With the increased interest in artificial intelligence (AI) to support medical decision making, physicians' confidence in the interpretation of complex medical images (X-ray, MRI, Angiography, Ultrasound, Diagnostic Radiology) can be greatly enhanced by a "second opinion" provided by an automated system. In addition, patients may be interested in the morphology/physiology and pathological status of anatomical structures around a lesion that has been well characterized by their healthcare providers. Although patients often turn to search engines to resolve the ambiguity of complex terms or obtain answers to aspects related to a medical image, search engine results can be non-specific and erroneous . In contrast, a medical VQA can be integrated into an online consultation system to provide reliable answers at any time.
Dataset:
VQA-Med-2019: a training set of 3,200 medical images with 12,792 question-answer (QA) pairs, a validation set of 500 medical images with 2,000 QA pairs, and a test set of 500 medical images with 500 questions. Link: https://github.com/abachaa/VQA-Med-2019