CT radiomics combined with clinical variables for predicting the overall survival of hepatocellular carcinoma patients after hepatectomy

PurposeTo establish a model for assessing the overall survival (OS) of the hepatocellular carcinoma (HCC) patients after hepatectomy based on the clinical and radiomics features.MethodsThis study recruited a total of 267 patients with HCC, which were randomly divided into the training (N = 188) and validation (N = 79) cohorts. In the training cohort, radiomic features were selected with the intra-reader and inter-reader correlation coefficient (ICC), Spearman's correlation coefficient, and the least absolute shrinkage and selection operator (LASSO). The radiomics signatures were built by COX regression analysis and compared the predictive potential in the different phases (arterial, portal, and double-phase) and regions of interest (tumor, peritumor 3 mm, peritumor 5 mm). A clinical-radiomics model (CR model) was established by combining the radiomics signatures and clinical risk factors. The validation cohort was used to validate the proposed models.ResultsA total of 267 patients 86 (45.74%) and 37 (46.84%) patients died in the training and validation cohorts, respectively. Among all the radiomics signatures, those based on the tumor and peritumor (5 mm) (AP-TP5-Signature) showed the best prognostic potential (training cohort 1–3 years AUC:0.774–0.837; validation cohort 1–3 years AUC:0.754–0.810). The CR model showed better discrimination, calibration, and clinical applicability as compared to the clinical model and radiomics features. In addition, the CR model could perform risk-stratification and also allowed for significant discrimination between the Kaplan-Meier curves in most of the subgroups.ConclusionsThe CR model could predict the OS of the HCC patients after hepatectomy.     

Comparative study of radiomics,tumor morphology,and clinicopathological factors in predicting overall survival of patients with rectal cancer before surgery

We compared the ability of a radiomics model, morphological imaging model, and clinicopathological risk model to predict 3-year overall survival (OS) in 206 patients with rectal cancer who underwent radical surgery and had magnetic resonance imaging, clinicopathological, and OS data available. The patients were randomized to a training cohort (n = 146) and a verification cohort (n = 60). Radiomics features were extracted from preoperative T2-weighted images, and a radiomics score model was constructed. Factors that were significant in the Cox multivariate analysis were used to construct the final morphological tumor model and clinicopathological model. A comprehensive model in the form of a line chart was established by combining the three models. Ten radiomics features significantly related to OS were selected to construct the radiomics feature model and calculate the radiomics score. In the morphological model, mesorectal extension depth and distance between the lower tumor margin and the anal margin were significant prognostic factors. N stage was the only significant clinicopathological factor. The comprehensive model combined with the above factors had the best prediction performance for OS. The C-index had a predictive performance of 0.872 (95% confidence interval [CI]: 0.832–0.912) in the training cohort and 0.944 (95% CI: 0.890–0.990) in the verification cohort, which was better than for any single model. The comprehensive model was divided into high-risk and low-risk groups. Kaplan-Meier curve analysis showed that all factors were significantly correlated with poor OS in the high-risk group. A comprehensive nomogram based on multi-model radiomics features can predict 3-year OS after rectal cancer surgery.     

Early risk-assessment of patients with nasopharyngeal carcinoma: the added prognostic value of MR-based radiomics

ObjectivesTo assess the additive prognostic value of MR-based radiomics in predicting progression-free survival (PFS) in patients with nasopharyngeal carcinoma (NPC)MethodsPatients newly diagnosed with non-metastatic NPC between June 2006 and October 2019 were retrospectively included and randomly grouped into training and test cohorts (7:3 ratio). Radiomic features (n=213) were extracted from T2-weighted and contrast-enhanced T1-weighted MRI. The patients were staged according to the 8^th edition of American Joint Committee on Cancer Staging Manual. The least absolute shrinkage and selection operator was used to select the relevant radiomic features. Univariate and multivariate Cox proportional hazards analyses were conducted for PFS, yielding three different survival models (clinical, stage, and radiomic). The integrated time-dependent area under the curve (iAUC) for PFS was calculated and compared among different combinations of survival models, and the analysis of variance was used to compare the survival models. The prognostic performance of all models was validated using a test set with integrated Brier scores.ResultsThis study included 81 patients (training cohort=57; test cohort=24), and the mean PFS was 57.5 ± 43.6 months. In the training cohort, the prognostic performances of survival models improved significantly with the addition of radiomics to the clinical (iAUC, 0.72–0.80; p=0.04), stage (iAUC, 0.70–0.79; p=0.001), and combined models (iAUC, 0.76–0.81; p<0.001). In the test cohort, the radiomics and combined survival models were robustly validated for their ability to predict PFS.ConclusionIntegration of MR-based radiomic features with clinical and stage variables improved the prediction PFS in patients diagnosed with NPC.     

Construction of a prognostic immune signature for lower grade glioma that can be recognized by MRI radiomics features to predict survival in LGG patients

BackgroundThis study aimed to identify a series of prognostically relevant immune features by immunophenoscore. Immune features were explored using MRI radiomics features to prediction the overall survival (OS) of lower-grade glioma (LGG) patients and their response to immune checkpoints.MethodLGG data were retrieved from TCGA and categorized into training and internal validation datasets. Patients attending the First Affiliated Hospital of Harbin Medical University were included in an external validation cohort. An immunophenoscore-based signature was built to predict malignant potential and response to immune checkpoint inhibitors in LGG patients. In addition, a deep learning neural network prediction model was built for validation of the immunophenoscore-based signature.ResultsImmunophenotype-associated mRNA signatures (IMriskScore) for outcome prediction and ICB therapeutic effects in LGG patients were constructed. Deep learning of neural networks based on radiomics showed that MRI radiomic features determined IMriskScore. Enrichment analysis and ssGSEA correlation analysis were performed. Mutations in CIC significantly improved the prognosis of patients in the high IMriskScore group. Therefore, CIC is a potential therapeutic target for patients in the high IMriskScore group. Moreover, IMriskScore is an independent risk factor that can be used clinically to predict LGG patient outcomes.ConclusionsThe IMriskScore model consisting of a sets of biomarkers, can independently predict the prognosis of LGG patients and provides a basis for the development of personalized immunotherapy strategies. In addition, IMriskScore features were predicted by MRI radiomics using a deep learning approach using neural networks. Therefore, they can be used for the prognosis of LGG patients.     

Outcomes and computed tomography radiomic features extraction in soft tissue sarcomas treated with neoadjuvant radiation therapy

BackgroundThe aim of the study was to evaluate the management, toxicity and treatment responses of patients treated with neoadjuvant radiotherapy (NART) for soft tissue sarcomas (STS) and to analyse the potential of radiomic features extracted from computed tomography (CT) scans.Materials and methodsThis is a retrospective and exploratory study with patients treated between 2006 and 2019. Acute and chronic toxicities are evaluated. Local progression free survival (LPFS), distant progression free survival (DPFS) and overall survival (OS) are analysed. Radiomic features are obtained.ResultsA total of 25 patients were included. Median follow-up is 24 months. Complications in surgical wound healing were observed in 20% of patients, chronic fibrosis was documented as grade 1 (12%) and grade 2 (12%) without grade 3 events and chronic lymphedema as grade 1 (8%) and grade 2 (20%) without grade 3 events. Survival variables were LPFS 76%, DPFS 62% and OS 67.2% at 2-year follow-up. CT radiomics features were associated significantly with local control (GLCM-correlation), systemic control (HUmin, HUpeak, volume, GLCM-correlation and GLZLM-GLNU) and OS (GLZLM-SZE).ConclusionsSTS treated with NART in our centre associate with an OS and toxicity comparable to other series. CT radiomic features have a prognosis potential in STS risk stratification. The results of our study may serve as a motivation for future prospective studies with a greater number of patients.     

