Disruptive Technology Enabled Healthcare 4.0 Model for Lesion Identification with Reduced Latency
Kumud Tiwari1, Sachin Kumar2, R.K Tiwari3
1Kumud Tiwari*, Amity School of Engineering and Technology, Amity University, Lucknow, India.
2Sachin Kumar, Amity School of Engineering and Technology, Amity University, Lucknow, India.
3R.K Tiwari, Department of Physics and Electronics, Dr RML Avadh University, Faizabad, India.
Manuscript received on October 14, 2019. | Revised Manuscript received on 22 October, 2019. | Manuscript published on November 10, 2019. | PP: 329-343 | Volume-9 Issue-1, November 2019. | Retrieval Number: A4120119119/2019©BEIESP | DOI: 10.35940/ijitee.A4120.119119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Advancement and innovations in technology have resulted in ease of accessibility and availability of resources, resulting in an increased liability on health-care services. However, the application of healthcare services in rural and undeveloped areas remains a foremost challenge, despite the investments made, largely due to unreliable communication infrastructures. Machine learning (ML) has witnessed a terrific amount of attention over the last few years in the field of medical imaging research for the lesion detection through a biomedical application such as Magnetic Resonance Images (MRI), CT scan, X-rays and Ultrasound etc. Normally, an MRI or CT scan are used by the experts to produce images of the soft tissue of the human body. Early detection of the lesion is a crucial part of follow-up care after completion of primary treatment. The goal is to reduce the mortality rate by early detection and treating the disease while it is still curable assuming a more effective salvage surgery and treatment. This paper presents a comprehensive review of the automated classification learning algorithms to identify lesion; indicates how learning algorithms have been applied to biomedical applications from data acquisition to image retrieval and from segmentation to disease prediction. This paper provides a brief overview of recent innovations and challenges associated with learning algorithms applied to medical image processing and analysis. Lastly, the paper concludes with a concise discussion and tries to predict direction for upcoming trends on more advanced research studies on lesion detection.
Keywords: Lesion, Pattern Recognition, Machine learning, Medical Image Analysis.
Scope of the Article: Machine learning