 cancer centers located in northern Manhattan. Results. Of 88 patients approached, 56 completed the survey. Only 19.3% reported shared involvement in their chemotherapy decisions. We observed significant differences in preferred involvement by gender, with women preferring more physician-controlled decisions. CC patients with higher levels of decisional self-efficacy significantly preferred shared decisions (F = 4.4 [2], P = 0.02). Actual involvement in decisions differed by race (physician controlled 33% for White v. 67% for Other, P < 0.01), age (shared control 18% for ≤55 y, 55% for 55-64 y, and 27% for 65+ y, P = 0.04), and perception of choice (shared control 73% "yes" v. 27% "no,"P = 0.02). Actual or preferred involvement did not differ by stage. Significantly higher levels of medical mistrust (discrimination t = 2.8 [50], P = 0.01; lack of support t = 3.6 [49], P < 0.01), and lower levels of decisional self-efficacy (t = 2.5 [49], P = 0.01) were reported among women. Discussion. Reports of shared involvement around chemotherapy decisions is limited among CC patients. Factors influencing preferred versus actual chemotherapy decision making are complex and may differ; hence, more research is needed to understand and address factors contributing to discordance between preferred and actual involvement in chemotherapy decision making for CC patients.HighlightsShared involvement around chemotherapy decisions remains limited for patients diagnosed with colon cancer.Sociodemographic (age, race, gender), interpersonal (medical mistrust), and intrapersonal (decisional self-efficacy, perception of choice) factors that influence preferred involvement in chemotherapy decision making may differ from those influencing actual involvement in chemotherapy decision making.Shared involvement in chemotherapy decisions may look different than currently conceptualized, notably when uncertainty around the benefits exists.
| S-EPMC10052499 | biostudies-literature
Project description:BackgroundAdjuvant chemotherapy reduces the risk of recurrence of stage III colon cancer (CC). However, more effective prognostic and predictive biomarkers are needed for better treatment stratification of affected patients. Here, we constructed a 55-gene classifier (55GC) and investigated its utility for classifying patients with stage III CC.MethodsWe retrospectively identified patients aged 20-79 years, with stage III CC, who received adjuvant chemotherapy with or without oxaliplatin, between the years 2009 and 2012.ResultsAmong 938 eligible patients, 203 and 201 patients who received adjuvant chemotherapy with and without oxaliplatin, respectively, were selected by propensity score matching. Of these, 95 patients from each group were analyzed, and their 5-year relapse-free survival (RFS) rates with and without oxaliplatin were 73.7 and 77.1%, respectively. The hazard ratios for 5-year RFS following adjuvant chemotherapy (fluoropyrimidine), with and without oxaliplatin, were 1.241 (95% CI, 0.465-3.308; P = 0.67) and 0.791 (95% CI, 0.329-1.901; P = 0.60), respectively. Stratification using the 55GC revealed that 52 (27.3%), 78 (41.1%), and 60 (31.6%) patients had microsatellite instability (MSI)-like, chromosomal instability (CIN)-like, and stromal subtypes, respectively. The 5-year RFS rates were 84.3 and 72.0% in patients treated with and without oxaliplatin, respectively, for the MSI-like subtype (HR, 0.495; 95% CI, 0.145-1.692; P = 0.25). No differences in RFS rates were noted in the CIN-like or stromal subtypes. Stratification by cancer sidedness for each subtype showed improved RFS only in patients with left-sided primary cancer treated with oxaliplatin for the MSI-like subtype (P = 0.007). The 5-year RFS rates of the MSI-like subtype in left-sided cancer patients were 100 and 53.9% with and without oxaliplatin, respectively.ConclusionsSubclassification using 55GC and tumor sidedness revealed increased RFS in patients within the MSI-like subtype with stage III left-sided CC treated with fluoropyrimidine and oxaliplatin compared to those treated without oxaliplatin. However, the predictive power of 55GC subtyping alone did not reach statistical significance in this cohort, warranting larger prospective studies.Trial registrationThe study protocol was registered in the University Hospital Medical Education Network (UMIN) clinical trial registry (UMIN study ID: 000023879 ).
