Congratulations to Bashir Dodo for his paper on “Level set Segmentation of Retinal OCT Images” that has been shortlisted for Best Paper at BIOIMAGING 2019!
Author: cssrajt
New paper accepted: Statistics and Computing
New paper accepted in Statistics and Computing on “Learning Bayesian Networks from Big Data with Greedy Search“.
IDA / BSEL Christmas Party 2018
IDA Group to advise MHRA / NHS Digital
Nicky Nicolson and Leila Yousefi at IDA 2018
Special Track at IEEE CBMS organised by the IDA Group
Please consider submitting your work to the special track on explainable AI at IEEE CBMS this year. Deadline for submissions is 14 Jan 2019!
IDA 2018 Call for Posters
New PhD student
Welcome to Ben Evans who has been awarded a prestigious London NERC DTP scholarship on the project “A global canonical image data set for automatic species classification” working with the Zoological Society of London and Google.
New Seminar Series in IDA
We have a new funded seminar series in the IDA group starting in October 2018 on the theme of “Opening the Black Box”.
Please look out for details on the website here in the upcoming months
CBMS 2018 Best Student Paper – Leila Yousefi
Congratulations to Leila Yousefi who won best student paper at IEEE CBMS 2018. The paper is titled “Predicting Disease Complications Using a Step-Wise Hidden Variable Approach for Learning Dynamic Bayesian Networks”
Below is the abstract and full list of authors.
Predicting Diabetes Type 2 Mellitus (T2DM) complications such as retinopathy and liver disease is still a challenge despite being a growing public health concern worldwide. This is due to the complex interactions between complications and other features, as well as between the different complications, themselves. What is more, there are likely to be many unmeasured effects that impact the disease progression of different patients. Probabilistic graphical models such as Dynamic Bayesian Networks (DBNs) have demonstrated much promise in the modeling of disease progression and they can naturally incorporate hidden (latent) variables using the EM algorithm. Unlike deep learning approaches that attempt to model complex interactions in data by using a large number of hidden variables, we adopt a different approach. We are interested in models that not only capture unmeasured effects but are also transparent in how they model data so that knowledge about disease processes can be extracted and trust in the model can be maintained by clinicians. As a result, we have developed a step-wise hidden variable structure learning process that incrementally adds hidden variables based on the IC* algorithm. To the best of our knowledge, this is the first study for classifying disease complication using a step-wise learning methodology for identifying hidden and T2DM features with a DBN structure from clinical data. Our extensive set of experiments show that the proposed method improves classification accuracy, identifying the correct number of hidden variables, and targeting their precise location within the network structure.
Leila Yousefi, Allan Tucker, Mashael Al-luhaybi, Lucia Saachi, Riccardo Bellazzi and Luca Chiovato.
Welly done Lilly!