“Signal Processing in the AI era” was the tagline of this year’s IEEE International Conference on Acoustics, Speech and Signal Processing, taking place in Rhodes, Greece.
In this context, Brent de Weerdt, Xiangyu Yang, Boris Joukovsky, Alex Stergiou and Nikos Deligiannis presented ETRO’s research during poster sessions and oral presentations, with novel ways to process and understand graph, video, and audio data. Nikos Deligiannis chaired a session on Graph Deep Learning, attended the IEEE T-IP Editorial Board Meeting, and had the opportunity to meet with collaborators from the VUB-Duke-Ugent-UCL joint lab.
Featured articles:
On February 5 2021 at 16.00 Alexander Soñora Mengana will defend his PhD entitled “COMPUTER AIDED DETECTION OF LUNG NODULES FROM CT IMAGING”.
Lung cancer is the first cause of cancer related death worldwide Early detection can have substantial impact on treatment outcome Computer aided detection (systems can play an important role in improving the detection rate and reducing the clinical workload, in particular considering the lung cancer screening protocols that are currently being set up.
Starting from an existing system for computer aided detection of lung cancer, several aspects of the processing pipeline were investigated, with the aim to improve the accuracy and robustness of the process The system employed a two stage approach, comprising of a candidate detector, and a false positive reduction step based on hand crafted features Initially the design of the system was changed to a modular architecture to facilitate introducing alterations at different stages, and evaluate their impact The system’s efficiency and usability was improved and individual components were tuned.
Next, a thorough characterisation of its performance by participating to the LUNA 16 Challenge The participation implied training and testing the system on large clinical dataset It also enabled the objective comparison to other proposed CAD approaches using a common evaluation methodology The system as a whole, was shown to perform well, achieving comparable results to other full system submissions at the time of the challenge Closer analysis, revealed this was mainly due to a sensitive nodule candidate detector, whereas other approaches were found to have better false positive reduction.
Subsequently, several aspects of the pipeline were investigated, to improve on this baseline results An improved lung segmentation procedure was added to the preprocessing stage The method reduces the amount of failed lung segmentations due to artefacts or even tracheotomy by performing an error detection and correction procedure, making the candidate detection process more robust.
Candidate detectors often mark a large number of non nodule structures compared to the of actual nodules This imbalance in the data during training, may hinder the performance of the classifier Data balancing methods, comprising both undersampling and oversampling approaches in feature space, were therefore investigated in detail Surprisingly, undersampling the majority class, as performed in the original system, was found to perform worse compared to no balancing Balancing by oversampling the minority class allowed to improve the result further
Over the course of my PhD, deep learning methods emerged for medical image analysis, and rapidly outperformed alternative approaches in the CAD domain I therefore investigated how to increase the accuracy of the false positive reduction by training a convolutional neural network using the candidates provided by my detector, and obtained a substantial increase in accuracy
Interestingly, combining the learnt features with the hand crafted features, improved the results even further
Sofia Granda attended the Master in Biomedical Engineering in 2020-2021. She chose the program because she really liked mathematics, physics, and biology at high school and liked to be able to find practical solutions to problems. Sofia described the program in the following three words: Empathy, Logic and Medicine. Strengths of the program were the flexibility in the second year choosing the electives from a very wide offer. It included many practical sessions and visits to the hospital. But sometimes is was difficult to understand the global picture and the purpose of some contents of the program. There were some overlaps. Her favorite course was Health Information and Decision support systems. The collaboration with the other students from different cultures lead sometimes towards cumbersome communication but in the end, it was enriching. Sofia’s golden tip for future students is: Be true to yourself and don’t be afraid of following your goals, even when you get demotivated due to bad scores or difficulties with learning, especially with courses you don’t like but that are mandatory.
Sofia would like to end up applying her knowledge improving people’s lives or investigating in a job that fulfills her and that she is proud of.
Students who think they have had the same course before, have to fill out the form for exemption, (https://student.vub.be/en/ir#regulations-and-forms) and together with the transcripts send everything to the faculty secretary office.
The programme starts every year in September (typically, the lectures start in the 4th week of September).
Ann Dooms from the Department of Mathematics and Data Science of VUB gave Manneken Pis a new costume, honouring Pythagoras. Quentin Bolsee from ETRO helped make the costume in his spare time and made the 3D printed part that demonstrates Pythagoras theorem by dispensing liquid from one square to another. It spins using custom electronics he made at the fablab.