Integrated analysis of a competing endogenous RNA network reveals key long noncoding RNAs as potential prognostic biomarkers for hepatocellular carcinoma

Growing evidence has revealed that long noncoding RNAs (lncRNAs) have an important impact on tumorigenesis and tumor progression via a mechanism involving competing endogenous RNAs (ceRNAs). However, their use in predicting the survival of a patient with hepatocellular carcinoma (HCC) remains unclear. The aim of this study was to develop a novel lncRNA expression–based risk score system to accurately predict the survival of patients with HCC. In our study, using expression profiles downloaded from The Cancer Genome Atlas database, the differentially expressed messenger RNAs (mRNAs), lncRNAs, and microRNAs (miRNAs) were explored in patients with HCC and normal liver tissues, and then a ceRNA network constructed. A risk score system was established between lncRNA expression of the ceRNA network and overall survival (OS) or recurrence-free survival (RFS); it was further analyzed for associations with the clinical features of patients with HCC. In HCC, 473 differentially expressed lncRNAs, 63 differentially expressed miRNAs, and 1417 differentially expressed mRNAs were detected. The ceRNA network comprised 41 lncRNA nodes, 12 miRNA nodes, 24 mRNA nodes, and 172 edges. The lncRNA expression–based risk score system for OS was constructed based on six lncRNAs (MYLK-AS1, AL359878.1, PART1, TSPEAR-AS1, C10orf91, and LINC00501), while the risk score system for RFS was based on four lncRNAs (WARS2-IT1, AL359878.1, AL357060.1, and PART1). Univariate and multivariate Cox analyses showed the risk score systems for OS or RFS were significant independent factors adjusted for clinical factors. Receiver operating characteristic curve analysis showed the area under the curve for the risk score system was 0.704 for OS, and 0.71 for RFS. Our result revealed a lncRNA expression–based risk score system for OS or RFS can effectively predict the survival of patients with HCC and aid in good clinical decision-making.     

A nomogram model integrating LI-RADS features and radiomics based on contrast-enhanced magnetic resonance imaging for predicting microvascular invasion in hepatocellular carcinoma falling the Milan criteria

PurposeTo establish and validate a nomogram model incorporating both liver imaging reporting and data system (LI-RADS) features and contrast enhanced magnetic resonance imaging (CEMRI)-based radiomics for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC) falling the Milan criteria.MethodsIn total, 161 patients with 165 HCCs diagnosed with MVI (n = 99) or without MVI (n = 66) were assigned to a training and a test group. MRI LI-RADS characteristics and radiomics features selected by the LASSO algorithm were used to establish the MRI and Rad-score models, respectively, and the independent features were integrated to develop the nomogram model. The predictive ability of the nomogram was evaluated with receiver operating characteristic (ROC) curves.ResultsThe risk factors associated with MVI (P<0.05) were related to larger tumor size, nonsmooth margin, mosaic architecture, corona enhancement and higher Rad-score. The areas under the ROC curve (AUCs) of the MRI feature model for predicting MVI were 0.85 (95% CI: 0.78–0.92) and 0.85 (95% CI: 0.74–0.95), and those for the Rad-score were 0.82 (95% CI: 0.73–0.90) and 0.80 (95% CI: 0.67–0.93) in the training and test groups, respectively. The nomogram presented improved AUC values of 0.87 (95% CI: 0.81–0.94) in the training group and 0.89 (95% CI: 0.81–0.98) in the test group (P<0.05) for predicting MVI. The calibration curve and decision curve analysis demonstrated that the nomogram model had high goodness-of-fit and clinical benefits.ConclusionsThe nomogram model can effectively predict MVI in patients with HCC falling within the Milan criteria and serves as a valuable imaging biomarker for facilitating individualized decision-making.     

The impact of chemokine receptor CXCR4 on breast cancer prognosis: A meta-analysis

Background: C-X-C chemokine receptor type 4 (CXCR4) has been implicated in the invasiveness and metastasis of diverse cancers. However, the published data remain controversial on the correlation between CXCR4 expression level, as well as its subcellular distribution in tumor cells, and the clinical outcome of patients with breast cancer. Methods: To identify the precise role of CXCR4 in the clinical outcome of breast cancer, we performed a meta-analysis including 15 published studies. Original data included the hazard ratios (HRs) of overall survival (OS) and disease-free survival (DFS) in breast cancer with high CXCR4 expression versus low expression. We pooled hazard ratios (HRs) with 95% confidence intervals (CIs) to estimate the hazard. Results: A total of 15 published studies (including 3104 patients) were eligible. Overall survival (OS) and disease-free survival (DFS) of breast cancer were found to be significantly related to CXCR4 expression level, with the HR being 1.65 (95%CI: 1.34–2.03; P < 0.00001) and 1.94 (95%CI: 1.42–2.65; P < 0.00001) respectively. Stratified analysis according to subcellular distribution of CXCR4 showed that high expression in whole cells, cytoplasm and nucleus could predict unfavorable OS, with the HR of 2.02 (95%CI: 1.43–2.85; P < 0.0001), 1.57 (95%CI: 1.13–2.18; P = 0.007), and 1.47 (95%CI: 1.19–1.81; P = 0.0004) respectively. As for DFS, elevated expression level of CXCR4 both in whole cells and cytoplasm predicted a poor outcome, with the HR being 2.23 (95%CI: 1.48–3.37; P = 0.0001) and 1.76 (95%CI: 1.11–2.80; P = 0.02), while high expression in the nucleus had no statistical significance, with HR 1.15 (95%CI: 0.52–2.55; P = 0.73). Conclusions: Increased CXCR4 expression, especially in whole cells and cytoplasm, may serve as a poor prognostic indicator in patients with breast cancer. Future studies are warranted to investigate the relationship between CXCR4 expression and survival of patients with breast carcinoma, which could help predict the clinical outcome and guide clinical decision-making for therapy.     

Efficacy and Safety of Radiotherapy Plus EGFR-TKIs in NSCLC Patients with Brain Metastases: A Meta-Analysis of Published Data

Background: The role of radiotherapy (RT) combined with epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) in non-small cell lung cancer (NSCLC) patients with brain metastasis (BM) remains controversial. Therefore, we conducted a meta-analysis to comprehensively evaluate the efficacy and safety of RT plus EGFR-TKIs in those patients. Materials and Methods: Relevant literatures published between 2012 and 2017 were searched. Objective response rate(ORR), disease control rate (DCR), overall survival (OS), intracranial progression-free survival (I-PFS) and adverse events (AEs) were extracted. The combined hazard ratios (HRs) and relative risks (RRs) were calculated using random effects models. Results: Twenty-four studies (2810 patients) were included in the analysis. Overall, RT plus EGFR-TKIs had higher ORR (RR?=?1.32, 95%CI: 1.13–1.55), DCR (RR?=?1.12, 95%CI: 1.04–1.22), and longer OS (HR?=?0.72, 95%CI: 0.59–0.89), I-PFS (HR?=?0.64, 95%CI: 0.50–0.82) than monotherapy, although with higher overall AEs (20.2% vs 11.8%, RR?=?1.34, 95% CI: 1.11–1.62). Furthermore, subgroup analyses found concurrent RT plus EGFR-TKIs could prolong OS (HR?=?0.69, 95%CI: 0.55–0.86) and I-PFS (HR?=?0.57, 95%CI: 0.44–0.75). Asian ethnicity and lung adenocarcinoma (LAC) patients predicted a more favorable prognosis (HR?=?0.69,95%CI: 0.54–0.88, HR?=?0.66, 95%CI: 0.53–0.83, respectively). Conclusion: RT plus EGFR-TKIs had higher response rate, longer OS and I-PFS than monotherapy in NSCLC patients with BM. Asian LAC patients with EGFR mutation had a better prognosis with concurrent treatment. The AEs of RT plus EGFR-TKIs were tolerated.     

Combined Ablation and Resection (CARe) as an Effective Parenchymal Sparing Treatment for Extensive Colorectal Liver Metastases

Background

Combined intra-operative ablation and resection (CARe) is proposed to treat extensive colorectal liver metastases (CLM). This multicenter study was conducted to evaluate overall survival (OS), local recurrence-free survival (LRFS), hepatic recurrence-free survival (HRFS) and progression-free survival (PFS), to identify factors associated with survival, and to report complications.

Materials and Methods

Four centers combined retropectively their clinical experiences regarding CLM treated by CARe. CLM characteristics, pre- and post-operative chemotherapy regimens, surgical procedures, complications and survivals were analyzed.

Results

Of the 288 patients who received CARe, 210 (73%) had synchronous and 255 (88%) had bilateral CLM. Twenty-two patients (8%) had extrahepatic disease. Median follow-up was 3.17 years (95%CI 2.83–4.08). Median OS was 3.33 years (95%CI 3.08–4.17) and 5-year OS was 37% (95%CI 29–45). One- and 5-year LRFS from ablated lesions were 87.9% (95%CI 83.3–91.2) and 78.0% (95%CI 71–83), respectively. Median HRFS and PFS were 14 months (95%CI 11–18) and 9 months (95%CI 8–11), respectively. One hundred patients experienced complications: 29 grade I, 68 grade II–III–IV, and three deaths. In the multivariate models adjusted for center, the occurrence of complications was confirmed as a major independent factor associated with 3-year OS (HR 1.80; P = 0.008). Five-year OS was 25.6% (95%CI 14.9–37.6) for patients with complications and 45% (95%CI 33.3–53.4) for patients without.

Conclusions

Recent strategies facing advanced CLM include non-anatomic resections, portal-induced hypertrophy of the future remnant liver and aggressive medical preoperative treatments. CARe has the qualities of an approach that allows effective tumor clearance while maintaining good tolerance for the patient.     

Investigating multi-radiomic models for enhancing prediction power of cervical cancer treatment outcomes

Quantitative image features, also known as radiomic features, have shown potential for predicting treatment outcomes in several body sites. We quantitatively analyzed ¹⁸Fluorine–fluorodeoxyglucose (¹⁸F-FDG) Positron Emission Tomography (PET) uptake heterogeneity in the Metabolic Tumor Volume (MTV) of eighty cervical cancer patients to investigate the predictive performance of radiomic features for two treatment outcomes: the development of distant metastases (DM) and loco-regional recurrent disease (LRR). We aimed to fit the highest predictive features in multiple logistic regression models (MLRs). To generate such models, we applied backward feature selection method as part of Leave-One-Out Cross Validation (LOOCV) within a training set consisting of 70% of the original patient cohort. The trained MLRs were tested on an independent set consisted of 30% of the original cohort. We evaluated the performance of the final models using the Area under the Receiver Operator Characteristic Curve (AUC). Accordingly, six models demonstrated superior predictive performance for both outcomes (four for DM and two for LRR) when compared to both univariate-radiomic feature models and Standard Uptake Value (SUV) measurements. This demonstrated approach suggests that the ability of the pre-radiochemotherapy PET radiomics to stratify patient risk for DM and LRR could potentially guide management decisions such as adjuvant systemic therapy or radiation dose escalation.     

Establishment and Validation of SSCLIP Scoring System to Estimate Survival in Hepatocellular Carcinoma Patients Who Received Curative Liver Resection

Background and Aims

There is no prognostic model that is reliable and practical for patients who have received curative liver resection (CLR) for hepatocellular carcinoma (HCC). This study aimed to establish and validate a Surgery-Specific Cancer of the Liver Italian Program (SSCLIP) scoring system for those patients.

Methods

668 eligible patients who underwent CLR for HCC from five separate tertiary hospitals were selected. The SSCLIP was constructed from a training cohort by adding independent predictors that were identified by Cox proportional hazards regression analyses to the original Cancer of the Liver Italian Program (CLIP). The prognostic performance of the SSCLIP at 12 and 36-months was compared with data from existing models. The patient survival distributions at different risk levels of the SSCLIP were also assessed.

Results

Four independent predictors were added to construct the SSCLIP, including age (HR = 1.075, 95%CI: 1.019–1.135, P = 0.009), albumin (HR = 0.804, 95%CI: 0.681–0.950, P = 0.011), prothrombin time activity (HR = 0.856, 95%CI: 0.751–0.975, P = 0.020) and microvascular invasion (HR = 19.852, 95%CI: 2.203–178.917, P = 0.008). In both training and validation cohorts, 12-month and 36-month prognostic performance of the SSCLIP were significantly better than those of the original CLIP, model of end-stage liver disease-based CLIP, Okuda and Child-Turcotte-Pugh score (all P < 0.05). The stratification of risk levels of the SSCLIP showed an enhanced ability to differentiate patients with different outcomes.

Conclusions

A novel SSCLIP to predict survival of HCC patients who received CLR based on objective parameters may provide a refined, useful prognosis algorithm.     

Fasting plasma glucose and alanine aminotransferase on the risk of hepatocellular carcinoma: A nested case-control study

BackgroundThe risk of hepatocellular carcinoma (HCC) is associated with a variety of factors. However, the possible association between the abnormal metabolism of fasting plasma glucose (FPG) and alanine aminotransferase (ALT) and the risk of HCC has not been widely studied. We examined this relationship based on a prospective cohort study.Methods162 first-attack HCC cases during three follow-up periods (2014–2020) were selected as the case group. A control group of 648 participants was obtained by 1:4 matching of age (± 2 years) and sex with noncancer participants in the same period. Conditional logistic regression models, restricted cubic spline models, additive interaction models, and generalized additive models were used to explore the effects of FPG and ALT on the risk of HCC.ResultsAfter correction for confounding factors, we found that abnormal FPG and elevated ALT increased the risk of HCC, respectively. Compared with the normal FPG group, the risk of HCC was significantly increased in the impaired fasting glucose (IFG) (OR = 1.91, 95 %CI: 1.04, 3.50) and diabetes groups (OR = 2.12, 95 %CI: 1.24, 3.63). Compared with the lowest quartile of ALT, subjects in the fourth quartile had an 84 % increased risk of HCC (OR = 1.84, 95 %CI: 1.05–3.21). Moreover, there was an interaction between FPG and ALT on the risk of HCC, and 74 % of the HCC risk could be attributed to their synergistic effect (AP = 0.74, 95 %CI: 0.56–0.92).ConclusionAbnormal FPG and elevated ALT are independent risk factors for HCC, and they have a synergistic effect on the risk of HCC. Therefore, serum FPG and ALT levels should be monitored to prevent the development of HCC.     

Development and validation of robust metabolism-related gene signature in the prognostic prediction of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is one of the most common malignant tumours worldwide. Given metabolic reprogramming in tumours was a crucial hallmark, several studies have demonstrated its value in the diagnostics and surveillance of malignant tumours. The present study aimed to identify a cluster of metabolism-related genes to construct a prediction model for the prognosis of HCC. Multiple cohorts of HCC cases (466 cases) from public datasets were included in the present analysis. (GEO cohort) After identifying a list of metabolism-related genes associated with prognosis, a risk score based on metabolism-related genes was formulated via the LASSO-Cox and LASSO-pcvl algorithms. According to the risk score, patients were stratified into low- and high-risk groups, and further analysis and validation were accordingly conducted. The results revealed that high-risk patients had a significantly worse 5-year overall survival (OS) than low-risk patients in the GEO cohort. (30.0% vs. 57.8%; hazard ratio [HR], 0.411; 95% confidence interval [95% CI], 0.302–0.651; p < 0.001) This observation was confirmed in the external TCGA-LIHC cohort. (34.5% vs. 54.4%; HR 0.452; 95% CI, 0.299–0.681; p < 0.001) To promote the predictive ability of the model, risk score, age, gender and tumour stage were integrated into a nomogram. According to the results of receiver operating characteristic curves and decision curves analysis, the nomogram score possessed a superior predictive ability than conventional factors, which indicate that the risk score combined with clinicopathological features was able to achieve a robust prediction for OS and improve the individualized clinical decision making of HCC patients. In conclusion, the metabolic genes related to OS were identified and developed a metabolism-based predictive model for HCC. Through a series of bioinformatics and statistical analyses, the predictive ability of the model was approved.     

Preoperative prealbumin-to-fibrinogen ratio to predict survival outcomes in hepatocellular carcinoma patients after hepatic resection

BackgroundThis study aimed to evaluate the clinical application of the preoperative prealbumin-to-fibrinogen ratio (PFR) in the clinical diagnosis of hepatocellular carcinoma (HCC) patients and its prognostic value.MethodsThe clinical and laboratory data of 269 HCC patients undergoing surgical treatment from January 2012 to January 2017 in Taizhou Hospital were retrospectively analysed. The Cox regression model was used to analyse the correlation between the PFR and other clinicopathological factors in overall survival (OS) and disease-free survival (DFS).ResultsCox regression analysis showed that the PFR (hazard ratio (HR)=2.123; 95% confidence interval (95% CI), 1.271-3.547; P=0.004) was an independent risk factor affecting the OS of HCC patients. Furthermore, a nomogram was built based on these risk factors. The C-index for the OS nomogram was 0.715.ConclusionsNomograms based on the PFR can be recommended as the correct and actual model to evaluate the prognosis of patients with HCC.     

Clinicopathological and prognostic value of lncRNA PANDAR expression in solid tumors: Evidence from a systematic review and meta-analysis

PANDAR (promoter of CDKN1A antisense DNA damage activated RNA) has been shown to be aberrantly expressed in many types of cancer. Considering conflicting data, the current study was aimed to assess its potential role as a prognostic marker in malignant tumors. A comprehensive literature search of PubMed, Medline, and Web of Science was performed to identify all eligible studies describing the use of PANDAR as a prognostic factor for different types of cancer. Data related to overall survival (OS) and clinicopathologic features were collected and analyzed. The pooled hazard ratio (HR) and odds radio (OR) with a 95% confidence interval (CI) were used to estimate associations. Ten original studies containing 1,231 patients were included. The results showed that in patients with cancer, high PANDAR expression is correlated with lymph node metastasis (LNM; OR = 2.57; 95% CI, 1.76–3.81; p < 0.001), tumor stage (OR = 2.90; 95% CI, 1.25–6.75; p = 0.013), and tumor size (OR = 1.79; 95% CI, 1.11–2.91; p = 0.018). However, sensitivity analysis further demonstrated a significant association between high PANDAR expression and OS, both in multivariate and univariate analysis models (pooled HR 2.01; 95% CI, 1.17–3.44 and pooled HR 2.62; 95% CI, 1.98–3.47, respectively), after omitting one study. These results suggested that PANDAR expression might be indicative of advanced disease and poor prognosis in patients with cancer. Further studies are necessary to determine the value of this risk stratification biomarker in clinical management of patients with cancer.     

No outcome disparities in patients with diffuse large B-cell lymphoma and a low socioeconomic status

IntroductionIn patients with diffuse large B-cell lymphoma (DLBCL) socioeconomic status (SES) is associated with outcome in several population-based studies. The aim of this study was to further investigate the existence of disparities in treatment and survival.MethodsA population-based cohort study was performed including 343 consecutive patients with DLBCL, diagnosed between 2005 and 2012, in the North-west of the Netherlands. SES was based on the socioeconomic position within the Netherlands by use of postal code and categorized as low, intermediate or high. With multivariable logistic regression and Cox proportional hazard models the association between SES and respectively treatment and overall survival (OS) was evaluated.ResultsTwo-third of patients was positioned in low SES. Irrespective of SES an equal proportion of patients received standard immunochemotherapy. SES was not a significant risk indicator for OS (intermediate versus low SES: hazard ratio (HR) 1.31 (95%CI 0.78–2.18); high versus low SES: HR 0.83 (95%CI 0.48–1.46)). The mortality risk remained significantly increased with higher age, advanced performance status, elevated LDH and presence of comorbidity.ConclusionWithin the setting of free access to health care, in this cohort of patients with DLBCL no disparities in treatment and survival were seen in those with lower SES.     

Prognostic Role of Pre-Treatment Serum AFP-L3% in Hepatocellular Carcinoma: Systematic Review and Meta-Analysis

Background

Serum lens culinaris agglutinin-reactive fraction of α-fetoprotein (AFP-L3%) has been widely used for HCC diagnosis and follow-up surveillance as tumor serologic marker. However, the prognostic value of high pre-treatment serum AFP-L3% in patients with hepatocellular carcinoma (HCC) remains controversial. We therefore conduct a meta-analysis to assess the relationship between high pre-treatment serum AFP-L3% and clinical outcome of HCC.

