Cargando…

Machine Learning Decision Support for Detecting Lipohypertrophy With Bedside Ultrasound: Proof-of-Concept Study

BACKGROUND: The most common dermatological complication of insulin therapy is lipohypertrophy. OBJECTIVE: As a proof of concept, we built and tested an automated model using a convolutional neural network (CNN) to detect the presence of lipohypertrophy in ultrasound images. METHODS: Ultrasound image...

Descripción completa

Detalles Bibliográficos
Autores principales: Bandari, Ela, Beuzen, Tomas, Habashy, Lara, Raza, Javairia, Yang, Xudong, Kapeluto, Jordanna, Meneilly, Graydon, Madden, Kenneth
Formato: Online Artículo Texto
Lenguaje:English
Publicado: JMIR Publications 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9123536/
https://www.ncbi.nlm.nih.gov/pubmed/35404833
http://dx.doi.org/10.2196/34830
_version_ 1784711571953418240
author Bandari, Ela
Beuzen, Tomas
Habashy, Lara
Raza, Javairia
Yang, Xudong
Kapeluto, Jordanna
Meneilly, Graydon
Madden, Kenneth
author_facet Bandari, Ela
Beuzen, Tomas
Habashy, Lara
Raza, Javairia
Yang, Xudong
Kapeluto, Jordanna
Meneilly, Graydon
Madden, Kenneth
author_sort Bandari, Ela
collection PubMed
description BACKGROUND: The most common dermatological complication of insulin therapy is lipohypertrophy. OBJECTIVE: As a proof of concept, we built and tested an automated model using a convolutional neural network (CNN) to detect the presence of lipohypertrophy in ultrasound images. METHODS: Ultrasound images were obtained in a blinded fashion using a portable GE LOGIQ e machine with an L8-18I-D probe (5-18 MHz; GE Healthcare). The data were split into train, validation, and test splits of 70%, 15%, and 15%, respectively. Given the small size of the data set, image augmentation techniques were used to expand the size of the training set and improve the model’s generalizability. To compare the performance of the different architectures, the team considered the accuracy and recall of the models when tested on our test set. RESULTS: The DenseNet CNN architecture was found to have the highest accuracy (76%) and recall (76%) in detecting lipohypertrophy in ultrasound images compared to other CNN architectures. Additional work showed that the YOLOv5m object detection model could be used to help detect the approximate location of lipohypertrophy in ultrasound images identified as containing lipohypertrophy by the DenseNet CNN. CONCLUSIONS: We were able to demonstrate the ability of machine learning approaches to automate the process of detecting and locating lipohypertrophy.
format Online
Article
Text
id pubmed-9123536
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher JMIR Publications
record_format MEDLINE/PubMed
spelling pubmed-91235362022-05-22 Machine Learning Decision Support for Detecting Lipohypertrophy With Bedside Ultrasound: Proof-of-Concept Study Bandari, Ela Beuzen, Tomas Habashy, Lara Raza, Javairia Yang, Xudong Kapeluto, Jordanna Meneilly, Graydon Madden, Kenneth JMIR Form Res Original Paper BACKGROUND: The most common dermatological complication of insulin therapy is lipohypertrophy. OBJECTIVE: As a proof of concept, we built and tested an automated model using a convolutional neural network (CNN) to detect the presence of lipohypertrophy in ultrasound images. METHODS: Ultrasound images were obtained in a blinded fashion using a portable GE LOGIQ e machine with an L8-18I-D probe (5-18 MHz; GE Healthcare). The data were split into train, validation, and test splits of 70%, 15%, and 15%, respectively. Given the small size of the data set, image augmentation techniques were used to expand the size of the training set and improve the model’s generalizability. To compare the performance of the different architectures, the team considered the accuracy and recall of the models when tested on our test set. RESULTS: The DenseNet CNN architecture was found to have the highest accuracy (76%) and recall (76%) in detecting lipohypertrophy in ultrasound images compared to other CNN architectures. Additional work showed that the YOLOv5m object detection model could be used to help detect the approximate location of lipohypertrophy in ultrasound images identified as containing lipohypertrophy by the DenseNet CNN. CONCLUSIONS: We were able to demonstrate the ability of machine learning approaches to automate the process of detecting and locating lipohypertrophy. JMIR Publications 2022-05-06 /pmc/articles/PMC9123536/ /pubmed/35404833 http://dx.doi.org/10.2196/34830 Text en ©Ela Bandari, Tomas Beuzen, Lara Habashy, Javairia Raza, Xudong Yang, Jordanna Kapeluto, Graydon Meneilly, Kenneth Madden. Originally published in JMIR Formative Research (https://formative.jmir.org), 06.05.2022. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Formative Research, is properly cited. The complete bibliographic information, a link to the original publication on https://formative.jmir.org, as well as this copyright and license information must be included.
spellingShingle Original Paper
Bandari, Ela
Beuzen, Tomas
Habashy, Lara
Raza, Javairia
Yang, Xudong
Kapeluto, Jordanna
Meneilly, Graydon
Madden, Kenneth
Machine Learning Decision Support for Detecting Lipohypertrophy With Bedside Ultrasound: Proof-of-Concept Study
title Machine Learning Decision Support for Detecting Lipohypertrophy With Bedside Ultrasound: Proof-of-Concept Study
title_full Machine Learning Decision Support for Detecting Lipohypertrophy With Bedside Ultrasound: Proof-of-Concept Study
title_fullStr Machine Learning Decision Support for Detecting Lipohypertrophy With Bedside Ultrasound: Proof-of-Concept Study
title_full_unstemmed Machine Learning Decision Support for Detecting Lipohypertrophy With Bedside Ultrasound: Proof-of-Concept Study
title_short Machine Learning Decision Support for Detecting Lipohypertrophy With Bedside Ultrasound: Proof-of-Concept Study
title_sort machine learning decision support for detecting lipohypertrophy with bedside ultrasound: proof-of-concept study
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9123536/
https://www.ncbi.nlm.nih.gov/pubmed/35404833
http://dx.doi.org/10.2196/34830
work_keys_str_mv AT bandariela machinelearningdecisionsupportfordetectinglipohypertrophywithbedsideultrasoundproofofconceptstudy
AT beuzentomas machinelearningdecisionsupportfordetectinglipohypertrophywithbedsideultrasoundproofofconceptstudy
AT habashylara machinelearningdecisionsupportfordetectinglipohypertrophywithbedsideultrasoundproofofconceptstudy
AT razajavairia machinelearningdecisionsupportfordetectinglipohypertrophywithbedsideultrasoundproofofconceptstudy
AT yangxudong machinelearningdecisionsupportfordetectinglipohypertrophywithbedsideultrasoundproofofconceptstudy
AT kapelutojordanna machinelearningdecisionsupportfordetectinglipohypertrophywithbedsideultrasoundproofofconceptstudy
AT meneillygraydon machinelearningdecisionsupportfordetectinglipohypertrophywithbedsideultrasoundproofofconceptstudy
AT maddenkenneth machinelearningdecisionsupportfordetectinglipohypertrophywithbedsideultrasoundproofofconceptstudy