文献检索文档翻译深度研究
Suppr Zotero 插件Zotero 插件
邀请有礼套餐&价格历史记录

新学期，新优惠

限时优惠:9月1日-9月22日

30天高级会员仅需29元

1天体验卡首发特惠仅需5.99元

了解详情
不再提醒
插件&应用
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
高级版
套餐订阅购买积分包
AI 工具
文献检索文档翻译深度研究
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2025

基于深度学习和多期 CT 成像的肝脏局灶性病变诊断。

Focal liver lesion diagnosis with deep learning and multistage CT imaging.

机构信息

Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China.

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.

出版信息

Nat Commun. 2024 Aug 15;15(1):7040. doi: 10.1038/s41467-024-51260-6.

DOI:10.1038/s41467-024-51260-6
PMID:39147767
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11327344/
Abstract

Diagnosing liver lesions is crucial for treatment choices and patient outcomes. This study develops an automatic diagnosis system for liver lesions using multiphase enhanced computed tomography (CT). A total of 4039 patients from six data centers are enrolled to develop Liver Lesion Network (LiLNet). LiLNet identifies focal liver lesions, including hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), metastatic tumors (MET), focal nodular hyperplasia (FNH), hemangioma (HEM), and cysts (CYST). Validated in four external centers and clinically verified in two hospitals, LiLNet achieves an accuracy (ACC) of 94.7% and an area under the curve (AUC) of 97.2% for benign and malignant tumors. For HCC, ICC, and MET, the ACC is 88.7% with an AUC of 95.6%. For FNH, HEM, and CYST, the ACC is 88.6% with an AUC of 95.9%. LiLNet can aid in clinical diagnosis, especially in regions with a shortage of radiologists.

摘要

诊断肝脏病变对于治疗选择和患者预后至关重要。本研究开发了一种使用多期增强 CT 的肝脏病变自动诊断系统。共有来自六个数据中心的 4039 名患者被纳入肝脏病变网络（LiLNet）进行开发。LiLNet 可识别局灶性肝脏病变，包括肝细胞癌（HCC）、肝内胆管细胞癌（ICC）、转移性肿瘤（MET）、局灶性结节性增生（FNH）、血管瘤（HEM）和囊肿（CYST）。该系统在四个外部中心进行了验证，并在两家医院进行了临床验证，其对良性和恶性肿瘤的准确率（ACC）为 94.7%，曲线下面积（AUC）为 97.2%。对于 HCC、ICC 和 MET，ACC 为 88.7%，AUC 为 95.6%。对于 FNH、HEM 和 CYST，ACC 为 88.6%，AUC 为 95.9%。LiLNet 可辅助临床诊断，特别是在放射科医生短缺的地区。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/043e2a03cc22/41467_2024_51260_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/c82fd5fc8622/41467_2024_51260_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/dddbaff19854/41467_2024_51260_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/2b35d91e5e01/41467_2024_51260_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/f81190df0e32/41467_2024_51260_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/3b21f16a981a/41467_2024_51260_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/d8b5cbe41098/41467_2024_51260_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/043e2a03cc22/41467_2024_51260_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/c82fd5fc8622/41467_2024_51260_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/dddbaff19854/41467_2024_51260_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/2b35d91e5e01/41467_2024_51260_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/f81190df0e32/41467_2024_51260_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/3b21f16a981a/41467_2024_51260_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/d8b5cbe41098/41467_2024_51260_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/de86/11327344/043e2a03cc22/41467_2024_51260_Fig7_HTML.jpg

相似文献

[1]
Focal liver lesion diagnosis with deep learning and multistage CT imaging.

Nat Commun. 2024-8-15

[2]
CPZ: A Highly Sensitive Diagnostic Biomarker for the Differentiation Between Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma, Particularly in Poorly Differentiated Hepatocellular Carcinoma.

