Integrating Clinical Infrared and Raman Spectroscopy with digital pathology and AI: CLIRPath-AI
Lead Research Organisation:
University of Manchester
Department Name: Chem Eng and Analytical Science
Abstract
A key feature of the diagnosis of any disease, but particularly various forms of cancer, is the critical information obtained through a biopsy. A biopsy involves the removal of a small sample of tissue, or a few cells, from the patient for examination by a pathologist looking down an optical microscope. In current practice is that the sample is stained with a combination of dyes to help gain some contrast in the image which helps the pathologist see the cells. Generally, based upon this visual inspection of the sample and other relevant medical information, a diagnosis is made. This process, however, is far from ideal since it relies on the expertise of the clinician concerned and is subject to intra in inter observer error. (In other words the process is not exact and depends upon the opinion of the clinicians which may differ). Recently a number of developments have been made in the field of Digital Pathology and Artificial Intelligence (AI). This is where a high resolution photograph of the biopsy slide is taken and examined by a computer algorithm which helps the pathologist make a diagnosis. However analysing the data from just the visible region of the spectrum severely restricts information content of the images obtained. Recently a number of proof of concept studies have shown that molecular spectroscopic techniques such as infrared and Raman are capable of distinguishing diseased from non-diseased cells and tissue based upon the inherent chemistry contained within the cells. (These regions of the spectrum have 40 times the bandwidth of the visible and therefore contain 40 times the amount of information.)
The UK is at the forefront in developments associated with both Digital Pathology and AI, the latter augmented by five new technology centres funded by the Industrial Strategy Challenge Fund. In addition, partly due to an EPSRC funded network (CLIRSPEC) the UK is also world leading in the field biomedical infrared and Raman spectroscopy. At present however the Digital pathology/AI and biomedical infrared/Raman these two communities are separate and are not interacting. As a result therefore, the advances made in one area are not being translated to another. In both areas of research there are many hurdles that need to be overcome if this technology is to move from the proof of concept stage through the translational stage and into the clinical setting. It is the belief of the academic community that we are much more likely to overcome these hurdles if we pool our resources, bring in both industrial and clinical partners and work on these generic problems together. This application is for funding to support such a network of partners that will develop dynamic and synergistic interaction between these separate communities for the next four years, for the specific aim of benefiting patients.
The UK is at the forefront in developments associated with both Digital Pathology and AI, the latter augmented by five new technology centres funded by the Industrial Strategy Challenge Fund. In addition, partly due to an EPSRC funded network (CLIRSPEC) the UK is also world leading in the field biomedical infrared and Raman spectroscopy. At present however the Digital pathology/AI and biomedical infrared/Raman these two communities are separate and are not interacting. As a result therefore, the advances made in one area are not being translated to another. In both areas of research there are many hurdles that need to be overcome if this technology is to move from the proof of concept stage through the translational stage and into the clinical setting. It is the belief of the academic community that we are much more likely to overcome these hurdles if we pool our resources, bring in both industrial and clinical partners and work on these generic problems together. This application is for funding to support such a network of partners that will develop dynamic and synergistic interaction between these separate communities for the next four years, for the specific aim of benefiting patients.
Publications
Whitley C
(2024)
Prediction of prognosis in oral squamous cell carcinoma using infrared microspectroscopy
in Cancer Medicine
Description | We have had three networking sandpits and a number of key findings have emerged. (i) We desperately need more spectroscopy data sets from well annotated tissue samples. This is needed for the AI groups to test their models on. This is fundamentally important for moving forward. (ii) Current Convolutional Neural Networks are not good for analysing data that contains both spectral and spatial information. These methods are biased towards the spatial (imaging) information even when the spectral content might give a more reliable classification. |
Exploitation Route | The network is still actively working on (i) producing more data and (ii) developing new AI tools that work specifically for this type of data. |
Sectors | Healthcare |
Description | Presentation to the NPIC Patient and Public Advisory Group |
Geographic Reach | Local/Municipal/Regional |
Policy Influence Type | Participation in a guidance/advisory committee |
Impact | To early to say |
URL | https://npic.ac.uk/2021/11/15/about-the-patient-and-public-advisory-group/ |
Description | Artificial intelligence driven infrared spectroscopy for improved prostate cancer risk stratification |
Amount | £117,580 (GBP) |
Organisation | Prostate Cancer UK |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 03/2023 |
End | 03/2025 |
Description | Breast Cancer Receptor Status Prediction through Vibrational Spectroscopy |
Organisation | University of Warwick |
Department | Department of Computer Science |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Tis is a pump priming project between the Universirt |
