Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.20495 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909298851840000 |
|---|---|
| author | Gu, Yi Otake, Yoshito Uemura, Keisuke Takao, Masaki Soufi, Mazen Okada, Seiji Sugano, Nobuhiko Talbot, Hugues Sato, Yoshinobu |
| author_facet | Gu, Yi Otake, Yoshito Uemura, Keisuke Takao, Masaki Soufi, Mazen Okada, Seiji Sugano, Nobuhiko Talbot, Hugues Sato, Yoshinobu |
| contents | While most vision tasks are essentially visual in nature (for recognition), some important tasks, especially in the medical field, also require quantitative analysis (for quantification) using quantitative images. Unlike in visual analysis, pixel values in quantitative images correspond to physical metrics measured by specific devices (e.g., a depth image). However, recent work has shown that it is sometimes possible to synthesize accurate quantitative values from visual ones (e.g., depth from visual cues or defocus). This research aims to improve quantitative image synthesis (QIS) by exploring pretraining and image resolution scaling. We propose a benchmark for evaluating pretraining performance using the task of QIS-based bone mineral density (BMD) estimation from plain X-ray images, where the synthesized quantitative image is used to derive BMD. Our results show that appropriate pretraining can improve QIS performance, significantly raising the correlation of BMD estimation from 0.820 to 0.898, while others do not help or even hinder it. Scaling-up the resolution can further boost the correlation up to 0.923, a significant enhancement over conventional methods. Future work will include exploring more pretraining strategies and validating them on other image synthesis tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20495 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Quantitative Image Synthesis through Pretraining and Resolution Scaling for Bone Mineral Density Estimation from a Plain X-ray Image Gu, Yi Otake, Yoshito Uemura, Keisuke Takao, Masaki Soufi, Mazen Okada, Seiji Sugano, Nobuhiko Talbot, Hugues Sato, Yoshinobu Image and Video Processing Computer Vision and Pattern Recognition While most vision tasks are essentially visual in nature (for recognition), some important tasks, especially in the medical field, also require quantitative analysis (for quantification) using quantitative images. Unlike in visual analysis, pixel values in quantitative images correspond to physical metrics measured by specific devices (e.g., a depth image). However, recent work has shown that it is sometimes possible to synthesize accurate quantitative values from visual ones (e.g., depth from visual cues or defocus). This research aims to improve quantitative image synthesis (QIS) by exploring pretraining and image resolution scaling. We propose a benchmark for evaluating pretraining performance using the task of QIS-based bone mineral density (BMD) estimation from plain X-ray images, where the synthesized quantitative image is used to derive BMD. Our results show that appropriate pretraining can improve QIS performance, significantly raising the correlation of BMD estimation from 0.820 to 0.898, while others do not help or even hinder it. Scaling-up the resolution can further boost the correlation up to 0.923, a significant enhancement over conventional methods. Future work will include exploring more pretraining strategies and validating them on other image synthesis tasks. |
| title | Enhancing Quantitative Image Synthesis through Pretraining and Resolution Scaling for Bone Mineral Density Estimation from a Plain X-ray Image |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.20495 |