Am J Surg Pathol. 2025-7-1

[3]
Comparison of Al 18 F-NOTA-FAPI-74 and 18 F-FDG PET/CT in the Evaluation and Staging of Hepatobiliary Malignancies : A Single-center Prospective Study.

Clin Nucl Med. 2025-7-1

[4]
Application of acoustic radiation force impulse imaging for the evaluation of focal liver lesion elasticity.

Hepatobiliary Pancreat Dis Int. 2013-4

[5]
Characterization of unifocal liver lesions with pulse inversion harmonic imaging after Levovist injection: preliminary results.

Eur Radiol. 2000

[6]
Molecular feature-based classification of retroperitoneal liposarcoma: a prospective cohort study.

Elife. 2025-5-23

[7]
Hepatocellular carcinoma and focal nodular hyperplasia of the liver: differentiation with CT spectral imaging.

Eur Radiol. 2013-1-10

[8]
Deep learning and digital pathology powers prediction of HCC development in steatotic liver disease.

Hepatology. 2025-3-1

[9]
Liver elastography malignancy prediction score for noninvasive characterization of focal liver lesions.

Liver Int. 2017-11-3

[10]
Focal nodular hyperplasia or focal nodular hyperplasia-like lesions of the liver: a special emphasis on diagnosis.

J Gastroenterol Hepatol. 2011-6

引用本文的文献

[1]
An interpretable CT-based deep learning model for predicting overall survival in patients with bladder cancer: a multicenter study.

NPJ Precis Oncol. 2025-8-16

[2]
PA/MR imaging-guided precision phototherapy and efficacy evaluation of hepatocellular carcinoma utilizing a targeted multifunctional nanoprobe.

Front Immunol. 2025-6-11

[3]
Deep Learning to Enhance Diagnosis and Management of Intrahepatic Cholangiocarcinoma.

Cancers (Basel). 2025-5-9

[4]
Applications of artificial intelligence in abdominal imaging.

Abdom Radiol (NY). 2025-5-26

[5]
Delaying liver aging: Analysis of structural and functional alterations.

World J Gastroenterol. 2025-4-21

[6]
A deep learning-based psi CT network effectively predicts early recurrence after hepatectomy in HCC patients.

Abdom Radiol (NY). 2025-2-26

[7]
Artificial Intelligence and Radiomics in Cholangiocarcinoma: A Comprehensive Review.

Diagnostics (Basel). 2025-1-10

本文引用的文献

[1]
Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma.

Nat Commun. 2023-12-14

[2]
Self-Supervised Tumor Segmentation With Sim2Real Adaptation.

IEEE J Biomed Health Inform. 2023-9

[3]
A Knowledge-Guided Framework for Fine-Grained Classification of Liver Lesions Based on Multi-Phase CT Images.

IEEE J Biomed Health Inform. 2023-1

[4]
Deep learning for image-based liver analysis - A comprehensive review focusing on malignant lesions.

Artif Intell Med. 2022-8

[5]
Anomaly detection-inspired few-shot medical image segmentation through self-supervision with supervoxels.

Med Image Anal. 2022-5

[6]
Deep learning for differential diagnosis of malignant hepatic tumors based on multi-phase contrast-enhanced CT and clinical data.

J Hematol Oncol. 2021-9-26

[7]
Development of an AI system for accurately diagnose hepatocellular carcinoma from computed tomography imaging data.

Br J Cancer. 2021-10

[8]
Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study.

Lancet Digit Health. 2021-4

[9]
Weakly-Supervised teacher-Student network for liver tumor segmentation from non-enhanced images.

Med Image Anal. 2021-5

[10]
Development and Validation of a Novel Computed-Tomography Enterography Radiomic Approach for Characterization of Intestinal Fibrosis in Crohn's Disease.

Gastroenterology. 2021-6

文献AI研究员

20分钟写一篇综述，助力文献阅读效率提升50倍

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

推荐工具

医学文档翻译智能文献检索