Artificial Intelligence in the Advanced Diagnosis of Bladder Cancer-Comprehensive Literature Review and Future Advancement

Identification of novel biomarkers to distinguish clear cell and non-clear cell renal cell carcinoma using bioinformatics and machine learning

Renal cell carcinoma (RCC), accounting for 90% of all kidney cancer, is categorized into clear cell RCC (ccRCC) and non-clear cell RCC (non-ccRCC) for treatment based on the current NCCN Guidelines. Thus, the classification will be associated with therapeutic implications. This study aims to identify novel biomarkers to differentiate ccRCC from non-ccRCC using bioinformatics and machine learning. The gene expression profiles of ccRCC and non-ccRCC subtypes (including papillary RCC (pRCC) and chromophobe RCC (chRCC)), were obtained from TCGA. Differential expression genes (DEGs) were identified, and specific DEGs for ccRCC and non-ccRCC were explored using a Venn diagram. Gene Ontology and pathway enrichment analysis were performed using DAVID. The top ten expressed genes in ccRCC were then selected for machine learning analysis. Feature selection was operated to identify a minimum highly effective gene set for constructing a predictive model. The expression of best-performing gene set was validated on tissue samples from RCC patients using immunohistochemistry techniques. Subsequently, machine learning models for diagnosing RCC were developed using H-scores. There were 910, 415, and 835 genes significantly specific for DEGs in ccRCC, pRCC, and chRCC, respectively. Specific DEGs in ccRCC enriched in PD-1 signaling, immune system, and cytokine signaling in the immune system, whereas TCA cycle and respiratory, signaling by insulin receptor, and metabolism were enriched in chRCC. Feature selection based on Decision Tree Classifier revealed that the model with two genes, including NDUFA4L2 and DAT, had an accuracy of 98.89%. Supervised classification models based on H-score of NDUFA4L2, and DAT revealed that Decision Tree models showed the best performance with 82% accuracy and 0.9 AUC. NDUFA4L2 expression was associated with lymphovascular invasion, pathologic stage and pT stage in ccRCC. Using integrated bioinformatics and machine learning analysis, NDUFA4L2 and DAT were identified as novel biomarkers to differential diagnosis ccRCC from non-ccRCC.

No causal association between insomnia and bladder cancer: a bidirectional two-sample Mendelian randomization study

BACKGROUND

Previous observational studies have indicated a potential link between insomnia and bladder cancer, yet the underlying causal relationship remains uncertain. The current study employed a bidirectional two-sample Mendelian randomization (MR) analysis to investigate this association.

METHODS

A two-sample MR analysis was conducted utilizing publicly available summary data from genome-wide association studies (GWAS) on insomnia and bladder cancer. Various regression methods including the inverse variance weighted (IVW), weighted median, MR-Egger, weighted mode, and simple mode methods were employed for the MR analysis. The presence of pleiotropy and heterogeneity in the MR results was also assessed. Furthermore, additional sensitivity tests were performed to mitigate potential biases.

RESULTS

No significant causal relationship was detected between insomnia and bladder cancer using IVW method (OR = 0.761, 95% CI 0.996-1.005; P = 0.76). Similarly, the IVW model did not reveal any causal effect of bladder cancer on the risk of insomnia (OR = 1.47, 95% CI 0.772-2.799; P = 0.24). Consistent results were obtained from the other four methods employed. There was no evidence of horizontal pleiotropy or heterogeneity in our MR analysis (P > 0.05). The sensitivity analyses further supported the reliability of the estimated causal effects.

CONCLUSIONS

This study presents no evidence for a causal relationship between insomnia and bladder cancer.

Enhancing bladder cancer diagnosis through transitional cell carcinoma polyp detection and segmentation: an artificial intelligence powered deep learning solution

Background

Bladder cancer, specifically transitional cell carcinoma (TCC) polyps, presents a significant healthcare challenge worldwide. Accurate segmentation of TCC polyps in cystoscopy images is crucial for early diagnosis and urgent treatment. Deep learning models have shown promise in addressing this challenge.

