Racial Differences in the Detection Rate of Bladder Cancer Using Blue Light Cystoscopy: Insights from a Multicenter Registry.

The use of blue light cystoscopy (BLC) has been shown to improve bladder tumor detection. However, data demonstrating the efficacy of BLC across different races are limited. Herein, we aim to evaluate heterogeneity in the characteristics of BLC for the detection of malignant lesions among various races. Clinicopathologic information was collected from patients enrolled in the multi-institutional Cysview® registry (2014-2021) who underwent transurethral resection or biopsy of bladder tumors. Outcome variables included sensitivity and negative and positive predictive values of BLC and white light cystoscopy (WLC) for the detection of malignant lesions among various races. Overall, 2379 separate lesions/tumors were identified from 1292 patients, of whom 1095 (85%) were Caucasian, 96 (7%) were African American, 51 (4%) were Asian, and 50 (4%) were Hispanic. The sensitivity of BLC was higher than that of WLC in the total cohort, as well as in the Caucasian and Asian subgroups. The addition of BLC to WLC increased the detection rate by 10% for any malignant lesion in the total cohort, with the greatest increase in Asian patients (18%). Additionally, the positive predictive value of BLC was highest in Asian patients (94%), while Hispanic patients had the highest negative predictive value (86%). Our study showed that regardless of race, BLC increases the detection of bladder cancer when combined with WLC.

Electronic Documentation of Intraoperative Observation of Cystoscopic Procedures Using the cMDX Information System.

PURPOSE: Accurate documentation of lesions during transurethral resection of bladder tumors (TURBT) is essential for precise diagnosis, treatment planning, and follow-up care. However, optimizing schematic documentation techniques for bladder lesions has received limited attention. MATERIALS AND METHODS: This prospective observational study used a cMDX-based documentation system that facilitates graphical representation, a lesion-specific questionnaire, and heatmap analysis with a posterization effect. We designed a graphical scheme for bladder covering bladder landmarks to visualize anatomic features and to document the lesion location. The lesion-specific questionnaire was integrated for comprehensive lesion characterization. Finally, spatial analyses were applied to investigate the anatomic distribution patterns of bladder lesions. RESULTS: A total of 97 TURBT cases conducted between 2021 and 2023 were included, identifying 176 lesions. The lesions were distributed in different bladder areas with varying frequencies. The distribution pattern, sorted by frequency, was observed in the following areas: posterior, trigone, lateral right and anterior, and lateral left and dome. Suspicious levels were assigned to the lesions, mostly categorized either as indeterminate or moderate. Lesion size analysis revealed that most lesions fell between 5 and 29 mm. CONCLUSION: The study highlights the potential of schematic documentation techniques for informed decision making, quality assessment, primary research, and secondary data utilization of intraoperative data in the context of TURBT. Integrating cMDX and heatmap analysis provides valuable insights into lesion distribution and characteristics.

PolypMixNet: Enhancing semi-supervised polyp segmentation with polyp-aware augmentation.

