Risk Analysis for Pathological Changes in Pulmonary Parenchyma Based on Lung Computed Tomography Images

Autor: He Ma, Wei Qian, Hong Yang Jiang, Guo Hui Wei
Rok vydání: 2016
Předmět:
Adult
Male
medicine.medical_specialty
Lung Neoplasms
02 engineering and technology
Latent Dirichlet allocation
Risk Assessment
Sensitivity and Specificity
03 medical and health sciences
symbols.namesake
0302 clinical medicine
Parenchyma
0202 electrical engineering
electronic engineering
information engineering
Medicine
Data Mining
Humans
Radiology
Nuclear Medicine and imaging
Image retrieval
Lung
Parenchymal Tissue
Aged
Aged
80 and over
Pixel
business.industry
Reproducibility of Results
Middle Aged
Decision Support Systems
Clinical
Image Enhancement
Data set
medicine.anatomical_structure
Radiology Information Systems
Risk analysis (engineering)
030220 oncology & carcinogenesis
symbols
Radiographic Image Interpretation
Computer-Assisted
020201 artificial intelligence & image processing
Female
Radiology
Tomography
business
Precision and recall
Tomography
X-Ray Computed
Zdroj: Journal of computer assisted tomography. 40(3)
ISSN: 1532-3145
Popis: Objective The purpose of this study is to design a content-based medical image retrieval system, which helps excavate and assess pathological change of pulmonary parenchyma for risks analysis. Methods A data set including lung computed tomography images obtained from 115 patients who experienced pathological changes in pulmonary parenchyma is used. Using morphological theory, images are preprocessed and decomposed into groups of pixel blocks (words), which construct vocabulary. A latent Dirichlet allocation (LDA) model is constructed to assess each image for risk analysis with the method of leave-one-out cross-validation. The precision and recall rate are used as the performance assessment criteria. Results The LDA model generates a relevance rank of retrieval results from high to low. From the top 50 images, precision of identical tissue is 0.76 ± 0.031 and precision of each attribute of pulmonary parenchyma range from 0.776 ± 0.043 to 0.984 ± 0.008. Conclusions The study results demonstrate that the proposed LDA model is conductive to lung computed tomography image retrieval and has reliable efficacy on risk analysis about pathological changes of pulmonary parenchyma.
Databáze: OpenAIRE
Externí odkaz: