IU Indianapolis ScholarWorks :: Browsing by Author "Salama, Paul"

Browsing by Author "Salama, Paul"

Now showing 1 - 10 of 84

A 2D PLUS DEPTH VIDEO CAMERA PROTOTYPE USING DEPTH FROM DEFOCUS IMAGING AND A SINGLE MICROFLUIDIC LENS
(2011-08) Li, Weixu; Christopher, Lauren; Rizkalla, Maher E.; Salama, Paul
A new method for capturing 3D video from a single imager and lens is introduced in this research. The benefit of this method is that it does not have the calibration and alignment issues associated with binocular 3D video cameras, and allows for a less expensive overall system. The digital imaging technique Depth from Defocus (DfD) has been successfully used in still camera imaging to develop a depth map associated with the image. However, DfD has not been applied in real-time video so far since the focus mechanisms are too slow to produce real-time results. This new research result shows that a Microfluidic lens is capable of the required focal length changes at 2x video frame rate, due to the electrostatic control of the focus. During the processing, two focus settings per output frame are captured using this lens combined with a broadcast video camera prototype. We show that the DfD technique using Bayesian Markov Random Field optimization can produce a valid depth map.
3-D Scene Reconstruction for Passive Ranging Using Depth from Defocus and Deep Learning
(2019-08) Emerson, David R.; Christopher, Lauren A.; Ben Miled, Zina; King, Brian; Salama, Paul
Depth estimation is increasingly becoming more important in computer vision. The requirement for autonomous systems to gauge their surroundings is of the utmost importance in order to avoid obstacles, preventing damage to itself and/or other systems or people. Depth measuring/estimation systems that use multiple cameras from multiple views can be expensive and extremely complex. And as these autonomous systems decrease in size and available power, the supporting sensors required to estimate depth must also shrink in size and power consumption. This research will concentrate on a single passive method known as Depth from Defocus (DfD), which uses an in-focus and out-of-focus image to infer the depth of objects in a scene. The major contribution of this research is the introduction of a new Deep Learning (DL) architecture to process the the in-focus and out-of-focus images to produce a depth map for the scene improving both speed and performance over a range of lighting conditions. Compared to the previous state-of-the-art multi-label graph cuts algorithms applied to the synthetically blurred dataset the DfD-Net produced a 34.30% improvement in the average Normalized Root Mean Square Error (NRMSE). Similarly the DfD-Net architecture produced a 76.69% improvement in the average Normalized Mean Absolute Error (NMAE). Only the Structural Similarity Index (SSIM) had a small average decrease of 2.68% when compared to the graph cuts algorithm. This slight reduction in the SSIM value is a result of the SSIM metric penalizing images that appear to be noisy. In some instances the DfD-Net output is mottled, which is interpreted as noise by the SSIM metric. This research introduces two methods of deep learning architecture optimization. The first method employs the use of a variant of the Particle Swarm Optimization (PSO) algorithm to improve the performance of the DfD-Net architecture. The PSO algorithm was able to find a combination of the number of convolutional filters, the size of the filters, the activation layers used, the use of a batch normalization layer between filters and the size of the input image used during training to produce a network architecture that resulted in an average NRMSE that was approximately 6.25% better than the baseline DfD-Net average NRMSE. This optimized architecture also resulted in an average NMAE that was 5.25% better than the baseline DfD-Net average NMAE. Only the SSIM metric did not see a gain in performance, dropping by 0.26% when compared to the baseline DfD-Net average SSIM value. The second method illustrates the use of a Self Organizing Map clustering method to reduce the number convolutional filters in the DfD-Net to reduce the overall run time of the architecture while still retaining the network