Skip to main content

Publications

Joseph C. Liao

Kathryn Simmons Stamey Professor

Publications

    • Field-effect-informed urine liquid biopsy for bladder cancer.

      Shi, W. Y., Liu, K. J., Esfahani, M. S., Mach, K. E., Phillips, N. A., Almanza, D., Bajpai, R. K., Schroers-Martin, J. G., Trabanino, L., Lee, T. J., La, V., Rodriguez, G., Holton, G., Chen, S. B., Mullane, P., Wu, D. J., Nesselbush, M. C., Sugio, T., Cheng, J. C., Jabara, I., Hamilton, E. G., Alig, S. K., Liu, C. L., Peterson, D. J., Prado, K., Shkolyar, E., Thong, A., Shah, J. B., Gill, H., Kunder, C. A., Chan, E., Khaki, A. R., Skinner, E. C., Alizadeh, A. A., Liao, J. C., Diehn, M.

      Cell

      ABSTRACT
      Diagnostic cystoscopy in combination with transurethral resection of the bladder tumour are the standard for the diagnosis, surgical treatment and surveillance of bladder cancer. The ability to inspect the bladder in its current form stems from a long chain of advances in imaging science and endoscopy. Despite these advances, bladder cancer recurrence and progression rates remain high after endoscopic resection. This stagnation is a result of the heterogeneity of cancer biology as well as limitations in surgical techniques and tools, as incomplete resection and provider-specific differences affect cancer persistence and early recurrence. An unmet clinical need remains for solutions that can improve tumour delineation and resection. Translational advances in enhanced cystoscopy technologies and artificial intelligence offer promising avenues to overcoming the progress plateau.
      https://www.ncbi.nlm.nih.gov/pubmed/41605210 https://doi.org/10.1016/j.cell.2025.12.054
      More

    • AI-Driven Defecation Analysis by Smart Healthcare Toilet: Exploring Biometric Patterns and Eu-Tenesmus.

      Song, Z., Kwon, T., Lee, J., Won, D. D., Lee, B. J., Choi, H. S., Liao, J. C., Park, W. G., Sonu, I., Rogalla, S., Rosen, M. J., Hu, D. L., Ziyang, J. K., Wong, S. H., Jun, B. H., Kim, S., Park, S. M.

      Advanced science (Weinheim, Baden-Wurttemberg, Germany)

      ABSTRACT
      Renal ultrasound (US) offers less radiation exposure than computed tomography (CT) for kidney stone surveillance but has lower sensitivity and specificity for nephrolithiasis diagnosis. Additionally, US may overestimate stone size, leading to unnecessary surgical interventions. Evidence on US performance for kidney stone surveillance is variable, making its clinical utility unclear. We aimed to assess US accuracy against CT and identify factors influencing US performance.We performed a retrospective review of patients with known nephrolithiasis seen in urology clinic at Stanford who underwent both renal US and CT within 90 days for surveillance from January to December 2022. Patients with spontaneous stone passage or interventions were excluded. Stone characteristics were recorded, and statistical analysis compared the diagnostic accuracy of US and CT.A total of 107 patients and 128 stones were included, with a mean time difference of 25.7 days between US and CT. US sensitivity was 77%, with a positive predictive value (PPV) of 75% for stone detection. The PPV was only 59% for stones >4 mm by CT. Mean stone size was 8.7 mm on US vs. 5.5 mm on CT (p=0.02), with more pronounced overestimation in smaller stones and higher body mass index (BMI) (p<0.05). No significant differences in US performance were found by stone location, laterality, or time between scans. Differences in stone detection (p=0.01) and size (p=0.03) were associated with the individual performing the ultrasound.US performance is limited compared to CT and is influenced by stone size, BMI, and sonographer. Overestimation by US may lead to unnecessary interventions in up to 40% of patients with stones >4 mm.
      https://www.ncbi.nlm.nih.gov/pubmed/40349171 https://doi.org/10.1002/advs.202503247
      More

    • Perspective on the use of optics in bladder cancer detection and diagnosis.

      Remmelink, M. J., Peterson, D. J., Nieuwenhuijzen, J. A., van Leeuwen, T. G., Liao, J. C., de Bruin, D. M.

