AIRIaL: Artificial Intelligence and Resistance Imaging in Lung Cancer
Lead Research Organisation:
King's College London
Department Name: Imaging & Biomedical Engineering
Abstract
Lung cancer is the most common cause of cancer death world-wide (~1.6 million deaths/year). Unfortunately, of all people who have lung cancer, only 5 out of 100 are living ten years after diagnosis. The main reason for this low survival rate is that standard lung cancer therapies fail due to the presence of cancer that does not respond to these treatments.
In this early-stage project performed in mice, we will develop new medical imaging tests to detect therapy resistance in lung cancer. Using this imaging test, we can predict if the cancer will respond to the prescribed treatment, and if so, how well. In the future, knowing early on about how a patient will respond to treatment will enable the clinical team to switch to alternative options if necessary. This will avoid patients being given potentially toxic treatments that will not benefit them. At present doctors have to wait for CT scans about 3 months after treatment starts to be able to tell if it is working or not.
We will create a computer programme (using artificial intelligence) which is able to automatically read lung scans and more accurately predict whether the cancer is resistant to treatment. Then, we will use engineered materials to deliver drugs only to the resistant cancer cells. At this stage we will test these new drugs and computer program in mice to see if this new approach is effective. By delivering the drug just to the cancer itself, we hope to reduce side effects for patients and significantly improve how well the treatment works. Finally, we will determine if our computer programme can monitor changes in cancer over time, which will provide insight into how treatment resistance occurs as this is currently not well-understood. Ultimately, we hope that the results of this project will enable doctors to tailor the treatment for lung cancer to the individual patient. Moreover, it might lead to the development of new treatments for this devastating disease.
In this early-stage project performed in mice, we will develop new medical imaging tests to detect therapy resistance in lung cancer. Using this imaging test, we can predict if the cancer will respond to the prescribed treatment, and if so, how well. In the future, knowing early on about how a patient will respond to treatment will enable the clinical team to switch to alternative options if necessary. This will avoid patients being given potentially toxic treatments that will not benefit them. At present doctors have to wait for CT scans about 3 months after treatment starts to be able to tell if it is working or not.
We will create a computer programme (using artificial intelligence) which is able to automatically read lung scans and more accurately predict whether the cancer is resistant to treatment. Then, we will use engineered materials to deliver drugs only to the resistant cancer cells. At this stage we will test these new drugs and computer program in mice to see if this new approach is effective. By delivering the drug just to the cancer itself, we hope to reduce side effects for patients and significantly improve how well the treatment works. Finally, we will determine if our computer programme can monitor changes in cancer over time, which will provide insight into how treatment resistance occurs as this is currently not well-understood. Ultimately, we hope that the results of this project will enable doctors to tailor the treatment for lung cancer to the individual patient. Moreover, it might lead to the development of new treatments for this devastating disease.
Technical Summary
Most lung cancer deaths result from ineffective treatment of stage 3 and 4 disease. Currently, there is no satisfactory way to identify patients that will not respond to standard-of-care treatments. Positron emission tomography (PET) imaging offers a potential solution to this clinical problem through the non-invasive assessment of molecular processes that underpin therapy-resistance. The identification of cancer patients that are refractory to treatment will allow the use of innovative second-line therapies that have the potential to improve patient response and survival.
Here, we will combine expertise in biological, physical, data, and medical sciences to identify and treat therapy-resistant non-small cell lung cancer (NSCLC). We have developed a PET radiotracer, [18F]FSPG, that can non-invasively detect therapy-resistant tumours in multiple models of NSCLC. [18F]FSPG is taken up by the amino acid transporter xCT, which provides the rate-limiting precursor for glutathione biosynthesis and is upregulated >10-fold in therapy-resistant NSCLC. Through innovations in artificial intelligence and machine learning, minimal preclinical [18F]FSPG imaging datasets will be used to identify, segment, and extract quantitative parameters from therapy-resistant tumours; far outperforming conventional methods of annotation. Concurrently, we will develop molecularly imprinted nanoparticles (nanoMIPs) that bind xCT to deliver a targeted payload of drug to these resistant tumours. An iterative selection process will be employed to manufacture double imprinted fluorescent nanoMIPs that bind both xCT and doxorubicin to produce therapeutic agents with excellent selectivity and potency. Finally, these innovative technologies will be combined to image, detect, and treat multifocal therapy-resistant disease in a genetically engineered mouse model of NSCLC. Together, this novel treatment platform will support our mission to provide treatment options where currently there are none.
Here, we will combine expertise in biological, physical, data, and medical sciences to identify and treat therapy-resistant non-small cell lung cancer (NSCLC). We have developed a PET radiotracer, [18F]FSPG, that can non-invasively detect therapy-resistant tumours in multiple models of NSCLC. [18F]FSPG is taken up by the amino acid transporter xCT, which provides the rate-limiting precursor for glutathione biosynthesis and is upregulated >10-fold in therapy-resistant NSCLC. Through innovations in artificial intelligence and machine learning, minimal preclinical [18F]FSPG imaging datasets will be used to identify, segment, and extract quantitative parameters from therapy-resistant tumours; far outperforming conventional methods of annotation. Concurrently, we will develop molecularly imprinted nanoparticles (nanoMIPs) that bind xCT to deliver a targeted payload of drug to these resistant tumours. An iterative selection process will be employed to manufacture double imprinted fluorescent nanoMIPs that bind both xCT and doxorubicin to produce therapeutic agents with excellent selectivity and potency. Finally, these innovative technologies will be combined to image, detect, and treat multifocal therapy-resistant disease in a genetically engineered mouse model of NSCLC. Together, this novel treatment platform will support our mission to provide treatment options where currently there are none.
Publications

Farooq R
(2025)
Compact and cGMP-compliant automated synthesis of [18F]FSPG on the Trasis AllinOne™
in EJNMMI Radiopharmacy and Chemistry

Garg S
(2024)
Electroactive Molecularly Imprinted Polymer Nanoparticles (eMIPs) for Label-free Detection of Glucose: Toward Wearable Monitoring.
in Small (Weinheim an der Bergstrasse, Germany)
Title | Growing cancer in chicken eggs |
Description | It's predicted from Cancer Research UK's data that 1 in 2 of us will develop cancer in our lifetime. In this short documentary, and in collaboration with King's College London, Understanding Animal Research explores one of the alternative models being developed in cancer research. Professor Tim Witney explains how his team is trying to reduce the number of mice used in science and medical research when imaging cancer, by using chicken eggs. |
Type Of Art | Film/Video/Animation |
Year Produced | 2024 |
Impact | Engagement with society regarding animal research |
URL | https://www.youtube.com/watch?v=tacaV0pbHME&ab_channel=UnderstandingAnimalResearch |
Description | Imaging radiation resistance: Molecular and Imaging biomarkers of radioresistance and clinical translation |
Amount | £255,600 (GBP) |
Funding ID | C220204 |
Organisation | Guy’s & St Thomas’ Charity |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 05/2024 |
End | 05/2030 |
Description | Supramolecular Agents as Radiotheranostic Drugs (SMARTdrugs) |
Amount | £3,400,000 (GBP) |
Funding ID | 10091247 |
Organisation | Innovate UK |
Sector | Public |
Country | United Kingdom |
Start | 01/2024 |
End | 12/2028 |
Title | AI tool to assess therapy resistance |
Description | AI/deep learning method to identify therapy resistant cancer from PET imaging scans. |
Type Of Material | Technology assay or reagent |
Year Produced | 2023 |
Provided To Others? | No |
Impact | None yet as still in development. |
Title | AI-based image segmentation method |
Description | We have developed a prototype AI-based image segmentation method designed to improve both the accuracy and efficiency of annotating relevant regions of interest (ROI), such as mouse organs and pathological structures (e.g., tumors). This method leverages advanced machine learning algorithms to automate and refine the segmentation process, reducing the need for manual intervention. |
Type Of Material | Technology assay or reagent |
Year Produced | 2024 |
Provided To Others? | No |
Impact | Although the technology is still in development, it is already demonstrating strong performance in preclinical PET/CT imaging. By rapidly identifying and segmenting key regions within seconds, the method has the potential to significantly accelerate research workflows, minimize variability in manual annotations, and enhance the reproducibility of image-based studies. Future improvements will focus on refining the model's accuracy across diverse datasets, expanding its applicability to other imaging modalities, and integrating real-time processing capabilities. Ultimately, this AI-driven approach aims to become a valuable tool for researchers, providing faster and more precise segmentation while reducing the time and effort required for data analysis. |
Title | Imaging agent to detect therapy resistant cancer - FSPG |
Description | Development of a novel positron emission tomography agents that binds to the amino acid transporter, xCT. Results in the identification of therapy resistant cancer in living subjects. |
Type Of Material | Technology assay or reagent |
Year Produced | 2023 |
Provided To Others? | Yes |
