Predicting the subcutaneous temperature in cryolipolysis using deep operator networks

IF 5.1 3区工程技术 Q2 ENERGY & FUELS

Thermal Science and Engineering Progress Pub Date : 2024-10-01 DOI:10.1016/j.tsep.2024.102946

{"title":"Predicting the subcutaneous temperature in cryolipolysis using deep operator networks","authors":"","doi":"10.1016/j.tsep.2024.102946","DOIUrl":null,"url":null,"abstract":"<div><div>Accurate monitoring of subcutaneous temperature is crucial for the safety and efficacy of cryolipolysis. However, existing measurement and simulation methods often require trade-offs between accuracy, depth, and computational efficiency. This study introduces a novel deep learning architecture, ConvD-DeepONet, specifically designed to predict subcutaneous temperature fields with both high accuracy and efficiency. The model effectively captures spatial information and produces multi-dimensional output, owing to the innovative integration of convolutional layers and the decoder network. An average absolute error (MAE) of 0.0038 ℃ and a root mean square error (RMSE) of 0.0083 ℃ are achieved, resulting in over a 50 % reduction compared to the baseline models. Moreover, each prediction is completed in just 5.9 ms, rendering it 120 times faster than traditional finite element method simulations. These results indicate that ConvD-DeepONet is a promising tool for real-time subcutaneous temperature prediction, with the potential to enhance the safety and efficacy of cryolipolysis.</div></div>","PeriodicalId":23062,"journal":{"name":"Thermal Science and Engineering Progress","volume":null,"pages":null},"PeriodicalIF":5.1000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Thermal Science and Engineering Progress","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S245190492400564X","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}

引用次数: 0

Abstract

Accurate monitoring of subcutaneous temperature is crucial for the safety and efficacy of cryolipolysis. However, existing measurement and simulation methods often require trade-offs between accuracy, depth, and computational efficiency. This study introduces a novel deep learning architecture, ConvD-DeepONet, specifically designed to predict subcutaneous temperature fields with both high accuracy and efficiency. The model effectively captures spatial information and produces multi-dimensional output, owing to the innovative integration of convolutional layers and the decoder network. An average absolute error (MAE) of 0.0038 ℃ and a root mean square error (RMSE) of 0.0083 ℃ are achieved, resulting in over a 50 % reduction compared to the baseline models. Moreover, each prediction is completed in just 5.9 ms, rendering it 120 times faster than traditional finite element method simulations. These results indicate that ConvD-DeepONet is a promising tool for real-time subcutaneous temperature prediction, with the potential to enhance the safety and efficacy of cryolipolysis.

Abstract Image

查看原文本刊更多论文

利用深度算子网络预测冷冻溶脂过程中的皮下温度

准确监测皮下温度对冷冻溶脂的安全性和有效性至关重要。然而，现有的测量和模拟方法往往需要在精度、深度和计算效率之间做出权衡。本研究引入了一种新颖的深度学习架构 ConvD-DeepONet，专门用于预测皮下温度场的高精度和高效率。由于创新性地整合了卷积层和解码器网络，该模型能有效捕捉空间信息并产生多维输出。该模型的平均绝对误差（MAE）为 0.0038 ℃，均方根误差（RMSE）为 0.0083 ℃，与基线模型相比降低了 50% 以上。此外，每次预测仅需 5.9 毫秒即可完成，比传统的有限元法模拟快 120 倍。这些结果表明，ConvD-DeepONet 是一种很有前途的皮下温度实时预测工具，有望提高冷冻溶脂的安全性和有效性。

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

Thermal Science and Engineering Progress Chemical Engineering-Fluid Flow and Transfer Processes

CiteScore

7.20

自引率

10.40%

发文量

327

审稿时长

41 days

期刊介绍： Thermal Science and Engineering Progress (TSEP) publishes original, high-quality research articles that span activities ranging from fundamental scientific research and discussion of the more controversial thermodynamic theories, to developments in thermal engineering that are in many instances examples of the way scientists and engineers are addressing the challenges facing a growing population – smart cities and global warming – maximising thermodynamic efficiencies and minimising all heat losses. It is intended that these will be of current relevance and interest to industry, academia and other practitioners. It is evident that many specialised journals in thermal and, to some extent, in fluid disciplines tend to focus on topics that can be classified as fundamental in nature, or are ‘applied’ and near-market. Thermal Science and Engineering Progress will bridge the gap between these two areas, allowing authors to make an easy choice, should they or a journal editor feel that their papers are ‘out of scope’ when considering other journals. The range of topics covered by Thermal Science and Engineering Progress addresses the rapid rate of development being made in thermal transfer processes as they affect traditional fields, and important growth in the topical research areas of aerospace, thermal biological and medical systems, electronics and nano-technologies, renewable energy systems, food production (including agriculture), and the need to minimise man-made thermal impacts on climate change. Review articles on appropriate topics for TSEP are encouraged, although until TSEP is fully established, these will be limited in number. Before submitting such articles, please contact one of the Editors, or a member of the Editorial Advisory Board with an outline of your proposal and your expertise in the area of your review.