Dr Tushar H Jaware
@rcpit.ac.in
Dean Research and Development
R C Patel Institute of Technology Shirpur
RESEARCH INTERESTS
Medical Image Processing
Scopus Publications
Scopus Publications
Tushar Hrishikesh Jaware, Vinodkumar Ramesh Patil, Chittaranjan Nayak, Ali Elmasri, Nawaf Ali, and Purnendu Mishra
Elsevier BV
Ravindra D Badgujar, Tushar H Jaware, Mahesh B Dembrani, Jitendra P Patil, and Prashant G Patil
IEEE
Diabetes has become a modern epidemic. Globally, the prevalence rate of diabetes is high and it tends to even higher. WHO reports, globally around 1.3 billion peoples suffer from some form of eye related diseases. Diabetic retinopathy (DR) is the leading cause of vision loss among working-age individuals and represents the most common repercussion of diabetes. Early DR diagnosis and therapy might stop or postpone its progression and subsequent vision loss. However, manual screening of DR is time-consuming and subject to inter-observer variability. Therefore, computer-aided methods for automated DR detection are of great interest. This article proposes the computer aided, automated DR detection approach. Initially anisotropic diffusion filtering is employed for pre-processing of retinal fundus images. In segmentation, the anatomical structures are identified and eliminated. The DR lesions segmentation is performed using active contour and modified Tsallis entropy approach. Active contour models, also known as snakes, have been extensively used for medical image segmentation and boundary detection. These models use an energy minimization approach to detect the contours of objects in an image. Finally feature extraction and classification of DR lesions is achieved with the help of Gray Wolf optimizer. Gray Wolf Optimizer (GWO) is an emerging optimization algorithm that draws inspiration from the hunting behavior of gray wolves. It has shown promising results in various optimization problems, including medical image segmentation. In this research work, we propose a novel method for DR detection using active contour and GWO. Our approach combines the strengths of these two techniques to improve the accuracy and efficiency of DR detection. We evaluate developed method using a publicly available dataset and compare its performance with recent DR detection approaches.
Narendra Lalchand Lokhande and Tushar Hrishikesh Jaware
IEEE
Lung cancer remains a significant global health concern, necessitating advancements in early detection and diagnosis. This research presents a comprehensive approach to lung cancer detection using computed tomography (CT) images and advanced image processing techniques. The proposed methodology encompasses image enhancement through Block-Matching 3D (BM3D) filtering, precise segmentation using Random Walker segmentation, and comprehensive feature extraction, incorporating Gray-Level Co-occurrence Matrix (GLCM) analysis and Haralick texture features. The study leverages the Lung Image Database Consortium (LIDC) database to evaluate effectiveness of the proposed approach. The pre-processing stage employs BM3D filtering to attenuate noise inherent in CT images, enhancing the subsequent analysis. Random Walker segmentation is then employed to accurately delineate lung nodules, even in cases of irregular boundaries. GLCM analysis and Haralick texture features extraction capture nuanced textural information within segmented nodules, facilitating the characterization of potential cancerous regions. Experimental results determine the effectiveness of proposed approach. By integrating BM3D filtering, Random Walker segmentation, and texture analysis, the method achieves robust lung nodule detection and accurate cancer region identification. Comparative analysis against existing techniques highlights its promising performance. This research contributes to the field of lung cancer detection by presenting an integrated framework that leverages cutting-edge image processing techniques. The combination of BM3D filtering, Random Walker segmentation, and texture analysis enhances CT image lung cancer detection accuracy. The findings underscore the potential of this approach as a valuable tool for early diagnosis, ultimately contributing to improved patient outcomes.
Svetlin Antonov, Mahesh Dembrani, Dipak Patil, Tushar Jaware, and Ravindra Badgujar
IEEE
Accurate identification of electrocardiogram (ECG) signals is crucial in clinical diagnostics. This research paper presents an implementation of an adaptive digital filter for reliable ECG signal identification. The study focuses on utilizing the Distributed Arithmetic (DA) and Fast Block LMS (FBLMS) algorithm to enhance accuracy and reduce power consumption. To achieve optimal clutter elimination and convergence speed, adaptive step size algorithms based on correlation coherence measurements of the reference signal are employed. The implementation is carried out on FPGA Virtex 5 boards, emphasizing minimal power and memory requirements. Experimental results demonstrate improved accuracy and reduced power consumption, indicating the potential of the proposed approach for reliable ECG signal identification.
Rashmi Saini, Prabhakar Semwal, and Tushar Hrishikesh Jaware
Springer Nature Switzerland
Patil Vinodkumar Ramesh, Jaware Tushar Hrishikesh, and Manisha S. Patil
Auricle Technologies, Pvt., Ltd.
Infant MRI brain soft tissue segmentation become more difficult task compare with adult MRI brain tissue segmentation, due to Infant’s brain have a very low Signal to noise ratio among the white matter_WM and the gray matter _GM. Due the fast improvement of the overall brain at this time , the overall shape and appearance of the brain differs significantly. Manual segmentation of anomalous tissues is time-consuming and unpleasant. Essential Feature extraction in traditional machine algorithm is based on experts, required prior knowledge and also system sensitivity has change. Recently, bio-medical image segmentation based on deep learning has presented significant potential in becoming an important element of the clinical assessment process. Inspired by the mentioned objective, we introduce a methodology for analysing infant image in order to appropriately segment tissue of infant MRI images. In this paper, we integrated random forest classifier along with deep convolutional neural networks (CNN) for segmentation of infants MRI of Iseg 2017 dataset. We segmented infants MRI brain images into such as WM- white matter, GM-gray matter and CSF-cerebrospinal fluid tissues, the obtained result show that the recommended integrated CNN-RF method outperforms and archives a superior DSC-Dice similarity coefficient, MHD-Modified Hausdorff distance and ASD-Average surface distance for respective segmented tissue of infants brain MRI.
T. Jaware, K. Kumar, R. Badgujar and S. Antonov
Wiley
Medical imaging and health informatics is a subfield of science and engineering which applies informatics to medicine and includes the study of design, development, and application of computational innovations to improve healthcare. The health domain has a wide range of challenges that can be addressed using computational approaches; therefore, the use of AI and associated technologies is becoming more common in society and healthcare. Currently, deep learning algorithms are a promising option for automated disease detection with high accuracy. Clinical data analysis employing these deep learning algorithms allows physicians to detect diseases earlier and treat patients more efficiently. Since these technologies have the potential to transform many aspects of patient care, disease detection, disease progression and pharmaceutical organization, approaches such as deep learning algorithms, convolutional neural networks, and image processing techniques are explored in this book.
Prashant G. Patil, Tushar H. Jaware, Sheetal P. Patil, Ravindra D. Badgujar, Felix Albu, Ibrahim Mahariq, Bahaa Al-Sheikh, and Chittaranjan Nayak
Institute of Electrical and Electronics Engineers (IEEE)
Globally, 1.6 billion individuals suffered from hearing disability in 2019. According to the World Health Organization, by 2050, the number of people with hearing impairments will rise to 2.5 billion. Speech perception in noisy surroundings is a challenge for hearing aid users. This study aimed to design a novel methodology to improve the speech recognition ability of hearing aid users from various backgrounds. To improve speech enhancement, we propose a discrete cosine transform (DCT)-based improved amplitude-magnitude spectrogram (I-AMS) algorithm with a fuzzy classifier. First, the I-AMS approach disintegrates speech signals containing noise into time-frequency units and eliminates the noise present in the signal. Next, the time frequency units (t-f units), modulation frequency (fm), and centre frequency (fc) are extracted from the denoised signal. A neuro-fuzzy classifier was used to classify the background speech environment into three different classes. The proposed I-AMS algorithm was tested, achieved improvements in terms of sensitivity (+1.02%) and accuracy (+11.80%). Speech denoising revealed a 1.27% improvement in speech recognition performance.
