Magne Stridh

Magne Stridh

Auto-generated profile, based on publicly available information

Magne Stridh

Department of Clinical Sciences Lund, Ophthalmology, Lund University, Lund, Sweden

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 April 2024 in Orbit
Verified
Journal Article
Open access
MSMagne Stridh
Magne Stridh
UDUlf Dahlstrand
Ulf Dahlstrand
MNMagdalena Naumovska
Magdalena Naumovska
KEKarl Engelsberg
Karl Engelsberg
BGBodil Gesslein
Bodil Gesslein
MMMalin Malmsjö
Malin Malmsjö
Skin cancer is one of the most common forms of cancer and is overrepresented around the eyes. The gold standard for the diagnosis and treatment of skin cancer is surgical excisional biopsy and hist...

15 October 2023 in medRxiv
Verified
Preprint
Open access
PDF file
EAEmil Andersson
Emil Andersson
JHJenny Hult
Jenny Hult
CTCarl Troein
Carl Troein
MSMagne Stridh
Magne Stridh
BSBenjamin Sjögren
Benjamin Sjögren
AMAboma Merdasa
Aboma Merdasa
In the dawning era of artificial intelligence (AI), health care stands to undergo a significant transformation with the increasing digitalization of patient data. Digital imaging, in particular, will serve as an important platform for AI to be implemented to aid decision making and diagnostics. A growing number of studies demonstrate the potential of AI for automatic pre-surgical skin tumor delineation, which could have tremendous impact on clinical practice. However, current methods have the drawback of relying on a ground truth image in which the tumor borders are already identified, which is not clinically possible. We report a novel approach where hyperspectral images provides spectra from small regions representing healthy tissue and tumor, which are used to generate prediction maps using artificial neural networks. Thereafter, a segmentation algorithm automatically manages to determine the skin tumor borders. Our approach therefore circumvents the need for a complete ground truth image, where the training data is contained within each individual patient. This links to an important strength of our approach as we develop individual network models for each patient. Our approach is therefore not only more clinically relevant, but it also interesting for emerging precision skin tumor diagnostics where adaptability toward the individual is key.