Cargando…
Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images
SIMPLE SUMMARY: During breast-conserving surgeries, there is no accurate method available for evaluating the edges (margins) of breast cancer specimens to determine if the tumor has been removed completely. As a result, during the pathological examinations after 9% to 36% of breast-conserving surger...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10046373/ https://www.ncbi.nlm.nih.gov/pubmed/36980539 http://dx.doi.org/10.3390/cancers15061652 |
_version_ | 1785013656652611584 |
---|---|
author | Veluponnar, Dinusha de Boer, Lisanne L. Geldof, Freija Jong, Lynn-Jade S. Da Silva Guimaraes, Marcos Vrancken Peeters, Marie-Jeanne T. F. D. van Duijnhoven, Frederieke Ruers, Theo Dashtbozorg, Behdad |
author_facet | Veluponnar, Dinusha de Boer, Lisanne L. Geldof, Freija Jong, Lynn-Jade S. Da Silva Guimaraes, Marcos Vrancken Peeters, Marie-Jeanne T. F. D. van Duijnhoven, Frederieke Ruers, Theo Dashtbozorg, Behdad |
author_sort | Veluponnar, Dinusha |
collection | PubMed |
description | SIMPLE SUMMARY: During breast-conserving surgeries, there is no accurate method available for evaluating the edges (margins) of breast cancer specimens to determine if the tumor has been removed completely. As a result, during the pathological examinations after 9% to 36% of breast-conserving surgeries, it is found that some tumor tissue is present on the margins of the removed tissue. This potentially leads to additional surgery or boost radiotherapy for these patients. Here, we evaluated the use of computer-aided delineation of tumor boundaries in ultrasound images in order to predict positive and close margins (distance from tumor to margin ≤ 2.0 mm). We found that our method has a sensitivity of 96% and a specificity of 76% for predicting positive and close margins in the pathology result. These promising results display that computer-aided US evaluation has great potential to be applied as a margin assessment tool during breast-conserving surgeries. ABSTRACT: There is an unmet clinical need for an accurate, rapid and reliable tool for margin assessment during breast-conserving surgeries. Ultrasound offers the potential for a rapid, reproducible, and non-invasive method to assess margins. However, it is challenged by certain drawbacks, including a low signal-to-noise ratio, artifacts, and the need for experience with the acquirement and interpretation of images. A possible solution might be computer-aided ultrasound evaluation. In this study, we have developed new ensemble approaches for automated breast tumor segmentation. The ensemble approaches to predict positive and close margins (distance from tumor to margin ≤ 2.0 mm) in the ultrasound images were based on 8 pre-trained deep neural networks. The best optimum ensemble approach for segmentation attained a median Dice score of 0.88 on our data set. Furthermore, utilizing the segmentation results we were able to achieve a sensitivity of 96% and a specificity of 76% for predicting a close margin when compared to histology results. The promising results demonstrate the capability of AI-based ultrasound imaging as an intraoperative surgical margin assessment tool during breast-conserving surgery. |
format | Online Article Text |
id | pubmed-10046373 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100463732023-03-29 Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images Veluponnar, Dinusha de Boer, Lisanne L. Geldof, Freija Jong, Lynn-Jade S. Da Silva Guimaraes, Marcos Vrancken Peeters, Marie-Jeanne T. F. D. van Duijnhoven, Frederieke Ruers, Theo Dashtbozorg, Behdad Cancers (Basel) Article SIMPLE SUMMARY: During breast-conserving surgeries, there is no accurate method available for evaluating the edges (margins) of breast cancer specimens to determine if the tumor has been removed completely. As a result, during the pathological examinations after 9% to 36% of breast-conserving surgeries, it is found that some tumor tissue is present on the margins of the removed tissue. This potentially leads to additional surgery or boost radiotherapy for these patients. Here, we evaluated the use of computer-aided delineation of tumor boundaries in ultrasound images in order to predict positive and close margins (distance from tumor to margin ≤ 2.0 mm). We found that our method has a sensitivity of 96% and a specificity of 76% for predicting positive and close margins in the pathology result. These promising results display that computer-aided US evaluation has great potential to be applied as a margin assessment tool during breast-conserving surgeries. ABSTRACT: There is an unmet clinical need for an accurate, rapid and reliable tool for margin assessment during breast-conserving surgeries. Ultrasound offers the potential for a rapid, reproducible, and non-invasive method to assess margins. However, it is challenged by certain drawbacks, including a low signal-to-noise ratio, artifacts, and the need for experience with the acquirement and interpretation of images. A possible solution might be computer-aided ultrasound evaluation. In this study, we have developed new ensemble approaches for automated breast tumor segmentation. The ensemble approaches to predict positive and close margins (distance from tumor to margin ≤ 2.0 mm) in the ultrasound images were based on 8 pre-trained deep neural networks. The best optimum ensemble approach for segmentation attained a median Dice score of 0.88 on our data set. Furthermore, utilizing the segmentation results we were able to achieve a sensitivity of 96% and a specificity of 76% for predicting a close margin when compared to histology results. The promising results demonstrate the capability of AI-based ultrasound imaging as an intraoperative surgical margin assessment tool during breast-conserving surgery. MDPI 2023-03-08 /pmc/articles/PMC10046373/ /pubmed/36980539 http://dx.doi.org/10.3390/cancers15061652 Text en © 2023 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 Veluponnar, Dinusha de Boer, Lisanne L. Geldof, Freija Jong, Lynn-Jade S. Da Silva Guimaraes, Marcos Vrancken Peeters, Marie-Jeanne T. F. D. van Duijnhoven, Frederieke Ruers, Theo Dashtbozorg, Behdad Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images |
title | Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images |
title_full | Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images |
title_fullStr | Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images |
title_full_unstemmed | Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images |
title_short | Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images |
title_sort | toward intraoperative margin assessment using a deep learning-based approach for automatic tumor segmentation in breast lumpectomy ultrasound images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10046373/ https://www.ncbi.nlm.nih.gov/pubmed/36980539 http://dx.doi.org/10.3390/cancers15061652 |
work_keys_str_mv | AT veluponnardinusha towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages AT deboerlisannel towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages AT geldoffreija towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages AT jonglynnjades towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages AT dasilvaguimaraesmarcos towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages AT vranckenpeetersmariejeannetfd towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages AT vanduijnhovenfrederieke towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages AT ruerstheo towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages AT dashtbozorgbehdad towardintraoperativemarginassessmentusingadeeplearningbasedapproachforautomatictumorsegmentationinbreastlumpectomyultrasoundimages |