DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery.

Deep learning-based multi-omics data integration methods have the capability to reveal the mechanisms of cancer development, discover cancer biomarkers and identify pathogenic targets. However, current methods ignore the potential correlations between samples in integrating multi-omics data. In addition, providing accurate biological explanations still poses significant challenges due to the complexity of deep learning models. Therefore, there is an urgent need for a deep learning-based multi-omics integration method to explore the potential correlations between samples and provide model interpretability. Herein, we propose a novel interpretable multi-omics data integration method (DeepKEGG) for cancer recurrence prediction and biomarker discovery. In DeepKEGG, a biological hierarchical module is designed for local connections of neuron nodes and model interpretability based on the biological relationship between genes/miRNAs and pathways. In addition, a pathway self-attention module is constructed to explore the correlation between different samples and generate the potential pathway feature representation for enhancing the prediction performance of the model. Lastly, an attribution-based feature importance calculation method is utilized to discover biomarkers related to cancer recurrence and provide a biological interpretation of the model. Experimental results demonstrate that DeepKEGG outperforms other state-of-the-art methods in 5-fold cross validation. Furthermore, case studies also indicate that DeepKEGG serves as an effective tool for biomarker discovery. The code is available at https://github.com/lanbiolab/DeepKEGG.

IBPGNET: lung adenocarcinoma recurrence prediction based on neural network interpretability.

Lung adenocarcinoma (LUAD) is the most common histologic subtype of lung cancer. Early-stage patients have a 30-50% probability of metastatic recurrence after surgical treatment. Here, we propose a new computational framework, Interpretable Biological Pathway Graph Neural Networks (IBPGNET), based on pathway hierarchy relationships to predict LUAD recurrence and explore the internal regulatory mechanisms of LUAD. IBPGNET can integrate different omics data efficiently and provide global interpretability. In addition, our experimental results show that IBPGNET outperforms other classification methods in 5-fold cross-validation. IBPGNET identified PSMC1 and PSMD11 as genes associated with LUAD recurrence, and their expression levels were significantly higher in LUAD cells than in normal cells. The knockdown of PSMC1 and PSMD11 in LUAD cells increased their sensitivity to afatinib and decreased cell migration, invasion and proliferation. In addition, the cells showed significantly lower EGFR expression, indicating that PSMC1 and PSMD11 may mediate therapeutic sensitivity through EGFR expression.

Radiomics model based on contrast-enhanced computed tomography imaging for early recurrence monitoring after radical resection of AFP-negative hepatocellular carcinoma.

BACKGROUND: Although radical surgical resection is the most effective treatment for hepatocellular carcinoma (HCC), the high rate of postoperative recurrence remains a major challenge, especially in patients with alpha-fetoprotein (AFP)-negative HCC who lack effective biomarkers for postoperative recurrence surveillance. Emerging radiomics can reveal subtle structural changes in tumors by analyzing preoperative contrast-enhanced computer tomography (CECT) imaging data and may provide new ways to predict early recurrence (recurrence within 2 years) in AFP-negative HCC. In this study, we propose to develop a radiomics model based on preoperative CECT to predict the risk of early recurrence after surgery in AFP-negative HCC. PATIENTS AND METHODS: Patients with AFP-negative HCC who underwent radical resection were included in this study. A computerized tool was used to extract radiomic features from the tumor region of interest (ROI), select the best radiographic features associated with patient's postoperative recurrence, and use them to construct the radiomics score (RadScore), which was then combined with clinical and follow-up information to comprehensively evaluate the reliability of the model. RESULTS: A total of 148 patients with AFP-negative HCC were enrolled in this study, and 1,977 radiographic features were extracted from CECT, 2 of which were the features most associated with recurrence in AFP-negative HCC. They had good predictive ability in both the training and validation cohorts, with an area under the ROC curve (AUC) of 0.709 and 0.764, respectively. Tumor number, microvascular invasion (MVI), AGPR and radiomic features were independent risk factors for early postoperative recurrence in patients with AFP-negative HCC. The AUCs of the integrated model in the training and validation cohorts were 0.793 and 0.791, respectively. The integrated model possessed the clinical value of predicting early postoperative recurrence in patients with AFP-negative HCC according to decision curve analysis, which allowed the classification of patients into subgroups of high-risk and low-risk for early recurrence. CONCLUSION: The nomogram constructed by combining clinical and imaging features has favorable performance in predicting the probability of early postoperative recurrence in AFP-negative HCC patients, which can help optimize the therapeutic decision-making and prognostic assessment of AFP-negative HCC patients.

It is time to implement molecular classification in endometrial cancer.

A huge effort has been done in redefining endometrial cancer (EC) risk classes in the last decade. However, known prognostic factors (FIGO staging and grading, biomolecular classification and ESMO-ESGO-ESTRO risk classes stratification) are not able to predict outcomes and especially recurrences. Biomolecular classification has helped in re-classifying patients for a more appropriate adjuvant treatment and clinical studies suggest that currently used molecular classification improves the risk assessment of women with EC, however, it does not clearly explain differences in recurrence profiles. Furthermore, a lack of evidence appears in EC guidelines. Here, we summarize the main concepts why molecular classification is not enough in the management of endometrial cancer, by highlighting some promising innovative examples in scientific literature studies with a clinical potential significant impact.

Orbital solitary fibrous tumours: clinicopathological characteristics and recurrence prediction.

BACKGROUND: SFTs are thought to have an unpredictable clinical course and currently have no recognized prognostic criterion. Our study aimed to determine the relationship between clinicopathological characteristics and the prognosis of patients with orbital SFTs. METHODS: The clinicopathological features of these patients were extracted from clinical records. The relationships between these features and prognosis were analysed. RESULTS: The positive rates of CD34, CD99, Blc2, and STAT6 expression were 90.3%, 90.3%, 83.9%, and 100%, respectively. The tumour recurrence rate was 38.7%. A higher recurrence rate was observed in patients with Ki67 index ≥ 5 (56.25% vs. 20%, P = 0.038). CONCLUSION: A Ki67 index ≥ 5 was an effective parameter for predicting tumour recurrence of orbital SFTs. Close follow-up is needed for these patients.

Forecasting determinants of recurrence in lung cancer patients exploiting various machine learning models.

Lung cancer recurrence seems to be the most leading cause of death as well as deterioration of lifespan. Proper assessment of the probability of recurrence in early-stage lung cancer is necessary to push up the treatment progress. We therefore employed machine-learning technologies to forecast post-operative recurrence risks using 174 lung cancer patient records. Six classification algorithms logistic regression, SVM, decision tree classification, random forest classification, XGBoost and lightGBM were used to predict the cancer recurrence. The patient samples were divided into training and test group with the split ratio of 3:1 for model generation and the accuracy were validated using k-fold cross-validation method. It is worth noting that the logistic regression model outperformed all the models in both training (Accuracy = 0.82) and test set (Accuracy = 0.79) on k-fold validation. Further, the optimal features (n = 7) identified using the RFE method is certainly helpful to improve the model in a high precision. The imperative risk factors associated with recurrence were identified using three feature selection methods. Importantly, our research showed that age is an important prognostic factor to be considered during the recurrence prediction. Indeed, severe concern on the identified risk factors combined with predictive models assists the physician to reduce the cancer recurrence rate in patients with lung cancer.

Preliminary analysis of predicting the first recurrence in patients with neovascular age-related macular degeneration using deep learning.

BACKGROUND: To predict, using deep learning, the first recurrence in patients with neovascular age-related macular degeneration (nAMD) after three monthly loading injections of intravitreal anti-vascular endothelial growth factor (anti-VEGF). METHODS: Optical coherence tomography (OCT) images were obtained at baseline and after the loading phase. The first recurrence was defined as the initial appearance of a new retinal hemorrhage or intra/subretinal fluid accumulation after the initial resolution of exudative changes after three loading injections. Standard U-Net architecture was used to identify the three retinal fluid compartments, which include pigment epithelial detachment, subretinal fluid, and intraretinal fluid. To predict the first recurrence of nAMD, classification learning was conducted to determine whether the first recurrence occurred within three months after the loading phase. The recurrence classification architecture was built using ResNet50. The model with retinal regions of interest of the entire region and fluid region on OCT at baseline and after the loading phase is presented. RESULTS: A total of 1,444 eyes of 1,302 patients were included. The mean duration until the first recurrence after the loading phase was 8.20 ± 15.56 months. The recurrence classification system revealed that the model with the fluid region of OCT after the loading phase provided the highest classification performance, with an area under the receiver operating characteristic curve (AUC) of 0.725 ± 0.012. Heatmap analysis revealed that three pathological fluids, subsided choroidal neovascularization lesions, and hyperreflective foci were important areas for the first recurrence. CONCLUSIONS: The deep learning algorithm allowed for the prediction of the first recurrence for three months after the loading phase with adequate feasibility. An automated prediction system may assist in establishing patient-specific treatment plans and the provision of individualized medical care for patients with nAMD.