Collaborator Contribution | This is a partnership for a pump priming grant. Spectroscopic data of pathology samples have been sent to Warwick for analysis using the latest AL models. The project is ongoing. |
Impact | the project is active and outcomes are expected later in the year. |
Start Year | 2023 |
Description | Breast Cancer Receptor Status Prediction through Vibrational Spectroscopy (Raman) |
Organisation | University of Exeter |
Department | School of Physics |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | We are providing oversight of the project |
Collaborator Contribution | Exeter are carrying out the Raman measurements on the Breast tissue |
Impact | The project is still active but there are no outputs yet. They are expected later in the year. |
Start Year | 2023 |
Description | Breast Cancer Receptor Status Prediction through Vibrational Spectroscopy (pathology) |
Organisation | University of Dundee |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | We measure the spectroscopic data from pathology slides provided by Prof Valerie Speirs at the Institute of Medical Sciences |
Collaborator Contribution | Prof Speirs provides the slides and the pathologist annotation. |
Impact | The project is ongoing and outputs are expected later in the year. |
Start Year | 2023 |
Description | An invited presentation at the International Conference on Advanced Vibrational Spectroscopy (ICAVS-12) in Krakow Poland |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Title of presentation CLIRPath-AI. A National Network to Bring Together Spectral Pathology, Digital Pathology and AI. The purpose of the talk and general discussion was to show how network funding in this area could help accelerate innovation in the field. |
Year(s) Of Engagement Activity | 2023 |
URL | https://icavs.org/ |
Description | CLIRPath-AI Manchester Sandpit |
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 first CLIRPath-AI Sandpit event will be held on 28 and 29 March at the Manchester Conference Centre, Sackville St, Manchester M1 3BB. CLIRPath-AI is an EPSRC funded network bringing together researchers in the fields of Spectral Pathology, Digital Pathology and Artificial Intelligence, to work together to find creative solutions to diagnostic problems. The UK is at the forefront of developments in these fields, but at present the communities are distinct and independent, and advances in one area are not translated to the other. We hope to facilitate discussions and offer opportunities for further research that reaches across the disciplines. Our first sandpit event will focus on linking the disciplines of Spectral Pathology and Artificial Intelligence. Those involved in Digital Pathology are encouraged to attend as well, to share their perspectives and expertise. The event will be an interactive sandpit with focused talks and workshops to formulate potential projects. Funding will be available for project applications derived from this conference. This event is FREE for UK based academics, early-career researchers and industry. Unfortunately due to funding, UK students and non-UK based academics, early-career researchers and industry will need to pay a fee; Registration is required for all Hotel accommodation at the venue will be provided for UK based academics, early-career researchers and industry and can be booked at time of registration. We are happy to arrange booking for other attendees but hotel charges will apply. Please contact admin@CLIRPath-AI.org with any special considerations and dietary requirements. |
Year(s) Of Engagement Activity | 2021 |
URL | https://clirpath-ai.org/sandpit-1/ |
Description | CLIRPath-AI Online Symposium |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | CLIRPath-AI is an EPSRC funded network bringing together researchers in the fields of Spectral Pathology, Digital Pathology and Artificial Intelligence, to work together to find creative solutions to diagnostic problems. The UK is at the forefront of developments in these fields, but at present the communities are distinct and independent, and advances in one area are not translated to the other. We hope to facilitate discussions and offer opportunities for further research that reaches across the disciplines. The Symposium is a free event that replaces an in-person Sandpit event postponed due to rail strikes. The in-person event will be re-scheduled for later in the year. |
Year(s) Of Engagement Activity | 2022 |
URL | https://clirpath-ai.org/clirpath-ai-online-symposium/ |
Description | CLIRSPEC/CLIRPath-AI Summer school 2022 |
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 | The International Society for Clinical Spectroscopy (CLIRSPEC) would like to invite all students, industrialists and postdoctoral researchers in the multidisciplinary area of clinical infrared and Raman spectroscopy to attend the 6th CLIRSPEC Summer School. This year we will be co-hosting the Summer School with CLIRPath-AI, a UK funded network connecting clinical spectroscopy, digital pathology and artificial intelligence. Building upon previous successful summer schools the 2022 Summer School will provide an excellent grounding in spectroscopic fundamentals through to current cutting edge clinical applications and discuss the future of vibrational spectroscopy in the clinical environment including interactive and exciting group problem-based learning sessions. This Summer School will have more of a data analysis focus than in previous years. |
Year(s) Of Engagement Activity | 2022 |
URL | https://clirspec.org/summer-school/ |
Description | Patient and Public Advisory Group (PPAG) |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | Regional |
Primary Audience | Public/other audiences |
Results and Impact | A general discussion and question and answer session on Spectral Pathology and the Role of AI in this process. |
Year(s) Of Engagement Activity | 2023 |
URL | https://npic.ac.uk/patient-and-public-involvement-2/ |