      Journal of biomedical optics

      ABSTRACT
      Kidney stones are a common disorder associated with significant morbidity and often requires surgical intervention. Pathogenic bacteria are found in almost 40% of stones, where they form biofilms that are protected from systemic antibiotic treatments. Stone surgeries disperse biofilms resulting in up to 30% of patients developing postoperative urinary tract infections and 15% developing sepsis. This work is based on the hypothesis that chitosan, an antimicrobial polymer, can eradicate bacterial biofilms present in the stone and potentially serve as an adjunct to irrigation during stone surgery. First, fresh patient-derived kidney stone fragments (n = 56) are collected from stone surgeries. A total of 32% of stones are colonized, predominantly with Enterococcus faecalis, Escherichia coli, and Proteus mirabilis. A short, clinically relevant, chitosan treatment reduces the bacterial burden on colonized stones by over 90% in all specimens tested, regardless of stone composition and bacterial strain. To assess this approach toxicity, ex vivo human ureters and in vivo porcine bladders are exposed to topical chitosan irrigation. No toxic or pathological abnormalities other than urothelial exfoliation are noted. In conclusion, chitosan effectively disrupts kidney stone-associated bacterial biofilms with minimal urothelial toxicity and may provide an effective and safe approach to reducing postoperative complications.
      https://www.ncbi.nlm.nih.gov/pubmed/40190592 https://doi.org/10.1117/1.JBO.30.4.040601
      More

    • Limitations of ultrasound compared with computed tomography for kidney stone surveillance.

      Sun, R., Sommer, E., Ganesan, C., Pao, A. C., Liao, J., Leppert, J., Chang, H., Conti, S., Chang, T.

      Canadian Urological Association journal = Journal de l'Association des urologues du Canada

      ABSTRACT
      Antimicrobial stewardship plays an essential role in combating the global health threat posed by multidrug-resistant pathogens. Phenotypic antimicrobial susceptibility testing (AST) is the gold standard for analyzing bacterial responses to antimicrobials. However, current AST techniques, which rely on end-point bulk measurements of bacterial growth under antimicrobial treatment in a broth solution, have limitations in resembling the physiological working environment and resolving heterogeneity in response kinetics within the population. In this study, we investigate the responses of uropathogenic bacteria under antimicrobial treatment in individual urine. Our results demonstrate substantial heterogeneity in time-kill kinetics in response to antimicrobials in a host-dependent manner. We also establish a microfluidic gel encapsulation platform for single cell imaging to rapidly resolve heterogeneous subpopulations in response to antimicrobials. The platform captures both bacterial growth and killing within the gel and enables medium exchange to assess the ability of surviving cells to resume growth after antimicrobial removal. Our study lays the foundation for a new generation of precision single cell analysis for personalizing antimicrobial treatment.
      https://www.ncbi.nlm.nih.gov/pubmed/40116666 https://doi.org/10.5489/cuaj.9043
      More

    • Disrupting Biofilms on Human Kidney Stones-A Path Toward Reducing Infectious Complications During Stone Surgery.

      Massana Roquero, D., Holton, G. H., Ge, T. J., Kornberg, Z., Mach, K. E., Rodriguez, G., La, V., Lau, H., Sun, R., Chang, T. C., Conti, S., Liao, J. C.

      Advanced healthcare materials

      ABSTRACT
      Antimicrobial stewardship plays an essential role in combating the global health threat posed by multidrug-resistant pathogens. Phenotypic antimicrobial susceptibility testing (AST) is the gold standard for analyzing bacterial responses to antimicrobials. However, current AST techniques, which rely on end-point bulk measurements of bacterial growth under antimicrobial treatment in a broth solution, have limitations in resembling the physiological working environment and resolving heterogeneity in response kinetics within the population. In this study, we investigate the responses of uropathogenic bacteria under antimicrobial treatment in individual urine. Our results demonstrate substantial heterogeneity in time-kill kinetics in response to antimicrobials in a host-dependent manner. We also establish a microfluidic gel encapsulation platform for single cell imaging to rapidly resolve heterogeneous subpopulations in response to antimicrobials. The platform captures both bacterial growth and killing within the gel and enables medium exchange to assess the ability of surviving cells to resume growth after antimicrobial removal. Our study lays the foundation for a new generation of precision single cell analysis for personalizing antimicrobial treatment.
      https://www.ncbi.nlm.nih.gov/pubmed/40012448 https://doi.org/10.1002/adhm.202403470
      More

    • Upstaging and risk migration with blue light cystoscopy for non-muscle-invasive bladder cancer: Results from a prospective multi-center registry.