Monitoring of intestinal inflammation and prediction of recurrence in ulcerative colitis.

Background and objectives: Ulcerative colitis is a chronic recurrent intestinal inflammatory disease, and its recurrence is difficult to predict. In this review, we summarized the objective indicators that can be used to evaluate intestinal inflammation, the purpose is to better predict the clinical recurrence of UC, formulate individualized treatment plan during remission of UC, and improve the level of diagnosis and treatment of UC.Methods: Based on the search results in the PUBMED database, we explored the accuracy and value of these methods in predicting the clinical recurrence of UC from the following three aspects: endoscopic and histological scores, serum biomarkers and fecal biomarkers.Results: Colonoscopy with biopsy is the gold standard for assessing intestinal inflammation, but it is invasive, inconvenient and expensive. At present, there is no highly sensitive and specific endoscopic or histological score to predict the clinical recurrence of UC. Compared with serum biomarkers, fecal biomarkers have higher sensitivity and specificity because they are in direct contact with the intestine and are closer to the site of intestinal inflammation. Fecal calprotectin is currently the most studied and meaningful fecal biomarker. Lactoferrin and S100A12, as novel biomarkers, have no better performance than FC in predicting the recurrence of UC.Conclusions: FC is currently the most promising predictive marker, but it lacks an accurate cut-off value. Combining patient symptoms, incorporating multiple indicators to construct a UC recurrence prediction model, and formulating individualized treatment plans for high recurrence risk patients will be the focus of UC remission management.

Deep Learning-Based Recurrence Prediction of Atrial Fibrillation After Catheter Ablation.

BACKGROUND: Radiofrequency catheter ablation (RFCA) is an effective therapy for atrial fibrillation (AF). However, it the problem of AF recurrence remains. This study investigates whether a deep convolutional neural network (CNN) can accurately predict AF recurrence in patients with AF who underwent RFCA, and compares CNN with conventional statistical analysis.Methods and Results:Three-hundred and ten patients with AF after RFCA treatment, including 94 patients with AF recurrence, were enrolled. Nine variables are identified as candidate predictors by univariate Cox proportional hazards regression (CPH). A CNNSurv model for AF recurrence prediction was proposed. The model's discrimination ability is validated by a 10-fold cross validation method and measured by C-index. After back elimination, 4 predictors are used for model development, they are N-terminal pro-BNP (NT-proBNP), paroxysmal AF (PAF), left atrial appendage volume (LAAV) and left atrial volume (LAV). The average testing C-index is 0.76 (0.72-0.79). The corresponding calibration plot appears to fit well to a diagonal, and the P value of the Hosmer-Lemeshow test also indicates the proposed model has good calibration ability. The proposed model has superior performance compared with the DeepSurv and multivariate CPH. The result of risk stratification indicates that patients with non-PAF, higher NT-proBNP, larger LAAV and LAV would have higher risks of AF recurrence. CONCLUSIONS: The proposed CNNSurv model has better performance than conventional statistical analysis, which may provide valuable guidance for clinical practice.

A Quantitative Comparison between Shannon and Tsallis-Havrda-Charvat Entropies Applied to Cancer Outcome Prediction.

In this paper, we propose to quantitatively compare loss functions based on parameterized Tsallis-Havrda-Charvat entropy and classical Shannon entropy for the training of a deep network in the case of small datasets which are usually encountered in medical applications. Shannon cross-entropy is widely used as a loss function for most neural networks applied to the segmentation, classification and detection of images. Shannon entropy is a particular case of Tsallis-Havrda-Charvat entropy. In this work, we compare these two entropies through a medical application for predicting recurrence in patients with head-neck and lung cancers after treatment. Based on both CT images and patient information, a multitask deep neural network is proposed to perform a recurrence prediction task using cross-entropy as a loss function and an image reconstruction task. Tsallis-Havrda-Charvat cross-entropy is a parameterized cross-entropy with the parameter α. Shannon entropy is a particular case of Tsallis-Havrda-Charvat entropy for α=1. The influence of this parameter on the final prediction results is studied. In this paper, the experiments are conducted on two datasets including in total 580 patients, of whom 434 suffered from head-neck cancers and 146 from lung cancers. The results show that Tsallis-Havrda-Charvat entropy can achieve better performance in terms of prediction accuracy with some values of α.

Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [68Ga]Ga-PSMA-11 PET/MRI.

PURPOSE: Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning. METHODS: Fifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses. RESULTS: The area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively. CONCLUSION: Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.

Decreased sphingomyelin (t34:1) is a candidate predictor for lung squamous cell carcinoma recurrence after radical surgery: a case-control study.

BACKGROUND: To reduce disease recurrence after radical surgery for lung squamous cell carcinomas (SQCCs), accurate prediction of recurrent high-risk patients is required for efficient patient selection for adjuvant chemotherapy. Because treatment modalities for recurrent lung SQCCs are scarce compared to lung adenocarcinomas (ADCs), accurately selecting lung SQCC patients for adjuvant chemotherapy after radical surgery is highly important. Predicting lung cancer recurrence with high objectivity is difficult with conventional histopathological prognostic factors; therefore, identification of a novel predictor is expected to be highly beneficial. Lipid metabolism alterations in cancers are known to contribute to cancer progression. Previously, we found that increased sphingomyelin (SM)(d35:1) in lung ADCs is a candidate for an objective recurrence predictor. However, no lipid predictors for lung SQCC recurrence have been identified to date. This study aims to identify candidate lipid predictors for lung SQCC recurrence after radical surgery. METHODS: Recurrent (n = 5) and non-recurrent (n = 6) cases of lung SQCC patients who underwent radical surgery were assigned to recurrent and non-recurrent groups, respectively. Extracted lipids from frozen tissue samples of primary lung SQCC were analyzed by liquid chromatography-tandem mass spectrometry. Candidate lipid predictors were screened by comparing the relative expression levels between the recurrent and non-recurrent groups. To compare lipidomic characteristics associated with recurrent SQCCs and ADCs, a meta-analysis combining SQCC (n = 11) and ADC (n = 20) cohorts was conducted. RESULTS: Among 1745 screened lipid species, five species were decreased (≤ 0.5 fold change; P < 0.05) and one was increased (≥ 2 fold change; P < 0.05) in the recurrent group. Among the six candidates, the top three final candidates (selected by AUC assessment) were all decreased SM(t34:1) species, showing strong performance in recurrence prediction that is equivalent to that of histopathological prognostic factors. Meta-analysis indicated that decreases in a limited number of SM species were observed in the SQCC cohort as a lipidomic characteristic associated with recurrence, in contrast, significant increases in a broad range of lipids (including SM species) were observed in the ADC cohort. CONCLUSION: We identified decreased SM(t34:1) as a novel candidate predictor for lung SQCC recurrence. Lung SQCCs and ADCs have opposite lipidomic characteristics concerning for recurrence risk. TRIAL REGISTRATION: This retrospective study was registered at the UMIN Clinical Trial Registry ( UMIN000039202 ) on January 21, 2020.

Sphingomyelin(d35:1) as a novel predictor for lung adenocarcinoma recurrence after a radical surgery: a case-control study.

BACKGROUND: To improve the postoperative prognosis of patients with lung cancer, predicting the recurrence high-risk patients is needed for the efficient application of adjuvant chemotherapy. However, predicting lung cancer recurrence after a radical surgery is difficult even with conventional histopathological prognostic factors, thereby a novel predictor should be identified. As lipid metabolism alterations are known to contribute to cancer progression, we hypothesized that lung adenocarcinomas with high recurrence risk contain candidate lipid predictors. This study aimed to identify candidate lipid predictors for the recurrence of lung adenocarcinoma after a radical surgery. METHODS: Frozen tissue samples of primary lung adenocarcinoma obtained from patients who underwent a radical surgery were retrospectively reviewed. Recurrent and non-recurrent cases were assigned to recurrent (n = 10) and non-recurrent (n = 10) groups, respectively. Extracted lipids from frozen tissue samples were subjected to liquid chromatography-tandem mass spectrometry analysis. The average total lipid levels of the non-recurrent and recurrent groups were compared. Candidate predictors were screened by comparing the folding change and P-value of t-test in each lipid species between the recurrent and non-recurrent groups. RESULTS: The average total lipid level of the recurrent group was 1.65 times higher than that of the non-recurrent group (P < 0.05). A total of 203 lipid species were increased (folding change, ≥2; P < 0.05) and 4 lipid species were decreased (folding change, ≤0.5; P < 0.05) in the recurrent group. Among these candidates, increased sphingomyelin (SM)(d35:1) in the recurrent group was the most prominent candidate predictor, showing high performance of recurrence prediction (AUC, 9.1; sensitivity, 1.0; specificity, 0.8; accuracy, 0.9). CONCLUSION: We propose SM(d35:1) as a novel candidate predictor for lung adenocarcinoma recurrence. Our finding can contribute to precise recurrence prediction and qualified postoperative therapeutic strategy for lung adenocarcinomas. TRIAL REGISTRATION: This retrospective study was registered at the UMIN Clinical Trial Registry ( UMIN000039202 ) on 21st January 2020.

