Evolution of Big Data in Medical Imaging Modalities to Extract Features Using Region Growing Segmentation, GLCM, and Discrete Wavelet Transform

Evolution of Big Data in Medical Imaging Modalities to Extract Features Using Region Growing Segmentation, GLCM, and Discrete Wavelet Transform

Yogesh Kumar Gupta
DOI: 10.4018/978-1-6684-3662-2.ch022
(Individual Chapters)
No Current Special Offers


Big data refers to the massive amount of data from sundry sources (gregarious media, healthcare, different sensor, etc.) with very high velocity. Due to expeditious growth, the multimedia or image data has rapidly incremented due to the expansion of convivial networking, surveillance cameras, satellite images, and medical images. Healthcare is the most promising area where big data can be applied to make a vicissitude in human life. The process for analyzing the intricate data is mundanely concerned with the disclosing of hidden patterns. In healthcare fields capturing the visual context of any medical images, extraction is a well introduced word in digital image processing. The motive of this research is to present a detailed overview of big data in healthcare and processing of non-invasive medical images with the avail of feature extraction techniques such as region growing segmentation, GLCM, and discrete wavelet transform.
Chapter Preview


In this digital, the astronomically immense data is a very critical quandary because of the tremendous amount of data engendered in routine life from sundry sources such as online transaction, e-mails, research journals and articles, convivial media sites (Facebook, Twitter, WhatsApp etc.) and web forums, different sensor’s data composed from sundry sources such as healthcare science or medical data, environmental organizations, meteorological department, business strategically data, trading market, company data being engendered daily life in different format such as structured, semi-structured and unstructured with a great velocity is customarily referred to as sizably voluminous Data (Singh, 2016). Data can be engendered on web in sundry forms like texts, audios, videos, images, texture or gregarious media posts data etc. This tremendous data is no more time stable in environment; rather it is updated according to time at rapid celerity. So that put an immensely colossal number of critical challenges on sizably voluminous data processing and storage. As an outcome, the conventional database computation implements and algorithms as well as data storage and management techniques has not able to deal with these data (Altera, 2016). Thus the astronomically immense data need to describe sundry innovative storage and processing implements (such as Hadoop, MapReduce, NoSQL database, HPCC and Apache Hive etc.) to acquire, store, distribute, handle and analyze. The process for analyzing the perplexed data mundanely concerned with the disclosing the hidden patterns. Big data involves sizably voluminous distributed file systems in commodity hardware for storing, which should be more flexible, fault tolerant, scalable and reliable (Singh, 2016).

This digitized era needs to process the images for the manipulation of image properties. As immensely colossal data comes with the flood of intricate and digitize data so as to manage this data, there is need to have a discussion in an optimistic manner which describes its valuable and valid positive aspects. Healthcare industry conventionally has engendering astronomically immense amounts of data. As authors ken that historically the data stored in hard copies but nowadays there is a rapid digitization of this massive amount of stored data. The immensely colossal data analysis holds a broad accumulation of medical and healthcare applications such as public health management, clinical assessment and disease scrutiny. Big data analytics in healthcare has the puissance to decrement the costs of treatment, amend care, preserve lives and additionally ameliorate the quality of life.

From the commencement of evolution to 2003, only 5 Exabyte’s of information has engendered, currently by 2012 the authors engender that equipollent amount in just two days, if authors consider data of digital macrocosm that will cultivate to 2.72 Zeta bytes and by 2015 that will twice over every two years to reach 8 Zeta bytes (Tamilselvan, 2015).

According to the report given by McKinney Ecumenical Institute, it is considered that the healthcare sector could engender more than $300 billion value per year, if US healthcare organizations were to utilize immensely colossal data resourcefully and prosperously (Lodha, 2014). Big data in Healthcare is irresistible on account of its broadly expounded aspects termed as degree, verities of data and its pace .i.e. rate at which data is engendered (Archenaa, 2015). The electronic healthcare data includes medical imaging engendered through minimal and non-invasive medical imaging modalities techniques such as PET-Scan, CT-Scan, X-ray, MRI, Ultrasound etc., diagnostic reports, pharmacy information for health indemnification, medical research journals, and laboratory experiment values, implants and surgery test results, medication information etc. which is prone to avail the organizations to build a 360˚ view of each and every patient. The pace of Electronic Care Records (ECR) implementation exponentially increases in inpatient and outpatient aspects. To enhance the amelioration in outcomes, reduction of costs and excellence of care, this digitization of healthcare informatics is opening tremendous promising possibilities to avail the payers, stakeholders and providers (Gupta, 2016). All the healthcare organizations are required to turn into data driven area to survive in the period of immense transformation.

Complete Chapter List

Search this Book: