Home

Medical image analysis

Gradient background from teal to light blue with hexagonal shapes forming a network pattern. Contains icons for a microscope, lungs, brain, DNA, and medical notes.

Our research group is dedicated to advancing medical image analysis through state-of-the-art machine and deep learning methods.

We focus on expanding the understanding of how deep learning technologies can be applied to medical image analysis and we develop cutting-edge solutions that improve the diagnosis, treatment and thereby patient outcomes. Our medical focus areas are cancer, orthopedics and body composition analysis using multiple image and data modalities.

The mission

We aim to develop new knowledge, implement and evaluate on AI advances for medical image applications and translate these into clinically useful tools that benefit the healthcare and the patients.

Research projects

The image consists of two parts: four sections views of a brain on the one side and fous sections of another brain on the other side

Synthetic images can save a lot of time in healthcare

AI makes it possible to quickly and accurately mark areas to be eliminated with radiation when treating cancerous tumors. But due to lack of medical data to train AI models with, attempts are underway to train models with synthetic medical images.
Info graphics with illustrations showing how local updates are being sent from the hospitals to a cloud. The cloud sends a new global modell to the hospitals. The trained model gives personal healthcare.

Developing medical AI without sharing sensitive information

Sharing sensitive data, such as images of brain tumor patients, is complicated. This makes development of AI models for medical image analysis challenging. LiU researchers shows how such models can be trained without sharing sensitive information.
Photo of a microscope and two close ups of tissue.

Optical Coherence Tomography (OCT)

In this project, OCT’s potentials for intra-operative and postoperative (laboratory) pathology diagnostics are investigated.
Hip prosthesis in titanium.

Pragmatic Research in Orthopedics - PRIO

Pragmatic Research in Orthopedics is a research group that aim to optimize the quality of care within the field of orthopedic surgery. We have a strong focus on the orthopedic interventions aimed at the lower extremities.

Education and courses

TBMI26 - Neural Networks and Learning Systems
TBMI02 - Medical Image Analysis
TSBB31 - Medical Images
732A82 - Deep learning
TBMT58 - Project - Biomedical Engineering
TBMT56 - Biomedical Engineering
TBME08 - Biomedical Modeling and Simulation
ETE368 - Safety in Hospitals

Research group

Photo of Anders Eklund

Anders Eklund

Senior Associate Professor

Photo of Magnus Borga

Magnus Borga

Deputy Dean, Professor

Photo of Neda Haj Hosseini

Neda Haj Hosseini

Associate Professor, Docent

Photo of Christoforos Spyretos

Christoforos Spyretos

PhD student

Photo of Iulian Emil Tampu

Iulian Emil Tampu

Principal Research Engineer

Publications in the research area of medical image analysis

Selected publications

Cover of publication 'Deep learning for medical image analysis in cancer diagnosis'
Iulian Emil Tampu (2024)
Deep learning for medical image analysis in cancer diagnosis
Cover of publication 'Modern multimodal methods in brain MRI'
David Abramian (2023)
Modern multimodal methods in brain MRI
Cover of publication 'A path along deep learning for medical image analysis: With focus on burn wounds and brain tumors'
Marco Domenico Cirillo (2021)
A path along deep learning for medical image analysis: With focus on burn wounds and brain tumors

Latest publications

2025

Alfredo Ordinola, David Abramian, Magnus Herberthson, Anders Eklund, Evren Özarslan (2025) Super-resolution mapping of anisotropic tissue structure with diffusion MRI and deep learning Scientific Reports, Vol. 15, Article 6580 (Article in journal) Continue to DOI
Humaira Batool, Asmat Mukhtar, Sajid Gul Khawaja, Norah Saleh Alghamdi, Asad Mansoor Khan, Adil Qayyum, Ruqqayia Adil, Zawar Khan, Muhammad Usman Akram, Muhammad Usman Akbar, Anders Eklund (2025) Knowledge Distillation and Transformer Based Framework for Automatic Spine CT Report Generation IEEE Access, p. 1-1 (Article in journal) Continue to DOI
Muhammad Usman Akbar, Wuhao Wang, Anders Eklund (2025) Beware of diffusion models for synthesizing medical images - A comparison with GANs in terms of memorizing brain MRI and chest x-ray images Machine Learning: Science and Technology (Article in journal) Continue to DOI
Iulian Emil Tampu, Per Nyman, Christoforos Spyretos, Ida Blystad, Alia Shamikh, Gabriela Prochazka, Teresita Díaz de Ståhl, Johanna Sandgren, Peter Lundberg, Neda Haj-Hosseini (2025) Pediatric brain tumor classification using digital pathology and deep learning: Evaluation of SOTA methods on a multi-center Swedish cohort Brain Pathology, Article e70029 (Article in journal) Continue to DOI
Iulian Emil Tampu, Tamara Bianchessi, Ida Blystad, Peter Lundberg, Per Nyman, Anders Eklund, Neda Haj-Hosseini (2025) Pediatric brain tumor classification using deep learning on MR-images with age fusion Neuro-Oncology Advances, Vol. 7, Article vdae205 (Article in journal) Continue to DOI

Master theses in medical image analysis

Code resources

Find the code for our projects on the group GitHub repository

Related research

Simulation of brain

Biomedical Image Science

We develop methods & techniques for depicting anatomy & function in the human body & its organs. From imaging techniques, through methods of analysis and quantification of image information, to validation of new methods and image-based biomarkers.
Two scientists are sitting infront of an MRI

Center for Medical Image Science and Visualization, CMIV

CMIV conducts focused front-line research providing solutions to tomorrow’s clinical issues. The CMIV mission is to develop future methods and tools for image analysis and visualization for applications within health care and medical research.
Illustrative image of cancer cells and networks.

Cancer

Cancer is a research network for scientists and health care professionals at Linköping University and at the County Council of Östergötland (Region Östergötland). The research is related to cancer diagnosis, pathogenesis and treatment.
Researchers around a computer.

AIDA

Analytic Imaging Diagnostics Arena (AIDA) is a national arena for research and innovation on analytic image-based diagnostics.

Organisation

Computer simulation of a person

Department of Biomedical Engineering (IMT)

A national centre for research, PhD studies and graduate studies within biomedical engineering, since 1972.

Faculty of Science and Engineering (Institute of Technology) (LITH)

With some 14,800 students, more than 1,000 employees and a budget exceeding SEK 1.7 billion, the Faculty of Science and Engineering is one of Sweden’s largest engineering education institutions. We are a fully integrated part of Linköping University.

Tags