Development of a Deep Learning Model for Classification of Hepatic Steatosis from Clinical Standard Ultrasound.

IF 2.4 3区医学 Q2 ACOUSTICS

Ultrasound in Medicine and Biology Pub Date : 2024-11-12 DOI:10.1016/j.ultrasmedbio.2024.09.020

Ahmed El Kaffas, Krishna Chaitanya Bhatraju, Jenny M Vo-Phamhi, Thodsawit Tiyarattanachai, Neha Antil, Lindsey M Negrete, Aya Kamaya, Luyao Shen

{"title":"Development of a Deep Learning Model for Classification of Hepatic Steatosis from Clinical Standard Ultrasound.","authors":"Ahmed El Kaffas, Krishna Chaitanya Bhatraju, Jenny M Vo-Phamhi, Thodsawit Tiyarattanachai, Neha Antil, Lindsey M Negrete, Aya Kamaya, Luyao Shen","doi":"10.1016/j.ultrasmedbio.2024.09.020","DOIUrl":null,"url":null,"abstract":"Objective: Early detection and monitoring of hepatic steatosis can help establish appropriate preventative measures against progression to more advanced disease. We aimed to develop a deep learning (DL) program for classification of hepatic steatosis from standard-of-care grayscale ultrasound (US) images.Methods: In this single-center retrospective study, we utilized grayscale US images from January 1, 2010, to October 23, 2022, labeled with magnetic resonance imaging (MRI) proton density fat fraction (MRI-PDFF) to develop a DL multi-instance program for differentiating normal (S0) from steatotic liver (S1/2/3) and normal/mild steatosis (S0/1) from moderate/severe steatosis (S2/3). Diagnostic performances were assessed with area under the receiver operating characteristic curves (AUC), sensitivity, specificity and balanced accuracy with 95% confidence interval (CI).Results: A total of 403 patients with 403 US exams were included: 171 (42%) were normal (S0: MRI-PDFF <5%), 154 (38%) had mild steatosis (S1: MRI-PDFF 5-17.4%), 29 (7%) had moderate steatosis (S2: MRI-PDFF >17.4%-22.1%) and 49 (12%) had severe steatosis (S3: MRI-PDFF >22.1%). The dataset was split to include 322 patients in train/validation and 81 patients in a holdout test set (kept blind). The S0 versus S1/2/3 model achieved 81.3% (95% CI 72.1-90.5) AUC, 81.1% (70.6-91.6) sensitivity, 71.4% (54.7-88.2) specificity and 76.3% (66.4-86.2) balanced accuracy. The S0/1 versus S2/3 model achieved 95.9% (89-100) AUC, 87.5% (71.3-100) sensitivity, 96.9% (92.7-100) specificity and 92.2% (83.8-100) balanced accuracy. A multi-class model achieved a sensitivity of 71.4% (54.7-88.2) for S0, 67.6% (52.5-82.7) for S1 and 87.5% (71.3-100) for S2/3; specificity for the same model was 81.1% (70.6-91.6) for S0, 77.3% (64.9-89.7) for S1 and 96.9% (92.7-100) for S2/3.Conclusion: Our DL program offered high sensitivity and accuracy in detecting and categorizing hepatic steatosis from standard-of-care ultrasound.","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ultrasound in Medicine and Biology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.ultrasmedbio.2024.09.020","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ACOUSTICS","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: Early detection and monitoring of hepatic steatosis can help establish appropriate preventative measures against progression to more advanced disease. We aimed to develop a deep learning (DL) program for classification of hepatic steatosis from standard-of-care grayscale ultrasound (US) images.

Methods: In this single-center retrospective study, we utilized grayscale US images from January 1, 2010, to October 23, 2022, labeled with magnetic resonance imaging (MRI) proton density fat fraction (MRI-PDFF) to develop a DL multi-instance program for differentiating normal (S0) from steatotic liver (S1/2/3) and normal/mild steatosis (S0/1) from moderate/severe steatosis (S2/3). Diagnostic performances were assessed with area under the receiver operating characteristic curves (AUC), sensitivity, specificity and balanced accuracy with 95% confidence interval (CI).

