Using time-series data to predict nodule evolution

Principal Investigator

Name
Joseph Jacob

Degrees
F.R.C.R., M.D.(Res).,

Institution
University College London

Position Title
Wellcome Trust Fellow

Email
j.jacob@ucl.ac.uk

About this CDAS Project

Study
NLST (Learn more about this study)

Project ID
NLST-526

Initial CDAS Request Approval
Jun 18, 2019

Title
Using time-series data to predict nodule evolution

Summary
To explore time-series data to predict the change in benign or indeterminate nodules at baseline or provide a risk assessment/probability of malignant transformation across repeated LDCTs.

Aims

Segment nodules across longitudinal CTs
Predict malignant risk associated with changes in nodule metrics using time series data

Collaborators

Joseph Jacob, University College London
Tahreema Matin, Health Education England
Pavan Alluri, Manas AI
Ashwini Kumar, Manas AI
Rahul Chakkara, Manas AI
Eyjolfur Gudmundsson, University College London
Ashkan Pakzad, University College London
Tony Cheung, University College London
Moucheng Xu, University College London

Related Publications

• Enhancing cancer prediction in challenging screen-detected incident lung nodules using time-series deep learning.
  Aslani S, Alluri P, Gudmundsson E, Chandy E, McCabe J, Devaraj A, Horst C, Janes SM, Chakkara R, Alexander DC, SUMMIT consortium, Nair A, Jacob J
  Comput Med Imaging Graph. 2024 Sep; Volume 116: Pages 102399 PUBMED