CT Liver Segmentation via PVT-based Encoding and Refined Decoding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913322438230016 |
|---|---|
| author | Jha, Debesh Tomar, Nikhil Kumar Biswas, Koushik Durak, Gorkem Medetalibeyoglu, Alpay Antalek, Matthew Velichko, Yury Ladner, Daniela Borhani, Amir Bagci, Ulas |
| author_facet | Jha, Debesh Tomar, Nikhil Kumar Biswas, Koushik Durak, Gorkem Medetalibeyoglu, Alpay Antalek, Matthew Velichko, Yury Ladner, Daniela Borhani, Amir Bagci, Ulas |
| contents | Accurate liver segmentation from CT scans is essential for effective diagnosis and treatment planning. Computer-aided diagnosis systems promise to improve the precision of liver disease diagnosis, disease progression, and treatment planning. In response to the need, we propose a novel deep learning approach, \textit{\textbf{PVTFormer}}, that is built upon a pretrained pyramid vision transformer (PVT v2) combined with advanced residual upsampling and decoder block. By integrating a refined feature channel approach with a hierarchical decoding strategy, PVTFormer generates high quality segmentation masks by enhancing semantic features. Rigorous evaluation of the proposed method on Liver Tumor Segmentation Benchmark (LiTS) 2017 demonstrates that our proposed architecture not only achieves a high dice coefficient of 86.78\%, mIoU of 78.46\%, but also obtains a low HD of 3.50. The results underscore PVTFormer's efficacy in setting a new benchmark for state-of-the-art liver segmentation methods. The source code of the proposed PVTFormer is available at \url{https://github.com/DebeshJha/PVTFormer}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09630 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CT Liver Segmentation via PVT-based Encoding and Refined Decoding Jha, Debesh Tomar, Nikhil Kumar Biswas, Koushik Durak, Gorkem Medetalibeyoglu, Alpay Antalek, Matthew Velichko, Yury Ladner, Daniela Borhani, Amir Bagci, Ulas Image and Video Processing Computer Vision and Pattern Recognition Accurate liver segmentation from CT scans is essential for effective diagnosis and treatment planning. Computer-aided diagnosis systems promise to improve the precision of liver disease diagnosis, disease progression, and treatment planning. In response to the need, we propose a novel deep learning approach, \textit{\textbf{PVTFormer}}, that is built upon a pretrained pyramid vision transformer (PVT v2) combined with advanced residual upsampling and decoder block. By integrating a refined feature channel approach with a hierarchical decoding strategy, PVTFormer generates high quality segmentation masks by enhancing semantic features. Rigorous evaluation of the proposed method on Liver Tumor Segmentation Benchmark (LiTS) 2017 demonstrates that our proposed architecture not only achieves a high dice coefficient of 86.78\%, mIoU of 78.46\%, but also obtains a low HD of 3.50. The results underscore PVTFormer's efficacy in setting a new benchmark for state-of-the-art liver segmentation methods. The source code of the proposed PVTFormer is available at \url{https://github.com/DebeshJha/PVTFormer}. |
| title | CT Liver Segmentation via PVT-based Encoding and Refined Decoding |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.09630 |