Abstract
The recent spread of Deep Learning (DL) in medical imaging is pushing researchers to explore its suitability for lesion segmentation in Dynamic Contrast-Enhanced Magnetic-Resonance Imaging (DCE-MRI), a complementary imaging procedure increasingly used in breast-cancer analysis. Despite some promising proposed solutions, we argue that a “naive” use of DL may have limited effectiveness as the presence of a contrast agent results in the acquisition of multimodal 4D images requiring thorough processing before training a DL model. We thus propose a pipelined approach where each stage is intended to deal with or to leverage a peculiar characteristic of breast DCE-MRI data: the use of a breast-masking pre-processing to remove non-breast tissues; the use of Three-Time-Points (3TP) slices to effectively highlight contrast agent time course; the application of a motion-correction technique to deal with patient involuntary movements; the leverage of a modified U-Net architecture tailored on the problem; and the introduction of a new “Eras/Epochs” training strategy to handle the unbalanced dataset while performing a strong data augmentation. We compared our pipelined solution against some literature works. The results show that our approach outperforms the competitors by a large margin (+9.13% over our previous solution) while also showing a higher generalization ability.
Highlights
World Cancer Research Fund reports [1] indicate breast cancer as the most common among women, with about 25% of all cancer occurrences
The recent spread of Deep Learning (DL) in medical imaging is pushing researchers to explore its suitability for lesion segmentation in Dynamic Contrast-Enhanced Magnetic-Resonance Imaging (DCE-MRI), a complementary imaging procedure increasingly used in breast-cancer analysis
We propose a pipelined approach where each stage is intended to deal with or to leverage a peculiar characteristic of breast DCEMRI data: the use of a breast-masking pre-processing to remove non-breast tissues; the use of Three-Time-Points (3TP) slices to effectively highlight contrast agent time course; the application of a motion-correction technique to deal with patient involuntary movements; the leverage of a modified U-Shaped Convolutional Neural Network (U-Net) architecture tailored on the problem; and the introduction of a new “Eras/Epochs” training strategy to handle the unbalanced dataset while performing a strong data augmentation
Summary
World Cancer Research Fund reports [1] indicate breast cancer as the most common among women, with about 25% of all cancer occurrences. Early diagnosis represents a key factor for reducing death rates since breast cancer usually develops and spreads unhindered, showing symptoms only in advanced stages [2]. In the last years, researchers are focusing on the use of other imaging techniques, mostly because of (i) mammography’s non-suitability for under-forty women, since density may lead to over-diagnosis, and (ii) because of the use of ionising radiations. Among all medical imaging techniques, Dynamic Contrast-Enhanced Magnetic-Resonance Imaging (DCE-MRI) is showing promising results for the early detection of different types of tumours [4], proving suitable for breast-cancer detection in women with extremely dense breast tissue [5]. Since the CA is a (super)paramagnetic liquid characterised by specific absorption and release times, its spread at different speeds highlights lesions over healthy tissues
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.