Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocol
Introduction Histopathological evaluation of prostate biopsies using the Gleason scoring system is critical for prostate cancer diagnosis and treatment selection. However, grading variability among pathologists can lead to inconsistent assessments, risking inappropriate treatment. Similar challenges...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2025-07-01
|
| Series: | BMJ Open |
| Online Access: | https://bmjopen.bmj.com/content/15/7/e097591.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849416253553246208 |
|---|---|
| author | Martin Eklund Brett Delahunt Lars Egevad Hemamali Samaratunga Mattias Rantalainen Marcello Gambacorta Einar Gudlaugsson Bodil Ginnerup Pedersen Xiaoyi Ji Karina Dalsgaard Sørensen Kelvin Szolnoky Nita Mulliqi Anders Blilie Henrik Olsson Matteo Titus Geraldine Martinez Gonzalez Sol Erika Boman Masi Valkonen Svein Reidar Kjosavik José Asenjo Paolo Libretti Marcin Braun Radzislaw Kordek Roman Łowicki Kristina Hotakainen Päivi Väre Benedicte Parm Ulhøi Pekka Ruusuvuori Toyonori Tsuzuki Emilius Adrianus Maria Janssen Kimmo Kartasalo |
| author_facet | Martin Eklund Brett Delahunt Lars Egevad Hemamali Samaratunga Mattias Rantalainen Marcello Gambacorta Einar Gudlaugsson Bodil Ginnerup Pedersen Xiaoyi Ji Karina Dalsgaard Sørensen Kelvin Szolnoky Nita Mulliqi Anders Blilie Henrik Olsson Matteo Titus Geraldine Martinez Gonzalez Sol Erika Boman Masi Valkonen Svein Reidar Kjosavik José Asenjo Paolo Libretti Marcin Braun Radzislaw Kordek Roman Łowicki Kristina Hotakainen Päivi Väre Benedicte Parm Ulhøi Pekka Ruusuvuori Toyonori Tsuzuki Emilius Adrianus Maria Janssen Kimmo Kartasalo |
| author_sort | Martin Eklund |
| collection | DOAJ |
| description | Introduction Histopathological evaluation of prostate biopsies using the Gleason scoring system is critical for prostate cancer diagnosis and treatment selection. However, grading variability among pathologists can lead to inconsistent assessments, risking inappropriate treatment. Similar challenges complicate the assessment of other prognostic features like cribriform cancer morphology and perineural invasion. Many pathology departments are also facing an increasingly unsustainable workload due to rising prostate cancer incidence and a decreasing pathologist workforce coinciding with increasing requirements for more complex assessments and reporting. Digital pathology and artificial intelligence (AI) algorithms for analysing whole slide images show promise in improving the accuracy and efficiency of histopathological assessments. Studies have demonstrated AI’s capability to diagnose and grade prostate cancer comparably to expert pathologists. However, external validations on diverse data sets have been limited and often show reduced performance. Historically, there have been no well-established guidelines for AI study designs and validation methods. Diagnostic assessments of AI systems often lack preregistered protocols and rigorous external cohort sampling, essential for reliable evidence of their safety and accuracy.Methods and analysis This study protocol covers the retrospective validation of an AI system for prostate biopsy assessment. The primary objective of the study is to develop a high-performing and robust AI model for diagnosis and Gleason scoring of prostate cancer in core needle biopsies, and at scale evaluate whether it can generalise to fully external data from independent patients, pathology laboratories and digitalisation platforms. The secondary objectives cover AI performance in estimating cancer extent and detecting cribriform prostate cancer and perineural invasion. This protocol outlines the steps for data collection, predefined partitioning of data cohorts for AI model training and validation, model development and predetermined statistical analyses, ensuring systematic development and comprehensive validation of the system. The protocol adheres to Transparent Reporting of a multivariable prediction model of Individual Prognosis Or Diagnosis+AI (TRIPOD+AI), Protocol Items for External Cohort Evaluation of a Deep Learning System in Cancer Diagnostics (PIECES), Checklist for AI in Medical Imaging (CLAIM) and other relevant best practices.Ethics and dissemination Data collection and usage were approved by the respective ethical review boards of each participating clinical laboratory, and centralised anonymised data handling was approved by the Swedish Ethical Review Authority. The study will be conducted in agreement with the Helsinki Declaration. The findings will be disseminated in peer-reviewed publications (open access). |
| format | Article |
| id | doaj-art-94e9fca9a8bf469bbeda5f9c142f4048 |
| institution | Kabale University |
| issn | 2044-6055 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Open |