BACKGROUND: AI-assisted polyp segmentation in colonoscopy plays a crucial role in enabling prompt diagnosis and treatment of colorectal cancer. However, the lack of sufficient annotated data poses a significant challenge for supervised learning approaches. Existing semi-supervised learning methods also suffer from performance degradation, mainly due to task-specific characteristics, such as class imbalance in polyp segmentation. PURPOSE: The purpose of this work is to develop an effective semi-supervised learning framework for accurate polyp segmentation in colonoscopy, addressing limited annotated data and class imbalance challenges. METHODS: We proposed PolypMixNet, a semi-supervised framework, for colorectal polyp segmentation, utilizing novel augmentation techniques and a Mean Teacher architecture to improve model performance. PolypMixNet introduces the polyp-aware mixup (PolypMix) algorithm and incorporates dual-level consistency regularization. PolypMix addresses the class imbalance in colonoscopy datasets and enhances the diversity of training data. By performing a polyp-aware mixup on unlabeled samples, it generates mixed images with polyp context along with their artificial labels. A polyp-directed soft pseudo-labeling (PDSPL) mechanism was proposed to generate high-quality pseudo labels and eliminate the dilution of lesion features caused by mixup operations. To ensure consistency in the training phase, we introduce the PolypMix prediction consistency (PMPC) loss and PolypMix attention consistency (PMAC) loss, enforcing consistency at both image and feature levels. Code is available at https://github.com/YChienHung/PolypMix. RESULTS: PolypMixNet was evaluated on four public colonoscopy datasets, achieving 88.97% Dice and 88.85% mIoU on the benchmark dataset of Kvasir-SEG. In scenarios where the labeled training data is limited to 15%, PolypMixNet outperforms the state-of-the-art semi-supervised approaches with a 2.88-point improvement in Dice. It also shows the ability to reach performance comparable to the fully supervised counterpart. Additionally, we conducted extensive ablation studies to validate the effectiveness of each module and highlight the superiority of our proposed approach. CONCLUSION: PolypMixNet effectively addresses the challenges posed by limited annotated data and unbalanced class distributions in polyp segmentation. By leveraging unlabeled data and incorporating novel augmentation and consistency regularization techniques, our method achieves state-of-the-art performance. We believe that the insights and contributions presented in this work will pave the way for further advancements in semi-supervised polyp segmentation and inspire future research in the medical imaging domain.

Revealing hidden patterns in deep neural network feature space continuum via manifold learning.

Deep neural networks (DNNs) extract thousands to millions of task-specific features during model training for inference and decision-making. While visualizing these features is critical for comprehending the learning process and improving the performance of the DNNs, existing visualization techniques work only for classification tasks. For regressions, the feature points lie on a high dimensional continuum having an inherently complex shape, making a meaningful visualization of the features intractable. Given that the majority of deep learning applications are regression-oriented, developing a conceptual framework and computational method to reliably visualize the regression features is of great significance. Here, we introduce a manifold discovery and analysis (MDA) method for DNN feature visualization, which involves learning the manifold topology associated with the output and target labels of a DNN. MDA leverages the acquired topological information to preserve the local geometry of the feature space manifold and provides insightful visualizations of the DNN features, highlighting the appropriateness, generalizability, and adversarial robustness of a DNN. The performance and advantages of the MDA approach compared to the existing methods are demonstrated in different deep learning applications.

Multiomics characterization of cell type repertoires for urine liquid biopsies.

Urine is assayed alongside blood in medicine, yet current clinical diagnostic tests utilize only a small fraction of its total biomolecular repertoire, potentially foregoing high-resolution insights into human health and disease. In this work, we characterized the joint landscapes of transcriptomic and metabolomic signals in human urine. We also compared the urine transcriptome to plasma cell-free RNA, identifying a distinct cell type repertoire and enrichment for metabolic signal. Untargeted metabolomic measurements identified a complementary set of pathways to the transcriptomic analysis. Our findings suggest that urine is a promising biofluid yielding prognostic and detailed insights for hard-to-biopsy tissues with low representation in the blood, offering promise for a new generation of liquid biopsies.

Efficient Augmented Intelligence Framework for Bladder Lesion Detection.

PURPOSE: Development of intelligence systems for bladder lesion detection is cost intensive. An efficient strategy to develop such intelligence solutions is needed. MATERIALS AND METHODS: We used four deep learning models (ConvNeXt, PlexusNet, MobileNet, and SwinTransformer) covering a variety of model complexity and efficacy. We trained these models on a previously published educational cystoscopy atlas (n = 312 images) to estimate the ratio between normal and cancer scores and externally validated on cystoscopy videos from 68 cases, with region of interest (ROI) pathologically confirmed to be benign and cancerous bladder lesions (ie, ROI). The performance measurement included specificity and sensitivity at frame level, frame sequence (block) level, and ROI level for each case. RESULTS: Specificity was comparable between four models at frame (range, 30.0%-44.8%) and block levels (56%-67%). Although sensitivity at the frame level (range, 81.4%-88.1%) differed between the models, sensitivity at the block level (100%) and ROI level (100%) was comparable between these models. MobileNet and PlexusNet were computationally more efficient for real-time ROI detection than ConvNeXt and SwinTransformer. CONCLUSION: Educational cystoscopy atlas and efficient models facilitate the development of real-time intelligence system for bladder lesion detection.

