Prof. Mark G. Luciano Profile

Prof. Mark G. Luciano

at Johns Hopkins Univ School of Medicine

SPIE Involvement:

Author

Publications (11)

Proceedings Article | 2 April 2024 Poster + Paper

Deep-learning-based segmentation of hydrocephalus brain ventricle from ultrasound

Yuli Wang, Yihao Liu, Shuwen Wei, Yuan Xue, Lianrui Zuo, Samuel Remedios, Zhangxing Bian, Michael Meggyesy, Jheesoo Ahn, Ryan Lee, Mark Luciano, Jerry Prince, Aaron Carass

Proceedings Volume 12926, 1292639 (2024) https://doi.org/10.1117/12.3007668

KEYWORDS: Ultrasonography, Image segmentation, Brain, Neuroimaging, Deep learning, Video, Magnetic resonance imaging, Education and training, Computed tomography, Convolution

Read Abstract +

Proceedings Article | 1 April 2024 Presentation + Paper

One-shot estimation of epistemic uncertainty in deep learning image formation with application to high-quality cone-beam CT reconstruction

Stephen Liu, Prasad Vagdargi, Craig Jones, Mark Luciano, William Anderson, Patrick Helm, Ali Uneri, Jeffrey Siewerdsen, Wojciech Zbijewski, Alejandro Sisniega

Proceedings Volume 12925, 129251E (2024) https://doi.org/10.1117/12.3006934

KEYWORDS: Medical image reconstruction, Cone beam computed tomography, Education and training, Deep learning, Brain, Computed tomography, Error analysis, Data modeling, 3D modeling, Monte Carlo methods

Read Abstract +

Deep Learning (DL) image synthesis has gained increasing popularity for the reconstruction of CT and cone-beam CT (CBCT) images, especially in combination with physically-principled reconstruction algorithms. However, DL synthesis is challenged by the generalizability of training data and noise in the trained model. Epistemic uncertainty has proven as an efficient way of quantifying erroneous synthesis in the presence of out-of-domain features, but its estimation with Monte Carlo (MC) dropout requires a large number of inference runs, variable as a function of the particular uncertain feature. We propose a single-pass method–the Moment Propagation Model–which approximates the MC dropout by analytically propagating the statistical moments through the network layers, removing the need for multiple inferences and removing errors in estimations from insufficient dropout realizations. The proposed approach jointly computes the change of the expectation and the variance of the input (first two statistical moments) through each network layer, where each moment undergoes a different numerical transformation. The expectation is initialized as the network input; the variance is solely introduced at dropout layers, modeled as a Bernoulli process. The method was evaluated using a 3D Bayesian conditional generative adversarial network (GAN) for synthesis of high-quality head MDCT from low-quality intraoperative CBCT reconstructions. 20 pairs of measured MDCT volumes (120kV, 400 to 550mAs) depicting normal head anatomy, and simulated CBCT volumes (100 to120kV, 32 to 200mAs) were used for training. Scatter, beam-hardening, detector lag and glare were added to the simulated CBCT and were corrected (assuming unknown) prior to reconstruction. Epistemic uncertainty was estimated for 30 heads (outside of the training set) containing simulated brain lesions using the proposed single-pass propagation model, and results were compared to the standard 200-pass dropout approach. Image quality and quantitative accuracy of the estimated uncertainty of lesions and other anatomical sites were further evaluated. The proposed propagation model captured >2HU increase in epistemic uncertainty caused by various hyper- and hypo-density lesions, with <0.31HU error over the brain compared to the reference MC dropout result at 200 inferences and <0.1HU difference to a converged MC dropout estimate at 100 inference passes. These findings indicate a potential 100-fold increase in computational efficiency of neural network uncertainty estimation. The proposed moment propagation model is able to achieve accurate quantification of epistemic uncertainty in a single network pass and is an efficient alternative to conventional MC dropout.

