A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI
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 promisin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/7/12/276 |
| _version_ | 1827671780699930624 |
|---|---|
| author | Antonio Galli Stefano Marrone Gabriele Piantadosi Mario Sansone Carlo Sansone |
| author_facet | Antonio Galli Stefano Marrone Gabriele Piantadosi Mario Sansone Carlo Sansone |
| author_sort | Antonio Galli |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T03:48:36Z |
| format | Article |
| id | doaj.art-3ce221278f124cd393f30c2419a0f754 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T03:48:36Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-3ce221278f124cd393f30c2419a0f7542023-11-23T09:00:52ZengMDPI AGJournal of Imaging2313-433X2021-12-0171227610.3390/jimaging7120276A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRIAntonio Galli0Stefano Marrone1Gabriele Piantadosi2Mario Sansone3Carlo Sansone4Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio 21, 80125 Naples, ItalyDepartment of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio 21, 80125 Naples, ItalyAltran Italia S.p.A., Centro Direzionale, Via Giovanni Porzio, 4, 80143 Naples, ItalyDepartment of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio 21, 80125 Naples, ItalyDepartment of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio 21, 80125 Naples, ItalyThe 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.https://www.mdpi.com/2313-433X/7/12/276breastDCE-MRIeras/epochslesion segmentationUNet3TP |
| spellingShingle | Antonio Galli Stefano Marrone Gabriele Piantadosi Mario Sansone Carlo Sansone A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI Journal of Imaging breast DCE-MRI eras/epochs lesion segmentation UNet 3TP |
| title | A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI |
| title_full | A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI |
| title_fullStr | A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI |
| title_full_unstemmed | A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI |
| title_short | A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI |
| title_sort | pipelined tracer aware approach for lesion segmentation in breast dce mri |
| topic | breast DCE-MRI eras/epochs lesion segmentation UNet 3TP |
| url | https://www.mdpi.com/2313-433X/7/12/276 |
| work_keys_str_mv | AT antoniogalli apipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT stefanomarrone apipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT gabrielepiantadosi apipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT mariosansone apipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT carlosansone apipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT antoniogalli pipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT stefanomarrone pipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT gabrielepiantadosi pipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT mariosansone pipelinedtracerawareapproachforlesionsegmentationinbreastdcemri AT carlosansone pipelinedtracerawareapproachforlesionsegmentationinbreastdcemri |