Tumor detection under cystoscopy with transformer-augmented deep learning algorithm.

Objective.Accurate tumor detection is critical in cystoscopy to improve bladder cancer resection and decrease recurrence. Advanced deep learning algorithms hold the potential to improve the performance of standard white-light cystoscopy (WLC) in a noninvasive and cost-effective fashion. The purpose of this work is to develop a cost-effective, transformer-augmented deep learning algorithm for accurate detection of bladder tumors in WLC and to assess its performance on archived patient data.Approach.'CystoNet-T', a deep learning-based bladder tumor detector, was developed with a transformer-augmented pyramidal CNN architecture to improve automated tumor detection of WLC. CystoNet-T incorporated the self-attention mechanism by attaching transformer encoder modules to the pyramidal layers of the feature pyramid network (FPN), and obtained multi-scale activation maps with global features aggregation. Features resulting from context augmentation served as the input to a region-based detector to produce tumor detection predictions. The training set was constructed by 510 WLC frames that were obtained from cystoscopy video sequences acquired from 54 patients. The test set was constructed based on 101 images obtained from WLC sequences of 13 patients.Main results.CystoNet-T was evaluated on the test set with 96.4 F1 and 91.4 AP (Average Precision). This result improved the benchmark of Faster R-CNN and YOLO by 7.3 points in F1 and 3.8 points in AP. The improvement is attributed to the strong ability of global attention of CystoNet-T and better feature learning of the pyramids architecture throughout the training. The model was found to be particularly effective in highlighting the foreground information for precise localization of the true positives while favorably avoiding false alarmsSignificance.We have developed a deep learning algorithm that accurately detects bladder tumors in WLC. Transformer-augmented AI framework promises to aid in clinical decision-making for improved bladder cancer diagnosis and therapeutic guidance.

Real-time Detection of Bladder Cancer Using Augmented Cystoscopy with Deep Learning: a Pilot Study.

BACKGROUND: Detection of bladder tumors under white light cystoscopy (WLC) is challenging yet impactful on treatment outcomes. Artificial intelligence (AI) holds the potential to improve tumor detection; however, its application in the real-time setting remains unexplored. AI has been applied to previously recorded images for post hoc analysis. In this study, we evaluate the feasibility of real-time AI integration during clinic cystoscopy and transurethral resection of bladder tumor (TURBT) on live, streaming video. METHODS: Patients undergoing clinic flexible cystoscopy and TURBT were prospectively enrolled. A real-time alert device system (real-time CystoNet) was developed and integrated with standard cystoscopy towers. Streaming videos were processed in real time to display alert boxes in sync with live cystoscopy. The per-frame diagnostic accuracy was measured. RESULTS AND LIMITATIONS: Real-time CystoNet was successfully integrated in the operating room during TURBT and clinic cystoscopy in 50 consecutive patients. There were 55 procedures that met the inclusion criteria for analysis including 21 clinic cystoscopies and 34 TURBTs. For clinic cystoscopy, real-time CystoNet achieved per-frame tumor specificity of 98.8% with a median error rate of 3.6% (range: 0 - 47%) frames per cystoscopy. For TURBT, the per-frame tumor sensitivity was 52.9% and the per-frame tumor specificity was 95.4% with an error rate of 16.7% for cases with pathologically confirmed bladder cancers. CONCLUSIONS: The current pilot study demonstrates the feasibility of using a real-time AI system (real-time CystoNet) during cystoscopy and TURBT to generate active feedback to the surgeon. Further optimization of CystoNet for real-time cystoscopy dynamics may allow for clinically useful AI-augmented cystoscopy.

Long noncoding RNA MALAT1 is dynamically regulated in leader cells during collective cancer invasion.