Proceedings Article | 29 March 2024 Presentation + Paper

End-to-end 3D neuroendoscopic video reconstruction for robot-assisted ventriculostomy

P. Vagdargi, A. Uneri, S. Liu, C. Jones, A. Sisniega, J. Lee, P. Helm, W. Anderson, M. Luciano, G. Hager, J. Siewerdsen

Proceedings Volume 12928, 129280M (2024) https://doi.org/10.1117/12.3008758

KEYWORDS: Video, Education and training, Deformation, 3D acquisition, Voxels, 3D image processing, Imaging systems, Endoscopy, 3D image reconstruction, Visualization

Read Abstract +

Proceedings Article | 3 April 2023 Presentation + Paper

Real-time 3D neuroendoscopic guidance using SLAM: first clinical studies

P. Vagdargi, A. Uneri, C. Jones, X. Zhang, P. Wu, R. Han, A. Sisniega, J. Lee, P. Helm, M. Luciano, W. Anderson, G. Hager, J. Siewerdsen

Proceedings Volume 12466, 1246604 (2023) https://doi.org/10.1117/12.2654595

KEYWORDS: Calibration, Distortion, Deformation, Video, Cameras, Point clouds, Endoscopy, Visualization, Neurosurgery, Vision based navigation, Navigation systems

Read Abstract +

Neurosurgical techniques often require accurate targeting of deep-brain structures even in the presence of deformation due intervention and egress of Cerebrospinal Fluid (CSF) during surgical access. Prior work reported Simultaneous Localization and Mapping (SLAM) methods for endoscopic guidance using 3D reconstruction. In this work, methods for correcting the geometric distortion of a neuroendoscope are reported in a form that have been translated intraoperative use in first clinical studies. Furthermore, SLAM methods are evaluated in first clinical studies for real-time 3D endoscopic navigation with near real-time registration in the presence of deep-brain tissue deformation. A custom calibration jig with swivel mounts was designed and manufactured for neuroendoscope calibration in the operating room. The process is potentially suitable to intraoperative use while maintaining sterility of the endoscope, although the current calibration system was used in the Operating Room (OR) immediately following the case for offline analysis. A six by seven checkerboard pattern was used to obtain corner locations for calibration, and the method was evaluated in terms of Reprojection Error (RPE). Neuroendoscopic video was acquired under an IRB-approved clinical study, demonstrating rich vascular features and other structures on the interior walls of the lateral ventricles for 3D point-cloud reconstruction. Geometric accuracy was evaluated in terms of Projected Error (PE) on a ground truth surface defined from MR or cone-beam CT (CBCT) images. Intraoperative neuroendoscope calibration was achieved with sub-pixel [0.61 ± 0.20 px] error. The calibration yielded a focal length of 816.42 px and 822.71 px in X and Y directions respectively, along with radial distortion coefficients of -0.432 (first order term [𝑘1]) and 0.158 (second order term [𝑘2]). The 3D reconstruction was performed successfully with a PE of 0.23 ± 0.15 mm compared to the ground truth surface. The system for neuroendoscopic guidance based on SLAM 3D point-cloud reconstruction provided a promising platform for the development of 3D neuroendoscopy. The studies reported in this work presented an important means of neuroendoscope calibration in the OR and provided preliminary evidence for accurate 3D video reconstruction in first clinical studies. Future work aims to further extend the clinical evaluation and improve reconstruction accuracy using ventricular shape priors.

Proceedings Article | 3 April 2023 Poster + Paper

Investigation of probability maps in deep-learning-based brain ventricle parcellation

Yuli Wang, Anqi Feng, Yuan Xue, Muhan Shao, Ari Blitz, Mark Luciano, Aaron Carass, Jerry Prince

Proceedings Volume 12464, 124642G (2023) https://doi.org/10.1117/12.2653999

KEYWORDS: Image segmentation, Magnetic resonance imaging, Brain mapping, Brain, Binary data, Voxels, Medicine, Image processing algorithms and systems

Read Abstract +

Proceedings Article | 4 April 2022 Paper

Deformable registration of MRI to intraoperative cone-beam CT of the brain using a joint synthesis and registration network

R. Han, C. Jones, P. Wu, P. Vagdargi, X. Zhang, A. Uneri, J. Lee, M. Luciano, W. Anderson, P. Helm, J. Siewerdsen

Proceedings Volume 12034, 1203407 (2022) https://doi.org/10.1117/12.2611783

KEYWORDS: Image registration, Magnetic resonance imaging, Brain

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Robot-assisted neuroendoscopy for real-time 3D guidance of transventricular approach to deep-brain targets