Steve Ankuo Chien, Minh N. Do, Alan Fern and Wheeler Ruml
IOP Publishing
Proceedings of the Global Sustainability Conference GSC 2022 We are honored and glad to welcome you at the Global Sustainability Conference 2022 organized by Advanced Computing Research Society on 18-19 April, 2022. The Conference was hosted at the Seminar hall of Bonfils Automation Technologies Pvt. Ltd., Chennai. Due to the ongoing pandemic situation, authors were given the opportunity to present both in online and offline mode. This conference and these proceedings are a unique opportunity for sharing ideas and achievements, discoveries and innovation for growing together our knowledge and contribute to expand the knowledge of humanity. The technological areas addressed in this meeting is in response to United Nations call of action to end poverty, protect the planet and ensure that all people enjoy peace and prosperity by 2030. The conference covers topics on the interdisciplinary areas of agriculture and food security, biodiversity conservation, circular economy, cities and urbanisation, climate change in holistic context, development, economy, ecosystem services, ecological protection, education, energy, environmental development, environmental law, finance, gender equality, green infrastructure, health and environment, human population, industrialization, innovation, land cover and land use change, natural capital, natural resources conservation and management, pollution, poverty, social and cultural, supply chain, waste, water–energy–food and water-soil-waste connections and others, all as related to sustainability. We received 36 papers and after peer review 13 papers were accepted and presented in this conference. The papers were evaluated on the basis of completeness, relevance to the conference, originality, sufficiently novel, technical quality, structure and presentation of the paper and adequate references to previous work. Every paper was reviewed by at least 3 reviewers and the review comments were shared with the authors for incorporating the suggestions and comments. List of Editors of the Proceedings, Committees are available in this pdf.
Vinodkumar R. Patil and Tushar H. Jaware
Springer Singapore
Narendra Lalchand Lokhande and Tushar Hrishikesh Jaware
Springer Singapore
Kishor V. Bhadane, M. S. Ballal, Anand Nayyar, D. P. Patil, T. H. Jaware, and H. P. Shukla
Springer Science and Business Media LLC
Tushar H. Jaware, Vinod R. Patil, Ravindra D. Badgujar, Sumanta Bhattacharyya, Rajesh Dey, and Rudra Sankar Dhar
Springer Science and Business Media LLC
Kishor V. Bhadane, Tushar H. Jaware, Dipak P. Patil, and Anand Nayyar
Springer International Publishing
Tushar Jaware, Kamlesh Khanchandani, and Ravindra Badgujar
Informa UK Limited
Abstract Objective: The newborn brain MRI (magnetic resonance imaging) tissue segmentation plays a vital part in assessment of primary brain growth. In the newborn stage (nearly less than 28 days old), in T1- as well as T2-weighted MR images similar levels of intensity are exhibited by WM and GM, makes segmentation of the tissue extremely challenging. In this newborn stage for tissue segmentation, very few methods are developed. Hence the development of accurate brain tissue segmentation of neonate is prime objective of this paper. Methods: In this research work, we propose a novel hybrid atlas-free hierarchical graph-based tissue segmentation method for newborn infants. Wavelet filter banks are a class of deep models wherein filters and local neighborhood processes are used alternately for efficient segmentation on the raw input images, and fuzzy-based SVM (support vector machine) is used for precise tissue classification. Results: Specifically, from T1, T2 images multimodality information are used as inputs and then as outputs the segmentation maps are generated. The proposed approach considerably outperforms preceding methods of tissue segmentation as reflected in results. With this approach, the newborn MRI images that are even suffered from noise, poor resolution or the low contrasted images are also segmented more effectively with precision of 90% and sensitivity 98%. Conclusion: In addition, our findings indicate that the incorporation of multi-modality image led to significant improvements in performance. Thus, the proposed work effectively tackles the unreliability as well as the other issues faced with the prior methodologies with an interactive accurate segmentation outline.
