Cargando…

Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification

We have developed a novel photoacoustic microscopy/ultrasound (PAM/US) endoscope to image post-treatment rectal cancer for surgical management of residual tumor after radiation and chemotherapy. Paired with a deep-learning convolutional neural network (CNN), the PAM images accurately differentiated...

Descripción completa

Detalles Bibliográficos
Autores principales: Leng, Xiandong, Amidi, Eghbal, Kou, Sitai, Cheema, Hassam, Otegbeye, Ebunoluwa, Chapman, William Jr, Mutch, Matthew, Zhu, Quing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8495416/
https://www.ncbi.nlm.nih.gov/pubmed/34631543
http://dx.doi.org/10.3389/fonc.2021.715332
_version_ 1784579547041103872
author Leng, Xiandong
Amidi, Eghbal
Kou, Sitai
Cheema, Hassam
Otegbeye, Ebunoluwa
Chapman, William Jr
Mutch, Matthew
Zhu, Quing
author_facet Leng, Xiandong
Amidi, Eghbal
Kou, Sitai
Cheema, Hassam
Otegbeye, Ebunoluwa
Chapman, William Jr
Mutch, Matthew
Zhu, Quing
author_sort Leng, Xiandong
collection PubMed
description We have developed a novel photoacoustic microscopy/ultrasound (PAM/US) endoscope to image post-treatment rectal cancer for surgical management of residual tumor after radiation and chemotherapy. Paired with a deep-learning convolutional neural network (CNN), the PAM images accurately differentiated pathological complete responders (pCR) from incomplete responders. However, the role of CNNs compared with traditional histogram-feature based classifiers needs further exploration. In this work, we compare the performance of the CNN models to generalized linear models (GLM) across 24 ex vivo specimens and 10 in vivo patient examinations. First order statistical features were extracted from histograms of PAM and US images to train, validate and test GLM models, while PAM and US images were directly used to train, validate, and test CNN models. The PAM-CNN model performed superiorly with an AUC of 0.96 (95% CI: 0.95-0.98) compared to the best PAM-GLM model using kurtosis with an AUC of 0.82 (95% CI: 0.82-0.83). We also found that both CNN and GLMs derived from photoacoustic data outperformed those utilizing ultrasound alone. We conclude that deep-learning neural networks paired with photoacoustic images is the optimal analysis framework for determining presence of residual cancer in the treated human rectum.
format Online
Article
Text
id pubmed-8495416
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-84954162021-10-08 Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification Leng, Xiandong Amidi, Eghbal Kou, Sitai Cheema, Hassam Otegbeye, Ebunoluwa Chapman, William Jr Mutch, Matthew Zhu, Quing Front Oncol Oncology We have developed a novel photoacoustic microscopy/ultrasound (PAM/US) endoscope to image post-treatment rectal cancer for surgical management of residual tumor after radiation and chemotherapy. Paired with a deep-learning convolutional neural network (CNN), the PAM images accurately differentiated pathological complete responders (pCR) from incomplete responders. However, the role of CNNs compared with traditional histogram-feature based classifiers needs further exploration. In this work, we compare the performance of the CNN models to generalized linear models (GLM) across 24 ex vivo specimens and 10 in vivo patient examinations. First order statistical features were extracted from histograms of PAM and US images to train, validate and test GLM models, while PAM and US images were directly used to train, validate, and test CNN models. The PAM-CNN model performed superiorly with an AUC of 0.96 (95% CI: 0.95-0.98) compared to the best PAM-GLM model using kurtosis with an AUC of 0.82 (95% CI: 0.82-0.83). We also found that both CNN and GLMs derived from photoacoustic data outperformed those utilizing ultrasound alone. We conclude that deep-learning neural networks paired with photoacoustic images is the optimal analysis framework for determining presence of residual cancer in the treated human rectum. Frontiers Media S.A. 2021-09-23 /pmc/articles/PMC8495416/ /pubmed/34631543 http://dx.doi.org/10.3389/fonc.2021.715332 Text en Copyright © 2021 Leng, Amidi, Kou, Cheema, Otegbeye, Chapman, Mutch and Zhu https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Leng, Xiandong
Amidi, Eghbal
Kou, Sitai
Cheema, Hassam
Otegbeye, Ebunoluwa
Chapman, William Jr
Mutch, Matthew
Zhu, Quing
Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification
title Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification
title_full Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification
title_fullStr Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification
title_full_unstemmed Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification
title_short Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification
title_sort rectal cancer treatment management: deep-learning neural network based on photoacoustic microscopy image outperforms histogram-feature-based classification
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8495416/
https://www.ncbi.nlm.nih.gov/pubmed/34631543
http://dx.doi.org/10.3389/fonc.2021.715332
work_keys_str_mv AT lengxiandong rectalcancertreatmentmanagementdeeplearningneuralnetworkbasedonphotoacousticmicroscopyimageoutperformshistogramfeaturebasedclassification
AT amidieghbal rectalcancertreatmentmanagementdeeplearningneuralnetworkbasedonphotoacousticmicroscopyimageoutperformshistogramfeaturebasedclassification
AT kousitai rectalcancertreatmentmanagementdeeplearningneuralnetworkbasedonphotoacousticmicroscopyimageoutperformshistogramfeaturebasedclassification
AT cheemahassam rectalcancertreatmentmanagementdeeplearningneuralnetworkbasedonphotoacousticmicroscopyimageoutperformshistogramfeaturebasedclassification
AT otegbeyeebunoluwa rectalcancertreatmentmanagementdeeplearningneuralnetworkbasedonphotoacousticmicroscopyimageoutperformshistogramfeaturebasedclassification
AT chapmanwilliamjr rectalcancertreatmentmanagementdeeplearningneuralnetworkbasedonphotoacousticmicroscopyimageoutperformshistogramfeaturebasedclassification
AT mutchmatthew rectalcancertreatmentmanagementdeeplearningneuralnetworkbasedonphotoacousticmicroscopyimageoutperformshistogramfeaturebasedclassification
AT zhuquing rectalcancertreatmentmanagementdeeplearningneuralnetworkbasedonphotoacousticmicroscopyimageoutperformshistogramfeaturebasedclassification