Abstract
Data science and artificial intelligence (AI) are the main factors driving a new technological revolution. Just recently (November 2019), key U.S. policymakers have announced intentions to create an agency that would invest $100 billion over 5 years on basic research in AI, with a focus on quantum computing, robotics, cybersecurity, and synthetic biology.
The need for well educated people in these areas is growing exponentially, and this is more stringent than ever for medical bioengineering professionals who are expected to play a leading role in the promotion of advanced algorithms and methods to advance health care in fields like diagnosis, monitoring, and therapy.
In a recent study on the current research areas of big data analytics and AI in health care, the authors have performed a systematic review of literature and found that out the primary interest area proved to be medical image processing and analysis (587 entries out of 2421 articles analysed) followed by decision-support systems and text mining and analysis.
Case-based learning is an instructional design model that is learner-centered and intensively used across a variety of disciplines. In this paper, we present a set of tools and a case study that would help medical bioengineering students to grasp both theoretical concepts (both medical, such as gynecological disorders and technological, such as deep learning, neural network architectures, learning algorithms) and delve into practical applications of these techniques in medical image processing.
The case study concerns the automated diagnosis of cervigrams (also called cervicographic images), that are colposcopy images used by the gynecologist for cervical cancer diagnosis, study and training. The tools described in this paper are based on using PyTorch, Keras and Tensor Flow. They allow image segmentation, automated detection of cervix, and cervical cancer classification, while also sustaining an intense interaction between participants to the case study. Based on these tools (for which we describe their distinctive advantages and provide comparisons in terms of accuracy and speed), we describe in full details different teaching strategies. |
Keywords
Data science, artificial intelligence, deep learning, case-based learning, colposcopy, cervigrams |