Prediction of non-muscle invasive bladder cancer recurrence using machine learning of quantitative nuclear features

An efficient graph attention framework enhances bladder cancer prediction

Bladder (BL) cancer is the 10th most common cancer worldwide, ranking 9th in males and 13th in females in the United States, respectively. BL cancer is a quick-growing tumor of all cancer forms. Given a malignant tumor's high malignancy, rapid metastasis prediction and accurate treatment are critical. The most significant drivers of the intricate genesis of cancer are complex genetics, including deoxyribonucleic acid (DNA) insertions and deletions, abnormal structure, copy number variations (CNVs), and single nucleotide variations (SNVs). The proposed method enhances the identification of driver genes at the individual patient level by employing attention mechanisms to extract features of both coding and non-coding genes and predict BL cancer based on the personalized driver gene (PDG) detection. The embedded vectors are propagated through the three dense blocks for the binary classification of PDGs. The novel constructure of graph neural network (GNN) with attention mechanism, called Multi Stacked-Layered GAT (MSL-GAT) leverages graph attention mechanisms (GAT) to identify and predict critical driver genes associated with BL cancer progression. In order to pick out and extract essential features from both coding and non-coding genes, including long non-coding RNAs (lncRNAs), which are known to be crucial to the advancement of BL cancer. The approach analyzes key genetic changes (such as SNVs, CNVs, and structural abnormalities) that lead to tumorigenesis and metastasis by concentrating on personalized driver genes (PDGs). The discovery of genes crucial for the survival and proliferation of cancer cells is made possible by the model's precise classification of PDGs. MSL-GAT draws attention to certain lncRNAs and other non-coding elements that control carcinogenic pathways by utilizing the attention mechanism. Tumor development, metastasis, and medication resistance are all facilitated by these lncRNAs, which are frequently overexpressed or dysregulated in BL cancer. In order to reduce the survival of cancer cells, the model's predictions can direct specific treatment approaches, such as RNA interference (RNAi), to mute or suppress the expression of these important genes. MSL-GAT is followed by three dense blocks that spread the embedded vectors to categorize PDGs, making it possible to determine which genes are more likely to cause BL cancer in a certain patient. The model facilitates the identification of new treatment targets by offering a thorough understanding of the molecular landscape of BL cancer through the integration of multi-omics data, encompassing as genomic, transcriptomic, and epigenomic metadata. We compared the novel approach with classical machine learning methods and other deep learning-based methods on benchmark TCGA-BLCA, and the leave-one-out experimental results showed that MSL-GAT achieved better performance than competitive methods. This approach achieves accuracy with 97.72% and improves specificity and sensitivity. It can potentially aid physicians during early prediction of BL cancer.

Predicting response to neoadjuvant chemotherapy in muscle-invasive bladder cancer via interpretable multimodal deep learning

Building accurate prediction models and identifying predictive biomarkers for treatment response in Muscle-Invasive Bladder Cancer (MIBC) are essential for improving patient survival but remain challenging due to tumor heterogeneity, despite numerous related studies. To address this unmet need, we developed an interpretable Graph-based Multimodal Late Fusion (GMLF) deep learning framework. Integrating histopathology and cell type data from standard H&E images with gene expression profiles derived from RNA sequencing from the SWOG S1314-COXEN clinical trial (ClinicalTrials.gov NCT02177695 2014-06-25), GMLF uncovered new histopathological, cellular, and molecular determinants of response to neoadjuvant chemotherapy. Specifically, we identified key gene signatures that drive the predictive power of our model, including alterations in TP63, CCL5, and DCN. Our discovery can optimize treatment strategies for patients with MIBC, e.g., improving clinical outcomes, avoiding unnecessary treatment, and ultimately, bladder preservation. Additionally, our approach could be used to uncover predictors for other cancers.

Radiofrequency induced hyperthermia in non-muscle invasive bladder cancer: Oncologic outcomes in a real-world scenario

OBJECTIVES

Patients with non-muscle invasive bladder cancer (NMIBC) face a high risk of recurrence and progression after transurethral resection, making adjuvant therapies necessary. Intravesical device-assisted therapies, such as radiofrequency-induced thermochemotherapy (RITE), have shown promise in enhancing the effectiveness of intravesical chemotherapies. This study aimed to evaluate oncological outcomes in patients with NMIBC treated with RITE in a real-world setting, encompassing those unresponsive to prior Bacillus Calmette-Guérin (BCG) or intravesical chemotherapy, as well as those who declined or were ineligible for BCG or radical cystectomy (RC).

METHODS

A retrospective multicenter analysis of patients treated with RITE for NMIBC between 2015 and 2024 was performed. Co-primary endpoints of the study were intravesical recurrence free survival (RFS) and high-grade intravesical recurrence free survival (HG-RFS). Secondary endpoints included radical cystectomy-free survival (RC-FS), overall survival (OS), cancer-specific survival (CSS), and adverse events (AEs).

RESULTS

Fifty-nine consecutive patients were included in the final analyses. Overall, 12 (20%) and 45 (76%) patients failed previous intravesical chemotherapy, and immunotherapy with BCG, respectively. The 24-months RFS and HG-RFS following RITE were 68.6% (95% CI: 0.568, 0.828) and 74.8% (95% CI: 0.632, 0.885). RC-FS at 24 months was 93.8% (95% CI: 0.872, 1.000). The OS probability at 24 months was 91%, with a CSS of 97.8%. Most common AEs were dysuria and urgency in 27 (45.7%) patients, treatment limiting bladder spasms in 11 (19%) patients, low bladder compliance in 11 (19%) patients and urethral strictures in 5 (8%) patients.

CONCLUSION

In our analyses, RITE resulted in notable antitumor activity and allows for the avoidance of more aggressive and quality-of-life-limiting therapies, such as radical cystectomy. RITE might be considered as a second-line bladder-sparing option in patients failing previous intravesical therapies. Long-term follow-up and larger-scale data are required to validate our findings.

Recent Advances and Emerging Innovations in Transurethral Resection of Bladder Tumor (TURBT) for Non-Muscle Invasive Bladder Cancer: A Comprehensive Review of Current Literature

Bladder cancer management, particularly non-muscle-invasive bladder cancer (NMIBC), has evolved significantly due to advancements in imaging techniques and surgical methodologies. Enhanced tumor visualization methods, including Photodynamic Diagnosis (PDD) and Narrow-Band Imaging (NBI), offer improved detection rates for both papillary tumors and carcinoma in situ (CIS), compared to traditional white-light cystoscopy (WLC). Recent studies suggest that these technologies enhance diagnostic accuracy, reduce recurrence rates, and improve oncological outcomes. Additionally, transurethral resection of bladder tumors (TURBT), performed with advanced imaging, has demonstrated better resection quality, particularly in terms of detrusor muscle presence. Despite these innovations, challenges remain in the long-term impact on recurrence-free and progression-free survival. Artificial intelligence (AI) integration into cystoscopic imaging further promises enhanced diagnostic precision and cost-effective bladder cancer management. As personalized treatment paradigms emerge, predictive biomarkers, including genomic and pathological markers, may help stratify patients for aggressive treatment, sparing those at lower risk from unnecessary interventions. Future research should focus on validating these AI models and combining them with enhanced imaging modalities to refine treatment protocols further. These advancements collectively represent a significant leap toward precision medicine in bladder cancer care.

Deep learning-based model for prediction of early recurrence and therapy response on whole slide images in non-muscle-invasive bladder cancer: a retrospective, multicentre study

Background

Accurate prediction of early recurrence is essential for disease management of patients with non-muscle-invasive bladder cancer (NMIBC). We aimed to develop and validate a deep learning-based early recurrence predictive model (ERPM) and a treatment response predictive model (TRPM) on whole slide images to assist clinical decision making.

Methods

In this retrospective, multicentre study, we included consecutive patients with pathology-confirmed NMIBC who underwent transurethral resection of bladder tumour from five centres. Patients from one hospital (Sun Yat-sen Memorial Hospital of Sun Yat-sen University, Guangzhou, China) were assigned to training and internal validation cohorts, and patients from four other hospitals (the Third Affiliated Hospital of Sun Yat-sen University, and Zhujiang Hospital of Southern Medical University, Guangzhou, China; the Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China; Shenshan Medical Centre, Shanwei, China) were assigned to four independent external validation cohorts. Based on multi-instance and ensemble learning, the ERPM was developed to make predictions on haematoxylin and eosin (H&E) staining and immunohistochemistry staining slides. Sharing the same architecture of the ERPM, the TRPM was trained and evaluated by cross validation on patients who received Bacillus Calmette-Guérin (BCG). The performance of the ERPM was mainly evaluated and compared with the clinical model, H&E-based model, and integrated model through the area under the curve. Survival analysis was performed to assess the prognostic capability of the ERPM.

Findings

Between January 1, 2017, and September 30, 2023, 4395 whole slide images of 1275 patients were included to train and validate the models. The ERPM was superior to the clinical and H&E-based model in predicting early recurrence in both internal validation cohort (area under the curve: 0.837 vs 0.645 vs 0.737) and external validation cohorts (area under the curve: 0.761-0.802 vs 0.626-0.682 vs 0.694-0.723) and was on par with the integrated model. It also stratified recurrence-free survival significantly (p < 0.0001) with a hazard ratio of 4.50 (95% CI 3.10-6.53). The TRPM performed well in predicting BCG-unresponsive NMIBC (accuracy 84.1%).

Interpretation

The ERPM showed promising performance in predicting early recurrence and recurrence-free survival of patients with NMIBC after surgery and with further validation and in combination with TRPM could be used to guide the management of NMIBC.

Funding

National Natural Science Foundation of China, the Science and Technology Planning Project of Guangdong Province, the National Key Research and Development Programme of China, the Guangdong Provincial Clinical Research Centre for Urological Diseases, and the Science and Technology Projects in Guangzhou.

An Unusual Presentation of Bladder Carcinoma in a Visceral Hernia: A Case Report and Literature Review

INTRODUCTION

Bladder carcinoma (BC) is the most prevalent malignancy of the urinary system. These cancers are primarily seen in adults > 60 years old and mostly present with microscopic or frank hematuria or obstruction of the urinary system. However, these rare cancers can be found in hernias.

