Measurement of Nuchal Translucency Thickness in First Trimester Ultrasound Fetal Images using Pose Invariant Context Aware Deep Learning Network
Kalyani Choudhari1, Shruti Oza2
1Kalyani Chaoudhari*, Research Scholar, Dept. of Electronics, Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, India.
2Dr. Shruti Oza, Professor, Dept. of E&TC, Bharati Vidyapeeth (Deemed to be University) college of Engineering, Pune, India.
Manuscript received on January 14, 2020. | Revised Manuscript received on January 21, 2020. | Manuscript published on February 10, 2020. | PP: 2196-2201 | Volume-9 Issue-4, February 2020. | Retrieval Number: D1736029420/2020©BEIESP | DOI: 10.35940/ijitee.D1736.029420
Open Access | Ethics and Policies | Cite | Mendeley
© 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: The downside of current NT estimation strategy is limited with bury and intra-eyewitness fluctuation and irregularity of results. Existing techniques, be that as it may, present costly computational overhead and in this manner are as yet unequipped for quick NT limitation and location, which is fundamental for independent identification frameworks. Henceforth, we present a robotized location and estimation technique for NT in this examination. We are introducing a setting mindful Circumstance Independent Searching, what we can do create exact element maps to be used NT alongside a multi level choice system for NT recognition. It can precisely find NT with an enormous difference of scales without presenting extra computational expense. We additionally build the primary enormous scale change emergency clinic dataset of 500 images, which gives a stage to specialist to assess the presentation of different NT restriction and identification calculations.
Keywords: CNN, NT.
Scope of the Article: Deep Learning