Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Cyprus

Marie Skłodowska-Curie Action · Ended early

DL-ElastoMark A deep learning-derived, shear wave elastography biomarker for cancer therapy prediction

Coordinator
University of Cyprus, Cyprus
Runs
1 September 2023 to 31 August 2025
Status
Ended early
EU funding
€148k
Total cost
—
Partners
1 organisations in 1 countries
Type
Marie Skłodowska-Curie Action
Grant agreement
101065325

What the project is doing

In the project's own words, from its summary on CORDIS.

The efficacy of standard cancer therapies varies, and while some patients respond to a particular treatment, other patients do not gain any benefit. In response, an era of individualized cancer treatments is emerging which are based on the identification of biomarkers that characterize the state of a tumor. Many solid tumors (e.g., breast cancers and sarcomas) stiffen as they grow within a normal tissue. Tumor stiffening is a known factor leading to compromised efficacy of therapeutics.

Repurposing drugs in order to alleviate tumor stiffness before the initiation of therapy has been tested in preclinical studies and has recently made it to the clinic. Despite recent success of these strategies, optimization of their application is understudied. Here, we aim to harness the power of deep learning (DL) methods in order to construct a robust biomarker based on ultrasound shear wave elastography (SWE). The biomarker will aim to: (i) predict the tumor’s response to treatment with chemo- and immuno-therapy and (ii) monitor treatment outcomes, in the case of strategies that target tumor stiffness.

The project will capitalize on the existing strengths of the applicant in medical image processing and DL and the expertise of the host in tumor mechanopathology and in vivo experiments. In past experiments, the host acquired a large number of SWE tumor data, which will enable the development of the DL biomarker. Through the experimental part of the project, additional data on murine cancer models will be acquired enabling the validation of the biomarker.

Formulation of the developed DL-derived biomarker in a user-friendly software will allow for potential clinical translation and further exploitation through IPR. The applicant will acquire new knowledge in the fields of cancer therapy, tumor biology and in vivo experimental design. The attained knowledge and skills will be instrumental to the applicant’s ambition to lead the field of artificial intelligence in biomedicine.

Topics

Who is involved

OrganisationCityCountryRole
University of CyprusNicosiaCyprusCoordinator

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI