A new approach to optical coherence tomography image analysis using machine learning

Lead Research Organisation: University of Nottingham
Department Name: School of Computer Science


This proposal describes a novel and adventurous pump-priming (pilot) project. The project fits the BBSRC Call for developing "new approaches to the analysis and interpretation of research data in bioimaging, including the development of software tools and algorithms that address challenges arising from emerging new types of data and known problems associated with data handling".

Specifically, in this pilot project we will develop a revolutionary approach to analyzing optical coherence tomography (OCT) images, that is, to automatically extract properties that may not be visible to the eye from the images using a mathematical technique called inversion, as well as machine learning techniques and knowledge about the physics of OCT imaging.

OCT is a relatively new imaging modality, which provides non-invasive imaging of living tissues based on the principle of optical interferometry. Contrast in OCT is derived from the difference in light scattering and absorption properties of tissue structures. As optical scattering is more varied across soft tissues than either acoustic scattering or x-ray absorption, thus OCT generally provides greater contrast than computed tomography (CT) and ultrasound and can even be sensitive to tissue structural properties at the nanometer length scale. Recent advances in OCT have mainly been driven by applications in biomedical applications such as ophthalmology to study optical nerves development and diagnose glaucoma. These applications rely on the fact that most physiological changes or disease processes affect the optical properties of biological tissue, and this change in tissue optical properties provide the contrast for this imaging technology. Application of OCT is however not limited to the medical domain, e.g., it is also being used in brain imaging, developmental biology, and in tissue engineering.

The motivation of the project is the limitation of current approaches to optical coherence tomography (OCT) image analysis, which are subjective and require that the image features to be detected are visible to the eye. However, most often the vital features are invisible to the eye as biological or disease processes are complex and this complexity is reflected in the images. The project will develop a radically different approach to OCT image analysis that extracts tissue optical properties that are invisible to the eye from OCT images to address life and health science research challenges, where little pilot data exists.

Technical Summary

Tissue optical properties are important for a wide range of applications including medical diagnosis, tissue engineering, and developmental biology. As such light scattering spectroscopy has emerged as a tool for characterizing biological tissue and cancer diagnosis by determination of the tissue optical properties. However these optical properties are not visible in optical coherence tomography (OCT) images and conventional image analysis algorithms cannot detect them. There are however established mathematical equations that describe the light transport through tissue / scattering media such as the Radiative Transfer Equation and the the Maxwell's equation. Given the tissue optical properties these equations calculate the OCT signal corresponding to the optical properties. The proposed project aims to develop a new approach to OCT image analysis by estimating the tissue optical properties given the OCT data, which is a inverse problem.

The proposed project will thus consider OCT image analysis as an inverse problem and take inspiration from the advances in solutions for inverse problems using machine learning techniques to learn the mapping/relationship between tissue optical properties and OCT data. With this mapping/relationship tissue optical properties can be predicted from new images. These optical properties can be used for classification of healthy and diseased images. The new OCT image analysis method will be validated using clinical OCT data.

Planned Impact

The proposed research is timely in the context that currently OCT image analysis is limited to detecting visible features in the image. OCT hardware technologies have developed significantly over the past decade but software development has yet to catch up. The technology developed in this project will have a wide range of applications, with immediate application in the diagnosis of paediatric glaucoma, which is associated with poor visual outcome.

Apart from the eye conditions, recent research has used OCT image analysis for detecting early Multiple Sclerosis, early Alzheimer's Disease, and Schizophrenia. Thus the technology developed in this project can improves the accuracy of early diagnosis and can potentially be used for neurological and psychiatric diseases, as well as other medical, tissue engineering, and developmental biology studies.

The project will thus have a direct impact on healthcare with the potential of diagnosing life threatening diseases and studying retina and optical nerve development, increasing patient benefit in areas with unmet clinical needs. The project has a clear pathway towards clinical adoption and commercialization due to the involvement of both clinical investigators and industrial partners. The economic and social impact of the proposed research will be significant.


