Carl Troein
Forskare
Facilitating clinically relevant skin tumor diagnostics with spectroscopy-driven machine learning
Författare
Summary, in English
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 aid decision making and diagnostics. A growing number of studies demonstrate the potential of automatic pre-surgical skin tumor delineation, which could have tremendous impact on clinical practice. However, current methods rely on having ground truth images in which tumor borders are already identified, which is not clinically possible. We report a novel approach where hyperspectral images provide spectra from small regions representing healthy tissue and tumor, which are used to generate prediction maps using artificial neural networks (ANNs), after which a segmentation algorithm automatically identifies the tumor borders. This circumvents the need for ground truth images, since an ANN model is trained with data from each individual patient, representing a more clinically relevant approach.
Avdelning/ar
- Centrum för miljö- och klimatvetenskap (CEC)
- Beräkningsvetenskap för hälsa och miljö
- Forskargruppen för oftalmologisk avbildning
- Oftalmologi, Lund
- LU profilområde: Ljus och material
- LUCC: Lunds universitets cancercentrum
- Hudcancerforskning vid Lunds universitet
- Dermatologi och venereologi, Lund
Publiceringsår
2024-05-17
Språk
Engelska
Publikation/Tidskrift/Serie
iScience
Volym
27
Issue
5
Dokumenttyp
Artikel i tidskrift
Förlag
Elsevier
Ämne
- Cancer and Oncology
- Biophysics
Nyckelord
- Hyperspectral imaging
- Machine learning
- Skin tumours
Status
Published
Projekt
- Computational Science for Health and Environment
Forskningsgrupp
- Computational Science for Health and Environment
- Ophthalmology Imaging Research Group
- LUSCaR- Lund University Skin Cancer Research group
ISBN/ISSN/Övrigt
- ISSN: 2589-0042