News
Latest updates from the Netherlands Cancer Institute in Artificial Intelligence
DeepSMILE published in Medical Image Analysis
In this work we use whole-slide image (WSI) compression and multiple instance learning to predict homologous recombination deficiency and microsatellite instability from breast cancer and colorectal cancer WSIs. Both these labels are closely related to a patient’s response to immune- and targeted therapies.
Read more
May 15, 2022
AI for Oncology present at SPIE Medical Imaging
The AI for Oncology Lab was present at SPIE Medical Imaging 2022 in San Diego, presenting a diversity of work. Shannon Doyle explored the use of self-supervised techniques for the detection of ducts in histopathological surgical specimens, Yoni Schirris presented a weak-label approach to predict the tumor-infiltrating lymphocytes score and George Yiasemis presented a deep learning-based accelerated MRI reconstruction algorithm.
Read more
Feb. 23, 2022
KWF grant on predicting invasive recurrence for DCIS has been awarded
Our project proposal together with the groups of Jelle Wesseling and Lodewyk Wessels to predict invasive recurrence of DCIS with AI has been awarded by KWF.
Read more
Dec. 21, 2021
Release of exclusive cross entropy loss code on GitHub
Code accompanying our ICCV paper Sparse-Shot Learning With Exclusive Cross-Entropy for Extremely Many Localisations has been released on GitHub and PyPi.
Read more
Dec. 1, 2021
Yoni Schirris wins pitch competition
Last week the pre-selected three best candidates from each UvA faculty competed against each other. Yoni Schirris was the overall winner with his pitch on AI and cancer histopathology. He is working to determine which cancer patients may benefit from immunotherapy.
Read more
Sept. 13, 2021