LFC-UNet: learned lossless medical image fast compression with U-Net
In the field of medicine, the rapid advancement of medical technology has significantly increased the speed of medical image generation, compelling us to seek efficient methods for image compression. Neural networks, owing to their outstanding image estimation capabilities, have provided new avenues...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2024-02-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1924.pdf |
| _version_ | 1797289213917396992 |
|---|---|
| author | Hengrui Liao Yue Li |
| author_facet | Hengrui Liao Yue Li |
| author_sort | Hengrui Liao |
| collection | DOAJ |
| description | In the field of medicine, the rapid advancement of medical technology has significantly increased the speed of medical image generation, compelling us to seek efficient methods for image compression. Neural networks, owing to their outstanding image estimation capabilities, have provided new avenues for lossless compression. In recent years, learning-based lossless image compression methods, combining neural network predictions with residuals, have achieved performance comparable to traditional non-learning algorithms. However, existing methods have not taken into account that residuals often concentrate excessively, hindering the neural network’s ability to learn accurate residual probability estimation. To address this issue, this study employs a weighted cross-entropy method to handle the imbalance in residual categories. In terms of network architecture, we introduce skip connections from U-Net to better capture image features, thereby obtaining accurate probability estimates. Furthermore, our framework boasts excellent encoding speed, as the model is able to acquire all residuals and residual probabilities in a single inference pass. The experimental results demonstrate that the proposed method achieves state-of-the-art performance on medical datasets while also offering the fastest processing speed. As illustrated by an instance using head CT data, our approach achieves a compression efficiency of 2.30 bits per pixel, with a processing time of only 0.320 seconds per image. |
| first_indexed | 2024-03-07T19:00:54Z |
| format | Article |
| id | doaj.art-cbbd246ee9ee467899ef08fcb661e775 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-03-07T19:00:54Z |
| publishDate | 2024-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-cbbd246ee9ee467899ef08fcb661e7752024-03-01T15:05:31ZengPeerJ Inc.PeerJ Computer Science2376-59922024-02-0110e192410.7717/peerj-cs.1924LFC-UNet: learned lossless medical image fast compression with U-NetHengrui Liao0Yue Li1School of Computer, University of South China, Hengyang, Hunan, ChinaSchool of Computer, University of South China, Hengyang, Hunan, ChinaIn the field of medicine, the rapid advancement of medical technology has significantly increased the speed of medical image generation, compelling us to seek efficient methods for image compression. Neural networks, owing to their outstanding image estimation capabilities, have provided new avenues for lossless compression. In recent years, learning-based lossless image compression methods, combining neural network predictions with residuals, have achieved performance comparable to traditional non-learning algorithms. However, existing methods have not taken into account that residuals often concentrate excessively, hindering the neural network’s ability to learn accurate residual probability estimation. To address this issue, this study employs a weighted cross-entropy method to handle the imbalance in residual categories. In terms of network architecture, we introduce skip connections from U-Net to better capture image features, thereby obtaining accurate probability estimates. Furthermore, our framework boasts excellent encoding speed, as the model is able to acquire all residuals and residual probabilities in a single inference pass. The experimental results demonstrate that the proposed method achieves state-of-the-art performance on medical datasets while also offering the fastest processing speed. As illustrated by an instance using head CT data, our approach achieves a compression efficiency of 2.30 bits per pixel, with a processing time of only 0.320 seconds per image.https://peerj.com/articles/cs-1924.pdfLossless compressionMedical imageNeural network |
| spellingShingle | Hengrui Liao Yue Li LFC-UNet: learned lossless medical image fast compression with U-Net PeerJ Computer Science Lossless compression Medical image Neural network |
| title | LFC-UNet: learned lossless medical image fast compression with U-Net |
| title_full | LFC-UNet: learned lossless medical image fast compression with U-Net |
| title_fullStr | LFC-UNet: learned lossless medical image fast compression with U-Net |
| title_full_unstemmed | LFC-UNet: learned lossless medical image fast compression with U-Net |
| title_short | LFC-UNet: learned lossless medical image fast compression with U-Net |
| title_sort | lfc unet learned lossless medical image fast compression with u net |
| topic | Lossless compression Medical image Neural network |
| url | https://peerj.com/articles/cs-1924.pdf |
| work_keys_str_mv | AT hengruiliao lfcunetlearnedlosslessmedicalimagefastcompressionwithunet AT yueli lfcunetlearnedlosslessmedicalimagefastcompressionwithunet |