Cancer cells collectively invade using a leader-follower organization, but the regulation of leader cells during this dynamic process is poorly understood. Using a dual double-stranded locked nucleic acid (LNA) nanobiosensor that tracks long noncoding RNA (lncRNA) dynamics in live single cells, we monitored the spatiotemporal distribution of lncRNA during collective cancer invasion. We show that the lncRNA MALAT1 (metastasis-associated lung adenocarcinoma transcript 1) is dynamically regulated in the invading fronts of cancer cells and patient-derived spheroids. MALAT1 transcripts exhibit distinct abundance, diffusivity, and distribution between leader and follower cells. MALAT1 expression increases when a cancer cell becomes a leader and decreases when the collective migration process stops. Transient knockdown of MALAT1 prevents the formation of leader cells and abolishes the invasion of cancer cells. Taken together, our single-cell analysis suggests that MALAT1 is dynamically regulated in leader cells during collective cancer invasion.

A magnetic hydrogel for the efficient retrieval of kidney stone fragments during ureteroscopy.

Only 60-75% of conventional kidney stone surgeries achieve complete stone-free status. Up to 30% of patients with residual fragments <2 mm in size experience subsequent stone-related complications. Here we demonstrate a stone retrieval technology in which fragments are rendered magnetizable with a magnetic hydrogel so that they can be easily retrieved with a simple magnetic tool. The magnetic hydrogel facilitates robust in vitro capture of stone fragments of clinically relevant sizes and compositions. The hydrogel components exhibit no cytotoxicity in cell culture and only superficial effects on ex vivo human urothelium and in vivo mouse bladders. Furthermore, the hydrogel demonstrates antimicrobial activity against common uropathogens on par with that of common antibiotics. By enabling the efficient retrieval of kidney stone fragments, our method can lead to improved stone-free rates and patient outcomes.

Conceptual framework and documentation standards of cystoscopic media content for artificial intelligence.

BACKGROUND: The clinical documentation of cystoscopy includes visual and textual materials. However, the secondary use of visual cystoscopic data for educational and research purposes remains limited due to inefficient data management in routine clinical practice. METHODS: A conceptual framework was designed to document cystoscopy in a standardized manner with three major sections: data management, annotation management, and utilization management. A Swiss-cheese model was proposed for quality control and root cause analyses. We defined the infrastructure required to implement the framework with respect to FAIR (findable, accessible, interoperable, reusable) principles. We applied two scenarios exemplifying data sharing for research and educational projects to ensure compliance with FAIR principles. RESULTS: The framework was successfully implemented while following FAIR principles. The cystoscopy atlas produced from the framework could be presented in an educational web portal; a total of 68 full-length qualitative videos and corresponding annotation data were sharable for artificial intelligence projects covering frame classification and segmentation problems at case, lesion, and frame levels. CONCLUSION: Our study shows that the proposed framework facilitates the storage of visual documentation in a standardized manner and enables FAIR data for education and artificial intelligence research.

Kawain Inhibits Urinary Bladder Carcinogenesis through Epigenetic Inhibition of LSD1 and Upregulation of H3K4 Methylation.

Epidemiological evidence suggests that kava (Piper methysticum Forst) drinks may reduce the risk of cancer in South Pacific Island smokers. However, little is known about the anti-carcinogenic effects of kava on tobacco smoking-related bladder cancer and its underlying mechanisms. Here we show that dietary feeding of kawain (a major active component in kava root extracts) to mice either before or after hydroxy butyl(butyl) nitrosamine (OH-BBN) carcinogen exposure slows down urinary bladder carcinogenesis and prolongs the survival of the OH-BBN-exposed mice. OH-BBN-induced bladder tumors exhibit significantly increased expression of lysine-specific demethylase 1 (LSD1), accompanied by decreased levels of H3K4 mono-methylation compared to normal bladder epithelium, whereas dietary kawain reverses the effects of OH-BBN on H3K4 mono-methylation. Human bladder cancer tumor tissues at different pathological grades also show significantly increased expression of LSD1 and decreased levels of H3K4 mono-methylation compared to normal urothelium. In addition, kava root extracts and the kavalactones kawain and methysticin all increase the levels of H3K4 mono- and di-methylation, leading to inhibitory effects on cell migration. Taken together, our results suggest that modification of histone lysine methylation may represent a new approach to bladder cancer prevention and treatment and that kavalactones may be promising agents for bladder cancer interception in both current and former smokers.