| spelling | doaj-art-94e9fca9a8bf469bbeda5f9c142f40482025-08-20T03:33:14ZengBMJ Publishing GroupBMJ Open2044-60552025-07-0115710.1136/bmjopen-2024-097591Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocolMartin Eklund0Brett Delahunt1Lars Egevad2Hemamali Samaratunga3Mattias Rantalainen4Marcello Gambacorta5Einar Gudlaugsson6Bodil Ginnerup Pedersen7Xiaoyi Ji8Karina Dalsgaard Sørensen9Kelvin Szolnoky10Nita Mulliqi11Anders Blilie12Henrik Olsson13Matteo Titus14Geraldine Martinez Gonzalez15Sol Erika Boman16Masi Valkonen17Svein Reidar Kjosavik18José Asenjo19Paolo Libretti20Marcin Braun21Radzislaw Kordek22Roman Łowicki23Kristina Hotakainen24Päivi Väre25Benedicte Parm Ulhøi26Pekka Ruusuvuori27Toyonori Tsuzuki28Emilius Adrianus Maria Janssen29Kimmo Kartasalo30Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, SwedenMalaghan Institute of Medical Research, Wellington, New ZealandDepartment of Oncology and Pathology, Karolinska Institutet, Stockholm, SwedenAquesta Uropathology and University of Queensland, Brisbane, Queensland, AustraliaDepartment of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, SwedenDepartment of Pathology, SYNLAB, Brescia, ItalyDepartment of Pathology, Stavanger University Hospital, Stavanger, NorwayDepartment of Radiology, Aarhus University Hospital, Aarhus, DenmarkDepartment of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, SwedenDepartment of Clinical Medicine, Aarhus University, Aarhus, DenmarkDepartment of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, SwedenDepartment of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, SwedenDepartment of Pathology, Stavanger University Hospital, Stavanger, NorwayDepartment of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, SwedenDepartment of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, SwedenDepartment of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, SwedenDepartment of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, SwedenInstitute of Biomedicine, University of Turku, Turku, FinlandThe General Practice and Care Coordination Research Group, Stavanger University Hospital, Stavanger, NorwayDepartment of Pathology, SYNLAB, Madrid, SpainDepartment of Pathology, SYNLAB, Brescia, ItalyDepartment of Pathology, Chair of Oncology, Medical University of Lodz, Lodz, PolandDepartment of Pathology, Chair of Oncology, Medical University of Lodz, Lodz, Polandst Department of Urology, Medical University of Lodz, Lodz, PolandDepartment of Clinical Chemistry, University of Helsinki, Helsinki, FinlandMehiläinen Länsi-Pohja Hospital, Kemi, FinlandDepartment of Pathology, Aarhus University Hospital, Aarhus, DenmarkInstitute of Biomedicine, University of Turku, Turku, FinlandDepartment of Surgical Pathology, School of Medicine, Aichi Medical University, Nagoya, JapanDepartment of Pathology, Stavanger University Hospital, Stavanger, NorwayDepartment of Medical Epidemiology and Biostatistics, SciLifeLab, Karolinska Institutet, Stockholm, SwedenIntroduction Histopathological evaluation of prostate biopsies using the Gleason scoring system is critical for prostate cancer diagnosis and treatment selection. However, grading variability among pathologists can lead to inconsistent assessments, risking inappropriate treatment. Similar challenges complicate the assessment of other prognostic features like cribriform cancer morphology and perineural invasion. Many pathology departments are also facing an increasingly unsustainable workload due to rising prostate cancer incidence and a decreasing pathologist workforce coinciding with increasing requirements for more complex assessments and reporting. Digital pathology and artificial intelligence (AI) algorithms for analysing whole slide images show promise in improving the accuracy and efficiency of histopathological assessments. Studies have demonstrated AI’s capability to diagnose and grade prostate cancer comparably to expert pathologists. However, external validations on diverse data sets have been limited and often show reduced performance. Historically, there have been no well-established guidelines for AI study designs and validation methods. Diagnostic assessments of AI systems often lack preregistered protocols and rigorous external cohort sampling, essential for reliable evidence of their safety and accuracy.Methods and analysis This study protocol covers the retrospective validation of an AI system for prostate biopsy assessment. The primary objective of the study is to develop a high-performing and robust AI model for diagnosis and Gleason scoring of prostate cancer in core needle biopsies, and at scale evaluate whether it can generalise to fully external data from independent patients, pathology laboratories and digitalisation platforms. The secondary objectives cover AI performance in estimating cancer extent and detecting cribriform prostate cancer and perineural invasion. This protocol outlines the steps for data collection, predefined partitioning of data cohorts for AI model training and validation, model development and predetermined statistical analyses, ensuring systematic development and comprehensive validation of the system. The protocol adheres to Transparent Reporting of a multivariable prediction model of Individual Prognosis Or Diagnosis+AI (TRIPOD+AI), Protocol Items for External Cohort Evaluation of a Deep Learning System in Cancer Diagnostics (PIECES), Checklist for AI in Medical Imaging (CLAIM) and other relevant best practices.Ethics and dissemination Data collection and usage were approved by the respective ethical review boards of each participating clinical laboratory, and centralised anonymised data handling was approved by the Swedish Ethical Review Authority. The study will be conducted in agreement with the Helsinki Declaration. The findings will be disseminated in peer-reviewed publications (open access).https://bmjopen.bmj.com/content/15/7/e097591.full |
| spellingShingle | Martin Eklund Brett Delahunt Lars Egevad Hemamali Samaratunga Mattias Rantalainen Marcello Gambacorta Einar Gudlaugsson Bodil Ginnerup Pedersen Xiaoyi Ji Karina Dalsgaard Sørensen Kelvin Szolnoky Nita Mulliqi Anders Blilie Henrik Olsson Matteo Titus Geraldine Martinez Gonzalez Sol Erika Boman Masi Valkonen Svein Reidar Kjosavik José Asenjo Paolo Libretti Marcin Braun Radzislaw Kordek Roman Łowicki Kristina Hotakainen Päivi Väre Benedicte Parm Ulhøi Pekka Ruusuvuori Toyonori Tsuzuki Emilius Adrianus Maria Janssen Kimmo Kartasalo Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocol BMJ Open |
| title | Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocol |
| title_full | Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocol |
| title_fullStr | Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocol |
| title_full_unstemmed | Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocol |
| title_short | Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocol |
| title_sort | development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies study protocol |
| url | https://bmjopen.bmj.com/content/15/7/e097591.full |
| work_keys_str_mv | AT martineklund developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT brettdelahunt developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT larsegevad developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT hemamalisamaratunga developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT mattiasrantalainen developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT marcellogambacorta developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT einargudlaugsson developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT bodilginneruppedersen developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT xiaoyiji developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT karinadalsgaardsørensen developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT kelvinszolnoky developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT nitamulliqi developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT andersblilie developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT henrikolsson developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT matteotitus developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT geraldinemartinezgonzalez developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT solerikaboman developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT masivalkonen developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT sveinreidarkjosavik developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT joseasenjo developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT paololibretti developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT marcinbraun developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT radzislawkordek developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT romanłowicki developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT kristinahotakainen developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT paivivare developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT benedicteparmulhøi developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT pekkaruusuvuori developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT toyonoritsuzuki developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT emiliusadrianusmariajanssen developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol AT kimmokartasalo developmentandretrospectivevalidationofanartificialintelligencesystemfordiagnosticassessmentofprostatebiopsiesstudyprotocol |