| S-EPMC8672629 | biostudies-literature
Project description:BackgroundThe risk of recurrence after resection of a stage II or III colon cancer, and therefore qualification for adjuvant chemotherapy (ACT), is traditionally based on clinicopathological parameters. However, the parameters used in clinical practice are not able to accurately identify all patients with or without minimal residual disease. Some patients considered 'low-risk' do develop recurrence (undertreatment), whilst other patients receiving ACT might not have developed recurrence at all (overtreatment). We previously analysed tumour tissue expression of 28 protein biomarkers that might improve identification of patients at risk of recurrence. In the present study we aimed to build a prognostic classifier based on these 28 biomarkers and clinicopathological parameters.MethodsClassification and regression tree (CART) analysis was used to build a prognostic classifier based on a well described cohort of 386 patients with stage II and III colon cancer. Separate classifiers were built for patients who were or were not treated with ACT. Routine clinicopathological parameters and tumour tissue immunohistochemistry data were included, available for 28 proteins previously published. Classification trees were pruned until lowest misclassification error was obtained. Survival of the identified subgroups was analysed, and robustness of the selected CART variables was assessed by random forest analysis (1000 trees).ResultsIn patients not treated with ACT, prognosis was estimated best based on expression of KCNQ1. Poor disease-free survival (DFS) was observed in those with loss of expression of KCNQ1 (HR = 3.38 (95% CI 2.12 - 5.40); p < 0.001). In patients treated with ACT, key prognostic factors were lymphovascular invasion (LVI) and expression of KCNQ1. Patients with LVI showed poorest DFS, whilst patients without LVI and high expression of KCNQ1 showed most favourable survival (HR = 7.50 (95% CI 3.57-15.74); p < 0.001). Patients without LVI and loss of expression of KCNQ1 had intermediate survival (HR = 3.91 (95% CI 1.76 - 8.72); p = 0.001).ConclusionKCNQ1 and LVI were identified as key features in prognostic classifiers for disease-free survival in stage II and III colon cancer patients.
| S-EPMC8991490 | biostudies-literature
Project description:BackgroundColon cancer incidence is rising in low- and middle-income countries (LMICs), where resource limitations and cost often dictate treatment decisions. In this study, we evaluate the cost-effectiveness of adjuvant chemotherapy for high-risk stage II and stage III colon cancer treatment in South Africa (ZA) and illustrate how such analyses can inform cancer treatment recommendations in a LMIC.MethodsWe created a decision-analytic Markov model to compare lifetime costs and outcomes for patients with high-risk stage II and stage III colon cancer treated with three adjuvant chemotherapy regimens in a public hospital in ZA: capecitabine and oxaliplatin (CAPOX) for 3 and 6 months, and capecitabine for 6 months, compared to no adjuvant treatment. The primary outcome was the incremental cost-effectiveness ratio (ICER) in international dollars (I$) per disability-adjusted life-year (DALY) averted, at a willingness-to-pay (WTP) threshold equal to the 2021 ZA gross domestic product per capita (I$13,764/DALY averted).ResultsCAPOX for 3 months was cost-effective for both patients with high-risk stage II and patients with stage III colon cancer (ICER = I$250/DALY averted and I$1042/DALY averted, respectively), compared to no adjuvant chemotherapy. In subgroup analyses of patients by tumor stage and number of positive lymph nodes, for patients with high-risk stage II colon cancer and T4 tumors, and patients with stage III colon cancer with T4 or N2 disease. CAPOX for 6 months was cost-effective and the optimal strategy. The optimal strategy in other settings will vary by local WTP thresholds. Decision analytic tools can be used to identify cost-effective cancer treatment strategies in resource-constrained settings.ConclusionColon cancer incidence is increasing in low- and middle-income countries, including South Africa, where resource constraints can impact treatment decisions. This cost-effectiveness study evaluates three systemic adjuvant chemotherapy options, compared to surgery alone, for patients in South African public hospitals after surgical resection for high-risk stage II and stage III colon cancer. Doublet adjuvant chemotherapy (capecitabine and oxaliplatin) for 3 months is the cost-effective strategy and should be recommended in South Africa.
| S-EPMC10417185 | biostudies-literature
Project description:BackgroundSince 2004, a regimen of 6 months of treatment with oxaliplatin plus a fluoropyrimidine has been standard adjuvant therapy in patients with stage III colon cancer. However, since oxaliplatin is associated with cumulative neurotoxicity, a shorter duration of therapy could spare toxic effects and health expenditures.MethodsWe performed a prospective, preplanned, pooled analysis of six randomized, phase 3 trials that were conducted concurrently to evaluate the noninferiority of adjuvant therapy with either FOLFOX (fluorouracil, leucovorin, and oxaliplatin) or CAPOX (capecitabine and oxaliplatin) administered for 3 months, as compared with 6 months. The primary end point was the rate of disease-free survival at 3 years. Noninferiority of 3 months versus 6 months of therapy could be claimed if the upper limit of the two-sided 95% confidence interval of the hazard ratio did not exceed 1.12.ResultsAfter 3263 events of disease recurrence or death had been reported in 12,834 patients, the noninferiority of 3 months of treatment versus 6 months was not confirmed in the overall study population (hazard ratio, 1.07; 95% confidence interval [CI], 1.00 to 1.15). Noninferiority of the shorter regimen was seen for CAPOX (hazard ratio, 0.95; 95% CI, 0.85 to 1.06) but not for FOLFOX (hazard ratio, 1.16; 95% CI, 1.06 to 1.26). In an exploratory analysis of the combined regimens, among the patients with T1, T2, or T3 and N1 cancers, 3 months of therapy was noninferior to 6 months, with a 3-year rate of disease-free survival of 83.1% and 83.3%, respectively (hazard ratio, 1.01; 95% CI, 0.90 to 1.12). Among patients with cancers that were classified as T4, N2, or both, the disease-free survival rate for a 6-month duration of therapy was superior to that for a 3-month duration (64.4% vs. 62.7%) for the combined treatments (hazard ratio, 1.12; 95% CI, 1.03 to 1.23; P=0.01 for superiority).ConclusionsAmong patients with stage III colon cancer receiving adjuvant therapy with FOLFOX or CAPOX, noninferiority of 3 months of therapy, as compared with 6 months, was not confirmed in the overall population. However, in patients treated with CAPOX, 3 months of therapy was as effective as 6 months, particularly in the lower-risk subgroup. (Funded by the National Cancer Institute and others.).
| S-EPMC6426127 | biostudies-literature
Project description:BackgroundAlthough adjuvant chemotherapy is recommended for patients with stage II colon cancer characterized by poor prognostic features, its pros and cons remain a controversial issue. We aim to evaluate the real effectiveness of chemotherapy on stage II colon cancer as well as select suitable patients.MethodsPatients during 1988-2013 were identified from the Surveillance, Epidemiology, and End Results (SEER) database. The competing risk regression model and propensity score matching method were used to evaluate colon-cancer-specific death (CCSD) and non-CCSD. Also, a competing-risk nomogram was constructed to identify risk of patients. Risk score (RS) was calculated according to nomogram.ResultsA total of 58,133 patients were included, 25.66% received chemotherapy, and 74.34% were without chemotherapy. In total, 19.95% and 25.78% of patients died of CCSD and non-CCSD, respectively. Univariate and multivariate analyses showed that receiving chemotherapy appears to be associated with more CCSD and less non-CCSD (HR 1.23, 95% CI 1.18-1.28; HR 0.45, 95% CI 0.43-0.47, respectively), even after adjustment for covariates and propensity score weighting. A competing-risk nomogram was established; the model was relatively good with a C-index of 0.661. Based on the RS, risk stage could only predict prognosis but failed to predict the benefit from chemotherapy.ConclusionsThe value of chemotherapy is much less than we thought. It is time to de-escalate chemotherapy for stage II colon cancer. CCSD, rather than overall survival, should be considered as an appropriate primary end point for future trials in stage II colon cancer.
