AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.

Accurate segmentation of breast masses is an essential step in computer aided diagnosis of breast cancer. The scarcity of annotated training data greatly hinders the model's generalization ability, especially for the deep learning based methods. However, high-quality image-level annotations are...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yeheng Sun, Yule Ji
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f30065215bbc4db5ba5c37eee5fabf4c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f30065215bbc4db5ba5c37eee5fabf4c
record_format	dspace
spelling	oai:doaj.org-article:f30065215bbc4db5ba5c37eee5fabf4c2021-12-02T20:19:21ZAAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.1932-620310.1371/journal.pone.0256830https://doaj.org/article/f30065215bbc4db5ba5c37eee5fabf4c2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0256830https://doaj.org/toc/1932-6203Accurate segmentation of breast masses is an essential step in computer aided diagnosis of breast cancer. The scarcity of annotated training data greatly hinders the model's generalization ability, especially for the deep learning based methods. However, high-quality image-level annotations are time-consuming and cumbersome in medical image analysis scenarios. In addition, a large amount of weak annotations is under-utilized which comprise common anatomy features. To this end, inspired by teacher-student networks, we propose an Anatomy-Aware Weakly-Supervised learning Network (AAWS-Net) for extracting useful information from mammograms with weak annotations for efficient and accurate breast mass segmentation. Specifically, we adopt a weakly-supervised learning strategy in the Teacher to extract anatomy structure from mammograms with weak annotations by reconstructing the original image. Besides, knowledge distillation is used to suggest morphological differences between benign and malignant masses. Moreover, the prior knowledge learned from the Teacher is introduced to the Student in an end-to-end way, which improves the ability of the student network to locate and segment masses. Experiments on CBIS-DDSM have shown that our method yields promising performance compared with state-of-the-art alternative models for breast mass segmentation in terms of segmentation accuracy and IoU.Yeheng SunYule JiPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 8, p e0256830 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Yeheng Sun Yule Ji AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.
description	Accurate segmentation of breast masses is an essential step in computer aided diagnosis of breast cancer. The scarcity of annotated training data greatly hinders the model's generalization ability, especially for the deep learning based methods. However, high-quality image-level annotations are time-consuming and cumbersome in medical image analysis scenarios. In addition, a large amount of weak annotations is under-utilized which comprise common anatomy features. To this end, inspired by teacher-student networks, we propose an Anatomy-Aware Weakly-Supervised learning Network (AAWS-Net) for extracting useful information from mammograms with weak annotations for efficient and accurate breast mass segmentation. Specifically, we adopt a weakly-supervised learning strategy in the Teacher to extract anatomy structure from mammograms with weak annotations by reconstructing the original image. Besides, knowledge distillation is used to suggest morphological differences between benign and malignant masses. Moreover, the prior knowledge learned from the Teacher is introduced to the Student in an end-to-end way, which improves the ability of the student network to locate and segment masses. Experiments on CBIS-DDSM have shown that our method yields promising performance compared with state-of-the-art alternative models for breast mass segmentation in terms of segmentation accuracy and IoU.
format	article
author	Yeheng Sun Yule Ji
author_facet	Yeheng Sun Yule Ji
author_sort	Yeheng Sun
title	AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.
title_short	AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.
title_full	AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.
title_fullStr	AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.
title_full_unstemmed	AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.
title_sort	aaws-net: anatomy-aware weakly-supervised learning network for breast mass segmentation.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/f30065215bbc4db5ba5c37eee5fabf4c
work_keys_str_mv	AT yehengsun aawsnetanatomyawareweaklysupervisedlearningnetworkforbreastmasssegmentation AT yuleji aawsnetanatomyawareweaklysupervisedlearningnetworkforbreastmasssegmentation
_version_	1718374260910587904

AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation.

Ejemplares similares