What is it about?
This paper deals with following components, (i). Analyzing and understanding different Medical Visual Question Answering (MVQA) datasets, (ii). Categorize the MVQA techniques based on its uniqueness (iii). The process w.r.t to the proposed MVQA system are discussed in terms of algorithms and system design (iv). Challenges w.r.t to the datasets, techniques, performance metrics are discussed along with its solutions.
Featured Image
Photo by Daniel Frank on Unsplash
Why is it important?
1. Interpretation from dataset 2. Challenges in terms of dataset, performance metrics, techniques are discussed 3. The improvisation of VQA-MED 2019, 2020 and 2021 datasets is used 4. The each step in the proposed MVQA system is explained with the help of algorithms
Perspectives
Writing this article was a great pleasure as it has co-authors with whom I have had long standing collaborations. This article also lead to young researchers to work in medical domain involving both image and text processing
Sheerin Sitara Noor Mohamed
Read the Original
This page is a summary of: A comprehensive interpretation for medical VQA: Datasets, techniques, and challenges, Journal of Intelligent & Fuzzy Systems, April 2023, IOS Press,
DOI: 10.3233/jifs-222569.
You can read the full text:
Contributors
The following have contributed to this page
