Cargando…
A Cross-Domain Weakly Supervised Diabetic Retinopathy Lesion Identification Method Based on Multiple Instance Learning and Domain Adaptation
Accurate identification of lesions and their use across different medical institutions are the foundation and key to the clinical application of automatic diabetic retinopathy (DR) detection. Existing detection or segmentation methods can achieve acceptable results in DR lesion identification, but t...
Autores principales: | Li, Renyu, Gu, Yunchao, Wang, Xinliang, Pan, Junjun |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10525098/ https://www.ncbi.nlm.nih.gov/pubmed/37760202 http://dx.doi.org/10.3390/bioengineering10091100 |
Ejemplares similares
-
Instance-Level Contrastive Learning for Weakly Supervised Object Detection
por: Zhang, Ming, et al.
Publicado: (2022) -
WS-RCNN: Learning to Score Proposals for Weakly Supervised Instance Segmentation
por: Ou, Jia-Rong, et al.
Publicado: (2021) -
Weakly supervised learning for classification of lung cytological images using attention-based multiple instance learning
por: Teramoto, Atsushi, et al.
Publicado: (2021) -
Multiple instance learning based classification of diabetic retinopathy in weakly-labeled widefield OCTA en face images
por: Matten, Philipp, et al.
Publicado: (2023) -
Weakly Supervised Sensitive Heatmap framework to classify and localize diabetic retinopathy lesions
por: Al-Mukhtar, Mohammed, et al.
Publicado: (2021)