M. Manjunatha

Review of laser speckle-based analysis in medical imaging

Speckle pattern forms when a rough object is illuminated with coherent light (laser) and the backscattered radiation is imaged on a screen. The pattern changes over time due to movement in the object. Such time-integrate speckle pattern can be statistically analyzed to reveal the flow profile. For higher velocity the speckle contrast gets reduced. This theory can be utilized for tissue perfusion in capillaries of human skin tissue and cerebral blood flow mapping in rodents. Early, the technique was suffered from low resolution and computational intricacies for real-time monitoring purpose. However, modern engineering has made it feasible for real-time monitoring in microcirculation imaging with improved resolution. This review illustrates several modifications over classical technique done by many researchers. Recent advances in speckle contrast methods gain major interest, leading towards practical implementation of this technique. The review also brings out the scopes of laser speckle-based analysis in various medical applications.

An electronic travel aid for navigation of visually impaired persons

This paper presents an electronic travel aid for blind people to navigate safely and quickly, an obstacle detection system using ultrasonic sensors and USB camera based visual navigation has been considered. The proposed system detects the obstacles up to 300 cm via sonar and sends feedback (beep sound) to inform the person about its location. In addition to this, an USB webcam is connected with eBox 2300™ Embedded System for capturing the field of view of the user, which is used for finding the properties of the obstacle in particular, in the context of this work, locating a human being. Identification of human presence is based on face detection and cloth texture analysis. The major constraints for these algorithms to run on Embedded System are small image frame (160×120) having reduced faces, limited memory and very less processing time available to achieve real time image processing requirements. The algorithms are implemented in C++ using Visual Studio 5.0 IDE, which runs on Windows CE™ environment.

Segmentation of blood smear images using normalized cuts for detection of malarial parasites

This paper presents an optimized normalized cut method for segmentation of RBCs infected with malarial parasites using peripheral blood smears. The algorithm is applied over various color spaces to find its optimal performance for microscopic blood smear images. We tested the efficacy of results in RGB, YCbCr, HSV and NTSC using the Rands Index. The work is useful in telepathology applications and can automate the screening of malaria in rural areas where healthcare manpower is limited.

Phonocardiogram signal analysis using adaptive line enhancer methods on Mixed Signal Processor

This paper presents the acquisition of heart sound signals and its separation from lung sounds based on the adaptive filtering technique. After signal acquisition, normal linear filtering techniques is not capable separated the two sounds, as both the sounds overlap in the spatial as well as temporal domains. Because of the signal tracking and noise elimination capability of adaptive line enhancer (ALE) it can be used for denoising the heart sounds. Here two methods of ALE have been discussed; using least mean square (LMS) and recursive least square (RLS). A comparative analysis has been carried out in terms of their power spectrum density (PSD) and percentage of heart sound recovery for their evaluation and finally both the algorithms have been implemented on MSP430 platform for designing a standalone diagnostic system to assist the cardiologists in their diagnosis. The scope of this study includes incorporation of the different diagnostic features into a single system for properly classifying the abnormal cardiac conditions.

Computer assisted cervical cytological nucleus localization

Cervical cancer is the second most common form of malignancy among women in India. Regular screening of cervix can mollify its incidence thus enabling adoption of better prevention strategies. Proper localization and delineation of nuclear attributes for identification of crucial cellular features in Papanicolau stained cervical liquid based cytological images are tricky. Reduction of false negativity in the screening technique is the need of the hour. These ambiguities in the detection of nuclei are due to relative differences in staining intensity, presence of inflammatory cells, necrotic background, presence of bacteria, cellular overlapping causing super-imposition of nuclei, and clustering/clumping of cells etc. In this paper we present here a computationally lightweight yet elegant computer assisted automated technique for localization of epithelial cell nuclei in optical microscopic images of Pap stained monolayer cervical smears. The set of developed algorithms efficiently handle background separation and identification of nuclei in overlapping cells occurring as clusters. It uses morphological selection of region of interest preceded by intensity based object separation. The region of interest is iteratively bound using minimum bounding rectangles, to locate nuclei in the cell clusters. This method accurately inserts seed points, eliminates false seeds and detects nucleus. Thereafter region growing technique is applied considering obtained seed points to segment the nucleus from cells. It is inferred that most of the problems faced while locating nuclei are overcome with the above algorithm; the only cases when it fails is in presence of overlapping nuclei and in presence of overlapping neutrophils.

Automated detection of air embolism in OCT contrast imaging: Anisotropic diffusion and active contour based approach

Embolism can be a cause of life threatening situation for which early detection and diagnosis is of major importance. This work describes an automatic approach for air embolism detection and measurement of different morphological features of the embolus using OCT contrast imaging technique. Firstly, the channel has been segmented through morphological processing. Manually selecting the initial contour for active contour (AC) technique is time consuming. To overcome this, anisotropic diffusion (AD) is implemented to automatically select the initial contour prior to AC. A snake based AC is executed to segment out the embolus. The proposed emboli segmentation mechanism has been compared with other segmentation techniques and it has been observed that it can efficiently extract the embolus with high segmentation accuracy (92%-94%) and reduced computational time. Different morphological descriptors showing the shape properties of the embolus have been computed to perform the shape analysis of it and measuring the criticality of the blockage area. It has been experimented that this method can also track multiple emboli flowing through the microchannel, thereby facilitating the study of contrast imaging in air embolism detection.

Pyramidal Refinement of Lucas - Kanade Optical Flow based Tracking of Peripheral Air Embolism in OCT Contrast Imaging

Air embolism often causes severe consequences in patients, in which several cases need fast treatment at the earlier stage. This paper proposes a computerized approach for detection as well as estimation of motion trajectory of air emboli using OCT contrast imaging technique. Due to change in optical properties, speckle pattern changes from fluid to air bubble and so does the speckle pattern on the image plane. This phenomenon helps to track the air bubble due to change in brightness pattern over a sequence of images. A top-down approach has been demonstrated from the image acquisition to the application of different image processing algorithms. Segmentation of the embolus has been carried out primarily by selecting seed contour through anisotropic diffusion (AD) technique and then implementation of a snake based active contour (AC) method. Both the techniques reduce the manual labour and computational time, thereby substantially increasing the segmentation accuracy (92% 94%). Besides, pyramidal construction of the Lucas – Kanade optical flow precisely optimizes the flow velocities of air bubble and also increases larger motion tracking ability. Hence, the proposed technique can becoming an assisting tool to the clinician for early detection of air embolism and tracking the air bubble through microcirculation. General Terms Image Processing, Optical Coherence Tomography, Medical Imaging, Computer Vision.

Efficacy of low cost Liquid Based Cytology for cerivcal smears in automated segmentation of cells and nuclei

This paper is aimed at the development of a cost effective monolayered LBC slide preparation technique for automated nuclear and cellular features segmentation using image processing techniques. The sensitivity of Liquid Based Cytology (LBC) in monolayer preparation is reported to be better than Conventional Pap Smears (CPS) in automated image analysis. In our study a low-cost monolayer preparation by LBC for cervical smear has been developed. The digital images of new LBC method and CPS were processed to segment out primary target features like cervical cells and their nuclei. The target feature segmentation was successfully done and the used nuclear segmentation method was applied for the first time for these images. The sensitivity of the present LBC technique was superior to CPS as the algorithms developed for the segmentation and analysis of nucleus run better on the newly developed monolayer images.

Technique of Topographical mapping of FDI muscle response after Single pulse TMS stimulation: A method to study inter hemispheric symmetry and plasticity of human motor cortex

The aim of this study was to investigate the technique of Topographical mapping of first dorsal interosseous (FDI) muscle response after Single pulse Trans cranial Magnetic stimulation (TMS), in a single normal subject, to study inter hemispheric symmetry of plasticity of motor cortex. TMS induced motor evoked potential (MEP) over an area of motor cortex was mapped in two dimensional space using pseudo colour. This is a simple technique which gives a qualitative as well as quantitative idea of brain excitability. Using this technique, a map of MEP of FDI for a normal individual was created followed by mapping of same individual after continuous theta bust stimulation (cTBS) and intermittent theta bust stimulation (iTBS), to induce plasticity of motor cortex. The scope of this technique to examine inter hemispheric symmetry of plasticity of motor cortex of human brain is discussed.

A comparative study of phonocardiogram analysis techniques based on mixed signal processor

Normal heart sounds provide an indication of the general state of the heart in terms of rhythm and contractility. Any cardiovascular abnormality introduces additional sounds, and murmurs that changes the temporal nature of the acoustic signature. Such variations provide vital information in diagnosis of cardiac disorders. However, at the time of signal acquisition, the heart sound gets mixed with lung sound in both spatial and temporal domain which cannot be separated through linear filtering technique as the frequency ranges of both the signals are overlapping. To overcome this problem, we comparatively study three parametric signal processing techniques viz. Auto Regressive (AR), Auto Regressive Moving Average (ARMA) and Adaptive Line Enhancer (ALE) using Least Mean Square (LMS). We also compare their performance with wavelet based de-noising strategies. The algorithms have been implemented and their performance is evaluated on the basis of Power Spectral Density (PSD) and percentage of heart sound recovery. The scope of the study also incorporated the applicability of the techniques for implementation on embedded mixed signal processing targets.