      Ghoreifi, A., Konety, B. R., Pohar, K. S., Holzbeierlein, J., Taylor III, J., Kates, M., Willard, B., Taylor, J. M., Liao, J. C., Kaimakliotis, H. Z., Porten, S. P., Steinberg, G. D., Tyson, M., Lotan, Y., Daneshmand, S.

      ABSTRACT
      The ability of the Veterans Health Administration System to care for veterans with bladder cancer is influenced by the increased complexity of both veterans and the system's capacity to do so, which is determined by personnel and equipment allocation. Herein, we review the guidelines for bladder cancer management in the context of this population and highlight unique veteran characteristics that impact the delivery of bladder cancer care within the Veterans Health Administration System. There are opportunities for standardization and implementation, which can improve the quality of this care, and we summarize the questions for which coordinated research efforts may provide answers.
      https://www.ncbi.nlm.nih.gov/pubmed/39898695 https://doi.org/10.1200/JCO.2025.43.5_suppl.686
      More

    • Microbial Product Cocktails for Personalized Cancer Immunotherapy.

      Yan, Y., Yang, S., Mach, K. E., Chen, G., DeGraff, D. J., Liao, J. C., Wong, P. K.

      Nature communications

      ABSTRACT
      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.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.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.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.
      https://www.ncbi.nlm.nih.gov/pubmed/41331244 https://doi.org/10.1038/s41467-025-66238-1
      More

    • Precision single cell analysis to characterize host dependent antimicrobial response heterogeneity in physiological medium.

      Abe, R., Lee, J. H., Chin, S. M., Ram-Mohan, N., Tjandra, K. C., Bobenchik, A. M., Mach, K. E., Liao, J. C., Wong, P. K., Yang, S.

      Lab on a chip

      ABSTRACT
      Early detection of the cell type changes underlying several genitourinary tract diseases largely remains an unmet clinical need, where existing assays, if available, lack the cellular resolution afforded by an invasive biopsy. While messenger RNA in urine could reflect the dynamic signal that facilitates early detection, current measurements primarily detect single genes and thus do not reflect the entire transcriptome and the underlying contributions of cell type-specific RNA.We isolated and sequenced the cell-free RNA (cfRNA) and sediment RNA from human urine samples (n = 6 healthy controls and n = 12 kidney stone patients) and measured the urine metabolome. We analyzed the resulting urine transcriptomes by deconvolving the noninvasively measurable cell type contributions and comparing to plasma cfRNA and the measured urine metabolome.Urine transcriptome cell type deconvolution primarily yielded relative fractional contributions from genitourinary tract cell types in addition to cell types from high-turnover solid tissues beyond the genitourinary tract. Comparison to plasma cfRNA yielded enrichment of metabolic pathways and a distinct cell type spectrum. Integration of urine transcriptomic and metabolomic measurements yielded enrichment for metabolic pathways involved in amino acid metabolism and overlapped with metabolic subsystems associated with proximal tubule function.Noninvasive whole transcriptome measurements of human urine cfRNA and sediment RNA reflects signal from hard-to-biopsy tissues exhibiting low representation in blood plasma cfRNA liquid biopsy at cell type resolution and are enriched in signal from metabolic pathways measurable in the urine metabolome.
      https://www.ncbi.nlm.nih.gov/pubmed/39898695 https://doi.org/10.1039/d4lc00765d
      More

    • An Organoid Biosensing Platform for Personalized Prognosis of Bladder Cancer.

      Yan, Y., Ahmed, M., Mach, K. E., Liao, J. C., Wong, P. K.