performance exhibited prior to the reduction. This method produces a reduced DfD-Net architecture that has a run time decrease of between 14.91% and 44.85% depending on the hardware architecture that is running the network. The final reduced DfD-Net resulted in a network architecture that had an overall decrease in the average NRMSE value of approximately 3.4% when compared to the baseline, unaltered DfD-Net, mean NRMSE value. The NMAE and the SSIM results for the reduced architecture were 0.65% and 0.13% below the baseline results respectively. This illustrates that reducing the network architecture complexity does not necessarily reduce the reduction in performance. Finally, this research introduced a new, real world dataset that was captured using a camera and a voltage controlled microfluidic lens to capture the visual data and a 2-D scanning LIDAR to capture the ground truth data. The visual data consists of images captured at seven different exposure times and 17 discrete voltage steps per exposure time. The objects in this dataset were divided into four repeating scene patterns in which the same surfaces were used. These scenes were located between 1.5 and 2.5 meters from the camera and LIDAR. This was done so any of the deep learning algorithms tested would see the same texture at multiple depths and multiple blurs. The DfD-Net architecture was employed in two separate tests using the real world dataset. The first test was the synthetic blurring of the real world dataset and assessing the performance of the DfD-Net trained on the Middlebury dataset. The results of the real world dataset for the scenes that were between 1.5 and 2.2 meters from the camera the DfD-Net trained on the Middlebury dataset produced an average NRMSE, NMAE and SSIM value that exceeded the test results of the DfD-Net tested on the Middlebury test set. The second test conducted was the training and testing solely on the real world dataset. Analysis of the camera and lens behavior led to an optimal lens voltage step configuration of 141 and 129. Using this configuration, training the DfD-Net resulted in an average NRMSE, NMAE and SSIM of 0.0660, 0.0517 and 0.8028 with a standard deviation of 0.0173, 0.0186 and 0.0641 respectively.
3D Centroidnet: Nuclei Centroid Detection with Vector Flow Voting
(IEEE, 2022-10) Wu, Liming; Chen, Alain; Salama, Paul; Dunn, Kenneth W.; Delp, Edward J.; Electrical and Computer Engineering, School of Engineering and Technology
Automated microscope systems are increasingly used to collect large-scale 3D image volumes of biological tissues. Since cell boundaries are seldom delineated in these images, detection of nuclei is a critical step for identifying and analyzing individual cells. Due to the large intra-class variability in nuclei morphology and the difficulty of generating ground truth annotations, accurate nuclei detection remains a challenging task. We propose a 3D nuclei centroid detection method by estimating the "vector flow" volume where each voxel represents a 3D vector pointing to its nearest nuclei centroid in the corresponding microscopy volume. We then use a voting mechanism to estimate the 3D nuclei centroids from the "vector flow" volume. Our system is trained on synthetic microscopy volumes and tested on real microscopy volumes. The evaluation results indicate our method outperforms other methods both visually and quantitatively.
3D EM/MPM MEDICAL IMAGE SEGMENTATION USING AN FPGA EMBEDDED DESIGN IMPLEMENTATION
(2011-08) Liu, Chao; Christopher, Lauren; Rizkalla, Maher E.; Salama, Paul
This thesis presents a Field Programmable Gate Array (FPGA) based embedded system which is used to achieve high speed segmentation of 3D images. Segmenta- tion is performed using Expectation-Maximization with Maximization of Posterior Marginals (EM/MPM) Bayesian algorithm. In this system, the embedded processor controls a custom circuit which performs the MPM and portions of the EM algorithm. The embedded processor completes the EM algorithm and also controls image data transmission between host computer and on-board memory. The whole system has been implemented on Xilinx Virtex 6 FPGA and achieved over 100 times improvement compared to standard desktop computing hardware.