PlexusNet: A neural network architectural concept for medical image classification.

State-of-the-art (SOTA) convolutional neural network models have been widely adapted in medical imaging and applied to address different clinical problems. However, the complexity and scale of such models may not be justified in medical imaging and subject to the available resource budget. Further increasing the number of representative feature maps for the classification task decreases the model explainability. The current data normalization practice is fixed prior to model development and discounting the specification of the data domain. Acknowledging these issues, the current work proposed a new scalable model family called PlexusNet; the block architecture and model scaling by the network's depth, width, and branch regulate PlexusNet's architecture. The efficient computation costs outlined the dimensions of PlexusNet scaling and design. PlexusNet includes a new learnable data normalization algorithm for better data generalization. We applied a simple yet effective neural architecture search to design PlexusNet tailored to five clinical classification problems that achieve a performance noninferior to the SOTA models ResNet-18 and EfficientNet B0/1. It also does so with lower parameter capacity and representative feature maps in ten-fold ranges than the smallest SOTA models with comparable performance. The visualization of representative features revealed distinguishable clusters associated with categories based on latent features generated by PlexusNet. The package and source code are at https://github.com/oeminaga/PlexusNet.git.

Passive monitoring by smart toilets for precision health.

Smart toilets are a key tool for enabling precision health monitoring in the home, but such passive monitoring has ethical considerations.

Conceptual Framework and Documentation Standards of Cystoscopic Media Content for Artificial Intelligence.

BACKGROUND: The clinical documentation of cystoscopy includes visual and textual materials. However, the secondary use of visual cystoscopic data for educational and research purposes remains limited due to inefficient data management in routine clinical practice. METHODS: A conceptual framework was designed to document cystoscopy in a standardized manner with three major sections: data management, annotation management, and utilization management. A Swiss-cheese model was proposed for quality control and root cause analyses. We defined the infrastructure required to implement the framework with respect to FAIR (findable, accessible, interoperable, re-usable) principles. We applied two scenarios exemplifying data sharing for research and educational projects to ensure the compliance with FAIR principles. RESULTS: The framework was successfully implemented while following FAIR principles. The cystoscopy atlas produced from the framework could be presented in an educational web portal; a total of 68 full-length qualitative videos and corresponding annotation data were sharable for artificial intelligence projects covering frame classification and segmentation problems at case, lesion and frame levels. CONCLUSION: Our study shows that the proposed framework facilitates the storage of the visual documentation in a standardized manner and enables FAIR data for education and artificial intelligence research.

Is a restaging TURBT necessary in high-risk NMIBC if the initial TURBT was performed with blue light?

OBJECTIVES: To evaluate whether a restaging transurethral resection of bladder tumor (TURBT) is necessary in high-risk nonmuscle invasive bladder cancer (NMIBC) if the initial TURBT was performed using blue light (BL) technology. METHODS AND MATERIALS: Using the multi-institutional Cysview registry between 2014 and 2021, all consecutive adult patients with known NMIBC (Ta and T1 disease) who underwent TURBT followed by a restaging TURBT within 8 weeks were reviewed. Patients were stratified according to their initial TURBT, BL vs. white light (WL), and compared to determine rates of residual disease and upstaging. Univariate analysis was performed using Mann-Whitney U and chi-square tests, with P < 0.05 considered significant. RESULTS: Overall, 115 patients had TURBT for NMIBC followed by a restaging TURBT within 8 weeks and were included in the analysis. Patients who underwent BL compared to WL for their initial TURBT had higher rates of benign pathology on restaging TURBT, although this was not statistically significant (47% vs. 30%; P = 0.08). Of patients with residual tumors on restaging TURBT, there were no differences in rates of Ta (22% vs. 26.5%; P = 0.62), T1 (22% vs. 26.5%; P = 0.62), or CIS (5.5% vs. 13%; P = 0.49) when the initial TURBT was done using BL compared to WL. Rates of upstaging to muscle invasive disease were also not different when initial TURBT was performed using BL compared to WL (3% vs. 4%; P = 0.78). CONCLUSIONS: TURBT using BL does not reduce rates of residual disease or risk of upstaging on restaging TURBT in Ta or T1 disease. Thus, a restaging TURBT is still necessary even if initial TURBT was performed using BL.

