Communal Domain Learning for Registration in Drifted Image Spaces

Mansoor, Awais; Linguraru, Marius George

doi:10.1007/978-3-030-32692-0_55

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the surveyed 31 symmetric approaches, direct approaches operated on the feature representations across domains by minimizing their differences (via mutual information [ 63 ], maximum mean discrepancy [ 46 , 49 , 64 ], Euclidean distance [ 65 , 66 , 67 , 68 , 69 , 70 , 71 ], Wasserstein distance [ 72 ], and average likelihood [ 73 ]), maximizing their correlation [ 74 , 75 ] or covariance [ 36 ], and introducing sparsity with L1/L2 norms [ 42 , 76 ]. On the other hand, indirect approaches were applied via adversarial training [ 28 , 41 , 54 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 ], and knowledge distillation [ 86 ].…”

Section: Resultsmentioning

confidence: 99%

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer’s diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For example, Dinsdale et al [45] proposed a method based on adversarial training unlearning information about the scanner sites enabling multi-scanner integration and generalization with a single classifier across data sets. Other works performed such an harmonization on the feature level by minimizing their distances via different metrics such as mutual information [52] or maximizing their correlation [53,54]. The results of this work show that a harmonization on the feature level is not necessarily needed if the differences across data sets are small (e.g.…”

Section: Comparison With Other Transfer Learning Approaches 441 Featu...mentioning

confidence: 91%

Transfer Learning for Neuroimaging via Re-use of Deep Neural Network Features

Holderrieth

Han

Smith

2022

Preprint

View full text Add to dashboard Cite

A major problem in the application of machine learning to neuroimaging is the technological variability in the MRI scanners and the different subject populations across studies. Transfer learning (TL) promises to alleviate this problem. TL refers to a family of methods which acquire knowledge from related tasks to improve generalization in the tasks of interest. In this work, we show that features of deep neural networks are transferable across data sets if the network was pre-trained on the prediction task of interest. Based on this, we propose a transfer learning pipeline which relies on the re-use of deep neural network features across data sets. We empirically study this pipeline on age and sex prediction using the UK Biobank for pre-training and three different small data sets for fine-tuning and evaluation. We find that our method outperforms classical regression methods and training a network from scratch. In particular, we improve state-of-the-art results on age and sex prediction. Our transfer learning method may therefore provide a simple and efficient pipeline to achieve high performance on small data sets.

show abstract

Communal Domain Learning for Registration in Drifted Image Spaces

Cited by 2 publications

References 10 publications

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

Transfer Learning for Neuroimaging via Re-use of Deep Neural Network Features

Contact Info

Product

Resources

About