4 papers
What Matters is the Prompt: Prompt Sensitivity and Prompt Generation in Foundation Models for Lung Nodule Segmentation
Jorge F. Lazo, Xixi Liu, Andreas Hallqvist +5
Lung nodule segmentation in computed tomography is essential for extracting clinically relevant information for lung cancer assessment and treatment planning. Foundation models hav…
CT-CLIP Representations for Multimodal Lung Cancer Survival Prediction
Sofie Allgöwer, Mikael Johansson, Andreas Hallqvist +4
Accurate prognosis prediction is important for treatment planning in lung cancer, but deep learning-driven survival modelling is often limited by the scarcity of curated imaging co…
CEVAR: Centerline Embedding Extraction for Endovascular Aneurysm Repair
Roman Naeem, Timo Niiniskorpi, Charlotte Sandström +6
Long-term mortality rates after endovascular aneurysm repair (EVAR) remain elevated due to post-EVAR rupture caused by loss of seal in stent graft sealing zones. Structured CT revi…
Exemplar Diffusion: Improving Medical Object Detection with Opportunistic Labels
Victor Wåhlstrand, Jennifer Alvén, Ida Häggström
We present a framework to take advantage of existing labels at inference, called \textit{exemplars}, in order to improve the performance of object detection in medical images. The…