IEICE TRANSACTIONS on Information
Inverse Heat Dissipation Model for Medical Image Segmentation
Summary :
The diffusion model has achieved success in generating and editing high-quality images because of its ability to produce fine details. Its superior generation ability has the potential to facilitate more detailed segmentation. This study presents a novel approach to segmentation tasks using an inverse heat dissipation model, a kind of diffusion-based models. The proposed method involves generating a mask that gradually shrinks to fit the shape of the desired segmentation region. We comprehensively evaluated the proposed method using multiple datasets under varying conditions. The results show that the proposed method outperforms existing methods and provides a more detailed segmentation.
- Publication
- IEICE TRANSACTIONS on Information Vol.E106-D No.11 pp.1930-1934
- Publication Date
- 2023/11/01
- Publicized
- 2023/08/22
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2023EDL8017
- Type of Manuscript
- LETTER
- Category
- Artificial Intelligence, Data Mining
Authors
Yu KASHIHARA
Osaka University
Takashi MATSUBARA
Osaka University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yu KASHIHARA, Takashi MATSUBARA, "Inverse Heat Dissipation Model for Medical Image Segmentation" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 11, pp. 1930-1934, November 2023, doi: 10.1587/transinf.2023EDL8017.
Abstract: The diffusion model has achieved success in generating and editing high-quality images because of its ability to produce fine details. Its superior generation ability has the potential to facilitate more detailed segmentation. This study presents a novel approach to segmentation tasks using an inverse heat dissipation model, a kind of diffusion-based models. The proposed method involves generating a mask that gradually shrinks to fit the shape of the desired segmentation region. We comprehensively evaluated the proposed method using multiple datasets under varying conditions. The results show that the proposed method outperforms existing methods and provides a more detailed segmentation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDL8017/_p
Copy
@ARTICLE{e106-d_11_1930,
author={Yu KASHIHARA, Takashi MATSUBARA, },
journal={IEICE TRANSACTIONS on Information},
title={Inverse Heat Dissipation Model for Medical Image Segmentation},
year={2023},
volume={E106-D},
number={11},
pages={1930-1934},
abstract={The diffusion model has achieved success in generating and editing high-quality images because of its ability to produce fine details. Its superior generation ability has the potential to facilitate more detailed segmentation. This study presents a novel approach to segmentation tasks using an inverse heat dissipation model, a kind of diffusion-based models. The proposed method involves generating a mask that gradually shrinks to fit the shape of the desired segmentation region. We comprehensively evaluated the proposed method using multiple datasets under varying conditions. The results show that the proposed method outperforms existing methods and provides a more detailed segmentation.},
keywords={},
doi={10.1587/transinf.2023EDL8017},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - Inverse Heat Dissipation Model for Medical Image Segmentation
T2 - IEICE TRANSACTIONS on Information
SP - 1930
EP - 1934
AU - Yu KASHIHARA
AU - Takashi MATSUBARA
PY - 2023
DO - 10.1587/transinf.2023EDL8017
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2023
AB - The diffusion model has achieved success in generating and editing high-quality images because of its ability to produce fine details. Its superior generation ability has the potential to facilitate more detailed segmentation. This study presents a novel approach to segmentation tasks using an inverse heat dissipation model, a kind of diffusion-based models. The proposed method involves generating a mask that gradually shrinks to fit the shape of the desired segmentation region. We comprehensively evaluated the proposed method using multiple datasets under varying conditions. The results show that the proposed method outperforms existing methods and provides a more detailed segmentation.
ER -
English
