Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network Models

Adrenal glands are vital endocrine organs whose accurate segmentation on CT imaging presents significant challenges due to their small size and variable morphology. This study evaluates the efficacy of deep learning approaches for automatic adrenal gland segmentation from multiphase CT scans. We imp...

Full description

Saved in:
Bibliographic Details
Main Authors: Vlad-Octavian Bolocan, Oana Nicu-Canareica, Alexandru Mitoi, Maria Glencora Costache, Loredana Sabina Cornelia Manolescu, Cosmin Medar, Viorel Jinga
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/10/5388
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711557451186176
author Vlad-Octavian Bolocan
Oana Nicu-Canareica
Alexandru Mitoi
Maria Glencora Costache
Loredana Sabina Cornelia Manolescu
Cosmin Medar
Viorel Jinga
author_facet Vlad-Octavian Bolocan
Oana Nicu-Canareica
Alexandru Mitoi
Maria Glencora Costache
Loredana Sabina Cornelia Manolescu
Cosmin Medar
Viorel Jinga
author_sort Vlad-Octavian Bolocan
collection DOAJ
description Adrenal glands are vital endocrine organs whose accurate segmentation on CT imaging presents significant challenges due to their small size and variable morphology. This study evaluates the efficacy of deep learning approaches for automatic adrenal gland segmentation from multiphase CT scans. We implemented three convolutional neural network architectures (U-Net, SegNet, and NablaNet) and assessed their performance on a dataset comprising 868 adrenal glands from contrast-enhanced abdominal CT scans. Performance was evaluated using the Dice similarity coefficient (DSC), alongside practical implementation metrics including training and deployment time. U-Net demonstrated superior segmentation performance (DSC: 0.630 ± 0.05 for right, 0.660 ± 0.06 for left adrenal glands) compared to NablaNet (DSC: 0.552 ± 0.08 for right, 0.550 ± 0.07 for left) and SegNet (DSC: 0.320 ± 0.10 for right, 0.335 ± 0.09 for left). While all models achieved high specificity, boundary delineation accuracy remained challenging. Our findings demonstrate the feasibility of deep learning-based adrenal gland segmentation while highlighting the persistent challenges in achieving the segmentation quality observed with larger abdominal organs. U-Net provides the optimal balance between accuracy and computational requirements, establishing a foundation for further refinement of AI-assisted adrenal imaging tools.
format Article
id doaj-art-8b920da39e784911a7af67d1f2b0a729
institution DOAJ
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-8b920da39e784911a7af67d1f2b0a7292025-08-20T03:14:35ZengMDPI AGApplied Sciences2076-34172025-05-011510538810.3390/app15105388Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network ModelsVlad-Octavian Bolocan0Oana Nicu-Canareica1Alexandru Mitoi2Maria Glencora Costache3Loredana Sabina Cornelia Manolescu4Cosmin Medar5Viorel Jinga6Doctoral Program Studies, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, RomaniaDepartment of Fundamental Sciences, Faculty of Midwifery and Nursing, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, RomaniaDoctoral Program Studies, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, RomaniaDepartment of Fundamental Sciences, Faculty of Midwifery and Nursing, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, RomaniaDepartment of Fundamental Sciences, Faculty of Midwifery and Nursing, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, RomaniaDepartment of Fundamental Sciences, Faculty of Midwifery and Nursing, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, RomaniaDepartment of Urology, Clinical Hospital “Prof. Dr. Theodor Burghele”, Faculty of Medicine, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, RomaniaAdrenal glands are vital endocrine organs whose accurate segmentation on CT imaging presents significant challenges due to their small size and variable morphology. This study evaluates the efficacy of deep learning approaches for automatic adrenal gland segmentation from multiphase CT scans. We implemented three convolutional neural network architectures (U-Net, SegNet, and NablaNet) and assessed their performance on a dataset comprising 868 adrenal glands from contrast-enhanced abdominal CT scans. Performance was evaluated using the Dice similarity coefficient (DSC), alongside practical implementation metrics including training and deployment time. U-Net demonstrated superior segmentation performance (DSC: 0.630 ± 0.05 for right, 0.660 ± 0.06 for left adrenal glands) compared to NablaNet (DSC: 0.552 ± 0.08 for right, 0.550 ± 0.07 for left) and SegNet (DSC: 0.320 ± 0.10 for right, 0.335 ± 0.09 for left). While all models achieved high specificity, boundary delineation accuracy remained challenging. Our findings demonstrate the feasibility of deep learning-based adrenal gland segmentation while highlighting the persistent challenges in achieving the segmentation quality observed with larger abdominal organs. U-Net provides the optimal balance between accuracy and computational requirements, establishing a foundation for further refinement of AI-assisted adrenal imaging tools.https://www.mdpi.com/2076-3417/15/10/5388deep learningadrenal glandCNN models
spellingShingle Vlad-Octavian Bolocan
Oana Nicu-Canareica
Alexandru Mitoi
Maria Glencora Costache
Loredana Sabina Cornelia Manolescu
Cosmin Medar
Viorel Jinga
Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network Models
Applied Sciences
deep learning
adrenal gland
CNN models
title Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network Models
title_full Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network Models
title_fullStr Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network Models
title_full_unstemmed Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network Models
title_short Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network Models
title_sort deep learning for adrenal gland segmentation comparing accuracy and efficiency across three convolutional neural network models
topic deep learning
adrenal gland
CNN models
url https://www.mdpi.com/2076-3417/15/10/5388
work_keys_str_mv AT vladoctavianbolocan deeplearningforadrenalglandsegmentationcomparingaccuracyandefficiencyacrossthreeconvolutionalneuralnetworkmodels
AT oananicucanareica deeplearningforadrenalglandsegmentationcomparingaccuracyandefficiencyacrossthreeconvolutionalneuralnetworkmodels
AT alexandrumitoi deeplearningforadrenalglandsegmentationcomparingaccuracyandefficiencyacrossthreeconvolutionalneuralnetworkmodels
AT mariaglencoracostache deeplearningforadrenalglandsegmentationcomparingaccuracyandefficiencyacrossthreeconvolutionalneuralnetworkmodels
AT loredanasabinacorneliamanolescu deeplearningforadrenalglandsegmentationcomparingaccuracyandefficiencyacrossthreeconvolutionalneuralnetworkmodels
AT cosminmedar deeplearningforadrenalglandsegmentationcomparingaccuracyandefficiencyacrossthreeconvolutionalneuralnetworkmodels
AT vioreljinga deeplearningforadrenalglandsegmentationcomparingaccuracyandefficiencyacrossthreeconvolutionalneuralnetworkmodels