3D ENDOSCOPY VIDEO GENERATED USING DEPTH INFERENCE: CONVERTING 2D TO 3D
(2013-08-20) Rao, Swetcha; Christopher, Lauren; Rizkalla, Maher E.; Salama, Paul; King, Brian
A novel algorithm was developed to convert raw 2-dimensional endoscope videos into 3-dimensional view. Minimally invasive surgeries aided with 3D view of the invivo site have shown to reduce errors and improve training time compared to those with 2D view. The novelty of this algorithm is that two cues in the images have been used to develop the 3D. Illumination is the rst cue used to nd the darkest regions in the endoscopy images in order to locate the vanishing point(s). The second cue is the presence of ridge-like structures in the in-vivo images of the endoscopy image sequence. Edge detection is used to map these ridge-like structures into concentric ellipses with their common center at the darkest spot. Then, these two observations are used to infer the depth of the endoscopy videos; which then serves to convert them from 2D to 3D. The processing time is between 21 seconds to 20 minutes for each frame, on a 2.27GHz CPU. The time depends on the number of edge pixels present in the edge-detection image. The accuracy of ellipse detection was measured to be 98.98% to 99.99%. The algorithm was tested on 3 truth images with known ellipse parameters and also on real bronchoscopy image sequences from two surgical procedures. Out of 1020 frames tested in total, 688 frames had single vanishing point while 332 frames had two vanishing points. Our algorithm detected the single vanishing point in 653 of the 688 frames and two vanishing points in 322 of the 332 frames.
3D Image Segmentation Implementation on FPGA Using EM/MPM Algorithm
(2010-12) Sun, Yan; Christopher, Lauren; Rizkalla, Maher E.; Salama, Paul
In this thesis, 3D image segmentation is targeted to a Xilinx Field Programmable Gate Array (FPGA), and verified with extensive simulation. Segmentation is performed using the Expectation-Maximization with Maximization of the Posterior Marginals (EM/MPM) Bayesian algorithm. This algorithm segments the 3D image using neighboring pixels based on a Markov Random Field (MRF) model. This iterative algorithm is designed, synthesized and simulated for the Xilinx FPGA, and greater than 100 times speed improvement over standard desktop computer hardware is achieved. Three new techniques were the key to achieving this speed: Pipelined computational cores, sixteen parallel data paths and a novel memory interface for maximizing the external memory bandwidth. Seven MPM segmentation iterations are matched to the external memory bandwidth required of a single source file read, and a single segmented file write, plus a small amount of latency.
3D Object Detection Using Virtual Environment Assisted Deep Network Training
(2020-12) Dale, Ashley S.; Christopher, Lauren; King, Brian; Salama, Paul
An RGBZ synthetic dataset consisting of five object classes in a variety of virtual environments and orientations was combined with a small sample of real-world image data and used to train the Mask R-CNN (MR-CNN) architecture in a variety of configurations. When the MR-CNN architecture was initialized with MS COCO weights and the heads were trained with a mix of synthetic data and real world data, F1 scores improved in four of the five classes: The average maximum F1-score of all classes and all epochs for the networks trained with synthetic data is F1∗ = 0.91, compared to F1 = 0.89 for the networks trained exclusively with real data, and the standard deviation of the maximum mean F1-score for synthetically trained networks is σ∗ = 0.015, compared to σ_F1 = 0.020 for the networks trained exclusively with real F1 data. Various backgrounds in synthetic data were shown to have negligible impact on F1 scores, opening the door to abstract backgrounds and minimizing the need for intensive synthetic data fabrication. When the MR-CNN architecture was initialized with MS COCO weights and depth data was included in the training data, the net- work was shown to rely heavily on the initial convolutional input to feed features into the network, the image depth channel was shown to influence mask generation, and the image color channels were shown to influence object classification. A set of latent variables for a subset of the synthetic datatset was generated with a Variational Autoencoder then analyzed using Principle Component Analysis and Uniform Manifold Projection and Approximation (UMAP). The UMAP analysis showed no meaningful distinction between real-world and synthetic data, and a small bias towards clustering based on image background.