P. Vagdargi, A. Uneri, C. Jones, P. Wu, R. Han, M. Luciano, W. Anderson, P. Helm, G. Hager, J. Siewerdsen

Proceedings Volume 12034, 120340E (2022) https://doi.org/10.1117/12.2613231

KEYWORDS: Cameras, 3D acquisition, Endoscopy, Video, Imaging systems, Visualization, 3D modeling, Navigation systems, Image filtering, Augmented reality, Computer vision technology

Read Abstract +

Purpose: Recent neurosurgical techniques require accurate targeting of deep-brain structures even in the presence of deformation due to egress of cerebrospinal fluid (CSF) during surgical access. Prior work reported Structure-from-Motion (SfM) based methods for endoscopic guidance using 3D reconstruction. We are developing feature detection and description methods for a real-time 3D endoscopic navigation system using simultaneous localization and mapping (SLAM) to for accurate and near real-time registration. Methods: Feature detectors and descriptors were evaluated in SLAM reconstruction in anthropomorphic phantom studies emulating neuroendoscopy. The experimental system utilized a mobile UR3e robot (Universal Robots, Denmark) and ventriculoscope (Karl Storz, Tuttlingen, Germany) affixed to the end effector as a repeatable ventriculoscopy platform. Experiments were conducted to quantify optimal feature detection parameters in scale-space. Neuroendoscopic images acquired in traversal of the lateral and third ventricles provided a rich feature space of vessels and other structures on ventricular walls supporting feature detection and 3D point-cloud reconstruction. Performance was evaluated in terms of the mean number of features detected per frame and the algorithm runtime. Results: Parameter search in scale-space for feature detection demonstrated the dependence on the mean number of features per image and the points of diminishing return in parameter selection (e.g., the number of octaves and scale levels) and tradeoffs in runtime. Nominal parameters were identified as 3 octaves and 9 scale levels, with a mean number of features detected as 492 and 806 respectively. Conclusions: The system for neuroendoscopic guidance based on SLAM 3D point-cloud reconstruction provided a promising platform for the development of robot-assisted endoscopic neurosurgery. The studies reported in this work provided an essential basis for rigorous selection of parameters for feature detection. Future work aims to further develop the SLAM framework, assess the geometric accuracy of reconstruction, and translate methods to clinical studies.

Proceedings Article | 23 February 2021 Presentation + Paper

Robot-assisted ventriculoscopic 3D reconstruction for guidance of deep-brain stimulation surgery

P. Vagdargi, A. Uneri, C. Jones, P. Wu, R. Han, M. Luciano, W. Anderson, G. Hager, J. Siewerdsen

Proceedings Volume 11598, 1159809 (2021) https://doi.org/10.1117/12.2582173

KEYWORDS: 3D modeling, Surgery, Calibration, Robotic systems, Imaging systems, Clouds, Cameras, Video, Image restoration, Image registration

Read Abstract +

Proceedings Article | 23 February 2021 Presentation + Paper

Data-driven deformable 3D-2D registration for guiding neuroelectrode placement in deep brain stimulation

A. Uneri, P. Wu, C. Jones, M. Ketcha, P. Vagdargi, R. Han, P. Helm, M. Luciano, W. Anderson, J. Siewerdsen

Proceedings Volume 11598, 115981B (2021) https://doi.org/10.1117/12.2582160

KEYWORDS: Brain stimulation, 3D modeling, Image registration, Model-based design, X-rays, Radiography, Performance modeling, Neural networks, Metals, Instrument modeling

Read Abstract +

Proceedings Article | 23 February 2021 Presentation + Paper

Deformable MR-CT image registration using an unsupervised synthesis and registration network for neuro-endoscopic surgery

R. Han, C. Jones, M. Ketcha, P. Wu, P. Vagdargi, A. Uneri, J. Lee, M. Luciano, W. Anderson, J. Siewerdsen

Proceedings Volume 11598, 1159819 (2021) https://doi.org/10.1117/12.2581567

KEYWORDS: Image registration, Endoscopy, Computed tomography, Magnetic resonance imaging, Brain, 3D image processing, Surgery, Neural networks, Computer simulations

