Multiscale Time-Sharing Elastography Algorithms and Transfer Learning of Clinicopathological Features of Uterine Cervical Cancer for Medical Intelligent Computing System.
J Med Syst
; 43(10): 310, 2019 Aug 26.
Article
em En
| MEDLINE
| ID: mdl-31448390
ABSTRACT
Intelligent medical diagnosis and computing system faces many challenges in complex object recognition, large-scale data imaging and real-time diagnosis, such as poor real-time computing, low efficiency of data storage and low recognition rate of lesions. In order to solve the above problems, this paper proposes a medical intelligent computing system and a series of algorithms for the clinical pathology of cervical cancer based on the multi-scale imaging and transfer learning framework. Firstly, based on data dimensions, imaging errors and other factors, this paper designs a multi-scale time-sharing elastic imaging algorithm based on image reconstruction time and data sample characteristics. Then, taking the burst imaging cohort and the calculation data set of new cervical cancer cases as the objects, based on the difficulties of cervical cancer feature modeling, this paper proposes the transfer learning algorithm of clinical and pathological features of cervical cancer. Finally, a medical intelligent computing system for cervical cancer pathology analysis and calculation with high efficiency and reliability is established. A series of proposed algorithms are compared with single-scale Retinex (SSR), which is based on single-scale Retinex migration learning (SSR-TL). The experimental results show that the proposed algorithm in cervical cancer pathological imaging and scoring, as well as the feature extraction and recognition of lesions, especially the efficiency of system execution, is obviously due to the comparison algorithm.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Algoritmos
/
Processamento de Imagem Assistida por Computador
/
Neoplasias do Colo do Útero
/
Técnicas de Imagem por Elasticidade
Tipo de estudo:
Diagnostic_studies
/
Prognostic_studies
Limite:
Female
/
Humans
Idioma:
En
Ano de publicação:
2019
Tipo de documento:
Article