CASE PRESENTATION

This report discusses a rare, localized bladder urothelial carcinoma (UC) manifestation. The patient had presented with lower abdominal pain several times. However, no accurate diagnosis was made due to the unspecified pain features. After being referred to a radiologic evaluation with ultrasonography, a bladder hernia was detected entering the abdominal wall, and it contained an unusual mass. Further evaluations revealed the malignant feature of the tumor. The abdominal wall hernia was replaced, and a TURP procedure was performed. The resulting sample showed UC without the involvement of the muscle layer.

CONCLUSION

One of the most common malignancies of the urogenital and reproductive systems in male patients is BCs. They are most commonly seen in men older than 60 years old with a history of smoking. The prevalent manifestations of cancer are microscopic or macroscopic hematuria, urinary obstruction, and abdominal pain. A rare but previously reported bladder cancer location is within inguinal or abdominal hernias. The diagnosis of this cancer is not always straightforward, and delays can result in the spread of malignancy and the transition of the patient's clinical condition to a poorer prognosis.

CLINICAL KEY MESSAGE

The presentation of bladder cancer is not always accompanied by typical symptoms such as hematuria or urinary obstruction. Patients with persistent lower abdominal pain should be evaluated to rule out bladder malignancy. These tumors might be hidden within abdominal or inguinal hernias, and more radiologic accuracy is demanded for their diagnosis.

AI predicting recurrence in non-muscle-invasive bladder cancer: systematic review with study strengths and weaknesses

Background

Non-muscle-invasive Bladder Cancer (NMIBC) is notorious for its high recurrence rate of 70-80%, imposing a significant human burden and making it one of the costliest cancers to manage. Current prediction tools for NMIBC recurrence rely on scoring systems that often overestimate risk and lack accuracy. Machine learning (ML) and artificial intelligence (AI) are transforming oncological urology by leveraging molecular and clinical data to enhance predictive precision.

Methods

This comprehensive review critically examines ML-based frameworks for predicting NMIBC recurrence. A systematic literature search was conducted, focusing on the statistical robustness and algorithmic efficacy of studies. These were categorised by data modalities (e.g., radiomics, clinical, histopathological, genomic) and types of ML models, such as neural networks, deep learning, and random forests. Each study was analysed for strengths, weaknesses, performance metrics, and limitations, with emphasis on generalisability, interpretability, and cost-effectiveness.

Results

ML algorithms demonstrate significant potential, with neural networks achieving accuracies of 65-97.5%, particularly with multi-modal datasets, and support vector machines averaging around 75%. Models combining multiple data types consistently outperformed single-modality approaches. However, challenges include limited generalisability due to small datasets and the "black-box" nature of advanced models. Efforts to enhance explainability, such as SHapley Additive ExPlanations (SHAP), show promise but require refinement for clinical use.

Conclusion

This review illuminates the nuances, complexities and contexts that influence the real-world advancement and adoption of these AI-driven techniques in precision oncology. It equips researchers with a deeper understanding of the intricacies of the ML algorithms employed. Actionable insights are provided for refining algorithms, optimising multimodal data utilisation, and bridging the gap between predictive accuracy and clinical utility. This rigorous analysis serves as a roadmap to advance real-world AI applications in oncological care, highlighting the collaborative efforts and robust datasets necessary to translate these advancements into tangible benefits for patient management.

Digital and Computational Pathology Applications in Bladder Cancer: Novel Tools Addressing Clinically Pressing Needs

Bladder cancer (BC) remains a major disease burden in terms of incidence, morbidity, mortality, and economic cost. Deciphering the intrinsic molecular subtypes and identification of key drivers of BC has yielded successful novel therapeutic strategies. Advances in computational and digital pathology are reshaping the field of anatomical pathology. This review offers an update on the most relevant computational algorithms in digital pathology that have been proposed to enhance BC management. These tools promise to enhance diagnostics, staging, and grading accuracy and streamline efficiency while advancing practice consistency. Computational applications that enable intrinsic molecular classification, predict response to neoadjuvant therapy, and identify targets of therapy are also reviewed.

FKBP10 Promotes the Muscle Invasion of Bladder Cancer via Lamin A Dysregulation

Bladder cancer (BC) is a prevalent urinary malignancy and muscle-invasive bladder cancer (MIBC) is particularly aggressive and associated with poor prognosis. One of MIBC features is the nuclear atypia. However, the molecular mechanism underlying MIBC remains unclear. Here, we find that FKBP10 is significantly upregulated in MIBC tissues and correlated with metastasis and poor outcomes. FKBP10 promotes tumor cell invasion, migration, and metastasis, but not proliferation. Notably, FKBP10 enhances the nuclear atypia of BC cells. Mechanistically, FKBP10 interacts with prelamin A and hinder the nuclear entry of prelamin A, thereby leading to the decrease in the nuclear lamin A, a key factor involved in nuclear atypia. In human BC tissues, nuclear lamin A is downregulated and negatively correlated with FKBP10 expression. Overall, our findings demonstrate that the FKBP10/prelamin A/lamin A axis contributes to MIBC.

The role of autophagy dysregulation in low and high-grade nonmuscle invasive bladder cancer: A survival analysis and clinicopathological association

INTRODUCTION

Bladder cancer disproportionately affects men and often presents as nonmuscle-invasive bladder cancer (NMIBC). Despite initial treatments, the recurrence and progression of NMIBC are linked to autophagy. This study investigates the expression of autophagy genes (mTOR, ULK1, Beclin1, and LC3) in low and high-grade NMIBC, providing insights into potential prognostic markers and therapeutic targets.

MATERIAL AND METHODS

A total of 115 tissue samples (n = 85 NMIBC (pTa, pT1, and CIS) and n = 30 control from BPH patients) were collected. The expression level of autophagy genes (mTOR, ULK1, Beclin1, and LC3) and their proteins were assessed in low and high-grade NMIBC, along with control tissue samples using quantitative real-time polymerase chain reaction and western blotting. Association with clinicopathological characteristics and autophagy gene expression was analyzed by multivariate and univariate survival analysis using SPSS.

RESULT

In high-grade NMIBC, ULK1, P = 0.0150, Beclin1, P = 0.0041, and LC3, P = 0.0014, were substantially downregulated, whereas mTOR, P = 0.0006, was significantly upregulated. The KM plots show significant survival outcomes with autophagy genes. The clinicopathological characters, high grade (P = 0.019), tumor stage (CIS P = 0.039, pT1 P = 0.018, P = 0.045), male (P = 0.010), lymphovascular invasion (P = 0.028) and autophagy genes (ULK1 P = 0.002, beclin1 (P = 0.010, P = 0.022) were associated as risk factors for survival outcome in NMIBC patients.

CONCLUSION

The upregulated mTOR, downregulated ULK1, and beclin1 expression is linked to a high-grade, CIS and pT1 stage, resulting in poor recurrence-free survival and progression-free survival and highlights the prognostic significance of autophagy gene in nonmuscle-invasive bladder cancer.

Artificial intelligence application in the diagnosis and treatment of bladder cancer: advance, challenges, and opportunities

Bladder cancer (BC) is a serious and common malignant tumor of the urinary system. Accurate and convenient diagnosis and treatment of BC is a major challenge for the medical community. Due to the limited medical resources, the existing diagnosis and treatment protocols for BC without the assistance of artificial intelligence (AI) still have certain shortcomings. In recent years, with the development of AI technologies such as deep learning and machine learning, the maturity of AI has made it more and more applied to the medical field, including improving the speed and accuracy of BC diagnosis and providing more powerful treatment options and recommendations related to prognosis. Advances in medical imaging technology and molecular-level research have also contributed to the further development of such AI applications. However, due to differences in the sources of training information and algorithm design issues, there is still room for improvement in terms of accuracy and transparency for the broader use of AI in clinical practice. With the popularization of digitization of clinical information and the proposal of new algorithms, artificial intelligence is expected to learn more effectively and analyze similar cases more accurately and reliably, promoting the development of precision medicine, reducing resource consumption, and speeding up diagnosis and treatment. This review focuses on the application of artificial intelligence in the diagnosis and treatment of BC, points out some of the challenges it faces, and looks forward to its future development.

AI powered quantification of nuclear morphology in cancers enables prediction of genome instability and prognosis

While alterations in nucleus size, shape, and color are ubiquitous in cancer, comprehensive quantification of nuclear morphology across a whole-slide histologic image remains a challenge. Here, we describe the development of a pan-tissue, deep learning-based digital pathology pipeline for exhaustive nucleus detection, segmentation, and classification and the utility of this pipeline for nuclear morphologic biomarker discovery. Manually-collected nucleus annotations were used to train an object detection and segmentation model for identifying nuclei, which was deployed to segment nuclei in H&E-stained slides from the BRCA, LUAD, and PRAD TCGA cohorts. Interpretable features describing the shape, size, color, and texture of each nucleus were extracted from segmented nuclei and compared to measurements of genomic instability, gene expression, and prognosis. The nuclear segmentation and classification model trained herein performed comparably to previously reported models. Features extracted from the model revealed differences sufficient to distinguish between BRCA, LUAD, and PRAD. Furthermore, cancer cell nuclear area was associated with increased aneuploidy score and homologous recombination deficiency. In BRCA, increased fibroblast nuclear area was indicative of poor progression-free and overall survival and was associated with gene expression signatures related to extracellular matrix remodeling and anti-tumor immunity. Thus, we developed a powerful pan-tissue approach for nucleus segmentation and featurization, enabling the construction of predictive models and the identification of features linking nuclear morphology with clinically-relevant prognostic biomarkers across multiple cancer types.

On relevant features for the recurrence prediction of urothelial carcinoma of the bladder

BACKGROUND

Urothelial bladder cancer (UBC) is characterized by a high recurrence rate, which is predicted by scoring systems. However, recent studies show the superiority of Machine Learning (ML) models. Nevertheless, these ML approaches are rarely used in medical practice because most of them are black-box models, that cannot adequately explain how a prediction is made.

OBJECTIVE

We investigate the global feature importance of different ML models. By providing information on the most relevant features, we can facilitate the use of ML in everyday medical practice.

DESIGN, SETTING, AND PARTICIPANTS

The data is provided by the cancer registry Rhineland-Palatinate gGmbH, Germany. It consists of numerical and categorical features of 1,944 patients with UBC. We retrospectively predict 2-year recurrence through ML models using Support Vector Machine, Gradient Boosting, and Artificial Neural Network. We then determine the global feature importance using performance-based Permutation Feature Importance (PFI) and variance-based Feature Importance Ranking Measure (FIRM).

