SM2C: Boost the Semi-supervised Segmentation for Medical Image by using Meta Pseudo Labels and Mixed Images

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Yifei, Zhu, Chuhong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911810841477120
author Wang, Yifei
Zhu, Chuhong
author_facet Wang, Yifei
Zhu, Chuhong
contents Recently, machine learning-based semantic segmentation algorithms have demonstrated their potential to accurately segment regions and contours in medical images, allowing the precise location of anatomical structures and abnormalities. Although medical images are difficult to acquire and annotate, semi-supervised learning methods are efficient in dealing with the scarcity of labeled data. However, overfitting is almost inevitable due to the limited images for training. Furthermore, the intricate shapes of organs and lesions in medical images introduce additional complexity in different cases, preventing networks from acquiring a strong ability to generalize. To this end, we introduce a novel method called Scaling-up Mix with Multi-Class (SM2C). This method uses three strategies - scaling-up image size, multi-class mixing, and object shape jittering - to improve the ability to learn semantic features within medical images. By diversifying the shape of the segmentation objects and enriching the semantic information within each sample, the SM2C demonstrates its potential, especially in the training of unlabelled data. Extensive experiments demonstrate the effectiveness of the SM2C on three benchmark medical image segmentation datasets. The proposed framework shows significant improvements over state-of-the-art counterparts.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16009
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SM2C: Boost the Semi-supervised Segmentation for Medical Image by using Meta Pseudo Labels and Mixed Images
Wang, Yifei
Zhu, Chuhong
Computer Vision and Pattern Recognition
Recently, machine learning-based semantic segmentation algorithms have demonstrated their potential to accurately segment regions and contours in medical images, allowing the precise location of anatomical structures and abnormalities. Although medical images are difficult to acquire and annotate, semi-supervised learning methods are efficient in dealing with the scarcity of labeled data. However, overfitting is almost inevitable due to the limited images for training. Furthermore, the intricate shapes of organs and lesions in medical images introduce additional complexity in different cases, preventing networks from acquiring a strong ability to generalize. To this end, we introduce a novel method called Scaling-up Mix with Multi-Class (SM2C). This method uses three strategies - scaling-up image size, multi-class mixing, and object shape jittering - to improve the ability to learn semantic features within medical images. By diversifying the shape of the segmentation objects and enriching the semantic information within each sample, the SM2C demonstrates its potential, especially in the training of unlabelled data. Extensive experiments demonstrate the effectiveness of the SM2C on three benchmark medical image segmentation datasets. The proposed framework shows significant improvements over state-of-the-art counterparts.
title SM2C: Boost the Semi-supervised Segmentation for Medical Image by using Meta Pseudo Labels and Mixed Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.16009