Methods

We evaluated deep learning architectures, including Unetplusplus_vgg19, Unet_vgg11, and FPN_resnet34, trained on a dataset of annotated cystoscopy images of low quality.

Results

The models showed promise, with Unetplusplus_vgg19 and FPN_resnet34 exhibiting precision of 55.40 and 57.41%, respectively, suitable for clinical application without modifying existing treatment workflows.

Conclusion

Deep learning models demonstrate potential in TCC polyp segmentation, even when trained on lower-quality images, suggesting their viability in improving timely bladder cancer diagnosis without impacting the current clinical processes.

BHLHE41 inhibits bladder cancer progression via regulation of PYCR1 stability and thus inactivating PI3K/AKT signaling pathway

BACKGROUND

The basic helix-loop-helix family member e41 (BHLHE41) is frequently dysregulated in tumors and plays a crucial role in malignant progression of various cancers. Nevertheless, its specific function and underlying mechanism in bladder cancer (BCa) remain largely unexplored.

METHODS

The expression levels of BHLHE41 in BCa tissues and cells were examined by qRT-PCR and western blot assays. BCa cells stably knocking down or overexpressing BHLHE41 were constructed through lentivirus infection. The changes of cell proliferation, cell cycle distribution, migration, and invasion were detected by CCK-8, flow cytometry, wound healing, transwell invasion assays, respectively. The expression levels of related proteins were detected by western blot assay. The interaction between BHLHE41 and PYCR1 was explored by co-immunoprecipitation analysis.

RESULTS

In this study, we found that BHLHE41 was lowly expressed in bladder cancer tissues and cell lines, and lower expression of BHLHE41 was associated with poor overall survival in bladder cancer patients. Functionally, by manipulating the expression of BHLHE41, we demonstrated that overexpression of BHLHE41 significantly retarded cell proliferation, migration, invasion, and induced cell cycle arrest in bladder cancer through various in vitro and in vivo experiments, while silence of BHLHE41 caused the opposite effect. Mechanistically, we showed that BHLHE41 directly interacted with PYCR1, decreased its stability and resulted in the ubiquitination and degradation of PYCR1, thus inactivating PI3K/AKT signaling pathway. Rescue experiments showed that the effects induced by BHLHE41 overexpression could be attenuated by further upregulating PYCR1.

CONCLUSION

BHLHE41 might be a useful prognostic biomarker and a tumor suppressor in bladder cancer. The BHLHE41/PYCR1/PI3K/AKT axis might be a potential therapeutic target for bladder cancer intervention.

Overexpressed KCNK1 regulates potassium channels affecting molecular mechanisms and biological pathways in bladder cancer

BACKGROUND

This study aimed to explore the expression, molecular mechanism and its biological function of potassium two pore domain channel subfamily K member 1 (KCNK1) in bladder cancer (BC).

METHODS

We integrated large numbers of external samples (n = 1486) to assess KCNK1 mRNA expression levels and collected in-house samples (n = 245) for immunohistochemistry (IHC) experiments to validate at the KCNK1 protein level. Single-cell RNA sequencing (scRNA-seq) analysis was performed to further assess KCNK1 expression and cellular communication. The transcriptional regulatory mechanisms of KCNK1 expression were explored by ChIP-seq, ATAC-seq and ChIA-PET data. Highly expressed co-expressed genes (HECEGs) of KCNK1 were used to explore potential signalling pathways. Furthermore, the immunoassay, clinical significance and molecular docking of KCNK1 were calculated.