A whole slide image-based machine learning approach to predict ductal carcinoma in situ (DCIS) recurrence risk.

BACKGROUND: Breast ductal carcinoma in situ (DCIS) represent approximately 20% of screen-detected breast cancers. The overall risk for DCIS patients treated with breast-conserving surgery stems almost exclusively from local recurrence. Although a mastectomy or adjuvant radiation can reduce recurrence risk, there are significant concerns regarding patient over-/under-treatment. Current clinicopathological markers are insufficient to accurately assess the recurrence risk. To address this issue, we developed a novel machine learning (ML) pipeline to predict risk of ipsilateral recurrence using digitized whole slide images (WSI) and clinicopathologic long-term outcome data from a retrospectively collected cohort of DCIS patients (n = 344) treated with lumpectomy at Nottingham University Hospital, UK. METHODS: The cohort was split case-wise into training (n = 159, 31 with 10-year recurrence) and validation (n = 185, 26 with 10-year recurrence) sets. The sections from primary tumors were stained with H&E, then digitized and analyzed by the pipeline. In the first step, a classifier trained manually by pathologists was applied to digital slides to annotate the areas of stroma, normal/benign ducts, cancer ducts, dense lymphocyte region, and blood vessels. In the second step, a recurrence risk classifier was trained on eight select architectural and spatial organization tissue features from the annotated areas to predict recurrence risk. RESULTS: The recurrence classifier significantly predicted the 10-year recurrence risk in the training [hazard ratio (HR) = 11.6; 95% confidence interval (CI) 5.3-25.3, accuracy (Acc) = 0.87, sensitivity (Sn) = 0.71, and specificity (Sp) = 0.91] and independent validation [HR = 6.39 (95% CI 3.0-13.8), p < 0.0001;Acc = 0.85, Sn = 0.5, Sp = 0.91] cohorts. Despite the limitations of our cohorts, and in some cases inferior sensitivity performance, our tool showed superior accuracy, specificity, positive predictive value, concordance, and hazard ratios relative to tested clinicopathological variables in predicting recurrences (p < 0.0001). Furthermore, it significantly identified patients that might benefit from additional therapy (validation cohort p = 0.0006). CONCLUSIONS: Our machine learning-based model fills an unmet clinical need for accurately predicting the recurrence risk for lumpectomy-treated DCIS patients.

A predictive nomogram for individualized recurrence stratification of bladder cancer using multiparametric MRI and clinical risk factors.

BACKGROUND: Preoperative prediction of bladder cancer (BCa) recurrence risk is critical for individualized clinical management of BCa patients. PURPOSE: To develop and validate a nomogram based on radiomics and clinical predictors for personalized prediction of the first 2 years (TFTY) recurrence risk. STUDY TYPE: Retrospective. POPULATION: Preoperative MRI datasets of 71 BCa patients (34 recurrent) were collected, and divided into training (n = 50) and validation cohorts (n = 21). FIELD STRENGTH/SEQUENCE: 3.0T MRI/T2 -weighted (T2 W), multi-b-value diffusion-weighted (DW), and dynamic contrast-enhanced (DCE) sequences. ASSESSMENT: Radiomics features were extracted from the T2 W, DW, apparent diffusion coefficient, and DCE images. A Rad_Score model was constructed using the support vector machine-based recursive feature elimination approach and a logistic regression model. Combined with the important clinical factors, including age, gender, grade, and muscle-invasive status (MIS) of the archived lesion, tumor size and number, surgery, and image signs like stalk and submucosal linear enhancement, a radiomics-clinical nomogram was developed, and its performance was evaluated in the training and the validation cohorts. The potential clinical usefulness was analyzed by the decision curve. STATISTICAL TESTS: Univariate and multivariate analyses were performed to explore the independent predictors for BCa recurrence prediction. RESULTS: Of the 1872 features, the 32 with the highest area under the curve (AUC) of receiver operating characteristic were selected for the Rad_Score calculation. The nomogram developed by two independent predictors, MIS and Rad_Score, showed good performance in the training (accuracy 88%, AUC 0.915, P << 0.01) and validation cohorts (accuracy 80.95%, AUC 0.838, P = 0.009). The decision curve exhibited when the risk threshold was larger than 0.3, more benefit was observed by using the radiomics-clinical nomogram than using the radiomics or clinical model alone. DATA CONCLUSION: The proposed radiomics-clinical nomogram has potential in the preoperative prediction of TFTY BCa recurrence. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;50:1893-1904.

