Selected Shape and Texture Features for Automatic Detection of Acute Lymphoblastic Leukemia

Acute Lymphoblastic Leukemia is a cancer of blood caused due to increase in number of immature lymphocyte cells. Detection is done manually by skilled pathologists which is time consuming and depends on the skills of the pathologist. The authors propose a methodology for discrimination of a normal lymphocyte cell from a malignant one by processing the blood sample image. Automatic detection process will reduce the diagnosis time and not be limited by human interpretation. The lymphocyte images are classified based on two types of extracted features: shape and texture. To identify prominent shape features, Correlation based Feature Selection is applied. Principal Component Analysis is applied on the texture features to reduce their dimensionality. Support Vector Machine is used for classification. It is observed that 16 shape features are able to give a classification accuracy of 92.3% and that changes in the geometrical properties of the nucleus emerge as significant features contributing towards detecting a malignant lymphocyte.

Biomedical Signal Analysis and Its Physio-Clinical Perspectives

The field of Biomedical engineering has brought two apparently diagonally placed poles of academia of excellence, i.e., field of medicine and the field of state of art engineering science to a closed proximity. Now a day most if not all of the state of art diagnostics in the field of medicine are almost totally dependent upon biomedical signal analysis. Whole of the biological systems are run by nothing but the bio-signals. The process of signal analysis depends upon the types of signals, recording methods, data types, need of compression and portability and possibility of artifacts. The important areas of the clinician's prime concern are the reliability of the data generated, the utility of the data produced in the real clinical settings in making a diagnosis and interference of the diverse type of equipment's signals with each other and its impact upon the final output. Physiologists act as a bridge between the biomedical engineering and the clinician's need assessment and product delivery process.

A Discrete-Wavelet-Transform- and Hidden-Markov-Model-Based Approach for Epileptic Focus Localization

Epilepsy is the most common neurological disorder with 40-50 million people suffering with it worldwide. Epilepsy is not life threatening but it disables the person to a greater extent due to its uncertainty of occurrences. Epilepsy is detected by repeated occurrences of seizure. Seizure can be generated in brain due to abnormal activity of group of neurons caused by brain tumor, genetic problem, infection, hemorrhage etc. Seizure can be detected by observing the variation in Electroencephalogram (EEG) signal. Focal seizure is defined as seizure localized in one lobe of brain. In this chapter discrete wavelet transform and Hidden Markov Model based focal seizure detection method is proposed for epileptic focus localization. EEG signal was decomposed up to level 5 using dual tree complex wavelet transform and entropy features such as collision entropy, minimum and modified sample entropy were extracted. Hidden Markov model was used for classification purpose. Maximum 80% accuracy was achieved in detecting focal and non-focal EEG signal.

Automated Classification of Focal and Non-Focal EEG Signals Based on Bivariate Empirical Mode Decomposition

The chapter presents a new approach of computer aided diagnosis of focal electroencephalogram (EEG) signals by applying bivariate empirical mode decomposition (BEMD). Firstly, the focal and non-focal EEG signals are decomposed using the BEMD, which results in intrinsic mode functions (IMFs) corresponding to each signal. Secondly, bivariate bandwidths namely, amplitude bandwidth, precession bandwidth, and deformation bandwidth are computed for each obtained IMF. Interquartile range (IQR) values of bivariate bandwidths of IMFs are employed as the features for classification. In order to perform classification least squares support vector machine (LS-SVM) is used. The results of the experiment suggest that the computed bivariate bandwidths are significantly useful to discriminate focal EEG signals. The resultant classification accuracy obtained using proposed methodology, applied on the Bern-Barcelona EEG database, is 84.01%. The obtained results are encouraging and the proposed methodology can be helpful for identification of epileptogenic focus.