RESULTS

KCNK1 mRNA was significantly overexpressed in BC (SMD = 0.58, 95% CI [0.05; 1.11]), validated at the protein level (p < 0.0001). Upregulated KCNK1 mRNA exhibited highly distinguishing ability between BC and control samples (AUC = 0.82 [0.78-0.85]). Further, scRNA-seq analysis revealed that KCNK1 expression was predominantly clustered in BC epithelial cells and tended to increase with cellular differentiation. BC epithelial cells were involved in cellular communication mainly through the MK signalling pathway. Secondly, the KCNK1 transcription start site (TSS) showed promoter-enhancer interactions in three-dimensional space, while being transcriptionally regulated by GRHL2 and FOXA1. Most of the KCNK1 HECEGs were enriched in cell cycle-related signalling pathways. KCNK1 was mainly involved in cellular metabolism-related pathways and regulated cell membrane potassium channel activity. KCNK1 expression was associated with the level of infiltration of various immune cells. Immunotherapy and chemotherapy (docetaxel, paclitaxel and vinblastine) were more effective in BC patients in the high KCNK1 expression group. KCNK1 expression correlated with age, pathology grade and pathologic_M in BC patients.

CONCLUSIONS

KCNK1 was significantly overexpressed in BC. A complex and sophisticated three-dimensional spatial transcriptional regulatory network existed in the KCNK1 TSS and promoted the upregulated of KCNK1 expression. The high expression of KCNK1 might be involved in the cell cycle, cellular metabolism, and tumour microenvironment through the regulation of potassium channels, and ultimately contributed to the deterioration of BC.

CT and MRI findings of small cell neuroendocrine carcinoma of the urinary bladder: comparison with urothelial carcinoma

OBJECTIVE

This study aimed to evaluate the efficacy of CT and MRI findings to differentiate small cell neuroendocrine carcinoma (SCNEC) from urothelial carcinoma (UC) of the urinary bladder.

MATERIALS AND METHODS

This study included 90 patients with histopathologically confirmed bladder cancer (10 SCNECs and 80 UCs). Eight patients with bladder SCNEC and 80 with UC underwent CT and MRI, whereas the remaining two patients with SCNEC underwent CT alone before treatment. CT and MRI findings were retrospectively evaluated and compared between the two pathologies.

RESULTS

The maximum diameter (36.5 mm vs. 19.0 mm, p < 0.01) and height (22.0 mm vs. 14.0 mm, p < 0.01) of the tumor in bladder SCNEC were higher than in UC. The pedunculated configuration (20% vs. 61%, p < 0.05) and irregular tumor margins (20% vs. 76%, p < 0.01) in bladder SCNEC were less common than in UC. The CT attenuation of the solid component in unenhanced CT images was higher in bladder SCNEC than in UC (37 Hounsfield unit [HU] vs. 34 HU, p < 0.01). The apparent diffusion coefficient (ADC) of the solid component in bladder SCNEC was lower than in UC (0.49 × 10-3 mm2/s vs. 1.02 × 10-3 mm2/s, p < 0.01).

CONCLUSION

In comparison with UC, bladder SCNEC was larger, had higher unenhanced CT attenuation, and had a lower ADC value. The pedunculated configuration and irregular tumor margins were typical of bladder UC.

ALYREF m5C RNA methylation reader predicts bladder cancer prognosis by regulating the tumor immune microenvironment

BACKGROUND

5-Methylcytidine (m5C) methylation is a recently emerging epigenetic modification that is closely related to tumor proliferation, occurrence, and metastasis. This study aimed to investigate the clinicopathological characteristics and prognostic value of m5C regulators in bladder cancer (BLCA), and their correlation with the tumor immune microenvironment.

METHODS

Thirteen m5C RNA methylation regulators were analyzed using RNA-sequencing and corresponding clinical information obtained from the TCGA database. The Cluster Profiler package was used to analyze the gene ontology function of potential targets and enriched the Kyoto Encyclopedia of Genes and Genomes pathway. Kaplan-Meier survival analysis was used to compare survival differences using the log-rank test and univariate Cox proportional hazards regression. The correlation between signature prognostic m5C regulators and various immune cells was analyzed. Univariate and multivariate Cox regression analyses identified independence of the ALYREF gene signature.

