Localization of the Locus Coeruleus in MRI via Coordinate Regression

Dünnwald, Max; Betts, Matthew J.; Düzel, Emrah; Oeltze-Jafra, Steffen

doi:10.1007/978-3-658-33198-6_5

Cited by 3 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The iterative multi-scale approach toward LC localization outperformed our previously published method [8] signifi- The multi-rater trainings showed several interesting effects. Mostly, the LC segmentation performance was on the same level as the inter-rater agreement, which is arguably the sensible upper limit as further agreement with a single rater would suggest overfitting to this particular rater's delineation style.…”

Section: Discussionmentioning

confidence: 85%

“…To the best of our knowledge, our previous work that explored the use of a 3D-Unet [6] variant for this task [9] as well as a preceding coordinate regression-based localization [8] are the only publications to date to investigate deep learning-based methods in segmenting the LC. However, for the Substantia Nigra, which can be visualized using the same MRI acquisitions, there are a few publications that make use of deep learning-based approaches, most notably [16] and [23].…”

Section: Related Workmentioning

confidence: 99%

“…We used two different datasets: one dataset comprising healthy aging subjects [2,8], which was used for the development, training and evaluation of the method as well as one comprising PD subjects, that was used merely for evaluation. The healthy aging dataset (HAD) comprises data of 82 subjects, of which 25 are younger (22-30 years old; 13 male, 12 female) and 57 are older healthy adults (61-80 years; 19 male, 38 female).…”

Section: Datasetsmentioning

confidence: 99%

“…As described in previous work [8], we use a preceding localization network, which regresses the center of mass of the LC. This allows focusing just on the nucleus itself and its vicinity for the following processes and reduces the amount of false positives.…”

Section: Iterative Multi-scale Localization Of the Lcmentioning

confidence: 99%

“…This work offers four contributions to this field. First, we propose a novel iterative, multi-scale strategy for the LC localization network, which is significantly more precise, requires less graphics processing unit (GPU) memory and less training time than our previously published method [8]. Secondly, we investigate the usage and advantages of the availability of multiple raters.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fully automated deep learning-based localization and segmentation of the locus coeruleus in aging and Parkinson’s disease using neuromelanin-sensitive MRI

Dünnwald

Ernst²,

Düzel

et al. 2021

Int J CARS

Self Cite

View full text Add to dashboard Cite

Purpose Development and performance measurement of a fully automated pipeline that localizes and segments the locus coeruleus in so-called neuromelanin-sensitive magnetic resonance imaging data for the derivation of quantitative biomarkers of neurodegenerative diseases such as Alzheimer’s disease and Parkinson’s disease. Methods We propose a pipeline composed of several 3D-Unet-based convolutional neural networks for iterative multi-scale localization and multi-rater segmentation and non-deep learning-based components for automated biomarker extraction. We trained on the healthy aging cohort and did not carry out any adaption or fine-tuning prior to the application to Parkinson’s disease subjects. Results The localization and segmentation pipeline demonstrated sufficient performance as measured by Euclidean distance (on average around 1.3mm on healthy aging subjects and 2.2mm in Parkinson’s disease subjects) and Dice similarity coefficient (overall around $$71\%$$ 71 % on healthy aging subjects and $$60\%$$ 60 % for subjects with Parkinson’s disease) as well as promising agreement with respect to contrast ratios in terms of intraclass correlation coefficient of $$\ge 0.80$$ ≥ 0.80 for healthy aging subjects compared to a manual segmentation procedure. Lower values ($$\ge 0.48$$ ≥ 0.48 ) for Parkinson’s disease subjects indicate the need for further investigation and tests before the application to clinical samples. Conclusion These promising results suggest the usability of the proposed algorithm for data of healthy aging subjects and pave the way for further investigations using this approach on different clinical datasets to validate its practical usability more conclusively.

show abstract

Section: Discussionmentioning

confidence: 85%

Section: Related Workmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Iterative Multi-scale Localization Of the Lcmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fully automated deep learning-based localization and segmentation of the locus coeruleus in aging and Parkinson’s disease using neuromelanin-sensitive MRI

Dünnwald

Ernst²,

Düzel

et al. 2021

Int J CARS

Self Cite

View full text Add to dashboard Cite

show abstract

Deep Coordinate Regression for Weakly Supervised Segmentation of the Locus Coeruleus in MRI

Dünnwald

Ernst

Düzel

et al. 2023

2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS)

View full text Add to dashboard Cite

A Coordinate-Regression-Based Deep Learning Model for Catheter Detection during Structural Heart Interventions

Aghasizade,

Kiyoumarsioskouei,

Hashemi

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

With a growing geriatric population estimated to triple by 2050, minimally invasive procedures that are image-guided are becoming both more popular and necessary for treating a variety of diseases. To lower the learning curve for new procedures, it is necessary to develop better guidance systems and methods to analyze procedure performance. Since fluoroscopy remains the primary mode of visualizations, the ability to perform catheter tracking from fluoroscopic images is an important part of this endeavor. This paper explores the use of deep learning to perform the landmark detection of a catheter from fluoroscopic images in 3D-printed heart models. We show that a two-stage deep-convolutional-neural-network-based model architecture can provide improved performance by initially locating a region of interest before determining the coordinates of the catheter tip within the image. This model has an average error of less than 2% of the image resolution and can be performed within 4 milliseconds, allowing for its potential use for real-time intraprocedural tracking. Coordinate regression models have the advantage of directly outputting values that can be used for quantitative tracking in future applications and are easier to create ground truth values (~50× faster), as compared to semantic segmentation models that require entire masks to be made. Therefore, we believe this work has better long-term potential to be used for a broader class of cardiac devices, catheters, and guidewires.

show abstract

Localization of the Locus Coeruleus in MRI via Coordinate Regression

Cited by 3 publications

References 8 publications

Fully automated deep learning-based localization and segmentation of the locus coeruleus in aging and Parkinson’s disease using neuromelanin-sensitive MRI

Fully automated deep learning-based localization and segmentation of the locus coeruleus in aging and Parkinson’s disease using neuromelanin-sensitive MRI

Deep Coordinate Regression for Weakly Supervised Segmentation of the Locus Coeruleus in MRI

A Coordinate-Regression-Based Deep Learning Model for Catheter Detection during Structural Heart Interventions

Contact Info

Product

Resources

About