Bharath Ramakrishna

Spectral/Spatial Hyperspectral Image Compression

This chapter investigates the applicability of direct application of 3D compression techniques to hyperspectral imagery and develops PCA-based spectral/spatial compression techniques in conjunction with the virtual dimensionality (VD) for hyperspectral image compression where the VD is used to estimate number of principal components required to be preserved. In particular, we conduct computer simulations based on a synthetic image and real image experiments to demonstrate that simple PCA-based spectral/spatial lossy compression techniques can perform at least as well as 3D lossy compression techniques in applications such as mixed pixel classification and quantification. This interesting finding provides evidence that PCA-based spectral/spatial compression can be as competitive as the 3D compression for hyperspectral image compression. Additionally, this chapter also further demonstrates that the number of PCs required to be preserved by lossy compression is crucial and the proposed VD provides a much better estimate than the commonly used criterion determined by the sum of largest eigenvalues. For more details we refer to [31].

Spectral/spatial hyperspectral image compression in conjunction with virtual dimensionality

Hyperspectral image compression can be performed by either 3-D compression or spectral/spatial compression. It has been demonstrated that due to high spectral resolution hyperspectral image compression can be more effective if compression is carried out spectrally and spatially in two separate stages. One commonly used spectral/spatial compression implements principal components analysis (PCA) or wavelet for spectral compression followed by a 2-D/3D compression technique for spatial compression. This paper presents another type of spectral/spatial compression technique, which uses Hyvarinen and Ojas Fast independent component analysis (FastICA) to perform spectral compression, while JPEG2000 is used for 2-D/3-D spatial compression. In order to determine how many independent components are required, a newly developed concept, virtual dimensionality (VD) is used. Since the VD is determined by the false alarm probability rather than the commonly used signal-to-noise ratio or mean squared error (MSE), our proposed FastICA-based spectral/spatial compression is more effective than PCA-based or wavelet-based spectral/spatial compression in data exploitation.

Automatic CAD of meniscal tears on MR imaging: a morphology-based approach

Knee-related injuries, including meniscal tears, are common in young athletes and require accurate diagnosis and appropriate surgical intervention. Although with proper technique and skill, confidence in the detection of meniscal tears should be high, this task continues to be a challenge for many inexperienced radiologists. The purpose of our study was to automate detection of meniscal tears of the knee using a computer-aided detection (CAD) algorithm. Automated segmentation of the sagittal T1-weighted MR imaging sequences of the knee in 28 patients with diagnoses of meniscal tears was performed using morphologic image processing in a 3-step process including cropping, thresholding, and application of morphological constraints. After meniscal segmentation, abnormal linear meniscal signal was extracted through a second thresholding process. The results of this process were validated by comparison with the interpretations of 2 board-certified musculoskeletal radiologists. The automated meniscal extraction algorithm process was able to successfully perform region of interest selection, thresholding, and object shape constraint tasks to produce a convex image isolating the menisci in more than 69% of the 28 cases. A high correlation was also noted between the CAD algorithm and human observer results in identification of complex meniscal tears. Our initial investigation indicates considerable promise for automatic detection of simple and complex meniscal tears of the knee using the CAD algorithm. This observation poses interesting possibilities for increasing radiologist productivity and confidence, improving patient outcomes, and applying more sophisticated CAD algorithms to orthopedic imaging tasks.

Low-bit rate exploitation-based lossy hyperspectral image compression

Hyperspectral image compression has become increasingly important in data exploitation because of enormous data volumes and high redundancy provided by hundreds of contiguous spectral channels. Since a hyperspectral image can be viewed as a 3-dimensional (3D) image cube, many efforts have been devoted to extending 2D image compression techniques to perform 3D image compression on hyperspectral image cubes. Unfortunately, some major issues generally encountered in hyperspectral data exploitation at low or very low-bit rate compression, for example, subpixels and mixed pixels which do not occur in traditional pure pixel-based image compression are often overlooked in such a 2D-to-3D compression. Accordingly, a direct application of 2D-to-3D compression techniques to hyperspectral image cubes without taking precaution may result in significant loss of crucial spectral information provided by subtle substances such as small objects, anomalies during low bit-rate lossy compression. This paper takes a rather different view by investigating lossy hyperspectral compression from a perspective of exploring spectral information, referred to as exploitation-based lossy compression and further develops spectral/spatial hyperspectral image compression to effectively preserve crucial and vital spectral information of objects which are generally missed by commonly used mean-squared error (MSE) or signal-to-noise ratio (SNR)-based compression techniques when lossy compression is performed at low bit rates. In order to demonstrate advantages of the proposed spectral/spatial compression approach applications of subpixel target detection and mixed pixel analysis are used for experiments for performance evaluation.

