Martijn P. A. Starmans

Martijn P. A. Starmans

Assistant Professor & PI Artificial Intelligence for Integrated Diagnostics (AIID) focused on Medical Imaging in Oncology

Erasmus Medical Center, Department of Radiology & Nuclear Medicine

Erasmus Medical Center, Department of Pathology

Biography

Martijn Starmans is an assistant professor at the Erasmus MC (Rotterdam, the Netherlands) leading the AI for Integrated Diagnostics (AIID) research line, with a dual appointment at the Biomedical Imaging Group Rotterdam (BIGR) (Dept. of Radiology & Nuclear Medicine) and PHANTOM group (Department of Pathology). His main research interest is the use of AI to improve the diagnostic work-up in oncology through integrated diagnostics, focussed on radiology (“radiomics”) and pathology (“pathomics”). Specifically, he develops multi-modal machine learning methods to simultanously co-learn from both modalities (“radiopathomics”), and automated machine learning and meta-learning methods to generalize these methods across clinial applications. He works on a variety of clinical applications (e.g. sarcoma, liver cancer, colorectal cancer, bladder cancer, melanoma, cardiology, neuroendocrine tumors).

Collaborations & Consortia Martijn is currently part of the MICCAI 2024 organization committee one of the two first ever Open Data chairs. To promote sharing of medical imaging data, he is organizing the first ever Open Data Event at MICCAI 2024, with a focus on underrepresented diseases and populations, with for this year special attention for African datasets. To facilitate sharing of data, he established the AFRICAI repository, which other resources can use to make data FAIR.

Martijn is one of the initiators and PIs of the Sarcoma Artificial Intelligence (SAI) consortium (grant awarded), the Liver AI (LAI) consortium (grant awarded), and project lead of the Colorectal Liver Metastes AI (COLIMA) consortium (grant submitted). In these consortia, in total 51 clinical centers, companies, professional- and patient associations from 18 countries are united. He is also part of the Trustworthy AI for MRI ICAI LAB.

Martijn is involved in various large European projects. He is leader of the platform work package of the Horizon 2020 EuCanImage consortium: Towards a European cancer imaging platform for enhanced Artificial Intelligence in oncology, and also work package leader of the Horizon 2021 EOSC4Cancer consortium. Additionally, he is external advisor of RadioVal, and member of the AI4HI AI Development working group, and of EUCAIM. He has been a visiting researcher of the BCN-AIM lab of Prof. Karim Lekadir at the University of Barcelona in 2023 for 4 months.

For a better overview on his projects, see his BIGR home page: https://bigr.nl/member/martijn/.

PhD Degree

Martijn obtained his PhD degree ‘‘cum laude’’ on February 1 2022 with his thesis titled Streamlined Quantitative Imaging Biomarker Development: Generalization of radiomics through automated machine learning. Following his passion to efficiently and automatically optimize routines, he developed an adaptive radiomics framework using automated machine learning, described in this paper. He collaborated with a large number of clinicians to develop radiomics biomarkers in a wide variety of clinical applications. His thesis was nominated for the Fredrik Philipsprijs 2023 for Best Dutch Radiology Thesis and made the top five.

Download my PhD Thesis.

Educational activities

Martijn has co-founded two courses in the MSc Technical Medicine, and is currently teaching two courses in the BSc MSC Technical Medicine and MSc Applied Physics of the TU Delft. Martijn also was part of the program committee and mentor in the first AFRICAI Summer School, and part of the first Rotterdam Radiology AI course organized by the Dutch Radiology Society. He enjoys working together with students and has so-far (co-)supervised 43 students in interships and thesis projects.

Download my (slightly outdated) resumé .

Interests
  • Radiomics
  • Pathomics
  • RadioPathomics
  • Multimodal machine learning
  • AutoML
  • Meta-Learning
  • Oncology
  • Soft-tissue tumors / sarcoma
  • Liver cancer
  • Colorectal liver metastases
Education
  • PhD ''Streamlined Quantitative Imaging Biomarker Development'' ("cum laude"), 2022

    Erasmus Medical Center, Rotterdam, the Netherlands

  • MSc Applied Physics, 2016

    Delft University of Technology, Delft, the Netherlands

  • BSc Applied Physics, 2013

    Delft University of Technology, Delft, the Netherlands

Awards & Grants

  • Role: Main applicant
  • Topic: Radiology and pathology join forces through Artificial Intelligence for Integrated Diagnostics (AIID)
  • Total funding: 2M Euro.
Research Grant
  • Role: Participant
  • Topic: PATH2XNAT: COVID 19 meets Pathomics meets XNAT
  • Total funding: 280k Euro.
  • Role: Co-applicant*
  • Topic: The Liver Artificial Intelligence (LAI) consortium: a benchmark dataset and optimized machine learning methods for MRI-based diagnosis of solid appearing liver lesions
  • Total funding: 1M Euro.

*Not officially mentioned as co-applicant due to formalities. Reference of formal applicant available upon request.

  • Role: Co-applicant
  • Topic: An artificial intelligence (AI)-based model for detection of incidental pulmonary embolism in chest CTs
  • Total funding: 1M Euro.
  • Role: Co-applicant*
  • Topic: Automatic grading and phenotyping of soft-tissue tumors through machine learning to guide personalized cancer treatment
  • Total funding: 400k Euro.

*Not officially mentioned as co-applicant due to formalities. Reference of formal applicant available upon request.

Erasmus Medical Center
Employee of the Year
Department of Radiology and Nuclear Medicine. Honorable Mention.

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). Automated Assessment of T2-Weighted MRI to Differentiate Malignant and Benign Primary Solid Liver Lesions in Noncirrhotic Livers Usiong Radiomics. Academic Radiology.

Cite DOI URL

(2024). Comprehensive characterization of circulating tumor cells and cell-free DNA in patients with metastatic melanoma. Molecular Oncology.

Cite DOI URL

(2024). MAMA-MIA: A Large-Scale Multi-Center Breast Cancer DCE-MRI Benchmark Dataset with Expert Segmentations.

Cite

Student Projects

We work on various clinical applications with different clinicians, and thus also various technical solutions within medical image analysis & AI. Hence, there are usually too many projects to describe here: Currently, we do not have any predefined projects available, but feel free to contact me for more information if you are interested in an internship / thesis! For an overview of some past projects, please see https://bigr.nl/open-projects/.

*

Experience and Education

 
 
 
 
 
Erasmus Medical Center
Assistant Professor & Group Leader
Jan 1, 2024 – Present Rotterdam, the Netherlands

With a joint appointment at the Radiology & Nuclear and Pathology departments, Martijn is heading the AI for Integrated Diagnostics (AIID) research line. The AIID group develops novel multimodal machine learning methods to develop quantitative biomarkers, focused on medical imaging and application in concology.

  • Collaboration and awards: Martijn is involved in various working groups and is work package leader in the Horizon 2020 EuCanImage and Horizon 2021 EOSC4Cancer projects. He is initiator and receiptient of various (consortium) grants, including an NWO NGF AINed Perfonal Fellowship (2M), the Liver AI (LAI) consortium (NWO OTP 1M grant), the Sarcoma Artificial Intelligence (SAI) consortium (Hanarth Fonds 400k grant), a Health-Holland 1M TKI grant on incidental pulmonary embolism, and project lead of the Colorectal Liver Metastes AI (COLIMA) consortium (grant submitted). In these consortia, in total 51 clinical centers, companies, professional- and patient associations from 18 countries are united. Additionally, and he is external advisor of RadioVal.
  • MICCAI 2024 organization: first ever Open Data Chair, initiator of the AFRICAI repository for medical imaging.
  • Trustworthy AI: co-lead of the FUTURE-AI guideline on trustworthy and deployable AI.
  • Supervision: 1 PostDoc, 9 PhD students, and 6 MSc students.
 
 
 
 
 
Erasmus Medical Center
Postdoctoral Researcher
Sep 1, 2021 – Dec 31, 2023 Rotterdam, the Netherlands

Extending the work of his PhD, Martijn’s research focused on generalization of radiomics biomarkers (conventional and deep learning based) using automated machine learning and meta-learning. He worked on a variety of clinical applications (e.g. sarcoma, liver cancer, colorectal cancer, bladder cancer, melanoma, cardiomyopathy, neuroendocrine tumors, CRPS).

  • Management: Co-developer of Imaging Office of department of Radiology and Nuclear Medicine.
  • Supervision: 17 MSc students.
  • Education: Teaching and continuous development of three courses in the BSc and MSc Technical Medicine
 
 
 
 
 
University of Barcelona, Artificial Intelligence in Medicine Lab
Visiting Postdoctoral Researcher
Sep 26, 2022 – Jan 15, 2023 Barcelona, Spain

Martijn will visit the group of Prof. Dr. Karim Lekadir to collaborate on AI for oncology and cardiac imaging within the context of the EuCanImage and euCanSHare consortia. While the main focus is on developing novel algorithms for (deep) radiomics, they will also work on federated learning, applying Martijn’s adaptive radiomics framework from his PhD to ``new’’ clinical applications, a second version of the FUTURE-AI guiding principles, and improving the clinical utility of (radiomics) AI tools.

Supervisors: Karim Lekadir

 
 
 
 
 
Erasmus Medical Center
PhD Candidate
Oct 1, 2016 – Feb 1, 2022 Rotterdam, the Netherlands

See extended description in the “about” section on this website.

Supervisors: Stefan Klein, Jan-Jaap Visser, Wiro Niessen

 
 
 
 
 
Delft University of Technology
MSc Applied Physics
Sep 1, 2014 – Sep 1, 2016 Delft, the Netherlands
  • Track: Imaging Physics
  • Specialisation: Research & Development
  • Thesis: Registration of 3D Breast Ultrasound Scans together with Erasmus Medical Center
  • Honours track: Quantum Nanoscience
 
 
 
 
 
Delft University of Technology
BSc Applied Physics
Sep 1, 2010 – Sep 1, 2013 Delft, the Netherlands
  • Thesis: Activation cycles of stochastically blinking molecules in super-resolution microscopy

Current Team Members

Jette Slettenhaar

MSc Biomedical Engineering, University of Twente

Predicting risk stratification and therapy response for patients with gastrointestinal stromal tumors (GIST) using deep learning on CT and clinical data.

Michael de Leeuw

MSc Applied Physics, Delft University of Technology, Delft, NL

Automatic quantification of histopathological grwoth patterns of colorectal liver metastases on histopathology using AI.

Natalia Oviedo Acosta

MSc Bioinformatics and System Biology, Vrije Universiteit (VU), Amsterdam, NL

Adaptive deep learning in oncology classification through automated machine learning (AutoML).

Yin Tai Wang

MSc Bioinformatics and System Biology, Vrije Universiteit (VU), Amsterdam, NL

Diagnosis of solid appearing lesions based on MRI and deep learning.

Yizhou Liu

MSc Bioinformatics and System Biology, Vrije Universiteit (VU), Amsterdam, NL

Preoperative prediction of colorectal liver metastases aggressiveness using radiomics and deep learning to select patients for chemotherapy.

Erik Kemper

PhD Student, Erasmus MC, Rotterdam, NL

An artificial intelligence (AI)-based model for detection of incidental pulmonary embolism in chest CTs

Xinyi Wan

PhD Student, Erasmus MC, Rotterdam, NL

Trustworthy AI for improved diagnosis of bone and soft-tissue lesions on MRI

Matthew Marzetti

PhD Student, Leeds Biomedical Research Centre, UK, and Erasmus MC, Rotterdam, NL

Evaluating the added value of quantitative MRI in automatic grading and phenotyping of soft-tissue tumors using AI

Zhen Qian

PhD Student, Erasmus MC Surgery Department, Rotterdam, NL

Automatic quantification of histopathological grwoth patterns of colorectal liver metastases on histopathology using AI.

Douwe Spaanderman

PhD Student, Erasmus MC, Rotterdam, NL

Automatic grading and phenotyping of soft-tissue tumors through machine learning to guide personalized cancer treatment

Former Team Members

MSc Thesis

Eline van Lange

MSc Thesis Technical Medicine, Delft University of Technology, Delft, NL (2021 - 2022)

Quantification of neuro-stimulation of CRPS patients using thermography and radiomics

Samuel van Gurp

MSc Biomedical Engineering, Delft University of Technology, Delft, NL (2022 - 2023)

Preoperative prediction of colorectal liver metastases aggressiveness using radiomics and deep learning to select patients for chemotherapy.

Aisha Goedhart

MSc Biomedical Engineering, Delft University of Technology, Delft, NL (2022 - 2023)

Phenotyping of primary liver tumors on multi-parametric MRI through deep radiomics.

Amber Heijdra

MSc Biomedical Engineering, Delft University of Technology, Delft, NL (2022)

Differentiation of Hypertrophic Cardiomyopathy Mutation Carriers without Left Ventricular Hypertrophy and Healthy Controls on CMR using Radiomics

Coen Gruijthuijsen

MSc Mechanical Engineering, Delft University of Technology, Delft, NL (2022)

Automated Machine Learning in Medical Image Segmentation

Teun Tanis

MSc Data Science and Entrepreneurship, Jheronimus Academy of Data Science, s Hertogenbosch, NL (2021)

AUTOMONAI: Towards automatic tuning of medical image segmentation networks

Li Shen Ho

MSc Medicine, Erasmus MC, Rotterdam, NL (2021)

Optimization of preoperative lymph node staging in patients with muscle-invasive bladder cancer using radiomics on CT

Mitchell Deen

MSc Computer Science, Delft University of Technology, Delft, NL (2020)

Automatic algorithm selection and hyperparameter optimization for medical image classification

Koen de Raad

MSc Data Science and Entrepreneurship, Jheronimus Academy of Data Science, s Hertogenbosch, NL (2020)

The Effect of Preprocessing on Convolutional Neural Networks for Medical Image Segmentation

Theodoros Theodoridis

MSc Applied Medical Sciences, VUMC, Amsterdam, NL (2020)

Optimal workflows for computer-aided dementia diagnosis

Alice Dudle

MSc Physics, ETH, Zurich, CH (2019)

Primary Liver Tumor Classification on MRI using Deep Learning

Sanne Hazen

MSc Medicine, Erasmus MC, Rotterdam, NL (2019)

Radiomics as a potential surrogate for histopathological growth patterns and as a prognostic biomarker in patients with resectable colorectal liver metastases

Florian Calvet

MSc Physics, Centrale Marseille, Marseille, FR (2018)

Segmentation of colorectal liver metastases on CT using convolututional neural networks and shape constraints

Michel Renckens

MSc Medicine, Erasmus MC, Rotterdam, NL (2018)

Radiomics for the mutation stratification of gastrointestinal stromal tumors

Guillaume Padmos

MSc Medicine, Erasmus MC, Rotterdam, NL (2017)

Radiomics in desmoid-type fibromatosis

MSc Internship

Ahmad Habbie Tias

MSc Biomedical Engineering, Delft University of Technology, Delft, NL (2023)

Automatic sorting of MRI DICOM images for soft tissue tumors using deep learning

Gini Raaijmakers

MSc Technical Medicine, Delft University of Technology, Delft, NL (2023)

Minimally interactive segmentation of desmoid-type fibromatosis and desmoid-like tumors using multi-modality MR imaging.

Gonnie van Erp

MSc Technical Medicine, Delft University of Technology, Delft, NL (2022)

Minimal Interactive segmentation of soft-tissue tumors on MRI with deep learning using the MIDeepSeg framework

Iris Huele

MSc Technical Medicine, Delft University of Technology, Delft, NL (2021)

Feature selection for an objective analysis of thermograms of patients with CRPS

Lucy Knops

MSc Technical Medicine, Delft University of Technology, Delft, NL (2020)

Evaluation of the differences between thermograms of CRPS patients acquired by different cameras

Jeffrey Visser

MSc Technical Medicine, Delft University of Technology, Delft, NL (2020)

Objective analysis of vasomotor disturbances in CRPS: validation of the classification model

Myrthe van Haaften

MSc Technical Medicine, Delft University of Technology, Delft, NL (2020)

Predicting the development of colorectal liver metastases based on the liver parenchyma on CT scans using radiomics

Marijn Mostert

MSc Technical Medicine, Delft University of Technology, Delft, NL (2020)

Objective analysis of vasomotor disturbances in CRPS: automatic segmentation and classification of thermography images

Lisa Klaassen

MSc Technical Medicine, Delft University of Technology, Delft, NL (2019)

Automatic segmentation of hepatocellular carcinoma with deep learning

Sybren van Hal

MSc Technical Medicine, Delft University of Technology, Delft, NL (2019)

Objective analysis of thermography images of patients with CRPS

Timo Oosterveer

MSc Technical Medicine, Delft University of Technology, Delft, NL (2019)

Classification of Complex Regional Pain Syndrome based on temperature asymmetry in the lower extremity: using Infrared Thermography and a Radiomics approach

Melissa van Gaalen

MSc Technical Medicine, Delft University of Technology, Delft, NL (2018)

Objective analysis of video thermography used as diagnostic tool in patients with Complex Regional Pain Syndrome

Michel Renckens

MSc Medicine, Erasmus MC, Rotterdam, NL (2017)

Radiomics for the prediction of histopathological growth patterns of colorectal liver metastases

Paul De Almeida

MSc Electronics, ENSEEIHT, Toulouse, FR (2017)

Robustness of Radiomics features to segmentation variation

Dai Rui

MSc Electronics, ENSEEIHT, Toulouse, FR (2017)

Missing feature in radiomics: application of the 1p/19q status in presumed low-grade glioma

BSc Thesis

Anna Walstra, Laura Artz, Marit Verboom and Emma Gommers

Bsc Technical Medicine, Delft University of Technology, Delft, NL (2020)

Analysis of videothermography images of patients with Complex Regional Pain Syndrome

Wouter Kessels

Bsc Applied Physics, Delft University of Technology, Delft, NL (2018)

Classification of Lipomatous Tumours

PhD Student

Thomas Phil

PhD Student, Erasmus MC, Rotterdam, NL (2022)

Radiomics in head-and-neck cancer

Contact