Comparative Study of Image Fusion Techniques in Treatment Planning | Chapter 6 | Emerging Trends in Engineering Research and Technology Vol. 5

 

The process by which different images or information from multiple images are combined is termed as Image fusion which is achieved by applying a sequence of operators on the images. Recently, a number of image fusion techniques have been developed. This chapter presents a review on the main categories of image fusion namely spatial domain technique, transform domain technique and statistical domain fusion technique. This chapter also reviews on the importance of image fusion techniques in treatment planning. Image Fusion is one of the latest fields adopted to solve the problems of digital image; image fusion produces high-quality images which contains additional information for the purposes of interpretation, classification, segmentation and compression, etc. The principle requirement of the fusion process is to identify the most significant features in the input images and to transfer them without loss of detail into the fused image. Image Fusion finds its application in vast range of areas. It is used for medical diagnostics and treatment. This chapter presents a brief description of some of the extensively used image fusion techniques for treatment planning. Comparison of all available image fusion techniques concludes a better approach for future research on image fusion.

 

 

Author(s) Details

Bhuvaneswari Balachander

Department  of Electronics and Communication Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India.

 

D. Dhanasekaran

Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India.

 

Please see the book here :- https://doi.org/10.9734/bpi/etert/v5

Novel Automatic Segmentation Approach for Early Brain Tumour Detection: Comparative Evaluation with AI Approaches | Chapter 5 | Medical Science: Updates and Prospects Vol. 1

 

Background: Automatic object detection in medical images is a crucial step in the diagnostic process. The problem of detecting brain tumours at an early stage is well advanced with deep learning algorithms (DLA) such as convolutional neural networks (CNN). The issue lies in the fact that these algorithms necessitate a training phase involving a large database of several hundred images, which can be time-consuming and require complex computational infrastructure.

 

Objective: This study aimed to comprehensively evaluate a proposed method, which relies on an active contour algorithm, for identifying and distinguishing brain tumours in magnetic resonance images.

 

Methods: The proposed algorithm was tested using brain images from the BRATS Challenges 2021, specifically focusing on glioma tumours. The proposed segmentation method is made up of an active contour algorithm, an anisotropic diffusion filter for pre-processing, active contour segmentation (Chan-Vese), and morphological operations for segmentation refinement.

 

Results: Its performance was evaluated using various metrics, such as accuracy, precision, sensitivity, specificity, Jaccard index, Dice index, and Hausdorff distance. The proposed method exhibited higher performance measures than most classical image segmentation methods and was comparable to the deep learning methods. These results indicate its ability to detect brain tumours accurately and rapidly.

 

Conclusion: The results section provided both numerical and visual insights into the similarity between segmented and ground truth tumour areas. The findings of this study highlighted the potential of computer-based methods in improving brain tumour identification using magnetic resonance imaging. Future work must validate the efficacy of these segmentation approaches across different brain tumour categories and improve computing efficiency to integrate the technology into potential clinical processes.

 

 

Author(s) Details

Mohammed Almijalli
Department of Biomedical Technology, College of Applied Medical Sciences, King Saud University, Riyadh 11433, Saudi Arabia.

 

Faten A. Almusayib
Department of Biomedical Technology, College of Applied Medical Sciences, King Saud University, Riyadh 11433, Saudi Arabia.

 

Ghala F. Albugami
Department of Biomedical Technology, College of Applied Medical Sciences, King Saud University, Riyadh 11433, Saudi Arabia.

 

Ziyad Aloqalaa
Department of Biomedical Technology, College of Applied Medical Sciences, King Saud University, Riyadh 11433, Saudi Arabia.

 

Omar Altwijri
Department of Biomedical Technology, College of Applied Medical Sciences, King Saud University, Riyadh 11433, Saudi Arabia.

 

Ali S. Saad
Department of Biomedical Technology, College of Applied Medical Sciences, King Saud University, Riyadh 11433, Saudi Arabia.

 

 

Please see the book here :- https://doi.org/10.9734/bpi/msup/v1/6551

Event Synchronous Segmentation of Phonocardiogram-A New Frontier to Heart Sound Delineation | Chapter 12 | Medicine and Medical Research: New Perspectives Vol. 12

Background: Phonocardiography is the study of human cardiac sounds. Phonocardiograms (cardiac sounds) as they are called, represent the most vital physiological and pathological information about the human body.

Objective: This paper presents an automatic method of segmentation of heart sounds using the occurrence of cardiac rhythmic events.

Methods: Noisy heart sound is filtered using the 6th order Chebyshev type I low pass filter to remove the redundant noise. The Bark Spectrogram is calculated from the cardiac signal by converting the spectrogram to the Bark scale. The bark spectrogram is smoothened and the loudness index is calculated by averaging the amplitude across all frequency bands. The loudness index is smoothened and differentiated to obtain the event detection function. The smoothened event detection function gives the occurrence of the cardiac events namely the first and the second heart sounds.

Result: This method is highly effective in identifying peaks S1 and S2 with a segmentation accuracy of 96.98% giving an F1 measure of 97.09%.

