Resume

• 2019

  Association for Computing Machinery

• 2014

  MICCAI Society

  English

  Japanese

  NSF CAREER Award

  NSF Award #1553436\n\nThe CAREER award is the National Science Foundation's most prestigious award in support of junior faculty who exhibit exceptional skill across both research and educational activities. The award comes with a $500K federal research grant for five consecutive years. The review

  award

  and selection process is one of the most competitive within the National Science Foundation.

  National Science Foundation (Division of Advanced Cyberinfrastructure)

  NSF Grant: Software Infrastructure for Sustained Innovation

  NSF Award #1642380\n\nThis award targets small groups that will create and deploy robust software elements for which there is a demonstrated national need; these elements will in turn advance one or more significant areas of science and engineering. It is expected that the created software elements will be designed so as to demonstrate potential for addressing issues of sustainability

  manageability

  usability and interoperability

  and will be disseminated into the community as reusable software resources. The development approach may support the hardening of early prototypes and/or expanding functionality to increase end user relevance.

  National Science Foundation (Division of Advanced Cyberinfrastructure)

  NSF Grant: Real Time Machine Learning

  NSF Award #1937419\n\nThis award targets a grand challenge in computing: the creation of machines that can proactively interpret and learn from data in real time

  solve unfamiliar problems using what they have learned

  and operate with the energy efficiency of the human brain. The National Science Foundation (NSF) and the Defense Advanced Research Projects Agency (DARPA) are teaming up through this Real-Time Machine Learning (RTML) program to explore high-performance

  energy-efficient hardware and machine-learning architectures that can learn from a continuous stream of new data in real time

  through opportunities for post-award collaboration between researchers supported by DARPA and NSF.

  National Science Foundation / DARPA

  Harry C. Bartels Endowed Faculty Engineering Development Award

  The support from this fund is presented to a promising junior faculty member with the goal of enhancing the ability of the recipient to present at scholarly meetings and conferences and to enrich teaching and research opportunities of the recipient.

  Office of the Dean

  College of Engineering

  Drexel University

  Drexel University

  Doctor of Philosophy (Ph.D.)

  Electrical and Computer Engineering

  (Instructor) Embedded Systems

  (Instructor) Systems Programming

  (Instructor) Digital Logic

  (Instructor) Performance Analysis of Computer Networks

  (Instructor) Design with Microcontrollers

  (Instructor) Principles of Computer Networking

  (Instructor) Advanced Programming for Engineers

  (Instructor) Programming for Engineers

• Algorithms

  CUDA

  Research

  High Performance Computing

  OpenMP

  Radiation Therapy

  Python

  Simulations

  CMake

  Image Processing

  University Teaching

  Medical Imaging

  Public Speaking

  Computer Vision

  GNU/Linux

  LaTeX

  C++

  Linux Kernel

  Signal Processing

  C

  An Octree Based Approach to Multi-Grid B-spline Registration

  In this paper we propose a new strategy for the recovery of complex anatomical deformations that exhibit local discontinuities

  such as the shearing found at the lung-ribcage interface

  using multi-grid octree B-splines. B- spline based image registration is widely used in the recovery of respiration induced deformations between CT images. However

  the continuity imposed upon the computed deformation field by the parametrizing cubic B- spline basis function results in an inability to correctly capture discontinuities such as the sliding motion at organ boundaries. The proposed technique efficiently captures deformation within and at organ boundaries without the need for prior knowledge

  such as segmentation

  by selectively increasing deformation freedom within image regions exhibiting poor local registration. Experimental results show that the proposed method achieves more physically plausible deformations than traditional global B-spline methods.

  An Octree Based Approach to Multi-Grid B-spline Registration

  Allan Pack

  Daniel Brady

  Diane Lim

  Journal of Applied Physiology

  Recent studies have shown an association between Obstructive Sleep Apnea (OSA) and cognitive impairment. This study was done to investigate whether varied levels of cyclical intermittent hypoxia (CIH) differentially affect the microvasculature in the hippocampus

  operating as a mechanistic link between OSA and cognitive impairment. We exposed C57BL/6 mice to Sham (continuous air

  SaO2 97%)

  Severe CIH to FiO2 = 0.10 (CIH10; SaO2 nadir of 61%) or Very Severe CIH to FiO2 = 0.05 (CIH5; SaO2 nadir of 37%) for 12 hrs/day for 2 weeks. We quantified capillary length using neurostereology techniques in the dorsal hippocampus

  and utilized qPCR methods to measure changes in sets of genes related to angiogenesis and to metabolism. Next

  we employed Immunohistochemistry Semi-Quantification (ISQ) algorithms to quantitate GLUT1 protein on endothelial cells within hippocampal capillaries. Capillary length differed among CIH severity groups (p=0.013) and demonstrated a linear relationship with CIH severity (p=0.002). There was a strong association between CIH severity and changes in mRNA for VEGFA (p<0.0001). Less strong

  but nominally significant associations with CIH severity were also observed for ANGPT2 (pANOVA=0.065

  pTREND=0.040)

