CS2 : A Controllable and Simultaneous Synthesizer of Images and Annotations with Minimal Human Intervention
25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022
; 13438 LNCS:3-12, 2022.
Artigo
em Inglês
| Scopus | ID: covidwho-2059730
ABSTRACT
The destitution of image data and corresponding expert annotations limit the training capacities of AI diagnostic models and potentially inhibit their performance. To address such a problem of data and label scarcity, generative models have been developed to augment the training datasets. Previously proposed generative models usually require manually adjusted annotations (e.g., segmentation masks) or need pre-labeling. However, studies have found that these pre-labeling based methods can induce hallucinating artifacts, which might mislead the downstream clinical tasks, while manual adjustment could be onerous and subjective. To avoid manual adjustment and pre-labeling, we propose a novel controllable and simultaneous synthesizer (dubbed CS$$
Data augmentation; Generative model; Semi-supervised segmentation; COVID-19; Diagnosis; Image annotation; Image segmentation; Medical imaging; Patient treatment; Diagnostic model; Expert annotations; High resolution CT; Human intervention; Image data; Labelings; Segmentation masks; Semi-supervised segmentations; Computerized tomography
Texto completo:
Disponível
Coleções:
Bases de dados de organismos internacionais
Base de dados:
Scopus
Tipo de estudo:
Estudo experimental
Idioma:
Inglês
Revista:
25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022
Ano de publicação:
2022
Tipo de documento:
Artigo
Similares
MEDLINE
...
LILACS
LIS