Deep Learning with Applications in Medical Imaging, 7.5 Credits

Contents

This course covers deep convolutional neural networks (CNNs) for computer vision, with applications in medical image analysis. The course provides an introduction to fundamental concepts in machine learning, describes neural networks and the field of deep learning, and goes into detail about deep CNNs. The course describes the different parts that are used when building deep CNNs, such as filters, activation functions, loss functions; regularization techniques such as e.g. batch normalization and dropout; explains several of the different non-linear optimization algorithms that are used when training the networks, and describes popular network architectures, and discusses their pros and cons. The course also covers generative models, such as variational autoencoders (VAE) and generative adversarial networks (GANs).

Students in this course will learn to implement and train modern network architectures and deep learning methods, and apply these to large image datasets with medical and other images.

The course has two modules:
Theory and method, 5.5 ECTS credits
Practical assignments, 2.0 ECTS credits

Expected learning outcomes

Knowledge and understanding:

The student must be able to

• Explain and describe central concepts in machine learning, such as e.g. training and validation data, classification and regression, supervised and unsupervised learning, bias and variance, loss function, generalization error, accuracy, precision, recall. (FSR1)
• In detail explain the central concepts in deep learning, such as e.g. depth, learning rate, hyper parameter, early stopping, overtraining regularization. (FSR2)
• In detail explain the different parts of a convolutional neural network and their purpose, such as e.g. layer, nodes, activation function, dropout, loss function, residual connection. (FSR3)
• Describe the stochastic gradient descent algorithm, its benefits, and the main differences between it and other non-linear optimization algorithms that are used when training neural networks. (FSR4)
• In detail explain some of the most common architectures and models used, and describe the main benefits of the different architectures. (FSR5) 

Skills and abilities:

The student must be able to

• Independently design and implement common network architectures, and use these in applications for e.g. classification and regression. (FSR6)
• Use modern software libraries for building and training deep convolutional neural networks to solve specific tasks. (FSR7)
• Evaluate and compare performance and generalization of deep convolutional neural networks. (FSR8) 

Evaluation ability and approach:

The student must be able to

• Reflect on and report on how modern machine learning and deep learning methods affect humans, companies, and the society. (FSR9)
• Reflect on the state of the field of deep learning and its place in machine learning, and explain the general capabilities of artificial intelligence in our time. (FSR10)
• In a scientific way evaluate different solutions pros and cons. (FSR11)
• Critically review results or statements from other studies, or e.g. products that either are based on deep learning or otherwise is using it. (FSR12)

Required Knowledge

Univ: For access to the course requires 90 credits of completed studies in one of the main areas of computer science, physics, electronics, chemistry, mathematics or mathematical statistics are required, or 2 years of completed studies (120 credits). Of these credits, at least 7.5 credits are required in basic programming methodology in Python, C, and/or Matlab, at least 7.5 credits dealing with Data Structures and Algorithms, at least 7.5 credits dealing with Linear Algebra, at least 7.5 credits dealing with analysis with concepts such as derivatives and limit values, at least 7.5 credits dealing with mathematical statistics, or equivalent knowledge. English A/6 if the teacing language is english.

Form of instruction

The course is campusbased and consists of lectures and practical assignments. In addition to scheduled activities, the students are required to work with the material individually. The students are required to cover the material and prepare questions in order to obtain appropriate feedback.
Teaching may be conducted in English.
 

Examination modes

Module 1 (Theory and method, 5.5 ECTS credits, ELO 1-5, 9-12): The module is assessed through a written exam. The grades for this module are: Fail (U), Pass (G), or Pass with merit (VG).
Module 2 (Practical assignments, 2.0 ECTS credits, ELO 6-8): The module is examined individually with written assignments, with one of the grades Fail (U) or Pass (G).

The entire course is given one of the grades Fail (U), Pass (G), Pass with distinction (VG). The grade is based on the grade received on module 1 and is only decided when all the course's tests have been completed and grades on both modules have been decided.

A student who has received a passing result on an exam may not take a new exam.

The examiner can decide on deviations from the examination form of the syllabus. Individual adaptation of the form of examination must be considered based on the student's needs. The form of the examination is adapted within the framework of the curriculum's expected study results. A student who needs an adapted examination, and who has received a decision on the right to support from the coordinator for students with disabilities at the Student Centre, must request adaptation from the department responsible for the course no later than 10 days before the examination. The examiner decides on an adapted examination, which is then notified to the student.
 

Other regulations

In the event that the course plan ceases or undergoes major changes, students are guaranteed at least three exam opportunities (including regular exam opportunities), according to the regulations in the course plan in which the student was originally registered, for a maximum of two years from the time the previous course plan expired.