Automatic needle tracking using Mask R-CNN for MRI-guided percutaneous interventions

Li, Xinzhou; Young, Adam S.; Raman, Steven S.; Lu, David; Lee, Yu‐Hsiu; Tsao, Tsu‐Chin; Wu, Holden H.

doi:10.1007/s11548-020-02226-8

Cited by 16 publications

(22 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It showed that the accuracy of imaging was improved by this algorithm and the processing time was saved, which was beneficial for researchers to obtain objective and true imaging results in a short time. This is consistent with the result that Li et al applied the CNN model to the segmentation of prostate MRI images, which can shorten the labeling time and have a relatively high standard accuracy [ 21 ]. Magnetic resonance examination found that the lateral ventricles of the ventricles of some children were significantly enlarged, there were obvious perivascular spaces, accompanied by cribriform signs of deep white matter around the ventricles, hemangioma was faintly visible, and the abnormal signal foci were prominent.…”

Section: Discussionsupporting

confidence: 90%

Tic Disorder of Children Analyzed and Diagnosed by Magnetic Resonance Imaging Features under Convolutional Neural Network

et al. 2021

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

This work aimed to explore the analysis and diagnosis of children with tic disorder by magnetic resonance imaging (MRI) features under convolutional neural network (CNN), to provide a certain reference basis for clinical identification. A total of 45 children diagnosed with tic disorder in hospital from January 2018 to June 2020 were selected as the research subjects. A total of 30 normal children were selected as the control group. MRI images were collected, and CNN was constructed for image processing. The results showed that the convolutional neural network could significantly improve the speed of MRI reconstruction and can improve the diagnostic accuracy. Compared with normal children, the metabolites in children with tic disorder were slightly increased, but there was no statistical significance P > 0.05 . The results of the Yale score showed that the proportion of children with moderate illness was significantly greater than that of children with mild and severe illness. In short, the pathological changes of tic disorder were effectively discovered by MRI based on CNN algorithms, which can provide a reference for clinical identification.

show abstract

Section: Discussionsupporting

confidence: 90%

Tic Disorder of Children Analyzed and Diagnosed by Magnetic Resonance Imaging Features under Convolutional Neural Network

et al. 2021

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

show abstract

“…Reduced artifact levels should also improve the performance of needle tip detection using traditional and more recent deep-learning based image processing techniques. [54][55][56] For example, in Figure 5C, the orientation of the bevel becomes apparent after shimming, which could be further elucidated by image processing.…”

Section: Discussionmentioning

confidence: 99%

Modeling of active shimming of metallic needles for interventional MRI

Sengupta

2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose Artifacts caused by large magnetic susceptibility differences between metallic needles and tissue are a persistent problem in many interventional MRI applications. The signal void caused by the needle can hide procedure targets and prevent accurate image‐based monitoring. In this paper, a solution to this problem is presented in the form of an active shim insert inspired from degaussing coils used in naval vessels, that is designed to correct the field disturbance (ΔB0) caused by the needle. Methods The ΔB0 induced by a 10 gauge hollow single‐beveled titanium needle at 3T is modeled in different orientations. A set of 63 orthogonal coil pairs with unique tip paths are evaluated for shimming performance, and an optimal coil pair is chosen. Shimming performance and current demands are evaluated over a range of needle orientations. Results Robust correction of the titanium needle induced ΔB0 is predicted using a flat no‐loop coil combined with an orthogonal 1½ turn loop coil angled at the bevel angle for most orientations, with currents well below 1 amp per coil. Reductions in ΔB0 standard deviations with shimming ranged from ~49% to ~10% depending on needle orientation, with performance worsening as the needle is aligned more along B0. Conclusion Simulations predict that it is possible to minimize metallic probe induced ΔB0 and signal losses using externally supplied direct current shim coil inserts in arbitrary orientations for potential benefits in many interventional MRI applications.

show abstract

“…In addition, the IoU level of auto-segmentation in this study was lower than that of auto-segmentation using MRI or ultrasonography in previous studies. [ 19 , 20 ] This is inevitable because the spatial resolution of fluoroscopy images is lower than that of MR or ultrasound images, which results in the lower contrast of the object in VFSS. In addition, we used the VFSS videoclips with 640 × 480 pixels in this study and, therefore, the boundaries of the structures in the VFSS frame were unclear.…”

Section: Discussionmentioning

confidence: 99%

“…Recent studies have used Mask R-CNN for automatic needle localization during ultrasound-guided prostate brachytherapy and automatic needle tracking during MRI-guided intervention. [ 18 , 19 ] A study used Mask R-CNN for automated thyroid nodule detection in ultrasonography. [ 20 ]…”

Section: Introductionmentioning

confidence: 99%

Measurement of laryngeal elevation by automated segmentation using Mask R-CNN

Lee

Kwon

Yang³

et al. 2021

Medicine

View full text Add to dashboard Cite

The methods of measuring laryngeal elevation during swallowing are time-consuming. We aimed to propose a quick-to-use neural network (NN) model for measuring laryngeal elevation quantitatively using anatomical structures auto-segmented by Mask region-based convolutional NN (R-CNN) in videofluoroscopic swallowing study. Twelve videofluoroscopic swallowing study video clips were collected. One researcher drew the anatomical structure, including the thyroid cartilage and vocal fold complex (TVC) on respective video frames. The dataset was split into 11 videos (4686 frames) for model development and one video (532 frames) for derived model testing. The validity of the trained model was evaluated using the intersection over the union. The mean intersections over union of the C1 spinous process and TVC were 0.73 ± 0.07 [0–0.88] and 0.43 ± 0.19 [0–0.79], respectively. The recall rates for the auto-segmentation of the TVC and C1 spinous process by the Mask R-CNN were 86.8% and 99.8%, respectively. Actual displacement of the larynx was calculated using the midpoint of the auto-segmented TVC and C1 spinous process and diagonal lengths of the C3 and C4 vertebral bodies on magnetic resonance imaging, which measured 35.1 mm. Mask R-CNN segmented the TVC with high accuracy. The proposed method measures laryngeal elevation using the midpoint of the TVC and C1 spinous process, auto-segmented by Mask R-CNN. Mask R-CNN auto-segmented the TVC with considerably high accuracy. Therefore, we can expect that the proposed method will quantitatively and quickly determine laryngeal elevation in clinical settings.

show abstract

Automatic needle tracking using Mask R-CNN for MRI-guided percutaneous interventions

Cited by 16 publications

References 34 publications

Tic Disorder of Children Analyzed and Diagnosed by Magnetic Resonance Imaging Features under Convolutional Neural Network

Tic Disorder of Children Analyzed and Diagnosed by Magnetic Resonance Imaging Features under Convolutional Neural Network

Modeling of active shimming of metallic needles for interventional MRI

Measurement of laryngeal elevation by automated segmentation using Mask R-CNN

Contact Info

Product

Resources

About