Fondamenti di IA in diagnostica per immagini
none
The examination consists of two parts, equally weighted. A written test with multiple-choice and/or open-ended answers, which focuses on ascertaining the knowledge and skills described in the learning objectives. An oral test where the lecturer will ask some specific questions (at least 4) on the topics covered in the course.
1. The module provides basic knowledge of the main concepts of image processing with special reference to medical images.
2. The module introduces the concepts of machine learning and Artificial Intelligence (AI), with application to medical imaging.
3. By the end of the course, the student is able to understand the potential of AI to improve the accuracy and efficiency of medical image interpretation.
1. Key concepts in image processing: sampling, quantization, resolution and filtering, image formats.
2. Image processing: contrast enhancement, sharpening, noise removal, segmentation.
3. Key concepts in AI: supervised and unsupervised machine learning, regression and classification problems, neural networks, deep learning, transfer learning, big-data, data analysis and the role of AI.
4. Applications: convolutional neural networks for medical image analysis, classification and segmentation. Case studies exemplifying how by learning from large medical image data sets, AI algorithms can identify patterns and anomalies that might be overlooked by the human eye.
24 hours of frontal lessons
The lecturer receives by appointment, upon request by e-mail to: silvia.corchs@uninsubria.it