Cargando…
Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation
Automatic segmentation methods are an important advancement in medical image analysis. Machine learning techniques, and deep neural networks in particular, are the state-of-the-art for most medical image segmentation tasks. Issues with class imbalance pose a significant challenge in medical datasets...
Autores principales: | Yeung, Michael, Sala, Evis, Schönlieb, Carola-Bibiane, Rundo, Leonardo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8785124/ https://www.ncbi.nlm.nih.gov/pubmed/34953431 http://dx.doi.org/10.1016/j.compmedimag.2021.102026 |
Ejemplares similares
-
Calibrating the Dice Loss to Handle Neural Network Overconfidence for Biomedical Image Segmentation
por: Yeung, Michael, et al.
Publicado: (2022) -
Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy
por: Yeung, Michael, et al.
Publicado: (2021) -
An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
por: Vito, Valentino, et al.
Publicado: (2022) -
Machine Learning for COVID-19 Diagnosis and Prognostication: Lessons
for Amplifying the Signal While Reducing the Noise
por: Driggs, Derek, et al.
Publicado: (2021) -
Deep learning-based multi-functional therapeutic peptides prediction with a multi-label focal dice loss function
por: Fan, Henghui, et al.
Publicado: (2023)