Convolutional Neural Network Detection of Axillary Lymph Node Metastasis Using Standard Clinical Breast MRI.
Anatomic Landmarks
Axilla
Breast Neoplasms
/ diagnosis
Datasets as Topic
Feasibility Studies
Female
Fluorodeoxyglucose F18
/ administration & dosage
Humans
Image Processing, Computer-Assisted
/ methods
Lymphatic Metastasis
/ diagnosis
Magnetic Resonance Imaging
Neural Networks, Computer
Positron-Emission Tomography
ROC Curve
Radiopharmaceuticals
/ administration & dosage
Reproducibility of Results
Sentinel Lymph Node
/ diagnostic imaging
Breast cancer
Machine learning
Magnetic resonance imaging
Pathological complete response
Sentinel lymph node biopsy
Journal
Clinical breast cancer
ISSN: 1938-0666
Titre abrégé: Clin Breast Cancer
Pays: United States
ID NLM: 100898731
Informations de publication
Date de publication:
06 2020
06 2020
Historique:
received:
16
09
2019
revised:
18
11
2019
accepted:
30
11
2019
pubmed:
7
3
2020
medline:
22
6
2021
entrez:
7
3
2020
Statut:
ppublish
Résumé
Axillary lymph node status is important for breast cancer staging and treatment planning as the majority of breast cancer metastasis spreads through the axillary lymph nodes. There is currently no reliable noninvasive imaging method to detect nodal metastasis associated with breast cancer. Magnetic resonance imaging (MRI) data were those from the peak contrast dynamic image from 1.5 Tesla MRI scanners at the pre-neoadjuvant chemotherapy stage. Data consisted of 66 abnormal nodes from 38 patients and 193 normal nodes from 61 patients. Abnormal nodes were those determined by expert radiologist based on The convolutional neural network model yielded a specificity of 79.3% ± 5.1%, sensitivity of 92.1% ± 2.9%, positive predictive value of 76.9% ± 4.0%, negative predictive value of 93.3% ± 1.9%, accuracy of 84.8% ± 2.4%, and receiver operating characteristic area under the curve of 0.91 ± 0.02 for the validation data set. These results compared favorably with scoring by radiologists (accuracy of 78%). The results are encouraging and suggest that this approach may prove useful for classifying lymph node status on MRI in clinical settings in patients with breast cancer, although additional studies are needed before routine clinical use can be realized. This approach has the potential to ultimately be a noninvasive alternative to lymph node biopsy.
Sections du résumé
BACKGROUND
Axillary lymph node status is important for breast cancer staging and treatment planning as the majority of breast cancer metastasis spreads through the axillary lymph nodes. There is currently no reliable noninvasive imaging method to detect nodal metastasis associated with breast cancer.
MATERIALS AND METHODS
Magnetic resonance imaging (MRI) data were those from the peak contrast dynamic image from 1.5 Tesla MRI scanners at the pre-neoadjuvant chemotherapy stage. Data consisted of 66 abnormal nodes from 38 patients and 193 normal nodes from 61 patients. Abnormal nodes were those determined by expert radiologist based on
RESULTS
The convolutional neural network model yielded a specificity of 79.3% ± 5.1%, sensitivity of 92.1% ± 2.9%, positive predictive value of 76.9% ± 4.0%, negative predictive value of 93.3% ± 1.9%, accuracy of 84.8% ± 2.4%, and receiver operating characteristic area under the curve of 0.91 ± 0.02 for the validation data set. These results compared favorably with scoring by radiologists (accuracy of 78%).
CONCLUSION
The results are encouraging and suggest that this approach may prove useful for classifying lymph node status on MRI in clinical settings in patients with breast cancer, although additional studies are needed before routine clinical use can be realized. This approach has the potential to ultimately be a noninvasive alternative to lymph node biopsy.
Identifiants
pubmed: 32139272
pii: S1526-8209(19)30757-8
doi: 10.1016/j.clbc.2019.11.009
pii:
doi:
Substances chimiques
Radiopharmaceuticals
0
Fluorodeoxyglucose F18
0Z5B2CJX4D
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e301-e308Informations de copyright
Copyright © 2019 Elsevier Inc. All rights reserved.