Cargando…
Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations
Background: The ultrasound is one of the most used medical imaging investigations worldwide. It is non-invasive and effective in assessing liver tumors or other types of parenchymal changes. Methods: The aim of the study was to build a deep learning model for image segmentation in ultrasound video i...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9695234/ https://www.ncbi.nlm.nih.gov/pubmed/36431012 http://dx.doi.org/10.3390/life12111877 |
_version_ | 1784838005311143936 |
---|---|
author | Mămuleanu, Mădălin Urhuț, Cristiana Marinela Săndulescu, Larisa Daniela Kamal, Constantin Pătrașcu, Ana-Maria Ionescu, Alin Gabriel Șerbănescu, Mircea-Sebastian Streba, Costin Teodor |
author_facet | Mămuleanu, Mădălin Urhuț, Cristiana Marinela Săndulescu, Larisa Daniela Kamal, Constantin Pătrașcu, Ana-Maria Ionescu, Alin Gabriel Șerbănescu, Mircea-Sebastian Streba, Costin Teodor |
author_sort | Mămuleanu, Mădălin |
collection | PubMed |
description | Background: The ultrasound is one of the most used medical imaging investigations worldwide. It is non-invasive and effective in assessing liver tumors or other types of parenchymal changes. Methods: The aim of the study was to build a deep learning model for image segmentation in ultrasound video investigations. The dataset used in the study was provided by the University of Medicine and Pharmacy Craiova, Romania and contained 50 video examinations from 49 patients. The mean age of the patients in the cohort was 69.57. Regarding presence of a subjacent liver disease, 36.73% had liver cirrhosis and 16.32% had chronic viral hepatitis (5 patients: chronic hepatitis C and 3 patients: chronic hepatitis B). Frames were extracted and cropped from each examination and an expert gastroenterologist labelled the lesions in each frame. After labelling, the labels were exported as binary images. A deep learning segmentation model (U-Net) was trained with focal Tversky loss as a loss function. Two models were obtained with two different sets of parameters for the loss function. The performance metrics observed were intersection over union and recall and precision. Results: Analyzing the intersection over union metric, the first segmentation model obtained performed better compared to the second model: 0.8392 (model 1) vs. 0.7990 (model 2). The inference time for both models was between 32.15 milliseconds and 77.59 milliseconds. Conclusions: Two segmentation models were obtained in the study. The models performed similarly during training and validation. However, one model was trained to focus on hard-to-predict labels. The proposed segmentation models can represent a first step in automatically extracting time-intensity curves from CEUS examinations. |
format | Online Article Text |
id | pubmed-9695234 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96952342022-11-26 Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations Mămuleanu, Mădălin Urhuț, Cristiana Marinela Săndulescu, Larisa Daniela Kamal, Constantin Pătrașcu, Ana-Maria Ionescu, Alin Gabriel Șerbănescu, Mircea-Sebastian Streba, Costin Teodor Life (Basel) Article Background: The ultrasound is one of the most used medical imaging investigations worldwide. It is non-invasive and effective in assessing liver tumors or other types of parenchymal changes. Methods: The aim of the study was to build a deep learning model for image segmentation in ultrasound video investigations. The dataset used in the study was provided by the University of Medicine and Pharmacy Craiova, Romania and contained 50 video examinations from 49 patients. The mean age of the patients in the cohort was 69.57. Regarding presence of a subjacent liver disease, 36.73% had liver cirrhosis and 16.32% had chronic viral hepatitis (5 patients: chronic hepatitis C and 3 patients: chronic hepatitis B). Frames were extracted and cropped from each examination and an expert gastroenterologist labelled the lesions in each frame. After labelling, the labels were exported as binary images. A deep learning segmentation model (U-Net) was trained with focal Tversky loss as a loss function. Two models were obtained with two different sets of parameters for the loss function. The performance metrics observed were intersection over union and recall and precision. Results: Analyzing the intersection over union metric, the first segmentation model obtained performed better compared to the second model: 0.8392 (model 1) vs. 0.7990 (model 2). The inference time for both models was between 32.15 milliseconds and 77.59 milliseconds. Conclusions: Two segmentation models were obtained in the study. The models performed similarly during training and validation. However, one model was trained to focus on hard-to-predict labels. The proposed segmentation models can represent a first step in automatically extracting time-intensity curves from CEUS examinations. MDPI 2022-11-14 /pmc/articles/PMC9695234/ /pubmed/36431012 http://dx.doi.org/10.3390/life12111877 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Mămuleanu, Mădălin Urhuț, Cristiana Marinela Săndulescu, Larisa Daniela Kamal, Constantin Pătrașcu, Ana-Maria Ionescu, Alin Gabriel Șerbănescu, Mircea-Sebastian Streba, Costin Teodor Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations |
title | Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations |
title_full | Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations |
title_fullStr | Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations |
title_full_unstemmed | Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations |
title_short | Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations |
title_sort | deep learning algorithms in the automatic segmentation of liver lesions in ultrasound investigations |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9695234/ https://www.ncbi.nlm.nih.gov/pubmed/36431012 http://dx.doi.org/10.3390/life12111877 |
work_keys_str_mv | AT mamuleanumadalin deeplearningalgorithmsintheautomaticsegmentationofliverlesionsinultrasoundinvestigations AT urhutcristianamarinela deeplearningalgorithmsintheautomaticsegmentationofliverlesionsinultrasoundinvestigations AT sandulescularisadaniela deeplearningalgorithmsintheautomaticsegmentationofliverlesionsinultrasoundinvestigations AT kamalconstantin deeplearningalgorithmsintheautomaticsegmentationofliverlesionsinultrasoundinvestigations AT patrascuanamaria deeplearningalgorithmsintheautomaticsegmentationofliverlesionsinultrasoundinvestigations AT ionescualingabriel deeplearningalgorithmsintheautomaticsegmentationofliverlesionsinultrasoundinvestigations AT serbanescumirceasebastian deeplearningalgorithmsintheautomaticsegmentationofliverlesionsinultrasoundinvestigations AT strebacostinteodor deeplearningalgorithmsintheautomaticsegmentationofliverlesionsinultrasoundinvestigations |