Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning
Pressure injuries represent a major concern in many nations. These wounds result from prolonged pressure on the skin, which mainly occur among elderly and disabled patients. If retrieving quantitative information using invasive methods is the most used method, it causes significant pain and discomfo...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/10/2933 |
_version_ | 1797567372949716992 |
---|---|
author | Sofia Zahia Begonya Garcia-Zapirain Adel Elmaghraby |
author_facet | Sofia Zahia Begonya Garcia-Zapirain Adel Elmaghraby |
author_sort | Sofia Zahia |
collection | DOAJ |
description | Pressure injuries represent a major concern in many nations. These wounds result from prolonged pressure on the skin, which mainly occur among elderly and disabled patients. If retrieving quantitative information using invasive methods is the most used method, it causes significant pain and discomfort to the patients and may also increase the risk of infections. Hence, developing non-intrusive methods for the assessment of pressure injuries would represent a highly useful tool for caregivers and a relief for patients. Traditional methods rely on findings retrieved solely from 2D images. Thus, bypassing the 3D information deriving from the deep and irregular shape of this type of wounds leads to biased measurements. In this paper, we propose an end-to-end system which uses a single 2D image and a 3D mesh of the pressure injury, acquired using the Structure Sensor, and outputs all the necessary findings such as: external segmentation of the wound as well as its real-world measurements (depth, area, volume, major axis and minor axis). More specifically, a first block composed of a Mask RCNN model uses the 2D image to output the segmentation of the external boundaries of the wound. Then, a second block matches the 2D and 3D views to segment the wound in the 3D mesh using the segmentation output and generates the aforementioned real-world measurements. Experimental results showed that the proposed framework can not only output refined segmentation with 87% precision, but also retrieves reliable measurements, which can be used for medical assessment and healing evaluation of pressure injuries. |
first_indexed | 2024-03-10T19:40:47Z |
format | Article |
id | doaj.art-94a7b9c779064dbc9c9c561fa17bc3d6 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T19:40:47Z |
publishDate | 2020-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-94a7b9c779064dbc9c9c561fa17bc3d62023-11-20T01:17:30ZengMDPI AGSensors1424-82202020-05-012010293310.3390/s20102933Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep LearningSofia Zahia0Begonya Garcia-Zapirain1Adel Elmaghraby2eVIDA Research Group, University of Deusto, 48007 Bilbao, SpaineVIDA Research Group, University of Deusto, 48007 Bilbao, SpainComputer Science and Engineering Department, University of Louisville, Louisville, KY 40292, USAPressure injuries represent a major concern in many nations. These wounds result from prolonged pressure on the skin, which mainly occur among elderly and disabled patients. If retrieving quantitative information using invasive methods is the most used method, it causes significant pain and discomfort to the patients and may also increase the risk of infections. Hence, developing non-intrusive methods for the assessment of pressure injuries would represent a highly useful tool for caregivers and a relief for patients. Traditional methods rely on findings retrieved solely from 2D images. Thus, bypassing the 3D information deriving from the deep and irregular shape of this type of wounds leads to biased measurements. In this paper, we propose an end-to-end system which uses a single 2D image and a 3D mesh of the pressure injury, acquired using the Structure Sensor, and outputs all the necessary findings such as: external segmentation of the wound as well as its real-world measurements (depth, area, volume, major axis and minor axis). More specifically, a first block composed of a Mask RCNN model uses the 2D image to output the segmentation of the external boundaries of the wound. Then, a second block matches the 2D and 3D views to segment the wound in the 3D mesh using the segmentation output and generates the aforementioned real-world measurements. Experimental results showed that the proposed framework can not only output refined segmentation with 87% precision, but also retrieves reliable measurements, which can be used for medical assessment and healing evaluation of pressure injuries.https://www.mdpi.com/1424-8220/20/10/2933computer-assisted interventionpressure injurybiomedical sensingdeep learning and diagnosis |
spellingShingle | Sofia Zahia Begonya Garcia-Zapirain Adel Elmaghraby Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning Sensors computer-assisted intervention pressure injury biomedical sensing deep learning and diagnosis |
title | Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning |
title_full | Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning |
title_fullStr | Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning |
title_full_unstemmed | Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning |
title_short | Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning |
title_sort | integrating 3d model representation for an accurate non invasive assessment of pressure injuries with deep learning |
topic | computer-assisted intervention pressure injury biomedical sensing deep learning and diagnosis |
url | https://www.mdpi.com/1424-8220/20/10/2933 |
work_keys_str_mv | AT sofiazahia integrating3dmodelrepresentationforanaccuratenoninvasiveassessmentofpressureinjurieswithdeeplearning AT begonyagarciazapirain integrating3dmodelrepresentationforanaccuratenoninvasiveassessmentofpressureinjurieswithdeeplearning AT adelelmaghraby integrating3dmodelrepresentationforanaccuratenoninvasiveassessmentofpressureinjurieswithdeeplearning |