Moderate alteration to gut microbiota brought by colorectal adenoma resection.

BACKGROUND AND AIM: Microbial dysbiosis is involved in the development of colorectal cancer and its most common precancerous lesion, colorectal adenoma. Endoscopic resection is one of the procedures for primary prevention of colorectal cancer, yet little is known about how the endoscopic therapy influences gut microbiota. METHODS: We conducted a prospective study of 20 patients who underwent endoscopic resection of colorectal adenoma and analyzed the fecal microbiota before and 3 months after adenoma resection. MiSeq sequencing of 16S rRNA genes was performed to determine the alterations in microbial diversity and structure. To discriminate the microbiota of the two groups, random forest and receiver operating characteristic analysis were applied, and a genus-based microbiota signature was obtained. RESULTS: Despite few alterations in overall microbial structure after adenoma resection, the abundance of Parabacteroides revealed a significant increase postoperatively (3.8% vs 1.5%, 0.1160), and the microbiota signature of Parabacteroides, Streptococcus, and Ruminococcus showed an optimal discriminating performance of postoperative status with the area under the curve 0.788, P < 0.001. CONCLUSION: Fecal microbial alterations indicate the moderate influence of adenoma resection on gut microbiota and lay the groundwork for microbial prediction of adenoma recurrence. Larger sample studies are further required to validate the findings.

Expression signatures of exosomal long non-coding RNAs in urine serve as novel non-invasive biomarkers for diagnosis and recurrence prediction of bladder cancer.

Recently, expression signatures of exosomal long non-coding RNAs (lncRNAs) have been proposed as potential non-invasive biomarkers for cancer detection. In this study, we aimed to develop a urinary exosome (UE)-derived lncRNA panel for diagnosis and recurrence prediction of bladder cancer (BC). Quantitative real-time polymerase chain reaction (qRT-PCR) was performed to screen and evaluate the expressions of eight candidate lncRNAs in a training set (208 urine samples) and a validation set (160 urine samples). A panel consisting of three differently expressed lncRNAs (MALAT1, PCAT-1 and SPRY4-IT1) was established for BC diagnosis in the training set, showing an area under the receiver-operating characteristic (ROC) curve (AUC) of 0.854. Subsequently, the performance of the panel was further verified with an AUC of 0.813 in the validation set, which was significantly higher than that of urine cytology (0.619). In addition, Kaplan-Meier analysis suggested that the up-regulation of PCAT-1 and MALAT1 was associated with poor recurrence-free survival (RFS) of non-muscle-invasive BC (NMIBC) (p < 0.001 and p = 0.002, respectively), and multivariate Cox proportional hazards regression analysis revealed that exosomal PCAT-1 overexpression was an independent prognostic factor for the RFS of NMIBC (p = 0.018). Collectively, our findings indicated that UE-derived lncRNAs possessed considerable clinical value in the diagnosis and prognosis of BC.

Construction of a novel multi-gene assay (42-gene classifier) for prediction of late recurrence in ER-positive breast cancer patients.