  VEGFR2 (pANOVA=0.032

  pTREND=0.429) and TIE2 (pANOVA=0.006

  pTREND=0.010). We found that the CIH5 group had increased GLUT1 protein relative to Sham (p=0.006) and CIH10 (p=0.001). There was variation in GLUT1 protein along the microvasculature in different hippocampal subregions. An effect of CIH5 on GLUT1 mRNA was seen (pANOVA=0.042

  pTREND=0.012). Thus

  CIH affects the microvasculature in the hippocampus

  but consequences depend on CIH severity.

  Different Cyclical Intermittent Hypoxia Severities have Different Effects on Hippocampal Microvasculature

  Greg Sharp

  Nagarajan Kandasamy

  This paper makes two contributions towards accelerating B-spline-based registration. First

  we propose a grid-alignment scheme and associated data structures that greatly reduce the complexity of the registration algorithm. Based on this grid-alignment scheme

  we then develop highly data parallel designs for B-spline registration within the stream-processing model

  suitable for implementation on multi-core processors such as graphics processing units (GPUs).

  On developing B-spline registration algorithms for multi-core processors

  Grep Sharp

  Nagarajan Kandasamy

  This chapter shows how to develop a B-spline-based deformable registration algorithm within the single instruction multiple thread (SIMT) model to effectively leverage the large number of processing cores available in modern GPUs. We focus on improving processing speed without sacrificing quality to make the use of deformable registration more viable within the medical community.

  GPU Computing Gems: Emerald Edition - Chapter 47

  Greg Sharp

  Justin Phillips

  Physics in Medicine and Biology

  While four-dimensional computed tomography (4DCT) and deformable registration can be used to assess the dose delivered to regularly moving targets

  there are few methods available for irregularly moving targets. 4DCT captures an idealized waveform

  but human respiration during treatment is characterized by gradual baseline shifts and other deviations from a periodic signal. This paper describes a method for computing the dose delivered to irregularly moving targets based on 1D or 3D waveforms captured at the time of delivery.

  Computing proton dose to irregularly moving targets

  In this paper

  we present a model to obtain prior knowledge for organ localization in CT thorax images using three dimensional convolutional neural networks (3D CNNs). Specifically

  we use the knowledge obtained from CNNs in a Bayesian detector to establish the presence and location of a given target organ defined within a spherical coordinate system. We train a CNN to perform a soft detection of the target organ potentially present at any point

  x = [r

  θ

  φ] | . This probability outcome is used as a prior in a Bayesian model whose posterior probability serves to provide a more accurate solution to the target organ detection problem. The likelihoods for the Bayesian model are obtained by performing a spatial analysis of the organs in annotated training volumes. Thoracic CT images from the NSCLC–Radiomics dataset are used in our case study

  which demonstrates the enhancement in robustness and accuracy of organ identification. The average value of the detector accuracies for the right lung

  left lung

  and heart were found to be 94.87%

  95.37%

  and 90.76% after the CNN stage

  respectively. Introduction of spatial relationship using a Bayes classifier improved the detector accuracies to 95.14%

  96.20%

  and 95.15%

  respectively

  showing a marked improvement in heart detection. This workflow improves the detection rate since the decision is made employing both lower level features (edges

  contour etc) and complex higher level features (spatial relationship between organs). This strategy also presents a new application to CNNs and a novel methodology to introduce higher level context features like spatial relationship between objects present at a different location in images to real world object detection problems.

  Organ Localization and Identification in Thoracic CT Volumes Using 3D CNNs Leveraging Spatial Anatomic Relations

  Allan Pack

  Brendan Keenan

  Diane Lim

  In this paper

  we present an objective method for localization of proteins in blood brain barrier (BBB) vasculature using standard immunohistochemistry (IHC) techniques and bright-field microscopy. Images from the hippocampal region at the BBB are acquired using bright-field microscopy and subjected to our segmentation pipeline which is designed to automatically identify and segment microvessels containing the protein glucose transporter 1 (GLUT1). Gabor filtering and k-means clustering are employed to isolate potential vascular structures within cryosectioned slabs of the hippocampus

  which are subsequently subjected to feature extraction followed by classification via decision forest. The false positive rate (FPR) of microvessel classification is characterized using synthetic and non-synthetic IHC image data for image entropies ranging between 3 and 8 bits. The average FPR for synthetic and non-synthetic IHC image data was found to be 5.48% and 5.04%

  respectively.