Conclusion and significance: This method does not require the setting up of any type of noise threshold. So, it is a highly effective type of segmentation of phonocardiogram corrupted with noise. To reduce the effect of noise the noisy phonocardiogram is heavily filtered using the time-frequency block thresholding method.

 

Author (s) Details

Vishwanath Madhava Shervegar
Department of Electronics & Communication Engineering, Moodlakatte Institute of Technology, Kundapura, Visvesvaraya Technological University, Belagavi, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mmrnp/v12/3241

Determination of Pulmonary Embolism in Lungs using Computer Assisted System |Chapter 2 | Research Developments in Science and Technology Vol. 7

 A pulmonary embolism (PE) occurs when a blood clot in the lungs produces an unexpected occlusion of a blood artery in the lungs. PE is a life-threatening illness that should be caught as soon as possible. This research provides a novel approach for detecting PE in contrast-enhanced CT images. Computed tomography is the most used method for gathering images in order to diagnose PE (CT). It's a quick test that yields high-resolution photographs with more contrast and multi-sliced images. Candidate identification, feature calculation, and classification are all part of the system. The major aims of candidate detection are to include PE even with total occlusions and to reduce erroneous tissue and parenchymal illness diagnosis. When defining characteristics, the location and structure of the pulmonary vascular tree, as well as the severity, form, and size of an embolus, are all taken into account. The ability of the CAD tool to detect emboli in the pulmonary Arterial Tree (PAT) sectional and sub sectional was studied.

Author(s) Details:

M. Sucharitha,
Department of ECE, Malla Reddy College of Engineering and Technology, Hyderabad-500100, India.

M. Mohammed Mohaideen,
Department of Aeronautical Engineering, Malla Reddy College of Engineering and Technology, Hyderabad-500100, India.

P. H. V. Sesha Talpa Sai,
Department of Mechanical Engineering and Dean- R & D, Malla Reddy College of Engineering and Technology, Hyderabad-500100, India.

Please see the link here: https://stm.bookpi.org/RDST-V7/article/view/7074

Implementation of a New Scaled Fuzzy Method Using PSO Segmentation (SePSO) Applied for Two Area Power System | Chapter 9 | Novel Perspectives of Engineering Research Vol.7

 The balance of supply and demand is one of the oldest approaches for power systems, which is considered a very complicated system (frequency control). Power system frequency response is an excellent indicator of multi-disturbance resilience. In this study, the fuzzy logic was scaled using PSO segmentation (SePSO), which is recommended for achieving high frequency stability. PSO has engaged in multisegments for computing scald-fuzzy membership using fundamental criteria. Two identical interconnected power zones were chosen to test the unique scaled fuzzy technique. The efficiency of the controller responsiveness has been tested using the MATLAB Simulink time response. In various time schedules and disturbance levels, the investigation's findings reveal that the suggested SePSO optimization for control is significantly faster and has a lower undershot than classical controllers. Because of its simplicity, traditional controllers have been employed in a variety of power system operation and control subjects.

Author(s) Details:

Balasim M. Hussein,
Department of Power and Electrical Machines, College of Engineering, University of Diyala, Iraq.

Please see the link here: https://stm.bookpi.org/NPER-V7/article/view/5906

Hierarchical Scale-space Representational Measure for Estimating Land Cover| Chapter 11 | Current Topics on Mathematics and Computer Science Vol. 2

 Shape-filling curves such as planar lines and rectilinear segments are the Minimum Mapping Unit (MMU) for an object-oriented image analysis operation. When the scale is changed, the space-filling curves do not change the feature object representation, thus representing spatial and aspatial features with finer or coarser granularity. The increased collinearity can be explained by the arrangement of topological objects (neighbors/objects) in the aggregated feature space, which results in image areal objects. Instead of performing a single operation on the imagery objects by scanline rows, we can compute on custom built algorithms applied to distinguishing objects. This operation produces super. relationships, taking advantage of multi-scale object-oriented analysis procedures A continuous hierarchical scale space filtering operation is adapted for segmentation purposes for information retrieval. In fact, MMU variations will generate instances of image objects that retain the spatial scale at a given optimizing parameter. This article focuses on object-oriented analysis and fuzzy inference analysis of the imagery scene. By denoting image analysis procedures based on image objects at the characteristic scale, imagery semantics at the low and how-level spatial context can be delineated. With object oriented scale space hierarchical theory and varying intra and inter scale parameters, such a method becomes feasible. Fuzzy modeling of mixed pixels is used to extract reliability without incorporating edges while using image objects to calculate multi-variate statistics (Entropy measure, heterogeneity measure, local mean vs. local variance measure, and mean vs. covariance measure). The Region Labeling Operator will use in-class variance measures to resolve homogeneous areas of mixed pixels. In between classes Variances can be used to calculate the distance between scale intervals that the scale object can resolve. This results in a hierarchical network that delineates the final object's features further. In the Region Growing and Region Merging procedures, the Scale Operator (SO) is defined as the varying optimizer selection. Individual objects with similar sub-class variance and texture characteristics will be fused to create a segmented super object during the region abstraction process. The Scale Operator diffuses the super-objects as a result of the increased heterogeneity, and thus more objects are merged and created within the class intervals.