PURPOSE: Prediction models for late (> 5 years) recurrence in ER-positive breast cancer need to be developed for the accurate selection of patients for extended hormonal therapy. We attempted to develop such a prediction model focusing on the differences in gene expression between breast cancers with early and late recurrence. METHODS: For the training set, 779 ER-positive breast cancers treated with tamoxifen alone for 5 years were selected from the databases (GSE6532, GSE12093, GSE17705, and GSE26971). For the validation set, 221 ER-positive breast cancers treated with adjuvant hormonal therapy for 5 years with or without chemotherapy at our hospital were included. Gene expression was assayed by DNA microarray analysis (Affymetrix U133 plus 2.0). RESULTS: With the 42 genes differentially expressed in early and late recurrence breast cancers in the training set, a prediction model (42GC) for late recurrence was constructed. The patients classified by 42GC into the late recurrence-like group showed a significantly (P = 0.006) higher late recurrence rate as expected but a significantly (P = 1.62 × E-13) lower rate for early recurrence than non-late recurrence-like group. These observations were confirmed for the validation set, i.e., P = 0.020 for late recurrence and P = 5.70 × E-5 for early recurrence. CONCLUSION: We developed a unique prediction model (42GC) for late recurrence by focusing on the biological differences between breast cancers with early and late recurrence. Interestingly, patients in the late recurrence-like group by 42GC were at low risk for early recurrence.

Myenteric plexitis at the proximal resection margin is a predictive marker for surgical recurrence of ileocaecal Crohn's disease.

AIM: Identifying predictors for the recurrence of Crohn's disease (CD) after surgery to improve disease surveillance or targeted therapy is rational. The purpose of this study was to examine the relationship between myenteric plexitis (MP) and clinical or surgical recurrence. METHOD: Between 2000 and 2010, patients who underwent primary ileocaecal resection for CD at a single tertiary referral centre were identified. The histopathology was retrospectively reviewed for MP at the resection margins. The severity of MP was graded from 0 to 3 using a previously described classification. Information on demographics, surgical details and evidence of clinical or surgical recurrence was obtained from medical records. RESULTS: There were 86 patients (49 women) of median age 31.5 (interquartile ratio 23.5-41.0) years. Seventy-six and 77 specimens were assessable for proximal and distal MP. Proximal MP was present in 53 (69.7%) patients and was classified as mild, moderate or severe in 30 (39.5%), 14 (18.4) and nine (11.8%). MP at the distal resection margin was present in 40 (51.9%). Forty (46.5%) patients developed clinical recurrence of whom 16 (18.6%) required surgery. Clinical factors that predicted recurrence included age > 40 (P = 0.001) and the presence of an anastomosis (P = 0.023). On univariate analysis severe plexitis (Grade 3 MP) was also associated with surgical recurrence (P = 0.035). CONCLUSION: This retrospective study supports the association between MP at the proximal resection margin and surgical recurrence.

Robustness of magnetic resonance imaging and positron emission tomography radiomic features in prostate cancer: Impact on recurrence prediction after radiation therapy.

Background and purpose: Radiomic features from MRI and PET are an emerging tool with potential to improve prostate cancer outcomes. However, feature robustness due to image segmentation variations is currently unknown. Therefore, this study aimed to evaluate the robustness of radiomic features with segmentation variations and their impact on predicting biochemical recurrence (BCR). Materials and methods: Multi-scanner, pre-radiation therapy imaging from 142 patients with localised prostate cancer was used. Imaging included T2-weighted (T2), apparent diffusion coefficient (ADC) MRI, and prostate-specific membrane antigen (PSMA)-PET. The prostate gland and intraprostatic tumours were manually and automatically segmented, and differences were quantified using Dice Coefficient (DC). Radiomic features including shape, first-order, and texture features were extracted for each segmentation from original and filtered images. Intraclass Correlation Coefficient (ICC) and Mean Absolute Percentage Difference (MAPD) were used to assess feature robustness. Random forest (RF) models were developed for each segmentation using robust features to predict BCR. Results: Prostate gland segmentations were more consistent (mean DC = 0.78) than tumour segmentations (mean DC = 0.46). 112 (3.6 %) radiomic features demonstrated 'excellent' robustness (ICC > 0.9 and MAPD < 1 %), and 480 features (15.4 %) demonstrated 'good' robustness (ICC > 0.75 and MAPD < 5 %). PET imaging provided more features with excellent robustness than T2 and ADC. RF models showed strong predictive power for BCR with a mean area under the receiver-operator-characteristics curve (AUC) of 0.89 (range 0.85-0.93). Conclusion: When using radiomic features for predictive modelling, segmentation variability should be considered. To develop BCR predictive models, radiomic features from the entire prostate gland are preferable over tumour segmentation-based features.