Title: Towards a deep augmented reality medical images diagnosis generation

Authors: Sabrine Benzarti; Wahiba Ben Abdessalem Karaa; Henda Hajjami Ben Ghezala

Addresses: RIADI Laboratory, High Institute of Management of Tunis, Tunis University, Tunisia ' RIADI Laboratory, High Institute of Management of Tunis, Tunis University, Tunisia ' RIADI Laboratory, National School of Computer Science, Manouba University, Tunisia

Abstract: Augmented reality (AR) and deep learning (DL) are promising areas. In this paper, we present the impact of such assortment (AR/DL) on the enhancement of generating textual and oral descriptions from a target medical image. The main purpose is to assist medical practitioners to make an accurate decision about a generated diagnosis. Automatic medical image report generation (textual and vocal) is used up as a diagnostic aid system for disease diagnoses depend strongly on visual properties. In this paper, we will describe how we develop an augmented report for the X-ray image target. Primary results using prototypes are promising. Doctors, learner's task are more efficient and feedbacks are encouraging.

Keywords: CNN; RNN; image captioning; augmented reality; medical image diagnosis generation.

DOI: 10.1504/IJIM.2021.115775

International Journal of Image Mining, 2021 Vol.4 No.1, pp.59 - 68

Received: 18 Aug 2020
Accepted: 13 Nov 2020
Published online: 21 Jun 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article