Medical image segmentation with limited supervision: a review of deep network models
J Peng, Y Wang - IEEE Access, 2021 - ieeexplore.ieee.org
Despite the remarkable performance of deep learning methods on various tasks, most
cutting-edge models rely heavily on large-scale annotated training examples, which are …
cutting-edge models rely heavily on large-scale annotated training examples, which are …
MRI and CT bladder segmentation from classical to deep learning based approaches: Current limitations and lessons
Precise determination and assessment of bladder cancer (BC) extent of muscle invasion
involvement guides proper risk stratification and personalized therapy selection. In this …
involvement guides proper risk stratification and personalized therapy selection. In this …
High-level prior-based loss functions for medical image segmentation: A survey
Today, deep convolutional neural networks (CNNs) have demonstrated state of the art
performance for supervised medical image segmentation, across various imaging modalities …
performance for supervised medical image segmentation, across various imaging modalities …
Weak label based Bayesian U-Net for optic disc segmentation in fundus images
Fundus images have been widely used in routine examinations of ophthalmic diseases. For
some diseases, the pathological changes mainly occur around the optic disc area; therefore …
some diseases, the pathological changes mainly occur around the optic disc area; therefore …
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 …
FedMix: Mixed supervised federated learning for medical image segmentation
The purpose of federated learning is to enable multiple clients to jointly train a machine
learning model without sharing data. However, the existing methods for training an image …
learning model without sharing data. However, the existing methods for training an image …
[HTML][HTML] CNN-based lung CT registration with multiple anatomical constraints
A Hering, S Häger, J Moltz, N Lessmann… - Medical Image …, 2021 - Elsevier
Deep-learning-based registration methods emerged as a fast alternative to conventional
registration methods. However, these methods often still cannot achieve the same …
registration methods. However, these methods often still cannot achieve the same …
Greybox XAI: A Neural-Symbolic learning framework to produce interpretable predictions for image classification
Abstract Although Deep Neural Networks (DNNs) have great generalization and prediction
capabilities, their functioning does not allow a detailed explanation of their behavior …
capabilities, their functioning does not allow a detailed explanation of their behavior …
Weakly supervised segmentation with cross-modality equivariant constraints
Weakly supervised learning has emerged as an appealing alternative to alleviate the need
for large labeled datasets in semantic segmentation. Most current approaches exploit class …
for large labeled datasets in semantic segmentation. Most current approaches exploit class …
Versatile medical image segmentation learned from multi-source datasets via model self-disambiguation
A versatile medical image segmentation model applicable to images acquired with diverse
equipment and protocols can facilitate model deployment and maintenance. However …
equipment and protocols can facilitate model deployment and maintenance. However …