Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives
Deep learning has demonstrated remarkable performance across various tasks in medical
imaging. However, these approaches primarily focus on supervised learning, assuming that …
imaging. However, these approaches primarily focus on supervised learning, assuming that …
Source-free domain adaptation for image segmentation
Abstract Domain adaptation (DA) has drawn high interest for its capacity to adapt a model
trained on labeled source data to perform well on unlabeled or weakly labeled target data …
trained on labeled source data to perform well on unlabeled or weakly labeled target data …
Improving calibration and out-of-distribution detection in deep models for medical image segmentation
D Karimi, A Gholipour - IEEE transactions on artificial …, 2022 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) have proved to be powerful medical image
segmentation models. In this study, we address some of the main unresolved issues …
segmentation models. In this study, we address some of the main unresolved issues …
Medical image segmentation with domain adaptation: a survey
Deep learning (DL) has shown remarkable success in various medical imaging data
analysis applications. However, it remains challenging for DL models to achieve good …
analysis applications. However, it remains challenging for DL models to achieve good …
Anatomy-guided domain adaptation for 3D in-bed human pose estimation
A Bigalke, L Hansen, J Diesel, C Hennigs… - Medical Image …, 2023 - Elsevier
Abstract 3D human pose estimation is a key component of clinical monitoring systems. The
clinical applicability of deep pose estimation models, however, is limited by their poor …
clinical applicability of deep pose estimation models, however, is limited by their poor …
Improving cross-domain generalizability of medical image segmentation using uncertainty and shape-aware continual test-time domain adaptation
J Zhu, B Bolsterlee, Y Song, E Meijering - Medical Image Analysis, 2024 - Elsevier
Continual test-time adaptation (CTTA) aims to continuously adapt a source-trained model to
a target domain with minimal performance loss while assuming no access to the source …
a target domain with minimal performance loss while assuming no access to the source …
[HTML][HTML] Constrained unsupervised anomaly segmentation
Current unsupervised anomaly localization approaches rely on generative models to learn
the distribution of normal images, which is later used to identify potential anomalous regions …
the distribution of normal images, which is later used to identify potential anomalous regions …
A human-in-the-loop method for pulmonary nodule detection in CT scans
Automated pulmonary nodule detection using computed tomography scans is vital in the
early diagnosis of lung cancer. Although extensive well-performed methods have been …
early diagnosis of lung cancer. Although extensive well-performed methods have been …
Test-time adaptation with shape moments for image segmentation
Supervised learning is well-known to fail at generalization under distribution shifts. In typical
clinical settings, the source data is inaccessible and the target distribution is represented …
clinical settings, the source data is inaccessible and the target distribution is represented …
[HTML][HTML] Proportion constrained weakly supervised histopathology image classification
J Silva-Rodríguez, A Schmidt, MA Sales… - Computers in Biology …, 2022 - Elsevier
Multiple instance learning (MIL) deals with data grouped into bags of instances, of which
only the global information is known. In recent years, this weakly supervised learning …
only the global information is known. In recent years, this weakly supervised learning …