RESULTS

We show reliable recurrence prediction of UBC with 82.02% to 83.89% F1-Score, 83.95% to 84.49% Precision, and an overall performance of 69.20% to 70.82% AUC on testing data, depending on the model. Gradient Boosting performs best among all black-box models with an average F1-Score (83.89%), AUC (70.82%), and Precision (83.95%). Furthermore, we show consistency across PFI and FIRM by identifying the same features as relevant across the different models. These features are exclusively therapeutic measures and are consistent with findings from both medical research and clinical trials.

CONCLUSIONS

We confirm the superiority of ML black-box models in predicting UBC recurrence compared to more traditional logistic regression. In addition, we present an approach that increases the explanatory power of black-box models by identifying the underlying influence of input features, thus facilitating the use of ML in clinical practice and therefore providing improved recurrence prediction through the application of black-box models.

Predicting non-muscle invasive bladder cancer outcomes using artificial intelligence: a systematic review using APPRAISE-AI

Accurate prediction of recurrence and progression in non-muscle invasive bladder cancer (NMIBC) is essential to inform management and eligibility for clinical trials. Despite substantial interest in developing artificial intelligence (AI) applications in NMIBC, their clinical readiness remains unclear. This systematic review aimed to critically appraise AI studies predicting NMIBC outcomes, and to identify common methodological and reporting pitfalls. MEDLINE, EMBASE, Web of Science, and Scopus were searched from inception to February 5th, 2024 for AI studies predicting NMIBC recurrence or progression. APPRAISE-AI was used to assess methodological and reporting quality of these studies. Performance between AI and non-AI approaches included within these studies were compared. A total of 15 studies (five on recurrence, four on progression, and six on both) were included. All studies were retrospective, with a median follow-up of 71 months (IQR 32-93) and median cohort size of 125 (IQR 93-309). Most studies were low quality, with only one classified as high quality. While AI models generally outperformed non-AI approaches with respect to accuracy, c-index, sensitivity, and specificity, this margin of benefit varied with study quality (median absolute performance difference was 10 for low, 22 for moderate, and 4 for high quality studies). Common pitfalls included dataset limitations, heterogeneous outcome definitions, methodological flaws, suboptimal model evaluation, and reproducibility issues. Recommendations to address these challenges are proposed. These findings emphasise the need for collaborative efforts between urological and AI communities paired with rigorous methodologies to develop higher quality models, enabling AI to reach its potential in enhancing NMIBC care.

Revolutionizing Treatment: Breakthrough Approaches for BCG-Unresponsive Non-Muscle-Invasive Bladder Cancer

Bladder cancer is the 10th most popular cancer in the world, and non-muscle-invasive bladder cancer (NMIBC) is diagnosed in ~80% of all cases. Treatments for NMIBC include transurethral resection of the bladder tumor (TURBT) and intravesical instillations of Bacillus Calmette-Guérin (BCG). Treatment of BCG-unresponsive tumors is scarce and usually leads to Radical Cystectomy. In this paper, we review recent advancements in conservative treatment of BCG-unresponsive tumors. The main focus of the paper is FDA-approved medications: Pembrolizumab and Nadofaragene Firadenovec (Adstiladrin). Other, less researched therapeutic possibilities are also included, namely: N-803 immunotherapy, TAR-200 and TAR-210 intravesical delivery systems and combined Cabazitaxel, Gemcitabine and Cisplatin chemotherapy. Conservative treatment and delaying radical cystectomy would greatly benefit patients' quality of life; it is undoubtedly the future of BCG-unresponsive NMIBC.

Prediction of cancer recurrence based on compact graphs of whole slide images

Cancer recurrence is one of the primary causes of patient mortality following treatment, indicating increased aggressiveness of cancer cells and difficulties in achieving a cure. A critical step to improve patients' survival is accurately predicting recurrence status and giving appropriate treatment. Whole Slide Images (WSIs) are a common type of image data in the field of digital pathology, containing high-resolution tissue information. Furthermore, WSIs of primary tumors contain microenvironmental information directly associated with the growth of tumor cells. To effectively utilize this microenvironmental information. Firstly, we represented microenvironmental features of histopathological images as compact graphs. Secondly, this work aims to develop an enhanced lightweight graph neural network called the Adaptive Graph Clustering Network (AGCNet) for predicting cancer recurrence. Experiments are conducted on three cancer datasets from The Cancer Genome Atlas (TCGA), and AGCNet achieved an accuracy of 81.81% in BLCA, 69.66% in PAAD, and 81.96% in STAD. These results indicated that AGCNet is an effective model for predicting cancer recurrence and is expected to be applied in clinical applications.

Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review

Bladder cancer (BC) diagnosis and prediction of prognosis are hindered by subjective pathological evaluation, which may cause misdiagnosis and under-/over-treatment. Computational pathology (CPATH) can identify clinical outcome predictors, offering an objective approach to improve prognosis. However, a systematic review of CPATH in BC literature is lacking. Therefore, we present a comprehensive overview of studies that used CPATH in BC, analyzing 33 out of 2285 identified studies. Most studies analyzed regions of interest to distinguish normal versus tumor tissue and identify tumor grade/stage and tissue types (e.g., urothelium, stroma, and muscle). The cell's nuclear area, shape irregularity, and roundness were the most promising markers to predict recurrence and survival based on selected regions of interest, with >80% accuracy. CPATH identified molecular subtypes by detecting features, e.g., papillary structures, hyperchromatic, and pleomorphic nuclei. Combining clinicopathological and image-derived features improved recurrence and survival prediction. However, due to the lack of outcome interpretability and independent test datasets, robustness and clinical applicability could not be ensured. The current literature demonstrates that CPATH holds the potential to improve BC diagnosis and prediction of prognosis. However, more robust, interpretable, accurate models and larger datasets-representative of clinical scenarios-are needed to address artificial intelligence's reliability, robustness, and black box challenge.

Examining longitudinal markers of bladder cancer recurrence through a semiautonomous machine learning system for quantifying specimen atypia from urine cytology

BACKGROUND

Urine cytology is generally considered the primary approach for screening for recurrence of bladder cancer. However, it is currently unclear how best to use cytological examinations for assessment and early detection of recurrence, beyond identifying a positive finding that requires more invasive methods to confirm recurrence and decide on therapeutic options. Because screening programs are frequent, and can be burdensome, finding quantitative means to reduce this burden for patients, cytopathologists, and urologists is an important endeavor and can improve both the efficiency and reliability of findings. Additionally, identifying ways to risk-stratify patients is crucial for improving quality of life while reducing the risk of future recurrence or progression of the cancer.

METHODS

In this study, a computational machine learning tool, AutoParis-X, was leveraged to extract imaging features from urine cytology examinations longitudinally to study the predictive potential of urine cytology for assessing recurrence risk. This study examined how the significance of imaging predictors changes over time before and after surgery to determine which predictors and time periods are most relevant for assessing recurrence risk.

RESULTS

Results indicate that imaging predictors extracted using AutoParis-X can predict recurrence as well or better than traditional cytological/histological assessments alone and that the predictiveness of these features is variable across time, with key differences in overall specimen atypia identified immediately before tumor recurrence.

CONCLUSIONS

Further research will clarify how computational methods can be effectively used in high-volume screening programs to improve recurrence detection and complement traditional modes of assessment.

Recurrence prediction in clear cell renal cell carcinoma using machine learning of quantitative nuclear features

The recurrence of non-metastatic renal cell carcinoma (RCC) may occur early or late after surgery. This study aimed to develop a recurrence prediction machine learning model based on quantitative nuclear morphologic features of clear cell RCC (ccRCC). We investigated 131 ccRCC patients who underwent nephrectomy (T1-3N0M0). Forty had recurrence within 5 years and 22 between 5 and 10 years; thirty-seven were recurrence-free during 5-10 years and 32 were for more than 10 years. We extracted nuclear features from regions of interest (ROIs) using a digital pathology technique and used them to train 5- and 10-year Support Vector Machine models for recurrence prediction. The models predicted recurrence at 5/10 years after surgery with accuracies of 86.4%/74.1% for each ROI and 100%/100% for each case, respectively. By combining the two models, the accuracy of the recurrence prediction within 5 years was 100%. However, recurrence between 5 and 10 years was correctly predicted for only 5 of the 12 test cases. The machine learning models showed good accuracy for recurrence prediction within 5 years after surgery and may be useful for the design of follow-up protocols and patient selection for adjuvant therapy.

Deep Learning Models for Cystoscopic Recognition of Hunner Lesion in Interstitial Cystitis

Background

Accurate cystoscopic recognition of Hunner lesions (HLs) is indispensable for better treatment prognosis in managing patients with Hunner-type interstitial cystitis (HIC), but frequently challenging due to its varying appearance.

Objective

To develop a deep learning (DL) system for cystoscopic recognition of a HL using artificial intelligence (AI).

Design setting and participants

A total of 626 cystoscopic images collected from January 8, 2019 to December 24, 2020, consisting of 360 images of HLs from 41 patients with HIC and 266 images of flat reddish mucosal lesions resembling HLs from 41 control patients including those with bladder cancer and other chronic cystitis, were used to create a dataset with an 8:2 ratio of training images and test images for transfer learning and external validation, respectively. AI-based five DL models were constructed, using a pretrained convolutional neural network model that was retrained to output 1 for a HL and 0 for control. A five-fold cross-validation method was applied for internal validation.

Outcome measurements and statistical analysis

True- and false-positive rates were plotted as a receiver operating curve when the threshold changed from 0 to 1. Accuracy, sensitivity, and specificity were evaluated at a threshold of 0.5. Diagnostic performance of the models was compared with that of urologists as a reader study.

Results and limitations

The mean area under the curve of the models reached 0.919, with mean sensitivity of 81.9% and specificity of 85.2% in the test dataset. In the reader study, the mean accuracy, sensitivity, and specificity were, respectively, 83.0%, 80.4%, and 85.6% for the models, and 62.4%, 79.6%, and 45.2% for expert urologists. Limitations include the diagnostic nature of a HL as warranted assertibility.

