Clinical applications of artificial intelligence in liver imaging

被引：24

作者：

Yamada, Akira ^{[1
]}

Kamagata, Koji ^{[2
]}

Hirata, Kenji ^{[3
]}

Ito, Rintaro ^{[4
]}

Nakaura, Takeshi ^{[5
]}

Ueda, Daiju ^{[6
]}

Fujita, Shohei ^{[7
]}

Fushimi, Yasutaka ^{[8
]}

Fujima, Noriyuki ^{[9
]}

Matsui, Yusuke ^{[10
]}

Tatsugami, Fuminari ^{[11
]}

Nozaki, Taiki ^{[12
]}

Fujioka, Tomoyuki ^{[13
]}

Yanagawa, Masahiro ^{[14
]}

Tsuboyama, Takahiro ^{[14
]}

Kawamura, Mariko ^{[4
]}

Naganawa, Shinji ^{[4
]}

机构：

[1] Shinshu Univ, Dept Radiol, Sch Med, Matsumoto, Nagano, Japan

[2] Juntendo Univ, Dept Radiol, Grad Sch Med, Bunkyo Ku, Tokyo, Japan

[3] Hokkaido Univ Hosp, Dept Nucl Med, Sapporo, Japan

[4] Nagoya Univ, Dept Radiol, Grad Sch Med, Nagoya, Aichi, Japan

[5] Kumamoto Univ, Dept Diagnost Radiol, Grad Sch Med, Chuo Ku, Kumamoto, Japan

[6] Osaka Metropolitan Univ, Grad Sch Med, Dept Diagnost & Intervent Radiol, Abeno Ku, Osaka, Japan

[7] Univ Tokyo, Dept Radiol, Tokyo, Japan

[8] Kyoto Univ, Dept Diagnost Imaging & Nucl Med, Grad Sch Med, Sakyo ku, Kyoto, Japan

[9] Hokkaido Univ Hosp, Dept Diagnost & Intervent Radiol, Sapporo, Japan

[10] Okayama Univ, Fac Med Dent & Pharmaceut Sci, Dept Radiol, Kita Ku, Okayama, Japan

[11] Hiroshima Univ, Dept Diagnost Radiol, Minami Ku, Hiroshima, Hiroshima, Japan

[12] St Lukes Int Hosp, Dept Radiol, Tokyo, Japan

[13] Tokyo Med & Dent Univ, Dept Diagnost Radiol, Tokyo, Japan

[14] Osaka Univ, Dept Radiol, Grad Sch Med, Suita, Osaka, Japan

来源：

RADIOLOGIA MEDICA | 2023年 / 128卷 / 06期

关键词：

Liver imaging; Artificial intelligence; Latent Dirichlet allocation; Topic analysis; 20TH ANNIVERSARY ISSUE; HEPATOCELLULAR-CARCINOMA; SEGMENTATION; RADIOMICS; DIAGNOSIS; FEATURES; RISK;

D O I：

10.1007/s11547-023-01638-1

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.

引用

页码：655 / 667

页数：13

共 100 条

[1] The effect of CT texture-based analysis using machine learning approaches on radiologists' performance in differentiating focal-type autoimmune pancreatitis and pancreatic duct carcinoma [J].