A multi‐stage fusion framework to classify breast lesions using deep learning and radiomics features computed from four‐view mammograms
Medical Physics · 2023-12 · 50 (12) · 7670-7683
DOI: 10.1002/mp.16419 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, online erschienen am 21.04.2023. Verfasst von Meredith A Jones und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, University of Oklahoma, Norman, Oklahoma, USA. Hauptthemen laut MEDLINE: Algorithms, Deep Learning. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS.
Abstract (Originalsprache)
Background
Developing computer aided diagnosis (CAD) schemes of mammograms to classify between malignant and benign breast lesions has attracted a lot of research attention over the last several decades. However, unlike radiologists who make diagnostic decisions based on the fusion of image features extracted from multi‐view mammograms, most CAD schemes are single‐view‐based schemes, which limit CAD performance and clinical utility.
Purpose
This study aims to develop and test a novel CAD framework that optimally fuses information extracted from ipsilateral views of bilateral mammograms using both deep transfer learning (DTL) and radiomics feature extraction methods.
Methods
An image dataset containing 353 benign and 611 malignant cases is assembled. Each case contains four images: the craniocaudal (CC) and mediolateral oblique (MLO) view of the left and right breast. First, we extract four matching regions of interest (ROIs) from images that surround centers of two suspicious lesion regions seen in CC and MLO views, as well as matching ROIs in the contralateral breasts. Next, the handcrafted radiomics (HCRs) features and VGG16 model‐generated automated features are extracted from each ROI resulting in eight feature vectors. Then, after reducing feature dimensionality and quantifying the bilateral and ipsilateral asymmetry of four ROIs to yield four new feature vectors, we test four fusion methods to build three support vector machine (SVM) classifiers by an optimal fusion of asymmetrical image features extracted from four view images.
Results
Using a 10‐fold cross‐validation method, results show that a SVM classifier trained using an optimal fusion of four view images yields the highest classification performance (AUC = 0.876 ± 0.031), which significantly outperforms SVM classifiers trained using one projection view alone, AUC = 0.817 ± 0.026 and 0.792 ± 0.026 for the CC and MLO view of bilateral mammograms, respectively ( p < 0.001).
Conclusions
The study demonstrates that the shift from single‐view CAD to four‐view CAD and the inclusion of both DTL and radiomics features significantly increases CAD performance in distinguishing between malignant and benign breast lesions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Biomedical Engineering, University of Oklahoma, Norman, Oklahoma, USA.
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, Oklahoma, USA.
Förderung
- NIGMS NIH HHS
Zitieren
APA
Jones, M. A., Sadeghipour, N., Chen, X., Islam, W., & Zheng, B. (2023). A multi‐stage fusion framework to classify breast lesions using deep learning and radiomics features computed from four‐view mammograms. Medical Physics, 50(12), 7670-7683. https://doi.org/10.1002/mp.16419
Vancouver
Jones MA, Sadeghipour N, Chen X, Islam W, Zheng B. A multi‐stage fusion framework to classify breast lesions using deep learning and radiomics features computed from four‐view mammograms. Medical Physics. 2023;50(12):7670-7683. doi:10.1002/mp.16419
BibTeX
@article{Jones2023,
author = {Jones, Meredith A and Sadeghipour, Negar and Chen, Xuxin and Islam, Warid and Zheng, Bin},
title = {A multi‐stage fusion framework to classify breast lesions using deep learning and radiomics features computed from four‐view mammograms},
journal = {Medical Physics},
year = {2023},
volume = {50},
number = {12},
pages = {7670--7683},
doi = {10.1002/mp.16419}
}
EUVIMED