Model-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation

In medical image segmentation, post-processing can effectively improve the performance of a segmentation model. Existing post-processing methods generally require additional training of a post-processing model using training data or designing a post-processing procedure based on a high level of doma...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jaeho Kim, Seokho Kang
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/52df5d1da8d14af6aeb0d7c13f3d273c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:52df5d1da8d14af6aeb0d7c13f3d273c
record_format dspace
spelling oai:doaj.org-article:52df5d1da8d14af6aeb0d7c13f3d273c2021-12-02T00:00:41ZModel-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation2169-353610.1109/ACCESS.2021.3130200https://doaj.org/article/52df5d1da8d14af6aeb0d7c13f3d273c2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9625944/https://doaj.org/toc/2169-3536In medical image segmentation, post-processing can effectively improve the performance of a segmentation model. Existing post-processing methods generally require additional training of a post-processing model using training data or designing a post-processing procedure based on a high level of domain knowledge. Their application is limited in many real-world situations due to the lack of prerequisites. In this study, we present a post-processing method that can be applied to any existing segmentation model without requiring the use of training data or domain knowledge. Given a segmentation model of any type, the proposed method improves its prediction based on the recursive feedback mechanism. For a query image, we first obtain its prediction mask by using the segmentation model. Based on the prediction mask, we modify the original image by selectively blurring the area in which the target object is expected to be absent. Subsequently, the modified image is fed again into the model to acquire a refined prediction mask. We repeat this process to obtain multiple prediction masks, which are then combined to yield the final prediction. We verified the effectiveness of the proposed method through experiments using real-world medical datasets.Jaeho KimSeokho KangIEEEarticleImage segmentationpost-processingrecursive feedbackconvolutional neural networkElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 157035-157042 (2021)
institution DOAJ
collection DOAJ
language EN
topic Image segmentation
post-processing
recursive feedback
convolutional neural network
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Image segmentation
post-processing
recursive feedback
convolutional neural network
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Jaeho Kim
Seokho Kang
Model-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation
description In medical image segmentation, post-processing can effectively improve the performance of a segmentation model. Existing post-processing methods generally require additional training of a post-processing model using training data or designing a post-processing procedure based on a high level of domain knowledge. Their application is limited in many real-world situations due to the lack of prerequisites. In this study, we present a post-processing method that can be applied to any existing segmentation model without requiring the use of training data or domain knowledge. Given a segmentation model of any type, the proposed method improves its prediction based on the recursive feedback mechanism. For a query image, we first obtain its prediction mask by using the segmentation model. Based on the prediction mask, we modify the original image by selectively blurring the area in which the target object is expected to be absent. Subsequently, the modified image is fed again into the model to acquire a refined prediction mask. We repeat this process to obtain multiple prediction masks, which are then combined to yield the final prediction. We verified the effectiveness of the proposed method through experiments using real-world medical datasets.
format article
author Jaeho Kim
Seokho Kang
author_facet Jaeho Kim
Seokho Kang
author_sort Jaeho Kim
title Model-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation
title_short Model-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation
title_full Model-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation
title_fullStr Model-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation
title_full_unstemmed Model-Agnostic Post-Processing Based on Recursive Feedback for Medical Image Segmentation
title_sort model-agnostic post-processing based on recursive feedback for medical image segmentation
publisher IEEE
publishDate 2021
url https://doaj.org/article/52df5d1da8d14af6aeb0d7c13f3d273c
work_keys_str_mv AT jaehokim modelagnosticpostprocessingbasedonrecursivefeedbackformedicalimagesegmentation
AT seokhokang modelagnosticpostprocessingbasedonrecursivefeedbackformedicalimagesegmentation
_version_ 1718403983343616000