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 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.

[1]  David Lo,et al.  Data Quality Matters: A Case Study on Data Label Correctness for Security Bug Report Prediction , 2022, IEEE Transactions on Software Engineering.

[2]  S. Hromis,et al.  Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study , 2022, JMIR medical informatics.

[3]  G. Varoquaux,et al.  Machine learning for medical imaging: methodological failures and recommendations for the future , 2022, npj Digital Medicine.

[4]  Damian Jankowicz,et al.  Tackling the Burden of Electronic Health Record Use Among Physicians in a Mental Health Setting: Physician Engagement Strategy , 2022, Journal of medical Internet research.

[5]  Y. Oda,et al.  Artificial intelligence for segmentation of bladder tumor cystoscopic images performed by U-Net with dilated convolution. , 2022, Journal of endourology.

[6]  T. Shanafelt.  Physician Well-being 2.0: Where Are We and Where Are We Going? , 2021, Mayo Clinic proceedings.

[7]  Q. Lv,et al.  An Artificial Intelligence System for the Detection of Bladder Cancer via Cystoscopy: A Multicenter Diagnostic Study. , 2021, Journal of the National Cancer Institute.

[8]  A. Masson-Lecomte,et al.  European Association of Urology Guidelines on Non-muscle-invasive Bladder Cancer (Ta, T1, and Carcinoma in Situ). , 2021, European urology.

[9]  T. Knoll,et al.  Deep learning-based classification of blue light cystoscopy imaging during transurethral resection of bladder tumors , 2021, Scientific Reports.

[10]  H. Nishiyama,et al.  Cystoscopic imaging for bladder cancer detection based on stepwise organic transfer learning with a pre-trained convolutional neural network. , 2020, Journal of endourology.

[11]  M. Babjuk,et al.  Best Practices to Optimise Quality and Outcomes of Transurethral Resection of Bladder Tumours. , 2020, European urology oncology.

[12]  Simon Hein,et al.  A novel endoimaging system for endoscopic 3D reconstruction in bladder cancer patients , 2020, Minimally invasive therapy & allied technologies : MITAT : official journal of the Society for Minimally Invasive Therapy.

[13]  J. Witjes,et al.  European Association of Urology Guidelines on Muscle-invasive and Metastatic Bladder Cancer: Summary of the 2020 Guidelines. , 2020, European urology.

[14]  S. Boorjian,et al.  Bladder Cancer, Version 3.2020, NCCN Clinical Practice Guidelines in Oncology. , 2020, Journal of the National Comprehensive Cancer Network : JNCCN.

[15]  H. Nishiyama,et al.  Support System of Cystoscopic Diagnosis for Bladder Cancer Based on Artificial Intelligence , 2019, Journal of endourology.

[16]  Timothy C. Chang,et al.  Augmented Bladder Tumor Detection Using Deep Learning. , 2019, European urology.

[17]  S. Joniau,et al.  Quality Control Indicators for Transurethral Resection of Non-Muscle-Invasive Bladder Cancer. , 2019, Clinical genitourinary cancer.

[18]  F. Balzarini,et al.  Development of a photographic handbook to improve cystoscopy findings during resident’s training: A randomised prospective study , 2019, Arab journal of urology.

[19]  Okyaz Eminaga,et al.  Diagnostic Classification of Cystoscopic Images Using Deep Convolutional Neural Networks. , 2018, JCO clinical cancer informatics.

[20]  J. Lubowitz,et al.  Expert Opinion Is Necessary: Delphi Panel Methodology Facilitates a Scientific Approach to Consensus. , 2018, Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association.

[21]  Ali Borji,et al.  Negative results in computer vision: A perspective , 2017, Image Vis. Comput..

[22]  Emmanuel Chazard,et al.  Secondary Use of Healthcare Structured Data: The Challenge of Domain-Knowledge Based Extraction of Features , 2018, EFMI-STC.

[23]  Timothy C. Chang,et al.  Image-Guided Transurethral Resection of Bladder Tumors – Current Practice and Future Outlooks , 2017, Bladder cancer.

[24]  Md. Zakirul Alam Bhuiyan,et al.  A Survey on Deep Learning in Big Data , 2017, 22017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC).

[25]  C. Compton,et al.  The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population‐based to a more “personalized” approach to cancer staging , 2017, CA: a cancer journal for clinicians.

[26]  Y. Lotan,et al.  Guideline of guidelines: non‐muscle‐invasive bladder cancer , 2017, BJU international.

[27]  Erik Schultes,et al.  The FAIR Guiding Principles for scientific data management and stewardship , 2016, Scientific Data.

[28]  Paul A. Harris,et al.  Secondary use of clinical data: The Vanderbilt approach , 2014, J. Biomed. Informatics.

[29]  Mark A. Musen,et al.  BioPortal as a dataset of linked biomedical ontologies and terminologies in RDF , 2013, Semantic Web.

[30]  Alan C. Bovik,et al.  No-Reference Image Quality Assessment in the Spatial Domain , 2012, IEEE Transactions on Image Processing.

[31]  Tim Benson,et al.  Principles of Health Interoperability HL7 and SNOMED , 2009 .

[32]  D. Hansel,et al.  Benign Diseases of the Bladder. , 2008, Surgical pathology clinics.

[33]  Emily Grantner,et al.  ISO 8000 : a standard for data quality , 2007 .

[34]  H. K. Huang,et al.  PACS and Imaging Informatics: Basic Principles and Applications , 2004 .

[35]  John Mingers,et al.  The paucity of multimethod research: a review of the information systems literature , 2003, Inf. Syst. J..