ANN uncertainty estimates in assessing fatty liver content from ultrasound data

IF 4.4 2区 生物学 Q2 BIOCHEMISTRY & MOLECULAR BIOLOGY Computational and structural biotechnology journal Pub Date : 2024-10-01 DOI:10.1016/j.csbj.2024.09.021
G. Del Corso , M.A. Pascali , C. Caudai , L. De Rosa , A. Salvati , M. Mancini , L. Ghiadoni , F. Bonino , M.R. Brunetto , S. Colantonio , F. Faita
{"title":"ANN uncertainty estimates in assessing fatty liver content from ultrasound data","authors":"G. Del Corso ,&nbsp;M.A. Pascali ,&nbsp;C. Caudai ,&nbsp;L. De Rosa ,&nbsp;A. Salvati ,&nbsp;M. Mancini ,&nbsp;L. Ghiadoni ,&nbsp;F. Bonino ,&nbsp;M.R. Brunetto ,&nbsp;S. Colantonio ,&nbsp;F. Faita","doi":"10.1016/j.csbj.2024.09.021","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and objective</h3><div>This article uses three different probabilistic convolutional architectures applied to ultrasound image analysis for grading Fatty Liver Content (FLC) in Metabolic Dysfunction Associated Steatotic Liver Disease (MASLD) patients. Steatosis is a new silent epidemic and its accurate measurement is an impelling clinical need, not only for hepatologists, but also for experts in metabolic and cardiovascular diseases. This paper aims to provide a robust comparison between different uncertainty quantification strategies to identify advantages and drawbacks in a real clinical setting.</div></div><div><h3>Methods</h3><div>We used a classical Convolutional Neural Network, a Monte Carlo Dropout, and a Bayesian Convolutional Neural Network with the goal of not only comparing the goodness of the predictions, but also to have access to an evaluation of the uncertainty associated with the outputs.</div></div><div><h3>Results</h3><div>We found that even if the prediction based on a single ultrasound view is reliable (relative RMSE [5.93%-12.04%]), networks based on two ultrasound views outperform them (relative RMSE [5.35%-5.87%]). In addition, the results show that the introduction of a “not confident” category contributes to increase the percentage of correctly predicted cases and to decrease the percentage of mispredicted cases, especially for semi-intrusive methods.</div></div><div><h3>Conclusions</h3><div>The possibility of having access to information about the confidence with which the network produces its outputs is a great advantage, both from the point of view of physicians who want to use neural networks as computer-aided diagnosis, and for developers who want to limit overfitting and obtain information about dataset problems in terms of out-of-distribution detection.</div></div>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":null,"pages":null},"PeriodicalIF":4.4000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational and structural biotechnology journal","FirstCategoryId":"99","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2001037024003088","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Background and objective

This article uses three different probabilistic convolutional architectures applied to ultrasound image analysis for grading Fatty Liver Content (FLC) in Metabolic Dysfunction Associated Steatotic Liver Disease (MASLD) patients. Steatosis is a new silent epidemic and its accurate measurement is an impelling clinical need, not only for hepatologists, but also for experts in metabolic and cardiovascular diseases. This paper aims to provide a robust comparison between different uncertainty quantification strategies to identify advantages and drawbacks in a real clinical setting.

Methods

We used a classical Convolutional Neural Network, a Monte Carlo Dropout, and a Bayesian Convolutional Neural Network with the goal of not only comparing the goodness of the predictions, but also to have access to an evaluation of the uncertainty associated with the outputs.

Results

We found that even if the prediction based on a single ultrasound view is reliable (relative RMSE [5.93%-12.04%]), networks based on two ultrasound views outperform them (relative RMSE [5.35%-5.87%]). In addition, the results show that the introduction of a “not confident” category contributes to increase the percentage of correctly predicted cases and to decrease the percentage of mispredicted cases, especially for semi-intrusive methods.

Conclusions

The possibility of having access to information about the confidence with which the network produces its outputs is a great advantage, both from the point of view of physicians who want to use neural networks as computer-aided diagnosis, and for developers who want to limit overfitting and obtain information about dataset problems in terms of out-of-distribution detection.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
从超声波数据评估脂肪肝含量的 ANN 不确定性估计
背景和目的本文将三种不同的概率卷积架构应用于超声图像分析,对代谢功能障碍相关性脂肪肝(MASLD)患者的脂肪肝含量(FLC)进行分级。脂肪肝是一种新的无声流行病,其精确测量不仅是肝病专家的迫切临床需求,也是代谢和心血管疾病专家的迫切临床需求。本文旨在对不同的不确定性量化策略进行稳健的比较,以确定在实际临床环境中的优势和缺点。方法我们使用了经典卷积神经网络、蒙特卡洛剔除和贝叶斯卷积神经网络,目的不仅是比较预测的好坏,而且是评估与输出相关的不确定性。结果我们发现,即使基于单个超声波视图的预测是可靠的(相对均方根误差[5.93%-12.04%]),基于两个超声波视图的网络也优于它们(相对均方根误差[5.35%-5.87%])。此外,研究结果表明,引入 "无信心 "类别有助于提高正确预测病例的百分比,降低错误预测病例的百分比,尤其是对于半侵入式方法而言。结论无论是从希望使用神经网络进行计算机辅助诊断的医生的角度,还是从希望限制过拟合和获得有关数据集问题的分布外检测信息的开发人员的角度来看,获取有关网络产生输出结果的信心信息的可能性都是一个巨大的优势。
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 去求助
来源期刊
Computational and structural biotechnology journal
Computational and structural biotechnology journal Biochemistry, Genetics and Molecular Biology-Biophysics
CiteScore
9.30
自引率
3.30%
发文量
540
审稿时长
6 weeks
期刊介绍: Computational and Structural Biotechnology Journal (CSBJ) is an online gold open access journal publishing research articles and reviews after full peer review. All articles are published, without barriers to access, immediately upon acceptance. The journal places a strong emphasis on functional and mechanistic understanding of how molecular components in a biological process work together through the application of computational methods. Structural data may provide such insights, but they are not a pre-requisite for publication in the journal. Specific areas of interest include, but are not limited to: Structure and function of proteins, nucleic acids and other macromolecules Structure and function of multi-component complexes Protein folding, processing and degradation Enzymology Computational and structural studies of plant systems Microbial Informatics Genomics Proteomics Metabolomics Algorithms and Hypothesis in Bioinformatics Mathematical and Theoretical Biology Computational Chemistry and Drug Discovery Microscopy and Molecular Imaging Nanotechnology Systems and Synthetic Biology
期刊最新文献
Corrigendum to "Cryo-EM reveals architectural diversity in active rotavirus particles" [Comput Struct Biotechnol J 31 (17) (2019) 1178-1183]. Spatial domains identification in spatial transcriptomics using modality-aware and subspace-enhanced graph contrastive learning. A systematic review on the state-of-the-art and research gaps regarding inorganic and carbon-based multicomponent and high-aspect ratio nanomaterials EEfinder, a general purpose tool for identification of bacterial and viral endogenized elements in eukaryotic genomes. Using patient-generated health data more efficient and effectively to facilitate the implementation of value-based healthcare in the EU – Innovation report
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1