Conclusions

We constructed the first DL system that recognizes HLs with accuracy exceeding that of humans. This AI-driven system assists physicians with proper cystoscopic recognition of a HL.

Patient summary

In this diagnostic study, we developed a deep learning system for cystoscopic recognition of Hunner lesions in patients with interstitial cystitis. The mean area under the curve of the constructed system reached 0.919 with mean sensitivity of 81.9% and specificity of 85.2%, demonstrating diagnostic accuracy exceeding that of human expert urologists in detecting Hunner lesions. This deep learning system assists physicians with proper diagnosis of a Hunner lesion.

Deep Multi-Magnification Similarity Learning for Histopathological Image Classification

Precise classification of histopathological images is crucial to computer-aided diagnosis in clinical practice. Magnification-based learning networks have attracted considerable attention for their ability to improve performance in histopathological classification. However, the fusion of pyramids of histopathological images at different magnifications is an under-explored area. In this paper, we proposed a novel deep multi-magnification similarity learning (DSML) approach that can be useful for the interpretation of multi-magnification learning framework and easy to visualize feature representation from low-dimension (e.g., cell-level) to high-dimension (e.g., tissue-level), which has overcome the difficulty of understanding cross-magnification information propagation. It uses a similarity cross entropy loss function designation to simultaneously learn the similarity of the information among cross-magnifications. In order to verify the effectiveness of DMSL, experiments with different network backbones and different magnification combinations were designed, and its ability to interpret was also investigated through visualization. Our experiments were performed on two different histopathological datasets: a clinical nasopharyngeal carcinoma and a public breast cancer BCSS2021 dataset. The results show that our method achieved outstanding performance in classification with a higher value of area under curve, accuracy, and F-score than other comparable methods. Moreover, the reasons behind multi-magnification effectiveness were discussed.

Multimodal investigation of bladder cancer data based on computed tomography, whole slide imaging, and transcriptomics

Background

Multimodal analysis has shown great potential in the diagnosis and management of cancer. This study aimed to determine the multimodal data associations between radiological, pathologic, and molecular characteristics in bladder cancer.

Methods

A retrospective study of computed tomography (CT), pathologic slice, and RNA sequencing data from 127 consecutive adult patients in China who underwent bladder surgery and were pathologically diagnosed with bladder cancer was conducted. A total of 200 radiological and 1,029 pathologic features were extracted by radiomics and pathomics. Multimodal associations analysis and structural equation modeling were used to measure the cross-modal associations and structural relationships between CT and pathologic slice. A convolutional neural network was constructed for molecular subtyping based on multimodal imaging features. Class activation maps were used to examine the feature contribution in model decision-making. Cox regression and Kaplan-Meier survival analysis were used to explore the relevance of multimodal features to the prognosis of patients with bladder cancer.

Results

A total of 77 densely associated blocks of feature pairs were identified between CT and whole slide images. The largest cross-modal associated block reflected the tumor-grade properties. A significant relation was found between pathological features and molecular subtypes (β=0.396; P<0.001). High-grade bladder cancer showed heterogeneity of significance across different scales and higher disorders at the microscopic level. The fused radiological and pathologic features achieved higher accuracy (area under the curve: 0.89; 95% CI: 0.75-1.0) than the unimodal method. Thirteen prognosis-related features from CT and whole slide images were identified.

Conclusions

Our work demonstrated the associations between CT, pathologic slices, and molecular signatures, and the potential to use multimodal data analysis in related clinical applications. Multimodal data analysis showed the potential of cross-inference of modal data and had higher diagnostic accuracy than the unimodal method.

The biological impacts of CEBPD on urothelial carcinoma development and progression

Urothelial carcinoma (UC), which includes urinary bladder urothelial carcinoma (UBUC) and upper tract urothelial carcinoma (UTUC), is one of the most common malignancies worldwide. Accordingly, a comprehensive understanding of the underlying mechanism governing UC development is compulsory. Aberrant CCAAT/enhancer-binding protein delta (CEBPD), a transcription factor, displays an oncogene or tumor suppressor depending on tumor type and microenvironments. However, CEBPD has been reported to possess a clear oncogenic function in UC through multiple regulation pathways. Genomic amplification of CEBPD triggered by MYC-driven genome instability is frequently examined in UC that drives CEBPD overexpression. Upregulated CEBPD transcriptionally suppresses FBXW7 to stabilize MYC protein and further induces hexokinase II (HK2)-related aerobic glycolysis that fuels cell growth. Apart from the MYC-dependent pathway, CEBPD also downregulates the level of hsa-miR-429 to enhance HK2-associated glycolysis and induce angiogenesis driven by vascular endothelial growth factor A (VEGFA). Additionally, aggressive UC is attributed to the tumor metastasis regulated by CEBPD-induced matrix metalloproteinase-2 (MMP2) overexpression. Furthermore, elevated CEBPD induced by cisplatin (CDDP) is identified to have dual functions, namely, CDDP-induced chemotherapy resistance or drive CDDP-induced antitumorigenesis. Given that the role of CEBPD in UC is getting clear but pending a more systemic reappraisal, this review aimed to comprehensively discuss the underlying mechanism of CEBPD in UC tumorigenesis.

A domain knowledge enhanced yield based deep learning classifier identifies perineural invasion in oral cavity squamous cell carcinoma

BACKGROUND

Perineural invasion (PNI), a form of local invasion defined as the ability of cancer cells to invade in, around, and through nerves, has a negative prognostic impact in oral cavity squamous cell carcinoma (OCSCC). Unfortunately, the diagnosis of PNI suffers from a significant degree of intra- and interobserver variability. The aim of this pilot study was to develop a deep learning-based human-enhanced tool, termed domain knowledge enhanced yield (Domain-KEY) algorithm, for identifying PNI in digital slides.

METHODS

Hematoxylin and eosin (H&E)-stained whole-slide images (WSIs, n = 85) were obtained from 80 patients with OCSCC. The model structure consisted of two parts to simulate human decision-making skills in diagnostic pathology. To this aim, two semantic segmentation models were constructed (i.e., identification of nerve fibers followed by the diagnosis of PNI). The inferred results were subsequently subjected to post-processing of generated decision rules for diagnostic labeling. Ten H&E-stained WSIs not previously used in the study were read and labeled by the Domain-KEY algorithm. Thereafter, labeling correctness was visually inspected by two independent pathologists.

RESULTS

The Domain-KEY algorithm was found to outperform the ResnetV2_50 classifier for the detection of PNI (diagnostic accuracy: 89.01% and 61.94%, respectively). On analyzing WSIs, the algorithm achieved a mean diagnostic accuracy as high as 97.50% versus traditional pathology. The observed accuracy in a validation dataset of 25 WSIs obtained from seven patients with oropharyngeal (cancer of the tongue base, n = 1; tonsil cancer, n = 1; soft palate cancer, n = 1) and hypopharyngeal (cancer of posterior wall, n = 2; pyriform sinus cancer, n = 2) malignancies was 96%. Notably, the algorithm was successfully applied in the analysis of WSIs to shorten the time required to reach a diagnosis. The addition of the hybrid intelligence model decreased the mean time required to reach a diagnosis by 15.0% and 23.7% for the first and second pathologists, respectively. On analyzing digital slides, the tool was effective in supporting human diagnostic thinking.

CONCLUSIONS

The Domain-KEY algorithm successfully mimicked human decision-making skills and supported expert pathologists in the routine diagnosis of PNI.

Predicting Recurrence of Non-Muscle-Invasive Bladder Cancer: Current Techniques and Future Trends

Bladder cancer (BC) is the 10th most common cancer globally and has a high mortality rate if not detected early and treated promptly. Non-muscle-invasive BC (NMIBC) is a subclassification of BC associated with high rates of recurrence and progression. Current tools for predicting recurrence and progression on NMIBC use scoring systems based on clinical and histopathological markers. These exclude other potentially useful biomarkers which could provide a more accurate personalized risk assessment. Future trends are likely to use artificial intelligence (AI) to enhance the prediction of recurrence in patients with NMIBC and decrease the use of standard clinical protocols such as cystoscopy and cytology. Here, we provide a comprehensive survey of the most recent studies from the last decade (N = 70 studies), focused on the prediction of patient outcomes in NMIBC, particularly recurrence, using biomarkers such as radiomics, histopathology, clinical, and genomics. The value of individual and combined biomarkers is discussed in detail with the goal of identifying future trends that will lead to the personalized management of NMIBC.

Does post-void residual urine volume affect potential recurrence risk for non-muscle invasive bladder cancer?

Aim

Bladder cancer is the second most common urological malignancy after prostate cancer. Increase in the post-void residual (PVR) volume may result in an increase in the risk of cancer recurrence.

Methods

Patient demographic data, tumor stage and grade, PVR volume and 2 years follow-up data for recurrence were obtained and evaluated.

Results

One-hundred-and-nineteen patients were subdivided into three groups according to PVR urine volume. The increase of PVR volume was related to short recurrence-free survival (RFS) especially for patients with PVR volume of 60 ml or more.

Conclusion

Low PVR volume in patients with non-muscle invasive bladder cancer may play a role in reducing cancer recurrence. However further research is needed in this field.

The Role of Artificial Intelligence in Early Cancer Diagnosis

Improving the proportion of patients diagnosed with early-stage cancer is a key priority of the World Health Organisation. In many tumour groups, screening programmes have led to improvements in survival, but patient selection and risk stratification are key challenges. In addition, there are concerns about limited diagnostic workforces, particularly in light of the COVID-19 pandemic, placing a strain on pathology and radiology services. In this review, we discuss how artificial intelligence algorithms could assist clinicians in (1) screening asymptomatic patients at risk of cancer, (2) investigating and triaging symptomatic patients, and (3) more effectively diagnosing cancer recurrence. We provide an overview of the main artificial intelligence approaches, including historical models such as logistic regression, as well as deep learning and neural networks, and highlight their early diagnosis applications. Many data types are suitable for computational analysis, including electronic healthcare records, diagnostic images, pathology slides and peripheral blood, and we provide examples of how these data can be utilised to diagnose cancer. We also discuss the potential clinical implications for artificial intelligence algorithms, including an overview of models currently used in clinical practice. Finally, we discuss the potential limitations and pitfalls, including ethical concerns, resource demands, data security and reporting standards.