Bookmark Saya

arXiv Open Access 2024

Hierarchical Loss And Geometric Mask Refinement For Multilabel Ribs Segmentation

Aleksei Leonov Aleksei Zakharov Sergey Koshelev Maxim Pisov Anvar Kurmukov +1 lainnya
Lihat Sumber

Abstrak

Automatic ribs segmentation and numeration can increase computed tomography assessment speed and reduce radiologists mistakes. We introduce a model for multilabel ribs segmentation with hierarchical loss function, which enable to improve multilabel segmentation quality. Also we propose postprocessing technique to further increase labeling quality. Our model achieved new state-of-the-art 98.2% label accuracy on public RibSeg v2 dataset, surpassing previous result by 6.7%.

Topik & Kata Kunci

eess.IV cs.CV cs.LG

Penulis (6)

A

Aleksei Leonov

A

Aleksei Zakharov

S

Sergey Koshelev

M

Maxim Pisov

A

Anvar Kurmukov

M

Mikhail Belyaev

Format Sitasi

APA MLA BibTeX
Leonov, A., Zakharov, A., Koshelev, S., Pisov, M., Kurmukov, A., Belyaev, M. (2024). Hierarchical Loss And Geometric Mask Refinement For Multilabel Ribs Segmentation. https://arxiv.org/abs/2405.15500

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2024
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