| S-EPMC6710694 | biostudies-literature
Project description:BackgroundWe evaluated the impact of 3 months of mFOLFOX6 adjuvant chemotherapy or surgery alone in comparison with 6 months of mFOLFOX6 on disease-free survival (DFS) in deficient mismatch repair (dMMR) colon cancer (CC) patients.MethodsThis retrospective study identified a cohort of patients with high-risk stage II and III dMMR CC who underwent curative surgery between May 2011 and July 2019. DFS was compared using the Kaplan-Meier survival methods and Cox proportional hazards models. Propensity-score matching was performed to reduce imbalance in baseline characteristics.ResultsA total of 242 dMMR CC patients were identified; 66 patients received 6 months of mFOLFOX6, 87 patients received 3 months of mFOLFOX6, and 89 patients were treated with surgery alone. The 3-year DFS rate was 72.8% in 3-month therapy group and 86.1% in 6-month therapy group, with a hazard ratio (HR) of 2.78 (95CI%, 1.18 to 6.47; P= 0.019). The difference in DFS between surgery alone group and 6-month therapy group was also observed but was nonsignificant (HR= 2.30, 95%CI, 0.99 to 5.38; P=0.054). The benefit of 6-month therapy in DFS compared with 3-month therapy group was pronounced for patients with stage III (HR=2.81, 95%CI, 1.03 to 7.67; P=0.044) but not for high-risk stage II patients. Propensity score matched analysis confirmed a DFS benefit in the 6-month therapy group.ConclusionThis study suggested that a 6-month duration of mFOLFOX6 adjuvant chemotherapy in dMMR CC patients may be associated with improved DFS compared with 3-month therapy, particularly in patients with stage III. The observational nature of the study implies caution should be taken in the interpretation of these results.
| S-EPMC7747753 | biostudies-literature
Project description:The advantage of adjuvant chemotherapy (ACT) for treating Stage III colon cancer patients is well established and widely accepted. However, many patients with Stage III colon cancer do not receive ACT. Moreover, there are controversies around the effectiveness of ACT for Stage II patients. We investigated the administration of ACT and its association with overall survival in resected Stage II (overall and stratified by low-/high-risk) and Stage III colon cancer patients in three European countries including The Netherlands (2009-2014), Belgium (2009-2013) and Sweden (2009-2014). Hazard ratios (HR) for death were obtained by Cox regression models adjusted for potential confounders. A total of 60244 resected colon cancer patients with pathological Stages II and III were analyzed. A small proportion (range 9-24%) of Stage II and over half (range 55-68%) of Stage III patients received ACT. Administration of ACT in Stages II and III tumors decreased with higher age of patients. Administration of ACT was significantly associated with higher overall survival in high-risk Stage II patients (in The Netherlands (HR; 95%CI = 0.82 (0.67-0.99), Belgium (0.73; 0.59-0.90) and Sweden (0.58; 0.44-0.75)), and in Stage III patients (in The Netherlands (0.47; 0.43-0.50), Belgium (0.46; 0.41-0.50) and Sweden (0.48; 0.43-0.54)). In Stage III, results were consistent across subgroups including elderly patients. Our results show an association of ACT with higher survival among Stage III and high-risk Stage II colon cancer patients. Further investigations are needed on the selection criteria of Stages II and III colon cancer patients for ACT.
| S-EPMC6002808 | biostudies-literature