Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images

<h3 dir="ltr">Background</h3><p dir="ltr">Penile curvature (PC) may occur in up to 10% of male births worldwide and is typically associated with the birth defect hypospadias. While the extent of PC impacts surgical management and patient outcomes, curvature eval...

Full description

Saved in:
Bibliographic Details
Main Author: Sriman Bidhan Baray (15302398) (author)
Other Authors: Saidanvar Agzamkhodjaev (22928887) (author), Mansour Ali (11247783) (author), Muhammad E.H. Chowdhury (17151154) (author), Tariq O. Abbas (11247771) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513524388069376
author Sriman Bidhan Baray (15302398)
author2 Saidanvar Agzamkhodjaev (22928887)
Mansour Ali (11247783)
Muhammad E.H. Chowdhury (17151154)
Tariq O. Abbas (11247771)
author2_role author
author
author
author
author_facet Sriman Bidhan Baray (15302398)
Saidanvar Agzamkhodjaev (22928887)
Mansour Ali (11247783)
Muhammad E.H. Chowdhury (17151154)
Tariq O. Abbas (11247771)
author_role author
dc.creator.none.fl_str_mv Sriman Bidhan Baray (15302398)
Saidanvar Agzamkhodjaev (22928887)
Mansour Ali (11247783)
Muhammad E.H. Chowdhury (17151154)
Tariq O. Abbas (11247771)
dc.date.none.fl_str_mv 2025-12-23T09:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.jpurol.2025.105703
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Implementation_of_Deep_Learning_for_Measurement_of_Penile_Curvature_on_Real_2D_Intraoperative_Images/31017373
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Penile curvature
artificial intelligence
machine learning
hypospadias
chordee
dc.title.none.fl_str_mv Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <h3 dir="ltr">Background</h3><p dir="ltr">Penile curvature (PC) may occur in up to 10% of male births worldwide and is typically associated with the birth defect hypospadias. While the extent of PC impacts surgical management and patient outcomes, curvature evaluation is inconsistent between surgeons due to a lack of reliable assessment techniques. Our goal was to create a dependable, automated deep-learning solution to precisely assess PC from real-time intraoperative 2D images. </p><h3 dir="ltr">Materials and Methods</h3><p dir="ltr">A dataset of 421 images was assembled and annotated by four human experts. Annotations were used to calculate PC angles and determine ground truth curvature degrees in each case. All images and ground truth angle information were used to train 3 different deep-learning models. A YOLOv8 model was trained to localize and crop the penile region, then a deep-learning model was employed to segment the shafts and generate binary mask images. In the final stage, a modified HRNet model was used to integrate angle error, predict four key points denoting mid-axes of the proximal and distal shaft, and then use these landmarks to calculate curvature automatically. </p><h3 dir="ltr">Results</h3><p dir="ltr">The proposed system demonstrated a high level of reliability in localizing penile areas, as evidenced by a mean average precision score of 99.4%. Furthermore, our pipeline exhibited strong performance in the segmentation task, achieving an impressive Intersection over the Union metric of 83.56% and a Dice Similarity Coefficient of 91.02%. In terms of angle prediction, the system achieved a mean absolute error of 7.9°. By comparison, variability among human raters ranged between 6.5–12.0° (median ≈ 8.9°), consistent with previously reported manual errors of 3.5–13.6°. Thus, the AI system matched or outperformed human raters, providing more consistent and reliable curvature estimation. The model achieved a median error of 7.8° across 421 images, with 82% of predictions within ±10° of ground truth. Only 6% of cases crossed the 30° surgical threshold, confirming the tool’s reliability for clinical decision-making. </p><h3 dir="ltr">Discussion</h3><p dir="ltr">This study demonstrates the successful implementation of deep learning and keypoint-based measurement of PC that could significantly improve patient assessment by surgeons and hypospadiology researchers.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: Journal of Pediatric Urology<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.jpurol.2025.105703" target="_blank">https://dx.doi.org/10.1016/j.jpurol.2025.105703</a></p>
eu_rights_str_mv openAccess
id Manara2_50b8027fed654e586ef881746af14510
identifier_str_mv 10.1016/j.jpurol.2025.105703
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/31017373
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative ImagesSriman Bidhan Baray (15302398)Saidanvar Agzamkhodjaev (22928887)Mansour Ali (11247783)Muhammad E.H. Chowdhury (17151154)Tariq O. Abbas (11247771)Biomedical and clinical sciencesClinical sciencesHealth sciencesHealth services and systemsInformation and computing sciencesArtificial intelligenceMachine learningPenile curvatureartificial intelligencemachine learninghypospadiaschordee<h3 dir="ltr">Background</h3><p dir="ltr">Penile curvature (PC) may occur in up to 10% of male births worldwide and is typically associated with the birth defect hypospadias. While the extent of PC impacts surgical management and patient outcomes, curvature evaluation is inconsistent between surgeons due to a lack of reliable assessment techniques. Our goal was to create a dependable, automated deep-learning solution to precisely assess PC from real-time intraoperative 2D images. </p><h3 dir="ltr">Materials and Methods</h3><p dir="ltr">A dataset of 421 images was assembled and annotated by four human experts. Annotations were used to calculate PC angles and determine ground truth curvature degrees in each case. All images and ground truth angle information were used to train 3 different deep-learning models. A YOLOv8 model was trained to localize and crop the penile region, then a deep-learning model was employed to segment the shafts and generate binary mask images. In the final stage, a modified HRNet model was used to integrate angle error, predict four key points denoting mid-axes of the proximal and distal shaft, and then use these landmarks to calculate curvature automatically. </p><h3 dir="ltr">Results</h3><p dir="ltr">The proposed system demonstrated a high level of reliability in localizing penile areas, as evidenced by a mean average precision score of 99.4%. Furthermore, our pipeline exhibited strong performance in the segmentation task, achieving an impressive Intersection over the Union metric of 83.56% and a Dice Similarity Coefficient of 91.02%. In terms of angle prediction, the system achieved a mean absolute error of 7.9°. By comparison, variability among human raters ranged between 6.5–12.0° (median ≈ 8.9°), consistent with previously reported manual errors of 3.5–13.6°. Thus, the AI system matched or outperformed human raters, providing more consistent and reliable curvature estimation. The model achieved a median error of 7.8° across 421 images, with 82% of predictions within ±10° of ground truth. Only 6% of cases crossed the 30° surgical threshold, confirming the tool’s reliability for clinical decision-making. </p><h3 dir="ltr">Discussion</h3><p dir="ltr">This study demonstrates the successful implementation of deep learning and keypoint-based measurement of PC that could significantly improve patient assessment by surgeons and hypospadiology researchers.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: Journal of Pediatric Urology<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.jpurol.2025.105703" target="_blank">https://dx.doi.org/10.1016/j.jpurol.2025.105703</a></p>2025-12-23T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.jpurol.2025.105703https://figshare.com/articles/journal_contribution/Implementation_of_Deep_Learning_for_Measurement_of_Penile_Curvature_on_Real_2D_Intraoperative_Images/31017373CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/310173732025-12-23T09:00:00Z
spellingShingle Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images
Sriman Bidhan Baray (15302398)
Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Penile curvature
artificial intelligence
machine learning
hypospadias
chordee
status_str publishedVersion
title Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images
title_full Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images
title_fullStr Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images
title_full_unstemmed Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images
title_short Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images
title_sort Implementation of Deep Learning for Measurement of Penile Curvature on Real 2D Intraoperative Images
topic Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Penile curvature
artificial intelligence
machine learning
hypospadias
chordee