AI-Driven Digital Pathology and Advanced Imaging for Early, Precise, and Personalized Skin Cancer Diagnostics

Our Areas of Research

Computational Pathology
The growing incidence of cancer places a heavy burden on pathology laboratories and often causes diagnostic delays. The digitalization of pathology enables the application of artificial intelligence (AI) and deep learning for advanced computational image analysis, improving diagnostic precision, reducing turnaround times, and minimizing inter-pathologist variability. Using thousands of digitized pathology images from primary tumors and metastases, we develop AI algorithms to diagnose primary lesions, detect metastases, and assess molecular and prognostic markers — with a strong focus on skin cancer. By integrating AI into digital pathology, we also aim to identify novel histopathological features, including prognostic and genetic markers, and to create digital biomarkers that enable earlier diagnoses and better prediction of treatment responses, enabling personalized therapy.

Bed side pathology - Ex Vivo Fluorescence Confocal Microscopy (FCM)
Ex vivo fluorescence confocal microscopy is a promising technique in pathology where fresh, unfixed tissue specimens are laser-scanned to generate high-quality images resembling conventional histopathology — within minutes. This enables rapid, bedside diagnostics without affecting subsequent standard histological examinations. The ability to perform fast pre- and intraoperative cancer evaluations with FCM offers greater speed and accuracy in the clinic, reducing operating room costs, patient wait times, and unnecessary follow-up visits. Given the high cancer incidence, this technology holds great potential for significantly lowering healthcare expenses while improving care.

Cancer lipidomics - ToF-SIMS Mass Spectrometry
Alterations in lipid metabolism — which can occur earlier than protein changes — are emerging as important indicators of cancer progression. Lipidomics has therefore become a key focus area in our research. Time-of-Flight Secondary Ion Mass Spectrometry (ToF-SIMS) provides high-resolution chemical imaging that maps lipid distributions in histopathological specimens, enabling side-by-side comparisons with standard stained slides. This makes it possible to detect subtle molecular and cellular differences between healthy and cancerous tissue and among different cancer subtypes. The insights gained from lipidomics via ToF-SIMS contribute to the discovery of earlier, more accurate cancer biomarkers and open new avenues for targeted therapeutic development.

Current collaborators

• Prof John Paoli, Department of Dermatology, Institute of Clinical sciences, Sahlgrenska Academy
• Prof Roger Olofsson Bagge, Department of Surgery, Institute of Clinical sciences, Sahlgrenska Academy
• Adjunct Professor Max levin, Department of Oncology, Institute of Clinical sciences, Sahlgrenska Academy
• Associate professor Kari Nielsen, Department of Clinical Sciences, Lund University
• Prof Ilkka Pölönen, Department of Information Technology, University of Jyväskylä
• Prof John Fletcher, Department of Chemistry and Molecular Biology, University of Gothenburg
• Associate professor Ida Häggström, Chalmers University of Technology and Gothenburg University
• PhD Gabriele Campanella, Senior data scientist, Memorial Sloan Kettering Cancer Center, NYC