Literature DB >> 31324579

Fully Automated Postlumpectomy Breast Margin Assessment Utilizing Convolutional Neural Network Based Optical Coherence Tomography Image Classification Method.

Diana Mojahed1, Richard S Ha2, Peter Chang3, Yu Gan4, Xinwen Yao4, Brigid Angelini4, Hanina Hibshoosh5, Bret Taback6, Christine P Hendon4.   

Abstract

BACKGROUND: The purpose of this study was to develop a deep learning classification approach to distinguish cancerous from noncancerous regions within optical coherence tomography (OCT) images of breast tissue for potential use in an intraoperative setting for margin assessment.
METHODS: A custom ultrahigh-resolution OCT (UHR-OCT) system with an axial resolution of 2.7 μm and a lateral resolution of 5.5 μm was used in this study. The algorithm used an A-scan-based classification scheme and the convolutional neural network (CNN) was implemented using an 11-layer architecture consisting of serial 3 × 3 convolution kernels. Four tissue types were classified, including adipose, stroma, ductal carcinoma in situ, and invasive ductal carcinoma.
RESULTS: The binary classification of cancer versus noncancer with the proposed CNN achieved 94% accuracy, 96% sensitivity, and 92% specificity. The mean five-fold validation F1 score was highest for invasive ductal carcinoma (mean standard deviation, 0.89 ± 0.09) and adipose (0.79 ± 0.17), followed by stroma (0.74 ± 0.18), and ductal carcinoma in situ (0.65 ± 0.15).
CONCLUSION: It is feasible to use CNN based algorithm to accurately distinguish cancerous regions in OCT images. This fully automated method can overcome limitations of manual interpretation including interobserver variability and speed of interpretation and may enable real-time intraoperative margin assessment.
Copyright © 2019 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  CNN; Lumpectomy; OCT

Year:  2019        PMID: 31324579     DOI: 10.1016/j.acra.2019.06.018

Source DB:  PubMed          Journal:  Acad Radiol        ISSN: 1076-6332            Impact factor:   3.173


  7 in total

Review 1.  Development of intraoperative assessment of margins in breast conserving surgery: a narrative review.

Authors:  Wanheng Li; Xiru Li
Journal:  Gland Surg       Date:  2022-01

2.  Multi-class classification of breast tissue using optical coherence tomography and attenuation imaging combined via deep learning.

Authors:  Ken Y Foo; Kyle Newman; Qi Fang; Peijun Gong; Hina M Ismail; Devina D Lakhiani; Renate Zilkens; Benjamin F Dessauvagie; Bruce Latham; Christobel M Saunders; Lixin Chin; Brendan F Kennedy
Journal:  Biomed Opt Express       Date:  2022-05-12       Impact factor: 3.562

Review 3.  Towards an Optical Biopsy during Visceral Surgical Interventions.

Authors:  David Benjamin Ellebrecht; Sarah Latus; Alexander Schlaefer; Tobias Keck; Nils Gessert
Journal:  Visc Med       Date:  2020-03-05

4.  Millimeter-scale chip-based supercontinuum generation for optical coherence tomography.

Authors:  Xingchen Ji; Diana Mojahed; Yoshitomo Okawachi; Alexander L Gaeta; Christine P Hendon; Michal Lipson
Journal:  Sci Adv       Date:  2021-09-17       Impact factor: 14.136

5.  Binary dose level classification of tumour microvascular response to radiotherapy using artificial intelligence analysis of optical coherence tomography images.

Authors:  Anamitra Majumdar; Nader Allam; W Jeffrey Zabel; Valentin Demidov; Costel Flueraru; I Alex Vitkin
Journal:  Sci Rep       Date:  2022-08-17       Impact factor: 4.996

Review 6.  Research progress on the application of optical coherence tomography in the field of oncology.

Authors:  Linhai Yang; Yulun Chen; Shuting Ling; Jing Wang; Guangxing Wang; Bei Zhang; Hengyu Zhao; Qingliang Zhao; Jingsong Mao
Journal:  Front Oncol       Date:  2022-07-25       Impact factor: 5.738

7.  Optical coherence tomography holds promise to transform the diagnostic anatomic pathology gross evaluation process.

Authors:  Diana Mojahed; Matthew Applegate; Hua Guo; Bret Taback; Richard Ha; Hanina Hibshoosh; Christine Hendon
Journal:  J Biomed Opt       Date:  2022-09       Impact factor: 3.758

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.