Author (S) Details

C. Rajabhushanam
Computer Science Engineering, BIST Bharath Institute of Higher Education and Research, Chennai, India.

View Book :- https://stm.bookpi.org/CTMCS-V2/article/view/1783

Assessment of Sign Using Facial Expression and Hand-gesture Recognition | Chapter 7 | Recent Developments in Engineering Research Vol. 3

 

This paper focuses on a review of recent work on facial expression and hand gesture recognitions.
Facial expressions and hand gestures are used to express emotions without oral communication.
Research has been conducted on human–machine interactions (HMIs), and the expectation is that
systems based on such HMI algorithms should respond similarly. Furthermore, when a person intends to express emotions orally, he or she automatically uses complementary facial expressions and hand gestures. Extant systems are designed to express these emotions through HMIs without oral communication. Other systems have added various combinations of hand gestures and facial
expressions as videos or images. Accordingly, the systems were trained and tested. Further, certain
extant systems have separately defined the meanings of such hand gestures and facial expressions.

Author (s) Details

Dr. Rajeshree Rokade
Department of Electronics and Telecommunication, Lokmanya Tilak College of Engineering, Koperkhairne, Navi Mumbai, 400709, India.

Dr. Ketki Kshirsagar
Department of Electronics and Telecommunication, Vishwakarma Institute of Information Technology, Pune, 411037, India.

Ms. Jayashree Sonawane
Department of Electronics and Telecommunication, Lokmanya Tilak College of Engineering, Koperkhairne, Navi Mumbai, 400709, India.

Ms. Sunita Munde
Department of Electronics and Telecommunication, Lokmanya Tilak College of Engineering, Koperkhairne, Navi Mumbai,400709, India.

View Book :- http://bp.bookpi.org/index.php/bpi/catalog/book/261

Comparative Study of Image Fusion Techniques in Treatment Planning | Chapter 6 | Emerging Trends in Engineering Research and Technology Vol. 5

The process by which different images or information from multiple images are combined is termed as Image fusion which is achieved by applying a sequence of operators on the images. Recently, a number of image fusion techniques have been developed. This chapter presents a review on the main categories of image fusion namely spatial domain technique, transform domain technique and statistical domain fusion technique. This chapter also reviews on the importance of image fusion techniques in treatment planning. Image Fusion is one of the latest fields adopted to solve the problems of digital image; image fusion produces high-quality images which contains additional information for the purposes of interpretation, classification, segmentation and compression, etc. The principle requirement of the fusion process is to identify the most significant features in the input images and to transfer them without loss of detail into the fused image. Image Fusion finds its application in vast range of areas. It is used for medical diagnostics and treatment. This chapter presents a brief description of some of the extensively used image fusion techniques for treatment planning. Comparison of all available image fusion techniques concludes a better approach for future research on image fusion.

Author(s) Details

Bhuvaneswari Balachander
Department of Electronics and Communication Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India.

Dr. D. Dhanasekaran
Principal, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India.

View Book :- http://bp.bookpi.org/index.php/bpi/catalog/book/187

Real Time Static Gesture Recognition Using Time of Flight Camera: Scientific Approach | Chapter 7 | Emerging Trends in Engineering Research and Technology Vol. 2

Hand gesture recognition is challenging task in machine vision due to similarity between inter class samples and high amount of variation in intra class samples. The gesture recognition independent of light intensity, independent of color has drawn some attention due to its requirement where system should perform during night time also. This paper provides an insight into dynamic hand gesture recognition using depth data and images collected from time of flight camera. It provides user interface to track down natural gestures. The area of interest and hand area is first segmented out using adaptive thresholding and region labeling. It is assumed that hand is the closet object to camera. A novel algorithm is proposed to segment the hand region only. The noise due to ToF camera measurement is eliminated by preprocessing algorithms. There are two algorithms which we have proposed for extracting the hand gestures features. The first algorithm is based on computing the region distance between the fingers and second one is about computing the shape descriptor of gesture boundary in radial fashion from the centroid of hand gestures. For matching the gesture the distance between two independent regions is computed for every row and column. Same process is repeated across the columns. The number of total region transitions are computed for every row and column. This number of transitions across rows and columns forms the feature vector. The proposed solution is easily able to deal with static and dynamic gestures. In case of second approach we compute the distance between the gesture centroid and shape boundaries at various angles from 0 to 360 degrees. These distances forms the feature vector. Comparison of result shows that this method is very effective in extracting the shape features and competent enough in terms of accuracy and speed. The gesture recognition algorithm mentioned in this paper can be used in automotive infotainment systems, consumer electronics where hardware needs to be cost effective and the response of the system should be fast enough.

Author(s) Details

Dr. Netra Lokhande
 School of Computer Engineering and Technology, MIT World Peace University, Kothrud, Pune, India

View Book :- http://bp.bookpi.org/index.php/bpi/catalog/book/170