Physics-Driven Mask R-CNN for Physical Needle Localization in MRI-Guided Percutaneous Interventions
Discrepancies between the needle feature position on magnetic resonance imaging (MRI) and the underlying physical needle position could increase localization errors during needle-based targeting procedures in MRI-guided percutaneous interventions. This work aimed to develop a deep learning-based fra...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9615046/ |
| _version_ | 1819004312649465856 |
|---|---|
| author | Xinzhou Li Yu-Hsiu Lee David S. Lu Tsu-Chin Tsao Holden H. Wu |
| author_facet | Xinzhou Li Yu-Hsiu Lee David S. Lu Tsu-Chin Tsao Holden H. Wu |
| author_sort | Xinzhou Li |
| collection | DOAJ |
| description | Discrepancies between the needle feature position on magnetic resonance imaging (MRI) and the underlying physical needle position could increase localization errors during needle-based targeting procedures in MRI-guided percutaneous interventions. This work aimed to develop a deep learning-based framework to automatically localize the physical needle position using only the needle features on MR images. Physics-based simulations were performed to generate single-slice and 3-slice images with needle features from a range of underlying needle positions and MRI parameters to form datasets for training single-slice and 3-slice Mask Region-Based Convolutional Neural Network (R-CNN) models for physical needle localization. <italic>Ex vivo</italic> tissue images were combined with simulated needle features for fine-tuning. Next, the physics-driven Mask R-CNN models were combined with a previously developed Mask R-CNN model for needle feature localization to form an automated framework to localize the physical needle. To test the accuracy of the proposed framework, both single-slice and 3-slice MRI data were acquired from needle insertion experiments in <italic>ex vivo</italic> tissue phantoms. Using the single-slice model, the proposed framework achieved sub-millimeter physical needle localization accuracy on single-slice images aligned with the needle. The fine-tuning step reduced in-plane physical needle tip localization error (mean±standard deviation) to 0.96±0.69 mm in <italic>ex vivo</italic> tissue data. The 3-slice model further reduced the through-plane physical needle tip localization error to 2.3±1.1 mm in situations where the imaging plane may be misaligned with the needle. The processing time of the framework using both models was 200 ms per frame. The proposed framework can achieve physical needle localization in real time to support MRI-guided interventions. |
| first_indexed | 2024-12-20T23:34:54Z |
| format | Article |
| id | doaj.art-26af43440f6a4580881e6cf264049597 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T23:34:54Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-26af43440f6a4580881e6cf2640495972022-12-21T19:23:13ZengIEEEIEEE Access2169-35362021-01-01916105516106810.1109/ACCESS.2021.31281639615046Physics-Driven Mask R-CNN for Physical Needle Localization in MRI-Guided Percutaneous InterventionsXinzhou Li0https://orcid.org/0000-0002-4219-9017Yu-Hsiu Lee1https://orcid.org/0000-0003-4363-2051David S. Lu2Tsu-Chin Tsao3https://orcid.org/0000-0003-2087-6221Holden H. Wu4https://orcid.org/0000-0002-2585-5916Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USADepartment of Mechanical and Aerospace Engineering, University of California Los Angeles, Los Angeles, CA, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USADepartment of Mechanical and Aerospace Engineering, University of California Los Angeles, Los Angeles, CA, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USADiscrepancies between the needle feature position on magnetic resonance imaging (MRI) and the underlying physical needle position could increase localization errors during needle-based targeting procedures in MRI-guided percutaneous interventions. This work aimed to develop a deep learning-based framework to automatically localize the physical needle position using only the needle features on MR images. Physics-based simulations were performed to generate single-slice and 3-slice images with needle features from a range of underlying needle positions and MRI parameters to form datasets for training single-slice and 3-slice Mask Region-Based Convolutional Neural Network (R-CNN) models for physical needle localization. <italic>Ex vivo</italic> tissue images were combined with simulated needle features for fine-tuning. Next, the physics-driven Mask R-CNN models were combined with a previously developed Mask R-CNN model for needle feature localization to form an automated framework to localize the physical needle. To test the accuracy of the proposed framework, both single-slice and 3-slice MRI data were acquired from needle insertion experiments in <italic>ex vivo</italic> tissue phantoms. Using the single-slice model, the proposed framework achieved sub-millimeter physical needle localization accuracy on single-slice images aligned with the needle. The fine-tuning step reduced in-plane physical needle tip localization error (mean±standard deviation) to 0.96±0.69 mm in <italic>ex vivo</italic> tissue data. The 3-slice model further reduced the through-plane physical needle tip localization error to 2.3±1.1 mm in situations where the imaging plane may be misaligned with the needle. The processing time of the framework using both models was 200 ms per frame. The proposed framework can achieve physical needle localization in real time to support MRI-guided interventions.https://ieeexplore.ieee.org/document/9615046/Interventional MRIdevice trackingneedle susceptibilitydeep learningconvolutional neural network |
| spellingShingle | Xinzhou Li Yu-Hsiu Lee David S. Lu Tsu-Chin Tsao Holden H. Wu Physics-Driven Mask R-CNN for Physical Needle Localization in MRI-Guided Percutaneous Interventions IEEE Access Interventional MRI device tracking needle susceptibility deep learning convolutional neural network |
| title | Physics-Driven Mask R-CNN for Physical Needle Localization in MRI-Guided Percutaneous Interventions |
| title_full | Physics-Driven Mask R-CNN for Physical Needle Localization in MRI-Guided Percutaneous Interventions |
| title_fullStr | Physics-Driven Mask R-CNN for Physical Needle Localization in MRI-Guided Percutaneous Interventions |
| title_full_unstemmed | Physics-Driven Mask R-CNN for Physical Needle Localization in MRI-Guided Percutaneous Interventions |
| title_short | Physics-Driven Mask R-CNN for Physical Needle Localization in MRI-Guided Percutaneous Interventions |
| title_sort | physics driven mask r cnn for physical needle localization in mri guided percutaneous interventions |
| topic | Interventional MRI device tracking needle susceptibility deep learning convolutional neural network |
| url | https://ieeexplore.ieee.org/document/9615046/ |
| work_keys_str_mv | AT xinzhouli physicsdrivenmaskrcnnforphysicalneedlelocalizationinmriguidedpercutaneousinterventions AT yuhsiulee physicsdrivenmaskrcnnforphysicalneedlelocalizationinmriguidedpercutaneousinterventions AT davidslu physicsdrivenmaskrcnnforphysicalneedlelocalizationinmriguidedpercutaneousinterventions AT tsuchintsao physicsdrivenmaskrcnnforphysicalneedlelocalizationinmriguidedpercutaneousinterventions AT holdenhwu physicsdrivenmaskrcnnforphysicalneedlelocalizationinmriguidedpercutaneousinterventions |