  Automated Protein Localization of Blood Brain Barrier Vasculature in Brightfield IHC Images

  Nagarajan Kandasamy

  Greg Sharp

  This book develops highly data-parallel image registration algorithms suitable for use on modern multicore architectures -- including graphics processing units (GPUs). Focusing on deformable registration

  we show how to develop registration algorithms suitable for massively data parallel execution.

  High Performance Deformable Image Registration Algorithms for Manycore Processors

  Greg Sharp

  Nagarajan Kandasamy

  Nadya Shusharina

  Qi Yang

  In this paper

  we develop an exact analytic method for computing the bending energy of a three-dimensional B-spline deformation field as a quadratic matrix operation on the spline coefficient values. Results presented on ten thoracic case studies indicate the analytic solution is between 61–1371x faster than a numerical central differencing solution.

  Analytic Regularization of Uniform Cubic B-spline Deformation Fields

  Traditional single-grid and pyramidal B-spline parameterizations used in deformable image registration require users to specify control point spacing configurations capable of accurately capturing both global and complex local deformations. In many cases

  such grid configurations are non-obvious and largely selected based on user experience. Recent regularization methods imposing sparsity upon the B-spline coefficients throughout simultaneous multi-grid optimization

  however

  have provided a promising means of determining suitable configurations automatically. Unfortunately

  imposing sparsity on over-parameterized B-spline models is computationally expensive and introduces additional difficulties such as undesirable local minima in the B-spline coefficient optimization process. To overcome these difficulties in determining B-spline grid configurations

  this paper investigates the use of convolutional neural networks (CNNs) to learn and infer expressive sparse multi-grid configurations prior to B-spline coefficient optimization. Experimental results show that multi-grid configurations produced in this fashion using our CNN based approach provide registration quality comparable to L1-norm constrained over-parameterizations in terms of exactness

  while exhibiting significantly reduced computational requirements.

  CNN Driven Sparse Multi-Level B-spline Image Registration

  Pingge Jiang

  Brain Informatics and Health

  In this paper

  we propose an improved B-spline registration algorithm for feature fusion of images from different neuroimaging techniques. The current B-spline registration method generally consists of several steps: initial curve estimation

  similarity estimation between the warped image and fixed image

  gradient computation

  optimization and curve re-estimation. We improved the accuracy and efficiency of gradient computation by introducing a map-reduce framework which partitions the volume into multiple subregions and each subregion can be processed independently and efficiently. Experimental results show that our method achieves higher accuracy than the traditional registration algorithm and computational burden is released for large scale neuroimages.

  B-Spline Registration of Neuroimaging Modalites with Map-Reduce Framework

  libkaze is a scientific image processing library written in C

  Plastimatch

  Plastimatch is an open source software for image computation with primary focus is high-performance volumetric registration of medical images

  such as X-ray computed tomography (CT)

  magnetic resonance imaging (MRI)

  and positron emission tomography (PET).

  James

  Shackleford

  University of Pennsylvania

  Drexel University

  Massachusetts General Hospital

  Philadelphia

  PA

  Tenured teaching/research position

  Associate Professor

  Drexel University

  Boston

  Massachusetts

  Conducted research on computer vision assisted tumor motion management for photon and proton based radiation therapies.

  Post Doctoral Fellow

  Massachusetts General Hospital

  Tenure-track teaching/research position

  Drexel University

  Adjunct Assistant Professor

  University of Pennsylvania

  US20110175183

  Metal-semiconductor-metal (MSM) photodetectors may see increased responsivity when a plasmonic lens is integrated with the photodetector. The increased responsivity of the photodetector may be a result of effectively ‘guiding’ photons into the active area of the device in the form of a surface plasmon polariton. In one embodiment

  the plasmonic lens may not substantially decrease the speed of the MSM photodetector. In another embodiment

  the Shottkey contacts of the MSM photodetector may be corrugated to provide integrated plasmonic lens. For example

  one or more of the cathodes and anodes can be modified to create a plurality of corrugations. These corrugations may be configured as a plasmonic lens on the surface of a photodetector. The corrugations may be configured as parallel linear corrugations

  equally spaced curved corrugations

  curved parallel corrugations

  approximately equally spaced concentric circular corrugations

  chirped corrugations or the like.

  us

  Integrated plasmonic lens photodetector

  IEEE - Institute of Electrical and Electronics Engineers

  The Linux Foundation