Results: A total of 403 patients with 403 US exams were included: 171 (42%) were normal (S0: MRI-PDFF <5%), 154 (38%) had mild steatosis (S1: MRI-PDFF 5-17.4%), 29 (7%) had moderate steatosis (S2: MRI-PDFF >17.4%-22.1%) and 49 (12%) had severe steatosis (S3: MRI-PDFF >22.1%). The dataset was split to include 322 patients in train/validation and 81 patients in a holdout test set (kept blind). The S0 versus S1/2/3 model achieved 81.3% (95% CI 72.1-90.5) AUC, 81.1% (70.6-91.6) sensitivity, 71.4% (54.7-88.2) specificity and 76.3% (66.4-86.2) balanced accuracy. The S0/1 versus S2/3 model achieved 95.9% (89-100) AUC, 87.5% (71.3-100) sensitivity, 96.9% (92.7-100) specificity and 92.2% (83.8-100) balanced accuracy. A multi-class model achieved a sensitivity of 71.4% (54.7-88.2) for S0, 67.6% (52.5-82.7) for S1 and 87.5% (71.3-100) for S2/3; specificity for the same model was 81.1% (70.6-91.6) for S0, 77.3% (64.9-89.7) for S1 and 96.9% (92.7-100) for S2/3.

Conclusion: Our DL program offered high sensitivity and accuracy in detecting and categorizing hepatic steatosis from standard-of-care ultrasound.

查看原文本刊更多论文

开发用于从临床标准超声波对肝脏脂肪变性进行分类的深度学习模型

目的：肝脏脂肪变性的早期检测和监测有助于制定适当的预防措施，防止疾病发展到晚期。我们旨在开发一种深度学习（DL）程序，用于从标准护理灰度超声（US）图像中对肝脂肪变性进行分类：在这项单中心回顾性研究中，我们利用 2010 年 1 月 1 日至 2022 年 10 月 23 日的灰度 US 图像，标注了磁共振成像（MRI）质子密度脂肪分数（MRI-PDFF），开发了一个多实例 DL 程序，用于区分正常肝脏（S0）和脂肪肝（S1/2/3），以及正常/轻度脂肪肝（S0/1）和中度/重度脂肪肝（S2/3）。用接收者操作特征曲线下面积（AUC）、灵敏度、特异性和平衡准确度（95% 置信区间（CI））评估诊断性能：共有 403 名患者接受了 403 次 US 检查：171例（42%）为正常（S0：MRI-PDFF 17.4%-22.1%），49例（12%）为严重脂肪变性（S3：MRI-PDFF >22.1%）。数据集进行了拆分，将 322 名患者纳入训练/验证集，将 81 名患者纳入保留测试集（保持盲测）。S0 与 S1/2/3 模型的 AUC 为 81.3%（95% CI 72.1-90.5），灵敏度为 81.1%（70.6-91.6），特异度为 71.4%（54.7-88.2），平衡准确率为 76.3%（66.4-86.2）。S0/1 与 S2/3 模型的 AUC 为 95.9%（89-100），灵敏度为 87.5%（71.3-100），特异度为 96.9%（92.7-100），平衡准确率为 92.2%（83.8-100）。多类模型对 S0 的灵敏度为 71.4%（54.7-88.2），对 S1 的灵敏度为 67.6%（52.5-82.7），对 S2/3 的灵敏度为 87.5%（71.3-100）；同一模型对 S0 的特异性为 81.1%（70.6-91.6），对 S1 的特异性为 77.3%（64.9-89.7），对 S2/3 的特异性为 96.9%（92.7-100）：我们的 DL 程序在通过标准护理超声波检测和分类肝脂肪变性方面具有很高的灵敏度和准确性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Ultrasound in Medicine and Biology 医学-核医学

CiteScore

6.20

自引率

6.90%

发文量

325

审稿时长

70 days

期刊介绍： Ultrasound in Medicine and Biology is the official journal of the World Federation for Ultrasound in Medicine and Biology. The journal publishes original contributions that demonstrate a novel application of an existing ultrasound technology in clinical diagnostic, interventional and therapeutic applications, new and improved clinical techniques, the physics, engineering and technology of ultrasound in medicine and biology, and the interactions between ultrasound and biological systems, including bioeffects. Papers that simply utilize standard diagnostic ultrasound as a measuring tool will be considered out of scope. Extended critical reviews of subjects of contemporary interest in the field are also published, in addition to occasional editorial articles, clinical and technical notes, book reviews, letters to the editor and a calendar of forthcoming meetings. It is the aim of the journal fully to meet the information and publication requirements of the clinicians, scientists, engineers and other professionals who constitute the biomedical ultrasonic community.