Visual interpretability of deep learning algorithms in medical applications

Artificial intelligence is having a very big boost in recent times, and after the success of deep learning algorithms in many applications, they are also providing successful results for medical imaging, especially because of the good performance of convolutional neural networks. However, the black...

Full description

Bibliographic Details
Author: Jorba Soler, Christian
Format: master thesis
Publication Date:2020
Country:España
Institution:Universitat Politècnica de Catalunya (UPC)
Repository:UPCommons. Portal del coneixement obert de la UPC
Language:English
OAI Identifier:oai:upcommons.upc.edu:2117/349401
Online Access:https://hdl.handle.net/2117/349401
Access Level:Open access
Keyword:Machine learning
Artificial intelligence
Neural networks (Computer science)
machine learning
artificial intelligence
interpretability
deep learning
convolutional neural network
transfer learning
LIME
occlusion
class activation mapping
saliency maps
activation maximization
Aprenentatge automàtic
Intel·ligència artificial
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Física
Description
Summary:Artificial intelligence is having a very big boost in recent times, and after the success of deep learning algorithms in many applications, they are also providing successful results for medical imaging, especially because of the good performance of convolutional neural networks. However, the black box behaviour of these networks makes it very difficult to assign them tasks that an expert human normally does. This project aims to interpret in human terms what a convolutional neural network trained to classify fetal different ultrasound planes is based on. We use transfer learning to build a network with good performance in the classification task and apply interpretability techniques on it. These methods include Activation Maximization, Saliency Maps, Occlusion Sensitivity Maps, Class Activation Mapping and LIME. The trained network is able to classify fetal ultrasound images with an accuracy of 91.7%, and we provide a robust interpretation of its performance that allows us to understand the most important characteristics of each class for the model.