Performance Analysis of Medical Visual Question Answering in Healthcare System
Implementation Plan:
————————–
Step 1: Initially, we collect and load data from the “Medical-Visual-Question-Answering-using-Multimodal-Fusion” Dataset.
Step 2: Then, we extract the medical image features using VGG16 and use ELECTRA-base transformer fo0r data encoding.
Step 3: Next, we perform Adaptive Answer Distillation and Querying Network using Enhanced Attention Mechanisms.
Step 4: Next, we fuse the image and text features using the novel Multi-Layer Transformers with Bi- directional Long Short-Term Memory (MLT-Bi-LSTM)
Step 5: Next, we classify the fused data using Overall ResNet152 and use a masked generative model to predict answers for a prompt related to abnormalities.
Step 6: Next, we train the data and encrypt it using Federate learning model optimization with Secure Aggregation approach .
Step 7: Finally, we plot performance metrics for the following
7.1: No of epochs vs. Accuracy (%)
7.2: No of epochs vs. Precision (%)
7.3: No of epochs vs. Recall (%)
7.4: No of epochs vs. F1-score (%)
7.5: No of epochs vs. False Positive rate (%)
7.6: No of epochs vs. False Negative Rate (%)
7.7: No of epochs vs. Loss (%)
Software Requirements:
—————————–
1. Development Tool: Python 3.11.4 or above
2. Operating System: Windows 10 (64-bit) or above
Dataset :
———–
Link:- https://github.com/KumarAditya98/Medical-Visual-Question-Answering-using-Multimodal-Fusion
Note:
——-
1) If the plan does not meet your requirements, provide detailed steps, parameters, models, or expected results in advance. Once implemented, changes won’t be possible without prior input; otherwise, we’ll proceed as per our implementation plan.
2) If the plan satisfies your requirement, Please confirm with us.
3) Project based on Simulation only, not a real time project.
4) If you have any changes in the Dataset , kindly provide before implementation.
5) Please understand that any modifications made to the confirmed implementation plan will not be made after the project development.
We perform with an existing approach Reference 4 :- Title:- Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learning
