EUVIMEDEUVIMED entdecken
BeobachtungsstudieStudienprotokoll

Artificial intelligence software CystoSmart™ for papillary or flat lesions during bladder endoscopy: a prospective observational pilot study protocol

Francesco Del Giudice, Roberta Corvino, Valerio Santarelli, Eleonora Razeto, Stefano Impaloni, Sarah Carvalho Ribeiro, Matilde Verde, Bernardo Rocco, Ettore De Berardinis, Jan Laszkiewicz, Benjamin I Chung, Amir Khan und 5 weitere

Canadian Journal of Urology · 2026 · 33 (5) · 1251-1259

DOI: 10.32604/cju.2026.079662 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift Canadian Journal of Urology, 2026. Verfasst von Francesco Del Giudice und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Maternal-Infant and Urological Sciences, "Sapienza" University of Rome, Umberto I Hospital, Rome, Italy. Hauptthemen laut MEDLINE: Cystoscopy, Urinary Bladder Neoplasms, Software, Artificial Intelligence.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: White light cystoscopy (WLC) remains the standard tool for the diagnosis and surveillance of bladder cancer (BC), but it may miss up to 20% of lesions, highlighting the potential role of artificial intelligence (AI) assisted systems such as CystoSmart™. The study aims to evaluate the sensitivity and specificity of CystoSmart™ in detecting papillary and flat lesions, using histopathology as the reference standard. METHODS: This is a prospective observational, non-interventional study with retrospective AI application, led by "Sapienza" University of Rome. Patients undergoing primary or follow up WLC for suspected BC will be enrolled and will provide informed consent for anonymized recording. Frames will be retrospectively analyzed by the software without influencing clinical decision-making. Exclusion criteria include metastatic disease, inability to provide consent, inadequate video quality, and contraindications to cystoscopy. A total sample size of 158 patients was determined to ensure at least 138 positive cases. Statistical analyses will apply confidence intervals and exact binomial testing. RESULTS: Based on the sample size calculation and the preliminary internal validation data, CystoSmart™ is expected to achieve sensitivity exceeding 90% for BC detection, with specificity also anticipated to exceed 90%. Diagnostic accuracy, sensitivity, specificity, positive and negative predictive values will be estimated at both the per-patient and per-lesion levels. Exploratory subgroup analyses will assess performance across primary diagnostic, intraoperative, and surveillance settings. CONCLUSION: AI-assisted cystoscopy has the potential to facilitate the integration of AI- based tools into routine BC clinical practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CystoscopyUrinary Bladder NeoplasmsSoftwareArtificial IntelligenceHumansPilot ProjectsProspective StudiesSensitivity and Specificity

Stichwörter der Autor:innen

Bladder cancerCystoSmartcystoscopyendoscopynon-muscle-invasive bladder cancerwhite-light cystoscopy

Autor:innen und Institutionen

  • Department of Maternal-Infant and Urological Sciences, "Sapienza" University of Rome, Umberto I Hospital, Rome, Italy.
  • Department of Urology, Stanford University School of Medicine, Stanford, CA, USA.
  • Guy's and St. Thomas' NHS Foundation Trust, Guy's Hospital, London, UK.
  • Department of Urology, IRCCS A. Gemelli University Polyclinic Foundation, Sacred Heart Catholic University, Rome, Italy.
  • Department of Minimally Invasive and Robotic Urology, University Center of Excellence in Urology, Wroclaw Medical University, Wroclaw, Poland.
  • Division of Urology, Department of Surgery, University of Maryland School of Medicine, Baltimore, MD, USA.

Zitieren

APA

Giudice, F. D., Corvino, R., Santarelli, V., Razeto, E., Impaloni, S., Ribeiro, S. C., Verde, M., Rocco, B., Berardinis, E., Laszkiewicz, J., Chung, B. I., Khan, A., Abu-Ghanem, Y., Mensah, E., Thurairaja, R., Khan, M. S., & Nair, R. (2026). Artificial intelligence software CystoSmart™ for papillary or flat lesions during bladder endoscopy: a prospective observational pilot study protocol. Canadian Journal of Urology, 33(5), 1251-1259. https://doi.org/10.32604/cju.2026.079662

Vancouver

Giudice FD, Corvino R, Santarelli V, Razeto E, Impaloni S, Ribeiro SC, et al. Artificial intelligence software CystoSmart™ for papillary or flat lesions during bladder endoscopy: a prospective observational pilot study protocol. Canadian Journal of Urology. 2026;33(5):1251-1259. doi:10.32604/cju.2026.079662

BibTeX
@article{Giudice2026,
  author = {Giudice, Francesco Del and Corvino, Roberta and Santarelli, Valerio and Razeto, Eleonora and Impaloni, Stefano and Ribeiro, Sarah Carvalho and Verde, Matilde and Rocco, Bernardo and Berardinis, Ettore De and Laszkiewicz, Jan and Chung, Benjamin I and Khan, Amir and Abu-Ghanem, Yasmin and Mensah, Elsie and Thurairaja, Ramesh and Khan, Muhammad Shamim and Nair, Rajesh},
  title = {Artificial intelligence software CystoSmart™ for papillary or flat lesions during bladder endoscopy: a prospective observational pilot study protocol},
  journal = {Canadian Journal of Urology},
  year = {2026},
  volume = {33},
  number = {5},
  pages = {1251--1259},
  doi = {10.32604/cju.2026.079662}
}
Kostenlos starten →