Impact | GMP synthesis of imaging agent for clinical use. Clinical trial initiated (NCT05889312) funded by RoseTrees, GST Charity, and the Royal Society of Radiologists. Adoption of imaging methods by others in USA and South Korea. Numerous publications describing its use. |
Title | NanoMIP for xCT |
Description | Specific nanoparticle for the binding and treatment of therapy-resistant cancer |
Type Of Material | Technology assay or reagent |
Year Produced | 2023 |
Provided To Others? | No |
Impact | N/A as still in development. |
Description | AI assessment of therapy resistant cancer |
Organisation | University of Oxford |
Department | Big Data Institute |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Creation of a new imaging agent to detect therapy resistant cancer. Imaging across eight different tumour types to provide extensive dataset for AI assessment. |
Collaborator Contribution | AI model creation and evaluation of our imaging dataset. |
Impact | Multidisciplinary research: Incorporates tumour biology, imaging research, and deep learning/mathematical modelling. Outputs are pending. |
Start Year | 2024 |
Description | AI-based image segmentation method |
Organisation | University of Oxford |
Department | Big Data Institute |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | We have provided annotated PET images with quantified tumour uptake measurements for model training. This includes eight different cancer models and our bespoke imaging agent developed in our lab, [18F]FSPG. We have provided biological know-how for this collaboration. |
Collaborator Contribution | Our partners have developed a prototype AI-based image segmentation method designed to improve both the accuracy and efficiency of annotating relevant regions of interest (ROI), such as mouse organs and pathological structures (e.g., tumors). This method leverages advanced machine learning algorithms to automate and refine the segmentation process, reducing the need for manual intervention. |
Impact | Although the technology is still in development, it is already demonstrating strong performance in preclinical PET/CT imaging. By rapidly identifying and segmenting key regions within seconds, the method has the potential to significantly accelerate research workflows, minimize variability in manual annotations, and enhance the reproducibility of image-based studies. Future improvements will focus on refining the model's accuracy across diverse datasets, expanding its applicability to other imaging modalities, and integrating real-time processing capabilities. Ultimately, this AI-driven approach aims to become a valuable tool for researchers, providing faster and more precise segmentation while reducing the time and effort required for data analysis. |
Start Year | 2023 |
Description | Creation of nanoMIPs targeting therapy resistant cancer |
Organisation | University of Manchester |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Generate know-how regarding lung cancer biology, tumour models, and therapeutic targets. Evaluate the resulting therapeutics. |
Collaborator Contribution | Development of a novel nanoMIP that targets a biomarker, xCT, expressed in therapy-resistant tumours. |
Impact | Multidisciplinary research: incorporating cancer biology, imaging research, medicinal and polymer chemistry. |
Start Year | 2023 |
Title | Imaging system xc- |
Description | Preclinical development of a system xc- specific radiotracer for cancer imaging. Demonstrated that this radiotracer is sensitive to the tumour redox microenvironment through assessment of de novo glutathione biosynthesis. We have used this tool to assess response to chemotherapy and predict responders from non-responders. |
Type | Diagnostic Tool - Imaging |
Current Stage Of Development | Refinement. Non-clinical |
Year Development Stage Completed | 2025 |
Development Status | Under active development/distribution |
Impact | This radiotracer is currently in clinical trials in North America and this reverse-translation project promises to repurpose this diagnostic tool for treatment efficacy monitoring. |
Description | Interactive talk and workshop "Radioactivity - the overlooked cancer remedy" at the Thriving Minds symposium, Sancton Wood School, Cambridge, hosted by Lucy Hawking. |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Schools |
Results and Impact | 80 pupils from across the country attended our interactive 2h workshop on the medical uses of radioactivity. The pupils gained a new understanding of the benefits, not just the risks of radiation, it's use in everyday life, and how it can be used to treat cancer patients. There was a lively discussion in this interactive workshop, which included practical activities, such as locating where the radioactive substance was inside a representation of a human body. The event was covered by the Cambridge local press and we got very positive feedback from the teachers, students, and organiser Lucy Hawking (Stephen Hawking's daughter). |
Year(s) Of Engagement Activity | 2023 |