An Efficient Framework for Video Documentation of Bladder Lesions for Cystoscopy: A Proof-of-Concept Study.

Processing full-length cystoscopy videos is challenging for documentation and research purposes. We therefore designed a surgeon-guided framework to extract short video clips with bladder lesions for more efficient content navigation and extraction. Screenshots of bladder lesions were captured during transurethral resection of bladder tumor, then manually labeled according to case identification, date, lesion location, imaging modality, and pathology. The framework used the screenshot to search for and extract a corresponding 10-seconds video clip. Each video clip included a one-second space holder with a QR barcode informing the video content. The success of the framework was measured by the secondary use of these short clips and the reduction of storage volume required for video materials. From 86 cases, the framework successfully generated 249 video clips from 230 screenshots, with 14 erroneous video clips from 8 screenshots excluded. The HIPPA-compliant barcodes provided information of video contents with a 100% data completeness. A web-based educational gallery was curated with various diagnostic categories and annotated frame sequences. Compared with the unedited videos, the informative short video clips reduced the storage volume by 99.5%. In conclusion, our framework expedites the generation of visual contents with surgeon's instruction for cystoscopy and potential incorporation of video data towards applications including clinical documentation, education, and research.

Artificial Intelligence-Based Prognostic Model for Urologic Cancers: A SEER-Based Study.

BACKGROUND: Prognostication is essential to determine the risk profile of patients with urologic cancers. METHODS: We utilized the SEER national cancer registry database with approximately 2 million patients diagnosed with urologic cancers (penile, testicular, prostate, bladder, ureter, and kidney). The cohort was randomly divided into the development set (90%) and the out-held test set (10%). Modeling algorithms and clinically relevant parameters were utilized for cancer-specific mortality prognosis. The model fitness for the survival estimation was assessed using the differences between the predicted and observed Kaplan-Meier estimates on the out-held test set. The overall concordance index (c-index) score estimated the discriminative accuracy of the survival model on the test set. A simulation study assessed the estimated minimum follow-up duration and time points with the risk stability. RESULTS: We achieved a well-calibrated prognostic model with an overall c-index score of 0.800 (95% CI: 0.795-0.805) on the representative out-held test set. The simulation study revealed that the suggestions for the follow-up duration covered the minimum duration and differed by the tumor dissemination stages and affected organs. Time points with a high likelihood for risk stability were identifiable. CONCLUSIONS: A personalized temporal survival estimation is feasible using artificial intelligence and has potential application in clinical settings, including surveillance management.

Diagnosis of Bloodstream Infections: An Evolution of Technologies towards Accurate and Rapid Identification and Antibiotic Susceptibility Testing.

Bloodstream infections (BSI) are a leading cause of death worldwide. The lack of timely and reliable diagnostic practices is an ongoing issue for managing BSI. The current gold standard blood culture practice for pathogen identification and antibiotic susceptibility testing is time-consuming. Delayed diagnosis warrants the use of empirical antibiotics, which could lead to poor patient outcomes, and risks the development of antibiotic resistance. Hence, novel techniques that could offer accurate and timely diagnosis and susceptibility testing are urgently needed. This review focuses on BSI and highlights both the progress and shortcomings of its current diagnosis. We surveyed clinical workflows that employ recently approved technologies and showed that, while offering improved sensitivity and selectivity, these techniques are still unable to deliver a timely result. We then discuss a number of emerging technologies that have the potential to shorten the overall turnaround time of BSI diagnosis through direct testing from whole blood-while maintaining, if not improving-the current assay's sensitivity and pathogen coverage. We concluded by providing our assessment of potential future directions for accelerating BSI pathogen identification and the antibiotic susceptibility test. While engineering solutions have enabled faster assay turnaround, further progress is still needed to supplant blood culture practice and guide appropriate antibiotic administration for BSI patients.