RESULTS

Nine out of the 13 m5C RNA methylation regulators were differentially expressed in BLCA and normal samples and were co-expressed. These 9 regulators were associated with clinicopathological tumor characteristics, particularly high or low tumor risk, pT or pTNM stage, and migration. Consensus clustering analysis divides the BLCA samples into 4 clusters. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment annotation and gene ontology function analysis identified 273 upregulated and 594 downregulated genes in BLCA. Notably, only ALYREF was significantly correlated with OS (P < .05). ALYREF exhibited significant infiltration levels in macrophage cells. Therefore, we constructed a nomogram for ALYREF as an independent prognostic factor. Additionally, we observed that both the mRNA and protein levels of ALYREF were upregulated, and immunofluorescence showed that ALYREF was mainly distributed in nuclear speckles. ALYREF overexpression was significantly associated with poor OS.

CONCLUSION

Our findings demonstrated the potential of ALYREF to predict clinical prognostic risks in BLCA patients and regulate the tumor immune microenvironment. As such, ALYREF may serve as a novel prognostic indicator in BLCA patients.

FGFR3 Mutations in Urothelial Carcinoma: A Single-Center Study Using Next-Generation Sequencing

Background: Mutations of fibroblast growth factor receptor 3 (FGFR3) are associated with urothelial carcinoma (UC) oncogenesis and are considered an important therapeutic target. Therefore, we evaluated the FGFR3 mutation rate and its clinical significance in urothelial carcinoma (UC) using next-generation sequencing. Methods: A total of 123 patients with UC who were treated at Chonnam National University Hospital (Gwang-ju, Korea) from January 2018 to December 2020 were enrolled. We performed NGS using the Oncomine panel with tumor specimens and blood samples corresponding to each specimen. We analyzed the FGFR3 mutation results according to the type of UC and the effects on early recurrence and progression. Results: The mean age of the patients was 71.39 ± 9.33 years, and 103 patients (83.7%) were male. Overall, the FGFR3 mutation rate was 30.1% (37 patients). The FGFR3 mutation rate was the highest in the non-muscle-invasive bladder cancer (NMIBC) group (45.1%), followed by the muscle-invasive bladder cancer (22.7%) and upper tract UC (UTUC) (14.3%) groups. Patients with FGFR3 mutations had a significantly lower disease stage (p = 0.019) but a high-risk of NMIBC (p < 0.001). Conclusions: Our results revealed that FGFR3 mutations were more prevalent in patients with NMIBC and lower stage UC and associated with a high-risk of NMIBC. Large multicenter studies are needed to clarify the clinical significance of FGFR3 mutations in UC.

Predictive nomograms for risk and prognostic factors in metastatic bladder cancer: a population-based study

Background

Given the poor prognosis of patients with metastatic bladder cancer (MBC), the development of an effective diagnostic and prognostic model is significant in cancer management and for guidance in clinical practice.

Methods

We acquired data of 23,180 bladder cancer patients from Surveillance Epidemiology and End Results (SEER) database registered from 2010 to 2019. The optimal cut-off value for patient age and tumor size was determined by x-tile software. Independent risk factors for MBC were identified by univariate and multivariate logistic regression analyses and prognosis factors were identified by univariate and multivariate cox regression analyses, and risk and prognostic nomograms were constructed. The accuracy of the nomograms was verified by receiver operating characteristic (ROC) curves, calibration curves, and its clinical utility was determined by decision curve analysis (DCA) curves and clinical impact curves (CIC). Kaplan-Meier (K-M) survival curves further confirmed the clinical validity of the prognostic model.

Results

Through logistic regression analyses, we derived that age, histological type, tumor size, T stage, and N stage were independent risk factors for metastasis in bladder cancer patients. By cox regression analyses, age, chemotherapy, histological type, bone, lung and liver metastases were identified as risk factors influencing prognosis of MBC patients. Area under the curve (AUC) of the risk nomogram was 0.80, the AUC values of 1/2/3 years were 0.74/0.71/0.71 in the training group and 0.81/0.77/0.77 in the validation group. Based on calibration curves, DCA curves, CIC and K-M curves, the nomograms were validated with excellent predictive performance and clinical utility for MBC.

Conclusions

The nomograms we constructed have perfect predictive accuracy and clinical practicality for MBC patients, enabling clinicians to provide treatment advice and clinical guidance to patients.

Diagnostics of Thyroid Cancer Using Machine Learning and Metabolomics

The objective of this research is, with the analysis of existing data of thyroid cancer (TC) metabolites, to develop a machine-learning model that can diagnose TC using metabolite biomarkers. Through data mining, pathway analysis, and machine learning (ML), the model was developed. We identified seven metabolic pathways related to TC: Pyrimidine metabolism, Tyrosine metabolism, Glycine, serine, and threonine metabolism, Pantothenate and CoA biosynthesis, Arginine biosynthesis, Phenylalanine metabolism, and Phenylalanine, tyrosine, and tryptophan biosynthesis. The ML classifications' accuracies were confirmed through 10-fold cross validation, and the most accurate classification was 87.30%. The metabolic pathways identified in relation to TC and the changes within such pathways can contribute to more pattern recognition for diagnostics of TC patients and assistance with TC screening. With independent testing, the model's accuracy for other unique TC metabolites was 92.31%. The results also point to a possibility for the development of using ML methods for TC diagnostics and further applications of ML in general cancer-related metabolite analysis.

Genomic Fabrics of the Excretory System's Functional Pathways Remodeled in Clear Cell Renal Cell Carcinoma

Clear cell renal cell carcinoma (ccRCC) is the most frequent form of kidney cancer. Metastatic stages of ccRCC reduce the five-year survival rate to 15%. In this report, we analyze the ccRCC-induced remodeling of the five KEGG-constructed excretory functional pathways in a surgically removed right kidney and its metastasis in the chest wall from the perspective of the Genomic Fabric Paradigm (GFP). The GFP characterizes every single gene in each region by these independent variables: the average expression level (AVE), relative expression variability (REV), and expression correlation (COR) with each other gene. While the traditional approach is limited to only AVE analysis, the novel REV analysis identifies the genes whose correct expression level is critical for cell survival and proliferation. The COR analysis determines the real gene networks responsible for functional pathways. The analyses covered the pathways for aldosterone-regulated sodium reabsorption, collecting duct acid secretion, endocrine and other factor-regulated sodium reabsorption, proximal tubule bicarbonate reclamation, and vasopressin-regulated water reabsorption. The present study confirms the conclusion of our previously published articles on prostate and kidney cancers that even equally graded cancer nodules from the same tumor have different transcriptomic topologies. Therefore, the personalization of anti-cancer therapy should go beyond the individual, to his/her major cancer nodules.

Development and validation of a competitive risk model in patients with rectal cancer: based on SEER database

BACKGROUND

Rectal cancer is one of the most common malignancies. To predict the specific mortality risk of rectal cancer patients, we constructed a predictive nomogram based on a competing risk model.

METHODS

The information on rectal cancer patients was extracted from the SEER database. Traditional survival analysis and specific death analysis were performed separately on the data.

RESULTS

The present study included 23,680 patients, with 16,580 in the training set and 7100 in the validation set. The specific mortality rate calculated by the competing risk model was lower than that of the traditional survival analysis. Age, Marriage, Race, Sex, ICD-O-3Hist/Behav, Grade, AJCC stage, T stage, N stage, Surgery, Examined LN, RX SUMM-SURG OTH, Chemotherapy, CEA, Deposits, Regional nodes positive, Brain, Bone, Liver, Lung, Tumor size, and Malignant were independent influencing factors of specific death. The overall C statistic of the model in the training set was 0.821 (Se = 0.001), and the areas under the ROC curve for cancer-specific survival (CSS) at 1, 3, and 5 years were 0.842, 0.830, and 0.812, respectively. The overall C statistic of the model in the validation set was 0.829 (Se = 0.002), and the areas under the ROC curve for CSS at 1, 3, and 5 years were 0.851, 0.836, and 0.813, respectively.

CONCLUSIONS

The predictive nomogram based on a competing risk model for time-specific mortality in patients with rectal cancer has very desirable accuracy. Thus, the application of the predictive nomogram in clinical practice can help physicians make clinical decisions and follow-up strategies.