Automatic Retinal Image Analysis for the Detection of Diabetic Retinopathy

Diabetic Retinopathy, a condition in the person affected by diabetes, is most common cause of blindness in the world. Recent research has given a better understanding of requirement in clinical eye care practice to identify better and cheaper ways of identification, management, diagnosis and treatment of retinal disease. The importance of diabetic retinopathy screening programs and difficulty in achieving reliable early diagnosis of diabetic retinopathy at a reasonable cost needs attention to develop computer-aided diagnosis tool. Computer aided disease diagnosis in retinal image analysis could ease mass screening of population with diabetes mellitus and help clinicians in utilizing their time more efficiently. The recent technological advances in computing power, communication systems, and machine learning techniques provide opportunities to the biomedical engineers and computer scientists to meet the requirements of clinical practice. With proper self-care, management, and medical professional support, individuals with diabetes can live a healthy and long life.

Classification and Compression of ECG Signal for Holter Device

ECG signal processing for holter monitoring of heart patients is still exploratory. Many signal processing techniques have been evolved for classification and compression of ECG signal. Despite an increase in research in this area, many challenges remain in designing an efficient classification and compression algorithm for ECG signal. These challenges include classification accuracy, good compression ratio with acceptable diagnostic quality etc. This chapter addresses a classification and a compression algorithm based on discrete wavelet transform. Classification algorithm uses discrete wavelet transform based feature to classify abnormal heart beat from ECG signal. Support vector machine is used as a classifier to detect abnormal heartbeat. The compression algorithm utilizes discrete wavelet transform and run-length encoding as a compression tool. Proposed classification and compression algorithms can be employed in monitoring of cardiac patients using holter device.

Development of a Wireless Controlled Iontophoretic Drug Delivery System

The current study describes the development of a wireless controlled iontophoretic drug delivery system. The control system was made using ZigBee communication protocol. The performance analysis of the current injecting circuit was performed to ascertain minimal error combined with high efficiency. Finally, the developed controlled system was used to manipulate the functioning of the two independent iontophoretic drug delivery systems. In gist, a wireless controlled drug delivery system based on ZigBee communication protocol was developed and tested successfully.

Rehabilitation and Medical Assistant Technique in Virtual Reality

In the modern world, Virtual Reality (VR) has been accepted by the researcher as a state-of-the-art neuropsychological assessment tool in clinical research. Owing to the two prominent VR attributes i.e. immersivity and interactivity, VR is being used as an assessment tool as well as a training module. Combining cognitive knowledge with existing VR technology can propel VR to achieve a quantum leap in the rehabilitation sector. In addition, it offers potential radical modifications in the traditional way of neuropsychological assessment in the clinical settings, by improving ecological validity of the existing tests. Subsequently, features of VR facilitate customisation of an individual's treatment plan with the informed gradual progression of the challenge. This chapter explains VR as an innovative platform in the sector of medical & others such as military and sports for assessment as well as for training.

Automated Method of Analysing Sputum Smear Tuberculosis Images Using Multifractal Approach

In this chapter, an attempt has been made to automate the analysis of positive and negative Tuberculosis (TB) sputum smear images using multifractal approach. The smear images (N=100) recorded under standard image acquisition protocol are considered. The images are subjected to multifractal analysis and the corresponding spectrum parameters are extracted. Most significant parameters are selected based on the principal component analysis. Further, these parameters are subjected to classification using support vector machine classifier with different kernels. Results demonstrate that the multifractal analysis is capable of discriminating positive and negative TB images. The values of apex, broadness and aperture of the singularity spectrum are higher for TB positive than negative images and are statistically significant. The performance estimators obtained in the classification process show that the polynomial kernel performs better. It appears that this method of texture analysis could be useful for automated analysis of TB using digital sputum smear images.

Image Registration in Ultrasound-Assisted Brain Surgery

Image registration is an essential step in the image guided brain surgery. A preoperative magnetic resonance (MR) image guides the neurosurgeon about the size and the location of the tumor inside the brain of the diseased person. Due to several reasons, brain shift occurs during the surgery, results in the shift of the actual position of the tumor. Intra-operative MR imaging is expensive and may not be financially viable for many hospitals. An effective intraoperative US can be used in replacement of MR. For performing registration of US and MR images, the most of the state-of-the-art methods use a suitable similarity or dissimilarity measure, a spline based deformation model, a smoothing technique and an effective fast optimization method. This chapter starts with a discussion on various types of brain tumors and their clinical significance. It also covers on various similarity measures, optimizations and the available database of US and MR brain images.