10 25 50
Title Animation of the research for dissemination on social media etc. 
Description We are currently working with a Science Animation company to produce an animation of the program for dissemination on social media etc. 
Type Of Art Film/Video/Animation 
Year Produced 2019 
Impact It is not completed yet. 
Description We have so far done what we proposed for the award for a pilot project on the feasibility of extracting tissue optical properties from OCT scans. This includes analytical approaches as well as Monte Carlo simulations.
We found that although analytical models have elegant mathematical forms and are efficient, they generally assume simple tissue models and optical geometries. MC based models can generate more realistic OCT images which contains random speckle noises as often observed from real OCT scans. One of the major objectives of the project is to explore machine learning to for tissue parameter estimation, which require a large amount of mappings of tissue parameters and OCT images for training but this is difficult to obtain. Synthesizing such data in a principled way for training is important to achieve the goal.
We can now simulate the OCT image formation process. Given some optical parameters, we can generate the OCT images corresponding to the parameters (the forward process), and we have been working on the inverse process, e.g., given an OCT images, to work out under what optical conditions the OCT image was obtained, and thus the tissue properties. We have sped up the Monte Carlo simulation, using both parallel computation on the GPU and the perturbation Monte Carlo method, for the inverse process, so that more data can be simulated for machine learning. The findings will be used to compose a full grant proposal.
Exploitation Route We have produced open source publications on the findings for researchers to use. We have achieved accurate simulation results through modelling photon propagation in tissue and photon detection schemes. We plan to put the software on the web for controlled public access, once our full grant proposal is submitted.
Sectors Digital/Communication/Information Technologies (including Software),Education,Healthcare

Title OCT image database 
Description Co-investigators at the University of Leicester have been collecting OCT images for the research. 
Type Of Material Database/Collection of data 
Year Produced 2018 
Provided To Others? No  
Impact So far this database has been used for research purposes by the research team and shared with the OCT manufacturer. 
Description Collaboration with OCT manufacturer 
Organisation Leica Microsystems GmbH
Country Germany 
Sector Private 
PI Contribution We collaborate with Leica USA, the OCT manufacturer, who provide us with knowledge of how the OCT machine works, to enable us develop computational algorithms to process and analyse OCT data. In turn, if successful, this project will contribute to the development of new OCT machines.
Collaborator Contribution We collaborate with Leica USA, the OCT manufacturer, who provide us with knowledge of how the OCT machine works, to enable us develop computational algorithms to process and analyse OCT data. In turn, if successful, this project will contribute to the development of new OCT machines.
Impact Outcome of this collaboration so far is a better understanding of the OCT image production process and the data that the machine produces. This is crucial to design algorithms to analyse OCT data.The collaboration is multi-disciplinary, involving computer science and optical scanner manufacturer.
Start Year 2017
Title Numerical simulation of RTE (radiative transfer equation) for multi-layered tissues, as well as Monte Carlo simulation for multi-layered tissues. 
Description The RTE simulation software for OCT imaging simulates how photons transfer within biological tissues. RTE simulation is based on the physical phenomenon of energy transfer in the form of electromagnetic radiation through a medium, and is affected by absorption, emission, and scattering processes. The absorption, emission, and scattering are optical properties of the tissue and are affected if the tissue is diseased. The Monte Carlo simulation software for OCT imaging can deal with more complex tissues. Full details are given in the publications. 
Type Of Technology Software 
Year Produced 2019 
Impact These are the output of this pilot project, which aims to test ideas and approaches and the insights from these will be used for a full grant proposal to enable machine learning to be used for extracting information from OCT images that is not visible to the human eye. 
Description Research presentations 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact We attended conference and workshop to present the research findings.
Year(s) Of Engagement Activity 2018
Description Startup 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact The meeting was held in the University of Kent, where experts in OCT technology, researchers, and industrial companies are based. The meeting set the goals for the research as well as future commercial exploitation. It was proposed that we should set up a special interest group in the UK to exploit the research.
Year(s) Of Engagement Activity 2018