Unsupervised domain adaptation for cross-modality liver segmentation via joint adversarial learning and self-learning
نویسندگان
چکیده
Liver segmentation on images acquired using computed tomography (CT) and magnetic resonance imaging (MRI) plays an important role in clinical management of liver diseases. Compared to MRI, CT are more abundant readily available. However, MRI can provide richer quantitative information the compared CT. Thus, it is desirable achieve unsupervised domain adaptation for transferring learned knowledge from source containing labeled target unlabeled MR images. In this work, we report a novel framework cross-modality via joint adversarial learning self-learning. We propose semantic-aware shape-entropy-aware with post-situ identification manner implicitly align distribution task-related features extracted those domain. proposed framework, network trained above two losses manner, then mean completer pseudo-label generation employed produce pseudo-labels train next (desired model). Additionally, self-learning methods, including pixel-adaptive mask refinement student-to-partner learning, desired model. To improve robustness model, low-signal augmentation function transform as input model handle hard samples. Using public datasets, our experiments demonstrated reached four supervised methods Dice score 0.912 ± 0.037 (mean standard deviation).
منابع مشابه
Joint cross-domain classification and subspace learning for unsupervised adaptation
Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain. Several approaches have been proposed for classification tasks in the unsupervised scenario, where no labeled target data are available. Most of the attention has been dedicated to searching a new domain-invariant representation, leaving the definition of the prediction fun...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملAdversarial Teacher-Student Learning for Unsupervised Domain Adaptation
The teacher-student (T/S) learning has been shown effective in unsupervised domain adaptation [1]. It is a form of transfer learning, not in terms of the transfer of recognition decisions, but the knowledge of posteriori probabilities in the source domain as evaluated by the teacher model. It learns to handle the speaker and environment variability inherent in and restricted to the speech signa...
متن کاملUnsupervised Domain Adaptation for Joint Segmentation and POS-Tagging
Sophisticated models have been developed for joint word segmentation and part-of-speech tagging, with increasing accuracies reported on the Chinese Treebank data. These systems, which rely on supervised learning, typically perform worse on texts from a different domain, for which little annotation is available. We consider self-training and character clustering for domain adaptation. Both metho...
متن کاملUnsupervised Domain Adaptation in Brain Lesion Segmentation with Adversarial Networks
Significant advances have been made towards building accurate automatic segmentation systems for a variety of biomedical applications using machine learning. However, the performance of these systems often degrades when they are applied on new data that differ from the training data, for example, due to variations in imaging protocols. Manually annotating new data for each test domain is not a ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied Soft Computing
سال: 2022
ISSN: ['1568-4946', '1872-9681']
DOI: https://doi.org/10.1016/j.asoc.2022.108729