Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation

Abstract Objectives To estimate the uncertainty of a deep learning (DL)-based prostate segmentation algorithm through conformal prediction (CP) and to assess its effect on the calculation of the prostate volume (PV) in patients at risk of prostate cancer (PC). Methods Three-hundred seventy-seven mul...

Full description

Saved in:
Bibliographic Details
Main Authors: Marius Gade, Kevin Mekhaphan Nguyen, Sol Gedde, Alvaro Fernandez-Quilez
Format: Article
Language:English
Published: SpringerOpen 2024-11-01
Series:Insights into Imaging
Subjects:
Online Access:https://doi.org/10.1186/s13244-024-01863-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850058051745218560
author Marius Gade
Kevin Mekhaphan Nguyen
Sol Gedde
Alvaro Fernandez-Quilez
author_facet Marius Gade
Kevin Mekhaphan Nguyen
Sol Gedde
Alvaro Fernandez-Quilez
author_sort Marius Gade
collection DOAJ
description Abstract Objectives To estimate the uncertainty of a deep learning (DL)-based prostate segmentation algorithm through conformal prediction (CP) and to assess its effect on the calculation of the prostate volume (PV) in patients at risk of prostate cancer (PC). Methods Three-hundred seventy-seven multi-center 3-Tesla axial T2-weighted exams from biopsied males (66.64  $$\pm$$ ±  7.47 years) at risk of PC were retrospectively included in the study. Assessment of PV based on PI-RADS 2.1 ellipsoid formula ( $${{{\rm{PV}}}}_{{ref}}$$ PV r e f ) was available for included patients. Prostate segmentations were obtained from a DL model and used to calculate the PV ( $${{{\rm{PV}}}}_{{DL}}$$ PV D L ). CP was applied at a confidence level of 85% to flag unreliable pixel segmentations of the DL model. Subsequently, the PV ( $${{{\rm{PV}}}}_{{CP}}$$ PV C P ) was calculated when disregarding uncertain pixel segmentations. Agreement between $${{{\rm{PV}}}}_{{DL}}$$ PV D L and $${{{\rm{PV}}}}_{{CP}}$$ PV C P was evaluated against the reference standard $${{{\rm{PV}}}}_{{ref}}$$ PV r e f . Intraclass correlation coefficient (ICC) and Bland–Altman plots were used to assess the agreement. The relative volume difference (RVD) was used to evaluate the PV calculation accuracy, and the Wilcoxon Signed-Rank Test was used to assess statistical differences. A p-value < 0.05 was considered statistically significant. Results Conformal prediction significantly reduced RVD when compared to the DL algorithm (RVD = − 2.81  $$\pm$$ ±  8.85 and RVD = −8.01  $$\pm$$ ±  11.50). $${{{\rm{PV}}}}_{{CP}}$$ PV C P showed a significantly larger agreement than $${{{\rm{PV}}}}_{{DL}}$$ PV D L when using the reference standard $${{{\rm{PV}}}}_{{ref}}$$ PV r e f (mean difference (95% limits of agreement) $${{{\rm{PV}}}}_{{CP}}$$ PV C P : 1.27 mL (− 13.64; 16.17 mL) $${{{\rm{PV}}}}_{{DL}}$$ PV D L : 6.07 mL (− 14.29; 26.42 mL)), with an excellent ICC ( $${{{\rm{PV}}}}_{{CP}}$$ PV C P : 0.97 (95% CI: 0.97 to 0.98)). Conclusion Uncertainty quantification through CP increases the accuracy and reliability of DL-based PV assessment in patients at risk of PC. Critical relevance statement Conformal prediction can flag uncertain pixel predictions of DL-based prostate MRI segmentation at a desired confidence level, increasing the reliability and safety of prostate volume assessment in patients at risk of prostate cancer. Key Points Conformal prediction can flag uncertain pixel predictions of prostate segmentations at a user-defined confidence level. Deep learning with conformal prediction shows high accuracy in prostate volumetric assessment. Agreement between automatic and ellipsoid-derived volume was significantly larger with conformal prediction. Graphical Abstract
format Article
id doaj-art-ab522de416e844ef9e6af9a45db59473
institution DOAJ
issn 1869-4101
language English
publishDate 2024-11-01
publisher SpringerOpen
record_format Article
series Insights into Imaging
spelling doaj-art-ab522de416e844ef9e6af9a45db594732025-08-20T02:51:15ZengSpringerOpenInsights into Imaging1869-41012024-11-0115111310.1186/s13244-024-01863-wImpact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentationMarius Gade0Kevin Mekhaphan Nguyen1Sol Gedde2Alvaro Fernandez-Quilez3Department of Electrical Engineering and Computer Science, University of StavangerDepartment of Electrical Engineering and Computer Science, University of StavangerStavanger Medical Imaging Laboratory (SMIL), Department of Radiology, Stavanger University HospitalDepartment of Electrical Engineering and Computer Science, University of StavangerAbstract Objectives To estimate the uncertainty of a deep learning (DL)-based prostate segmentation algorithm through conformal prediction (CP) and to assess its effect on the calculation of the prostate volume (PV) in patients at risk of prostate cancer (PC). Methods Three-hundred seventy-seven multi-center 3-Tesla axial T2-weighted exams from biopsied males (66.64  $$\pm$$ ±  7.47 years) at risk of PC were retrospectively included in the study. Assessment of PV based on PI-RADS 2.1 ellipsoid formula ( $${{{\rm{PV}}}}_{{ref}}$$ PV r e f ) was available for included patients. Prostate segmentations were obtained from a DL model and used to calculate the PV ( $${{{\rm{PV}}}}_{{DL}}$$ PV D L ). CP was applied at a confidence level of 85% to flag unreliable pixel segmentations of the DL model. Subsequently, the PV ( $${{{\rm{PV}}}}_{{CP}}$$ PV C P ) was calculated when disregarding uncertain pixel segmentations. Agreement between $${{{\rm{PV}}}}_{{DL}}$$ PV D L and $${{{\rm{PV}}}}_{{CP}}$$ PV C P was evaluated against the reference standard $${{{\rm{PV}}}}_{{ref}}$$ PV r e f . Intraclass correlation coefficient (ICC) and Bland–Altman plots were used to assess the agreement. The relative volume difference (RVD) was used to evaluate the PV calculation accuracy, and the Wilcoxon Signed-Rank Test was used to assess statistical differences. A p-value < 0.05 was considered statistically significant. Results Conformal prediction significantly reduced RVD when compared to the DL algorithm (RVD = − 2.81  $$\pm$$ ±  8.85 and RVD = −8.01  $$\pm$$ ±  11.50). $${{{\rm{PV}}}}_{{CP}}$$ PV C P showed a significantly larger agreement than $${{{\rm{PV}}}}_{{DL}}$$ PV D L when using the reference standard $${{{\rm{PV}}}}_{{ref}}$$ PV r e f (mean difference (95% limits of agreement) $${{{\rm{PV}}}}_{{CP}}$$ PV C P : 1.27 mL (− 13.64; 16.17 mL) $${{{\rm{PV}}}}_{{DL}}$$ PV D L : 6.07 mL (− 14.29; 26.42 mL)), with an excellent ICC ( $${{{\rm{PV}}}}_{{CP}}$$ PV C P : 0.97 (95% CI: 0.97 to 0.98)). Conclusion Uncertainty quantification through CP increases the accuracy and reliability of DL-based PV assessment in patients at risk of PC. Critical relevance statement Conformal prediction can flag uncertain pixel predictions of DL-based prostate MRI segmentation at a desired confidence level, increasing the reliability and safety of prostate volume assessment in patients at risk of prostate cancer. Key Points Conformal prediction can flag uncertain pixel predictions of prostate segmentations at a user-defined confidence level. Deep learning with conformal prediction shows high accuracy in prostate volumetric assessment. Agreement between automatic and ellipsoid-derived volume was significantly larger with conformal prediction. Graphical Abstracthttps://doi.org/10.1186/s13244-024-01863-wMagnetic resonance imagingDeep learningProstateConformal predictionUncertainty
spellingShingle Marius Gade
Kevin Mekhaphan Nguyen
Sol Gedde
Alvaro Fernandez-Quilez
Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation
Insights into Imaging
Magnetic resonance imaging
Deep learning
Prostate
Conformal prediction
Uncertainty
title Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation
title_full Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation
title_fullStr Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation
title_full_unstemmed Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation
title_short Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation
title_sort impact of uncertainty quantification through conformal prediction on volume assessment from deep learning based mri prostate segmentation
topic Magnetic resonance imaging
Deep learning
Prostate
Conformal prediction
Uncertainty
url https://doi.org/10.1186/s13244-024-01863-w
work_keys_str_mv AT mariusgade impactofuncertaintyquantificationthroughconformalpredictiononvolumeassessmentfromdeeplearningbasedmriprostatesegmentation
AT kevinmekhaphannguyen impactofuncertaintyquantificationthroughconformalpredictiononvolumeassessmentfromdeeplearningbasedmriprostatesegmentation
AT solgedde impactofuncertaintyquantificationthroughconformalpredictiononvolumeassessmentfromdeeplearningbasedmriprostatesegmentation
AT alvarofernandezquilez impactofuncertaintyquantificationthroughconformalpredictiononvolumeassessmentfromdeeplearningbasedmriprostatesegmentation