このエントリーをはてなブックマークに追加
ID 57928
Author
Tanaka, Takashi Department of Radiology, Okayama University Hospital ORCID Kaken ID researchmap
Huang, Yong Department of Medical Informatics, Okayama University Hospital
Marukawa, Yohei Department of Radiology, Okayama University Hospital
Tsuboi, Yuka Department of Radiology, Okayama University Hospital
Masaoka, Yoshihisa Department of Radiology, Okayama University Hospital
Kojima, Katsuhide Department of Radiology, Okayama University Hospital
Iguchi, Toshihiro Department of Radiology, Okayama University Hospital
Hiraki, Takao Department of Radiology, Okayama University Hospital
Gobara, Hideo Department of Radiology, Okayama University Hospital
Yanai, Hiroyuki Department of Radiology, Okayama University Hospital
Nasu, Yasutomo Department of Urology, Okayama University Hospital Kaken ID publons researchmap
Kanazawa, Susumu Department of Radiology, Okayama University Hospital Kaken ID publons
Abstract
OBJECTIVE.
This study evaluated the utility of a deep learning method for determining whether a small (≤ 4 cm) solid renal mass was benign or malignant on multiphase contrast-enhanced CT.
MATERIALS AND METHODS.
This retrospective study included 1807 image sets from 168 pathologically diagnosed small (≤ 4 cm) solid renal masses with four CT phases (unenhanced, corticomedullary, nephrogenic, and excretory) in 159 patients between 2012 and 2016. Masses were classified as malignant (n = 136) or benign (n = 32). The dataset was randomly divided into five subsets: four were used for augmentation and supervised training (48,832 images), and one was used for testing (281 images). The Inception-v3 architecture convolutional neural network (CNN) model was used. The AUC for malignancy and accuracy at optimal cutoff values of output data were evaluated in six different CNN models. Multivariate logistic regression analysis was also performed.
RESULTS.
Malignant and benign lesions showed no significant difference of size. The AUC value of corticomedullary phase was higher than that of other phases (corticomedullary vs excretory, p = 0.022). The highest accuracy (88%) was achieved in corticomedullary phase images. Multivariate analysis revealed that the CNN model of corticomedullary phase was a significant predictor for malignancy compared with other CNN models, age, sex, and lesion size.
CONCLUSION.
A deep learning method with a CNN allowed acceptable differentiation of small (≤ 4 cm) solid renal masses in dynamic CT images, especially in the corticomedullary image model.
Keywords
MDCT
artificial intelligence
kidney
neoplasms
neural network models
Published Date
2020-01-08
Publication Title
American journal of roentgenology
Publisher
American Roentgen Ray Society
Start Page
1
End Page
8
ISSN
0361-803X
NCID
AA00521224
Content Type
Journal Article
language
英語
OAI-PMH Set
岡山大学
File Version
author
PubMed ID
DOI
Related Url
isVersionOf https://doi.org/10.2214/AJR.19.22074