Tushar H. Jaware, K. B. Khanchandani, and Durgeshwari Kalal
Informa UK Limited
ABSTRACT Automatic segmentation and classification of infant brain MRI is a fundamentally difficult task because of the low contrast and the development process of the brain tissues. The strategies adapted for adult brain MRI segmentation are not reasonable to the neonatal brain, because of the immense differences in structure and tissue properties amongst infant and adult brains. The current infant brain MRI segmentation techniques depend on manual interaction and they used atlases or formats which could not fragment most extreme number of tissues. In this paper, we proposed an atlas-free infant brain image segmentation and classification scheme in light of self-organised map (SOM) – deep convolutional neural network (DCNN) with sparse auto encoder. The hybridisation of SOM-DCNN scheme gives accurate segmentation of infant brain tissues and the classification is performed through SAE (sparse auto encoder). Our proposed scheme is approved through dice metrics, which demonstrates that our proposed strategy gives accurate result, compare to existing segmentation schemes.
Tushar H. Jaware, K. B. Khanchandani, and Anita Zurani
Georg Thieme Verlag KG
Background Segmentation of brain MR images of neonates is a primary step for assessment of brain evolvement. Advanced segmentation techniques used for adult brain MRI are not companionable for neonates, due to extensive dissimilarities in tissue properties and head structure. Existing segmentation methods for neonates utilizes brain atlases or requires manual elucidation, which results into improper and atlas dependent segmentation. Objective The primary objective of this work is to develop fully automatic, atlas free, and robust system to segment and classify brain tissues of newborn infants from magnetic resonance images. Study Design In this study, we propose a fully automatic, atlas-free pipeline based Neural Tree approach for segmentation of newborn brain MRI which utilizes resourceful local resemblance factor such as concerning, connectivity, structure, and relative tissue location. Physical collaboration and uses of an atlas are not required in proposed method and at the same time skirting atlas-associated bias which results in improved segmentation. Proposed technique segments and classify brain tissues both at global and tissue level. Results We examined our results through visual assessment by neonatologists and quantitative comparisons that show first-rate concurrence with proficient manual segmentations. The implementation results of the proposed technique provided a good overall accuracy of 91.82% for the segmentation of brain tissues as compared with other methods. Conclusion The pipelined-based neural tree approach along with local similarity factor segments and classify brain tissues. The proposed automated system have higher dice similarity coefficient as well as computational speed.
Tushar H. Jaware, K.B. Khanchandani, and Anita Zurani
IEEE
This paper focuses on the development of an accurate neonatal brain MRI segmentation algorithm and its clinical application to characterize normal brain growth and explore the neuro-anatomical correlates of cognitive impairments. The segmentation of MR images of the neonatal brain is a fundamental step in the study and assessment of infant brain development. The highest level of development techniques for adult brain MRI segmentation are not suitable for neonatal brain, because of substantial contrasts in structure and tissue properties between newborn and fully developed brains. Current newborn brain MRI segmentation techniques either depend on manual interaction or require the utilization of atlases or templates, which unavoidably presents a bias of the results towards the population that was utilized to derive the atlases. In this paper, we proposed an atlas-free approach for the segmentation of neonatal brain MRI, based on the neural network approach. The segmentation is primary stage to obtain quantitative analysis of regional brain tissues. These measurements allow characterization of the regional brain growth and inspect the correlations with clinical factors.
Tushar H. Jaware, K. B. Khanchandani, and Anita Zurani
Springer Singapore
Tushar H. Jaware, K. B. Khanchandani, and Anita Zurani
Indian Society for Education and Environment
Objectives: Every year millions of babies born preterm and it is a serious issue in developed countries. Preterm birth is worldwide problem of young children. Methods/Statistical analysis: Advances in Magnetic Resonance Imaging (MRI), comprehensive images of the newborn brain is visualized non-invasively. Here we are focusing on the early assessment of brain development in neonates and premature infants using multi stage segmentation and classification approach with quantitative analysis. To achieve higher segmentation and classification accuracy neural network classifier are used. It is also helpful in detection and classification of more number of brain tissues. Findings: The accurate segmentation and classification of brain tissues is very much useful in evaluating the brain development of newborn and premature infants. Therefore, newborn brain MRI forms a crucial part in analytical neuro-imaging; principally in the neonatal stage.Our method gives higher dice similarity index values and higher computational speed as compared to existing methods. Application: Resulting segmentations are used for volumetric analysis and quantification of cortical descriptions. This analysis plays vital role for neonatologists in early detection and diagnosis of neural impairments.