Read Abstract +

Purpose: Deep-brain stimulation via neuro-endoscopic surgery is a challenging procedure that requires accurate targeting of deep-brain structures that can undergo deformations (up to 10 mm). Conventional deformable registration methods have the potential to resolve such geometric error between preoperative MR and intraoperative CT but at the expense of long computation time. New advances in deep learning methods offer benefits to inter-modality image registration accuracy and runtime using novel similarity metrics and network architectures. Method: An unsupervised deformable registration network is reported that first generates a synthetic CT from MR using CycleGAN and then registers the synthetic CT to the intraoperative CT using an inverse-consistent registration network. Diffeomorphism of the registration is maintained using deformation exponentiation “squaring and scaling” layers. The method was trained and tested on a dataset of CT and T1-weighted MR images with randomly simulated deformations that mimic deep-brain deformation during surgery. The method was compared to a baseline method using inter-modality deep learning registration, VoxelMorph. Results: The methods were tested on 10 pairs of CT/MR images from 5 subjects. The proposed method achieved a Dice score of 0.84±0.04 for the lateral ventricles, 0.72±0.09 for the 3^rd ventricle, and 0.63±0.10 for the 4^th ventricle, with target registration error (TRE) of 0.95±0.54 mm. The proposed method showed statistically significant improvement in both Dice score and TRE in comparison to inter-modality VoxelMorph, while maintaining a fast runtime of less than 3 seconds for a typical MR-CT pair of volume images. Conclusion: The proposed unsupervised image synthesis and registration network demonstrates the capability for accurate volumetric deformable MR-CT registration with near real-time performance. The method will be further developed for application in intraoperative CT (or cone-beam CT) guided neurosurgery.

Proceedings Article | 22 February 2021 Presentation + Paper

Cone-beam CT for neurosurgical guidance: high-fidelity artifacts correction for soft-tissue contrast resolution

P. Wu, A. Sisniega, A. Uneri, R. Han, M. Ketcha, C. Jones, P. Vagdargi, X. Zhang, M. Luciano, W. Anderson, J. Siewerdsen

Proceedings Volume 11595, 115950X (2021) https://doi.org/10.1117/12.2581686

KEYWORDS: Metals, Visualization, Quantum electronics, Image resolution, Image quality, Magnetic resonance imaging, Head, Convolutional neural networks, Bone

Read Abstract +

Purpose: Intraoperative cone-beam CT (CBCT) plays an important role in neurosurgical guidance but is conventionally limited to high-contrast bone visualization. This work reports a high-fidelity artifacts correction pipeline to advance image quality beyond conventional limits and achieve soft-tissue contrast resolution even in the presence of multiple metal objects – specifically, a stereotactic head frame. Methods: A new metal artifact reduction (MAR) method was developed based on a convolutional neural network (CNN) that simultaneously estimates metal-induced bias and metal path length in the projection domain. To improve generalizability of the network, a physics-based method was developed to generate highly accurate simulated, metalcontaminated projection training data. The MAR method was integrated with previously proposed artifacts correction methods (lag, glare, scatter, and beam-hardening) to form a high-fidelity artifacts correction pipeline. The proposed methods were tested using an intraoperative CBCT system (O-arm, Medtronic) emulating a realistic setup in stereotactic neurosurgery, including nominal (20 cm) and extended (40 cm) field of view (FOV) protocols. Results: The physics-based data generation method provided accurate simulation of metal in projection data, including scatter, polyenergetic, quantum noise, and electronic noise effects. The artifacts correction pipeline was able to accommodate both 20 cm and 40 cm FOV protocols and demonstrated ~80% improvement in image uniformity and ~20% increase in contrast-to-noise ratio (CNR). Fully corrected images in the smaller FOV mode exhibited ~32% increase in CNR compared to the 40 cm FOV mode, showing the method’s ability to handle truncated metal objects outside the FOV. Conclusion: The image quality of intraoperative CBCT was greatly improved with the proposed artifacts correction pipeline, with clear improvement in soft-tissue contrast resolution (e.g., cerebral ventricles) even in the presence of a complex metal stereotactic frame. Such capability gives clearer visualization of structures of interest for intracranial neurosurgery, and it provides an important basis for future work aiming to deformably register preoperative MRI to intraoperative CBCT. Ongoing work includes clinical studies now underway.

Showing 5 of 11 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years