      ACS nano

      ABSTRACT
      Bladder cancer (BC) diagnosis, management, and outcomes depend on the accurate detection of tumors via optical technologies. Accordingly, understanding the benefits and limitations of these technologies permits improvements in patient care and identifies areas for future research.We outline the current process of BC detection and diagnosis, explore the current role of optical technologies, and discuss the opportunities and challenges they present in this field.The current diagnostic pathway of BC, the use of optical technologies, and their shortcomings in this process are reviewed. From there, opportunities and challenges of optics in BC detection and diagnosis are discussed.BC management is expensive due to the limitations of white light cystoscopy, the requirement for histopathological confirmation, and the need for long-term surveillance. Alternative non-optical methods lack accuracy, and available optical techniques focus only on cancer detection. Alternatives to histopathology need to provide accurate real-time results to be effective. Optical advancements offer potential benefits; however, challenges include cost-effectiveness, device complexity, required training, and tumor heterogeneity.Optical techniques could accelerate BC diagnosis, reduce costs, and enable alternative treatments. However, overcoming technical and practical challenges is essential for their successful integration.
      https://www.ncbi.nlm.nih.gov/pubmed/41166099 https://doi.org/10.1021/acsnano.5c09883
      More

    • Ensuring Successful Biomarker Studies in Bladder Preservation Clinical Trials for Non-muscle Invasive Bladder Cancer.

      McConkey, D. J., Baumann, B. C., Cooper Greenberg, S., DeGraff, D. J., Delacroix, S. E., Efstathiou, J. A., Foster, J., Groshen, S., Kadel, E. E., Khani, F., Kim, W. Y., Lerner, S. P., Levin, T., Liao, J. C., Milowsky, M. I., Meeks, J. J., Miyamoto, D. T., Mouw, K. W., Pietzak, E. J., Solit, D. B., Sundi, D., Tawab-Amiri, A., West, P. J., Wobker, S. E., Wyatt, A. W., Apolo, A. B., Black, P. C.

      Bladder cancer (Amsterdam, Netherlands)

      ABSTRACT
      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.
      https://www.ncbi.nlm.nih.gov/pubmed/38993535 https://doi.org/10.3233/BLC-230082
      More

    • Optimizing cystoscopy and TURBT: enhanced imaging and artificial intelligence.

      Shkolyar, E., Zhou, S. R., Carlson, C. J., Chang, S., Laurie, M. A., Xing, L., Bowden, A. K., Liao, J. C.

      Nature reviews. Urology

      ABSTRACT
      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.
      https://www.ncbi.nlm.nih.gov/pubmed/38982304 https://doi.org/10.1038/s41585-024-00904-9
      More

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

      Eminaga, O., Lee, T. J., La, V., Breil, B., Xing, L., Liao, J. C.

      JCO clinical cancer informatics

      ABSTRACT
      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.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.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.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.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.
      https://www.ncbi.nlm.nih.gov/pubmed/38484216 https://doi.org/10.1200/CCI.23.00114
      More

    • LEVERAGING DIGITAL SPATIAL PROFILING TO IDENTIFY TRANSCRIPTIONAL SIGNATURES ASSOCIATED WITH UROTHELIAL CARCINOMA IN SITU

      Frydenlund, N., Meeks, J. J., Lu, X., Choy, B., Yang, R., Mach, K., Liao, J., Lau, H.

      ABSTRACT
      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.
      https://www.ncbi.nlm.nih.gov/pubmed/38325216 https://doi.org/10.1016/j.urolonc.2024.01.125
      More

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

      Jia, X., Shen, Y., Yang, J., Song, R., Zhang, W., Meng, M. Q., Liao, J. C., Xing, L.

      Computers in biology and medicine

      ABSTRACT
      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.
      https://www.ncbi.nlm.nih.gov/pubmed/38325216 https://doi.org/10.1016/j.compbiomed.2024.108006
      More

    • Ensuring Successful Biomarker Studies in Bladder Preservation Clinical Trials for Non-muscle Invasive Bladder Cancer

      McConkey, D. J., Baumann, B. C., Greenberg, S., DeGraff, D. J., Delacroix, S. E., Efstathiou, J. A., Foster, J., Groshen, S., Kadel, E. E., Khani, F., Kim, W. Y., Lerner, S. P., Levin, T., Liao, J. C., Milowsky, M. I., Meeks, J. J., Miyamoto, D. T., Mouw, K. W., Pietzak, E. J., Solit, D. B., Sundi, D., Tawab-Amiri, A., West, P. J., Wobker, S. E., Wyatt, A. W., Apolo, A. B., Black, P. C.

      BLADDER CANCER

      ABSTRACT
      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.
      https://www.ncbi.nlm.nih.gov/pubmed/38129376 https://doi.org/10.3233/BLC-230082
      More

    • Translating microbiota analysis for clinical applications

      Lee, J., Chin, S., Mach, K. E., Bobenchik, A. M., Liao, J. C., Yang, S., Wong, P.

      Nature Reviews Bioengineering

      ABSTRACT
      Development of intelligence systems for bladder lesion detection is cost intensive. An efficient strategy to develop such intelligence solutions is needed.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.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.Educational cystoscopy atlas and efficient models facilitate the development of real-time intelligence system for bladder lesion detection.
      https://www.ncbi.nlm.nih.gov/pubmed/38129376 http://dx.doi.org/10.1038/s44222-024-00168-3
      More

    • The Management of Non-Muscle-Invasive Bladder Cancer in a Veteran Patient Population: Issues and Recommendations.

      Taylor, J., Patel, S., Gaitonde, K., Greene, K., Liao, J. C., McWilliams, G., Sawyer, M., Schroeck, F., Alrabaa, A., Saffati, G., Kronstedt, S., Jones, J.

      Current oncology (Toronto, Ont.)

      ABSTRACT
      The intricate interactions between host and microbial communities hold significant implications for biology and medicine. However, traditional microbial profiling methods face limitations in processing time, measurement of absolute abundance, detection of low biomass, discrimination between live and dead cells, and functional analysis. This study introduces a rapid multimodal microbial characterization platform, Multimodal Biosensors for Transversal Analysis (MBioTA), for capturing the taxonomy, viability, and functional genes of the microbiota. The platform incorporates single cell biosensors, scalable microwell arrays, and automated image processing for rapid transversal analysis in as few as 2 h. The multimodal biosensors simultaneously characterize the taxon, viability, and functional gene expression of individual cells. By automating the image processing workflow, the single cell analysis techniques enable the quantification of bacteria with sensitivity down to 0.0075%, showcasing its capability in detecting low biomass samples. We illustrate the applicability of the MBioTA platform through the transversal analysis of the gut microbiota composition, viability, and functionality in a familial Alzheimer's disease mouse model. The effectiveness, rapid turnaround, and scalability of the MBioTA platform will facilitate its application from basic research to clinical diagnostics, potentially revolutionizing our understanding and management of diseases associated with microbe-host interactions.
      https://www.ncbi.nlm.nih.gov/pubmed/39590124 https://doi.org/10.3390/curroncol31110493
      More

    • Deconvolution of Human Urine across the Transcriptome and Metabolome.

      Vorperian, S. K., DeFelice, B. C., Buonomo, J. A., Chinchinian, H. J., Gray, I. J., Yan, J., Mach, K. E., La, V., Lee, T. J., Liao, J. C., Lafayette, R., Loeb, G. B., Bertozzi, C. R., Quake, S. R.

      Clinical chemistry

      ABSTRACT
      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.
      https://www.ncbi.nlm.nih.gov/pubmed/39383112 https://doi.org/10.1093/clinchem/hvae137
      More

    • Rapid Microbial Profiling through Multimodal Biosensors for Transversal Analysis.

      Lee, J. H., Chin, S. M., Chan, D. C., Liao, J. C., Yang, S., Zhang, N., Wong, P. K.

      Analytical chemistry

      ABSTRACT
      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.
      https://www.ncbi.nlm.nih.gov/pubmed/39007543 https://doi.org/10.1021/acs.analchem.4c02449
      More

    • ULTRASENSITIVE URINARY LIQUID BIOPSY ANALYSIS FOR BCG RESPONSE ASSESSMENT IN HIGH-RISK NON-MUSCLE INVASIVE BLADDER CANCER

      Shi, W. Y., Liu, K. J., Esfahani, M. S., Schroers-Martin, J. G., Nesselbush, M., Chen, S. B., Alig, S. K., Mullane, P., Mach, K. E., Trabanino, L., Lee, T. J., Yoo, I., Vinh La, Rodriguez, G., Kornberg, Z., Shkolyar, E., Gill, H., Thong, A., Shah, J. B., Prado, K., Skinner, E. C., Alizadeh, A. A., Liao, J. C., Diehn, M.

      ABSTRACT
      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.
      https://www.ncbi.nlm.nih.gov/pubmed/38993535 https://doi.org/10.3233/BLC-230082
      More
see all publications