Do Sharpness-Based Optimizers Improve Generalization in Medical Image Analysis?

Effective clinical deployment of deep learning models in healthcare demands high generalization performance to ensure accurate diagnosis and treatment planning. In recent years, significant research has focused on improving the generalization of deep learning models by regularizing the sharpness of...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohamed Hassan, Aleksandar Vakanski, Boyu Zhang, Min Xian
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10994767/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850134285956153344
author Mohamed Hassan
Aleksandar Vakanski
Boyu Zhang
Min Xian
author_facet Mohamed Hassan
Aleksandar Vakanski
Boyu Zhang
Min Xian
author_sort Mohamed Hassan
collection DOAJ
description Effective clinical deployment of deep learning models in healthcare demands high generalization performance to ensure accurate diagnosis and treatment planning. In recent years, significant research has focused on improving the generalization of deep learning models by regularizing the sharpness of the loss landscape. Among the optimization approaches that explicitly minimize sharpness, Sharpness-Aware Minimization (SAM) has shown potential in enhancing generalization performance on general domain image datasets. This success has led to the development of several advanced sharpness-based algorithms aimed at addressing the limitations of SAM, such as Adaptive SAM, Surrogate-Gap SAM, Weighted SAM, and Curvature Regularized SAM. These sharpness-based optimizers have shown improvements in model generalization compared to conventional stochastic gradient descent optimizers and their variants on general domain image datasets, but they have not been thoroughly evaluated on medical images. This work provides a review of recent sharpness-based methods for improving the generalization of deep learning networks and evaluates the methods’ performance on three medical image datasets, including breast ultrasound, chest X-ray, and colon histopathology images. Our findings indicate that the initial SAM method successfully enhances the generalization of various deep learning models. While Adaptive SAM improves generalization of convolutional neural networks, it fails to do so for vision transformers. Other sharpness-based optimizers, however, do not demonstrate consistent results. The results reveal that contrary to findings in the non-medical domain, SAM is the only recommended sharpness-based optimizer that consistently improves generalization in medical image analysis, and further research is necessary to refine the variants of SAM to enhance generalization performance in this field.
format Article
id doaj-art-c50fc13acdae4aa5872f0bbbcad407a0
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c50fc13acdae4aa5872f0bbbcad407a02025-08-20T02:31:44ZengIEEEIEEE Access2169-35362025-01-0113829728298510.1109/ACCESS.2025.356864110994767Do Sharpness-Based Optimizers Improve Generalization in Medical Image Analysis?Mohamed Hassan0https://orcid.org/0009-0005-6934-1385Aleksandar Vakanski1https://orcid.org/0000-0003-3365-1291Boyu Zhang2https://orcid.org/0000-0002-9401-6163Min Xian3https://orcid.org/0000-0001-6098-4441Department of Computer Science, University of Idaho, Idaho Falls, ID, USADepartment of Computer Science, University of Idaho, Idaho Falls, ID, USADepartment of Computer Science, University of Idaho, Idaho Falls, ID, USADepartment of Computer Science, University of Idaho, Idaho Falls, ID, USAEffective clinical deployment of deep learning models in healthcare demands high generalization performance to ensure accurate diagnosis and treatment planning. In recent years, significant research has focused on improving the generalization of deep learning models by regularizing the sharpness of the loss landscape. Among the optimization approaches that explicitly minimize sharpness, Sharpness-Aware Minimization (SAM) has shown potential in enhancing generalization performance on general domain image datasets. This success has led to the development of several advanced sharpness-based algorithms aimed at addressing the limitations of SAM, such as Adaptive SAM, Surrogate-Gap SAM, Weighted SAM, and Curvature Regularized SAM. These sharpness-based optimizers have shown improvements in model generalization compared to conventional stochastic gradient descent optimizers and their variants on general domain image datasets, but they have not been thoroughly evaluated on medical images. This work provides a review of recent sharpness-based methods for improving the generalization of deep learning networks and evaluates the methods’ performance on three medical image datasets, including breast ultrasound, chest X-ray, and colon histopathology images. Our findings indicate that the initial SAM method successfully enhances the generalization of various deep learning models. While Adaptive SAM improves generalization of convolutional neural networks, it fails to do so for vision transformers. Other sharpness-based optimizers, however, do not demonstrate consistent results. The results reveal that contrary to findings in the non-medical domain, SAM is the only recommended sharpness-based optimizer that consistently improves generalization in medical image analysis, and further research is necessary to refine the variants of SAM to enhance generalization performance in this field.https://ieeexplore.ieee.org/document/10994767/Deep learninggeneralizationmedical image analysisloss landscapesharpness-aware minimization
spellingShingle Mohamed Hassan
Aleksandar Vakanski
Boyu Zhang
Min Xian
Do Sharpness-Based Optimizers Improve Generalization in Medical Image Analysis?
IEEE Access
Deep learning
generalization
medical image analysis
loss landscape
sharpness-aware minimization
title Do Sharpness-Based Optimizers Improve Generalization in Medical Image Analysis?
title_full Do Sharpness-Based Optimizers Improve Generalization in Medical Image Analysis?
title_fullStr Do Sharpness-Based Optimizers Improve Generalization in Medical Image Analysis?
title_full_unstemmed Do Sharpness-Based Optimizers Improve Generalization in Medical Image Analysis?
title_short Do Sharpness-Based Optimizers Improve Generalization in Medical Image Analysis?
title_sort do sharpness based optimizers improve generalization in medical image analysis
topic Deep learning
generalization
medical image analysis
loss landscape
sharpness-aware minimization
url https://ieeexplore.ieee.org/document/10994767/
work_keys_str_mv AT mohamedhassan dosharpnessbasedoptimizersimprovegeneralizationinmedicalimageanalysis
AT aleksandarvakanski dosharpnessbasedoptimizersimprovegeneralizationinmedicalimageanalysis
AT boyuzhang dosharpnessbasedoptimizersimprovegeneralizationinmedicalimageanalysis
AT minxian dosharpnessbasedoptimizersimprovegeneralizationinmedicalimageanalysis