Role of Computer Aided Detection (CAD) Integration: Case Study with Meniscal and Articular Cartilage CAD applications

Knee-related injuries involving the meniscal or articular cartilage are common and require accurate diagnosis and surgical intervention when appropriate. With proper techniques and experience, confidence in detection of meniscal tears and articular cartilage abnormalities can be quite high. However, for radiologists without musculoskeletal training, diagnosis of such abnormalities can be challenging. In this paper, the potential of improving diagnosis through integration of computer-aided detection (CAD) algorithms for automatic detection of meniscal tears and articular cartilage injuries of the knees is studied. An integrated approach in which the results of algorithms evaluating either meniscal tears or articular cartilage injuries provide feedback to each other is believed to improve the diagnostic accuracy of the individual CAD algorithms due to the known association between abnormalities in these distinct anatomic structures. The correlation between meniscal tears and articular cartilage injuries is exploited to improve the final diagnostic results of the individual algorithms. Preliminary results from the integrated application are encouraging and more comprehensive tests are being planned.

A concurrent computer aided detection (CAD) tool for articular cartilage disease of the knee on MR imaging using active shape models

Osteoarthritis (OA) is the most common form of arthritis and a major cause of morbidity affecting millions of adults in the US and world wide. In the knee, OA begins with the degeneration of joint articular cartilage, eventually resulting in the femur and tibia coming in contact, and leading to severe pain and stiffness. There has been extensive research examining 3D MR imaging sequences and automatic/semi-automatic techniques for 2D/3D articular cartilage extraction. However, in routine clinical practice the most popular technique still remain radiographic examination and qualitative assessment of the joint space. This may be in large part because of a lack of tools that can provide clinically relevant diagnosis in adjunct (in near real time fashion) with the radiologist and which can serve the needs of the radiologists and reduce inter-observer variation. Our work aims to fill this void by developing a CAD application that can generate clinically relevant diagnosis of the articular cartilage damage in near real time fashion. The algorithm features a 2D Active Shape Model (ASM) for modeling the bone-cartilage interface on all the slices of a Double Echo Steady State (DESS) MR sequence, followed by measurement of the cartilage thickness from the surface of the bone, and finally by the identification of regions of abnormal thinness and focal/degenerative lesions. A preliminary evaluation of CAD tool was carried out on 10 cases taken from the Osteoarthritis Initiative (OAI) database. When compared with 2 board-certified musculoskeletal radiologists, the automatic CAD application was able to get segmentation/thickness maps in little over 60 seconds for all of the cases. This observation poses interesting possibilities for increasing radiologist productivity and confidence, improving patient outcomes, and applying more sophisticated CAD algorithms to routine orthopedic imaging tasks.

CHESAPEAKE BAY WATER QUALITY MONITORING USING SATELLITE IMAGERY

The Chesapeake Bay is a valued ecological, economic, recreational, cultural and scenic resource. The Bay watershed States and the District of Columbia, in conjunction with the EPA Chesapeake Bay Program, have worked and teamed together over the past 20 years to protect and restore the Bay ecosystem. A key component of this effort is water quality and habitat monitoring to assess the impact of management actions and natural processes, and evaluate habitat parameters on living resources such as submerged aquatic vegetation (SAV), oysters, and fisheries. Using aerial and satellite remote sensing imagery has become a practical and effective means of monitoring water quality in a timely manner. Of particular interest in evaluation of water clarity are several initiative measures. Specifically, Secchi-Disk Transparency (SDT) and Chlorophyll a (Chl-a) have been widely accepted as critical indicators of water quality and their reliable estimation using satellite imagery provides a cost effective and speedy means for water quality monitoring. Work done at Water Resources Center, University of Minnesota has demonstrated the feasibility of performing regional assessment of lake water quality using LANDSAT image data. This paper investigates an approach similar to their work but uses a different type of satellite imagery, EO-1 ALI imagery where the SDT and Chl-a are also used as indicators to estimate water quality for the Chesapeake Bay and DC area (Potomac River). In doing so, three major issues are investigated, which are (1) the study site that is an open Bay area, not a self-contained lake; (2) investigation of applicability of equations that are used to specify the SDT and Chl-a to our Bay area study; (3) the use of a different type of satellite imagery for water quality monitoring. This paper develops techniques to address these three issues and presents preliminary experiments which show encouraging results.

An embedded system developed for hand held assay used in water monitoring

The US Army Joint Service Agent Water Monitor (JSAWM) program is currently interested in an approach that can implement a hardware- designed device in ticket-based hand-held assay (currently being developed) used for chemical/biological agent detection. This paper presents a preliminary investigation of the proof of concept. Three components are envisioned to accomplish the task. One is the ticket development which has been undertaken by the ANP, Inc. Another component is the software development which has been carried out by the Remote Sensing Signal and Image Processing Laboratory (RSSIPL) at the University of Maryland, Baltimore County (UMBC). A third component is an embedded system development which can be used to drive the UMBC-developed software to analyze the ANP-developed HHA tickets on a small pocket-size device like a PDA. The main focus of this paper is to investigate the third component that is viable and is yet to be explored. In order to facilitate to prove the concept, a flatbed scanner is used to replace a ticket reader to serve as an input device. The Stargate processor board is used as the embedded System with Embedded Linux installed. It is connected to an input device such as scanner as well as output devices such as LCD display or laptop etc. It executes the C-Coded processing program developed for this embedded system and outputs its findings on a display device. The embedded system to be developed and investigated in this paper is the core of a future hardware device. Several issues arising in such an embedded system will be addressed. Finally, the proof-of-concept pilot embedded system will be demonstrated.