Anatomically guided cross-domain repair and screening for ultrasound Fetal biometry

J Gao, Q Lao, P Liu, H Yi, Q Kang… - IEEE Journal of …, 2023 - ieeexplore.ieee.org
Ultrasound based estimation of fetal biometry is extensively used to diagnose prenatal
abnormalities and to monitor fetal growth, for which accurate segmentation of the fetal …

MI-SegNet: Mutual information-based US segmentation for unseen domain generalization

Y Bi, Z Jiang, R Clarenbach, R Ghotbi, A Karlas… - … Conference on Medical …, 2023 - Springer
Generalization capabilities of learning-based medical image segmentation across domains
are currently limited by the performance degradation caused by the domain shift, particularly …

A new imbalance-aware loss function to be used in a deep neural network for colorectal polyp segmentation

O Gökkan, M Kuntalp - Computers in Biology and Medicine, 2022 - Elsevier
Colorectal cancers may occur in colon region of human body because of late detection of
polyps. Therefore, colonoscopists often use colonoscopy device to view the entire colon in …

Fourier Test-Time Adaptation with Multi-level Consistency for Robust Classification

Y Huang, X Yang, X Huang, X Zhou, H Chi… - … Conference on Medical …, 2023 - Springer
Deep classifiers may encounter significant performance degradation when processing
unseen testing data from varying centers, vendors, and protocols. Ensuring the robustness …

Pay Attention to the Atlas: Atlas-Guided Test-Time Adaptation Method for Robust 3D Medical Image Segmentation

J Guo, W Zhang, M Sinclair, D Rueckert… - arXiv preprint arXiv …, 2023 - arxiv.org
Convolutional neural networks (CNNs) often suffer from poor performance when tested on
target data that differs from the training (source) data distribution, particularly in medical …

DG-TTA: Out-of-domain medical image segmentation through Domain Generalization and Test-Time Adaptation

C Weihsbach, CN Kruse, A Bigalke… - arXiv preprint arXiv …, 2023 - arxiv.org
Applying pre-trained medical segmentation models on out-of-domain images often yields
predictions of insufficient quality. Several strategies have been proposed to maintain model …