Spatio-Temporal Signatures to Predict Retinal Disease Recurrence
نویسندگان
چکیده
We propose a method to predict treatment response patterns based on spatio-temporal disease signatures extracted from longitudinal spectral domain optical coherence tomography (SD-OCT) images. We extract spatio-temporal disease signatures describing the underlying retinal structure and pathology by transforming total retinal thickness maps into a joint reference coordinate system. We formulate the prediction as a multi-variate sparse generalized linear model regression based on the aligned signatures. The algorithm predicts if and when recurrence of the disease will occur in the future. Experiments demonstrate that the model identifies predictive and interpretable features in the spatio-temporal signature. In initial experiments recurrence vs. non-recurrence is predicted with a ROC AuC of 0.99. Based on observed longitudinal morphology changes and a time-to-event based Cox regression model we predict the time to recurrence with a mean absolute error (MAE) of 1.25 months comparing favorably to elastic net regression (1.34 months), demonstrating the benefit of a spatio-temporal survival model.
منابع مشابه
Assessment of Neonate's Congenital Hypothyroidism Pattern Using Poisson Spatio-temporal Model in Disease Mapping under the Bayesian Paradigm during 2011-18 in Guilan, Iran
Background: Congenital Hypothyroidism (CH) is one of the reasons for mental retardation and defective growth in neonates. It can be treated if it is diagnosed early. The congenital hypothyroidism can be diagnosed using newborn screening in the first days after birth. Disease mapping helps to identify high-risk areas of the disease. This study aimed to evaluate the pattern of CH using the Poisso...
متن کاملSpatio-temporal Analysis of Myocardial Infarction in an Iranian Military Community During the Period 2015-2018
Background and Aim: Myocardial infarction (MI) is one of the leading causes of mortality worldwide. This disease imposes a high socio-economic burden on patients. Since the Spatio-temporal analysis of diseases plays an essential role in the design of prevention and management programs. The present study aimed to identify regional clusters of MI and also analyze the time trend of the disease amo...
متن کاملSpatio-temporal agent based simulation of COVID-19 disease and investigating the effect of vaccination (case study: Urmia)
Proper management of epidemic diseases such as Covid-19 is very important because of its effects on the economy, culture and society of nations. By applying various control strategies such as closing schools, restricting night traffic and mass vaccination program, the spread of this disease has been somewhat controlled but not completely stopped. The main goal of this research is to provide a f...
متن کاملThe Retinal Nerve Fiber Layer Thickness is Related to Severity of Parkinson’s Disease
Introduction: We investigated correlation between the retinal nerve fiber layer (RNFL) thickness and the severity of Parkinson's disease (PD). Methods: In this study, the RNFL thickness of 23 patients with Parkinson’s disease (PD) was compared to normal controls (NCs). PD severity was assessed by the MDS-UPDRS (movement disorder society Unified Parkinson Disea...
متن کاملSpatio-temporal analysis of the covid-19 impacts on the using Chicago urban shared bicycles by tensor-based approach
Cycling is a phenomenon in urban transportation that has the ability to allocate a specific location at any moment in time. Accordingly, spatial analysis of bicycle trips can be accompanied by temporal analysis. The use of a GIS environment is commonly recommended to display the extent of the phenomenon's spatial changes. However, in order to apply and display changes over time, it will requir...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Information processing in medical imaging : proceedings of the ... conference
دوره 24 شماره
صفحات -
تاریخ انتشار 2015