70329 Automated Lungs Segmentation and Airways Skeletonization from CT Scans in Patients with Cystic Fibrosis
(Cambridge University Press, 2021) Chie, Juan A. Chong; Territo, Paul R.; Salama, Paul; Medicine, School of Medicine
ABSTRACT IMPACT: Improve healthcare of patients with Cystic Fibrosis by reducing the time needed to generate results. OBJECTIVES/GOALS: We developed an automated framework capable of segmenting the lungs, extract the airways, and create a skeletonize map of the airways from CT scans of Cystic Fibrosis patients. As future expansion, the framework will be expanded to measure the airways diameters, detect the abnormal airways, and count the number of visible airways generations. METHODS/STUDY POPULATION: For this study, 35 CT scans from CF patients with different levels of severity were used to test the developed framework. The lungs segmentation was performed using an algorithm based on Gaussian Mixture Models for mild cases, and for severe cases a technique that uses convex hull and the recurrent addition of ‘dots’ was implemented. The airways extraction was performed using a 26-points connected components algorithm in conjunction with a curve fitting technique over the histogram of voxel values. Medial axis transform was used to perform the skeletonization of the extracted airways, and airways diameters determined via ray-casting. RESULTS/ANTICIPATED RESULTS: The framework was able to correctly obtain the segmented lungs in all 35 sample volumes regardless of disease severity. In contrast, it tends to fail to skeletonize the airways for severe cases where the framework is unable to differentiate between abnormal lungs conditions and dilated airways. Fine tuning is required to achieve better results. The expected result of the future implemented sections of the framework are focused to characterize the extracted airways by: 1) measuring the airways diameters; 2) detect and count the number of abnormal airways sizes; and 3) count the number of visible airways branching which will permit determination of stage and grade of the lungs of CF patients. DISCUSSION/SIGNIFICANCE OF FINDINGS: The proposed framework allows a fast and reproducible way to segment the lungs and create a skeletonized map of the airways that are independent of clinical training. In addition, this framework will be extended to obtain measurements of airway dilation and branching level, which could provide a deeper insight of the airways in CF patients.
An Ensemble Learning and Slice Fusion Strategy for Three-Dimensional Nuclei Instance Segmentation
(IEEE, 2022-06) Wu, Liming; Chen, Alain; Salama, Paul; Dunn, Kenneth W.; Delp, Edward J.; Electrical and Computer Engineering, School of Engineering and Technology
Automated microscopy image analysis is a fundamental step for digital pathology and computer aided diagnosis. Most existing deep learning methods typically require post-processing to achieve instance segmentation and are computationally expensive when directly used with 3D microscopy volumes. Supervised learning methods generally need large amounts of ground truth annotations for training whereas manually annotating ground truth masks is laborious especially for a 3D volume. To address these issues, we propose an ensemble learning and slice fusion strategy for 3D nuclei instance segmentation that we call Ensemble Mask R-CNN (EMR-CNN) which uses different object detectors to generate nuclei segmentation masks for each 2D slice of a volume and propose a 2D ensemble fusion and a 2D to 3D slice fusion to merge these 2D segmentation masks into a 3D segmentation mask. Our method does not need any ground truth annotations for training and can inference on any large size volumes. Our proposed method was tested on a variety of microscopy volumes collected from multiple regions of organ tissues. The execution time and robustness analyses show that our method is practical and effective.
Analysis of Heart Rate Variability During Focal Parasympathetic Drive of the Rat Baroreflex
(2020-05) Bustamante, David J.; Schild, John; Yoshida, Ken; Salama, Paul
Autonomic control of the heart results in variations in the intervals between heart beats, known as heart rate variability. One of the defining components of autonomic control is the baroreflex, a negative feedback controller that balances heart rate and blood pressure. The baroreflex is under constant command from the branches of the autonomic nervous system. To better understand how the autonomic nervous system commands the baroreflex, a baroreflex reflexogenic animal protocol was carried out. Heart rate variability analysis and baroreflex sensitivity were used to quantify the neural control of the heart. This thesis reconfirmed the existence of sexually dimorphic properties in the baroreflex through the use of heart rate variability analysis and baroreflex sensitivity. It was discovered that there are many caveats to utilizing heart rate variability analysis, which have to be addressed both in the experimental protocol and the signal processing technique. Furthermore, it was suggested that the slope method for quantifying baroreflex sensitivity also has many caveats, and that other baroreflex sensitivity methods are likely more optimal for quantifying sustained activation of the baroreflex. By utilizing various heart rate variability signal processing algorithms to assess autonomic tone in Sprague-Dawley rats during rest and sustained electrical activation of the baroreflex, the null hypothesis was rejected.

Browsing by Author "Salama, Paul"

Results Per Page

Sort Options