Methods

Eligible studies were identified through systematic literature searches. A meta-analysis of fifteen studies (4,465 patients) was carried out to evaluate the association between high pre-treatment serum AFP-L3% and overall survival (OS) and disease-free survival (DFS) in HCC patients. Sensitivity and subgroup analyses were also conducted in this meta-analysis.

Results

Our analysis results showed that high pre-treatment serum AFP-L3% implied poor OS (HR: 1.65, 95%CI: 1.45–1.89 p<0.00001) and DFS (HR: 1.80, 95% CI: 1.49–2.17 p<0.00001) of HCC. Subgroup analysis revealed that there was association between pre-treatment serum AFP-L3% and endpoint (OS and DFS) in low AFP concentration HCC patients (HR: 1.96, 95% CI: 1.24–3.10, p = 0.004; HR: 2.53, 95% CI: 1.09–5.89, p = 0.03, respectively).

Conclusion

The current evidence suggests that high pre-treatment serum AFP-L3% levels indicated a poor prognosis for patients with HCC and AFP-L3% may have significant prognostic value in HCC patients with low AFP concentration.     

Machine learning helps identifying volume-confounding effects in radiomics

PurposeHighlighting the risk of biases in radiomics-based models will help improve their quality and increase usage as decision support systems in the clinic. In this study we use machine learning-based methods to identify the presence of volume-confounding effects in radiomics features.Methods841 radiomics features were extracted from two retrospective publicly available datasets of lung and head neck cancers using open source software. Unsupervised hierarchical clustering and principal component analysis (PCA) identified relations between radiomics and clinical outcomes (overall survival). Bootstrapping techniques with logistic regression verified features’ prognostic power and robustness.ResultsOver 80% of the features had large pairwise correlations. Nearly 30% of the features presented strong correlations with tumor volume. Using volume-independent features for clustering and PCA did not allow risk stratification of patients. Clinical predictors outperformed radiomics features in bootstrapping and logistic regression.ConclusionsThe adoption of safeguards in radiomics is imperative to improve the quality of radiomics studies. We proposed machine learning (ML) – based methods for robust radiomics signatures development.     

Deep radiomic model based on the sphere–shell partition for predicting treatment response to chemotherapy in lung cancer

BackgroundThe prognosis of chemotherapy is important in clinical decision-making for non-small cell lung cancer (NSCLC) patients.ObjectivesTo develop a model for predicting treatment response to chemotherapy in NSCLC patients from pre-chemotherapy CT images.Materials and MethodsThis retrospective multicenter study enrolled 485 patients with NSCLC who received chemotherapy alone as a first-line treatment. Two integrated models were developed using radiomic and deep-learning-based features. First, we partitioned pre-chemotherapy CT images into spheres and shells with different radii around the tumor (0–3, 3–6, 6–9, 9–12, 12–15 mm) containing intratumoral and peritumoral regions. Second, we extracted radiomic and deep-learning-based features from each partition. Third, using radiomic features, five sphere–shell models, one feature fusion model, and one image fusion model were developed. Finally, the model with the best performance was validated in two cohorts.ResultsAmong the five partitions, the model of 9–12 mm achieved the highest area under the curve (AUC) of 0.87 (95% confidence interval: 0.77–0.94). The AUC was 0.94 (0.85–0.98) for the feature fusion model and 0.91 (0.82–0.97) for the image fusion model. For the model integrating radiomic and deep-learning-based features, the AUC was 0.96 (0.88–0.99) for the feature fusion method and 0.94 (0.85–0.98) for the image fusion method. The best-performing model had an AUC of 0.91 (0.81–0.97) and 0.89 (0.79–0.93) in two validation sets, respectively.ConclusionsThis integrated model can predict the response to chemotherapy in NSCLC patients and assist physicians in clinical decision-making.