Deep semi-supervised learning for medical image segmentation: A review

Han, Kai; Sheng, Victor S.; Song, Yuqing; Liu, Yi; Qiu, Chengjian; Ma, Siqi; Liu, Zhe

doi:10.1016/j.eswa.2023.123052

Cited by 13 publications

(6 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, these types of models are supervised, that is, the ground truth is considered as known and the model is tasked with connecting the supplied input features with these ground truth measurements (e.g., presence or absence of binding) via a set of non-linear functions incorporating weights which are optimised in the training process. For this reason, we focus on supervised approaches here, but other types of models are also extremely useful in biology, such as unsupervised learning of cell clusters from single-cell RNA-sequencing [54] or semi-supervised deep learning for biological imaging analysis [55], just to name two applications.…”

Section: Features and Model Architecturementioning

confidence: 99%

Deep Learning for Elucidating Modifications to RNA—Status and Challenges Ahead

Rennie

2024

Genes

View full text Add to dashboard Cite

RNA-binding proteins and chemical modifications to RNA play vital roles in the co- and post-transcriptional regulation of genes. In order to fully decipher their biological roles, it is an essential task to catalogue their precise target locations along with their preferred contexts and sequence-based determinants. Recently, deep learning approaches have significantly advanced in this field. These methods can predict the presence or absence of modification at specific genomic regions based on diverse features, particularly sequence and secondary structure, allowing us to decipher the highly non-linear sequence patterns and structures that underlie site preferences. This article provides an overview of how deep learning is being applied to this area, with a particular focus on the problem of mRNA-RBP binding, while also considering other types of chemical modification to RNA. It discusses how different types of model can handle sequence-based and/or secondary-structure-based inputs, the process of model training, including choice of negative regions and separating sets for testing and training, and offers recommendations for developing biologically relevant models. Finally, it highlights four key areas that are crucial for advancing the field.

show abstract

Section: Features and Model Architecturementioning

confidence: 99%

Deep Learning for Elucidating Modifications to RNA—Status and Challenges Ahead

Rennie

2024

Genes

View full text Add to dashboard Cite

show abstract

“…Notably, most studies have only conducted classification and segmentation tasks separately, while the two tasks can be connected to construct a joint network for classification and segmentation to improve the overall performance. Previous studies have demonstrated the superiority of some models in the task o lesion segmentation, but they rely highly on the pixel-level annotation of large-scale da tasets [19]. In general, pixel-by-pixel annotation of images is laborious and time-consum ing, which is difficult for doctors with heavy workloads.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, some works [27,28] attempt to impose explicit shape con straints or add input image shape information to enhance the boundary segmentation ca pabilities of the model. Nevertheless, most previous studies have not simultaneously con sidered multilevel contrast learning between features of different paradigms and shape Previous studies have demonstrated the superiority of some models in the task of lesion segmentation, but they rely highly on the pixel-level annotation of large-scale datasets [19]. In general, pixel-by-pixel annotation of images is laborious and timeconsuming, which is difficult for doctors with heavy workloads.…”

Section: Introductionmentioning

confidence: 99%

Multitask Learning for Concurrent Grading Diagnosis and Semi-Supervised Segmentation of Honeycomb Lung in CT Images

Dong,

Yang,

Feng

2024

Electronics

View full text Add to dashboard Cite

Honeycomb lung is a radiological manifestation of various lung diseases, seriously threatening patients’ lives worldwide. In clinical practice, the precise localization of lesions and assessment of their severity are crucial. However, accurate segmentation and grading are challenging for physicians due to the heavy annotation burden and diversity of honeycomb lungs. In this paper, we propose a multitask learning architecture for semi-supervised segmentation and grading diagnosis to achieve automatic localization and assessment of lesions. To the best of our knowledge, this is the first method that integrates a grading diagnosis task into honeycomb lung semi-supervised segmentation. Firstly, we adapt cross-learning to capture local features and long-range dependencies from the CNN and transformer. Secondly, considering the diversity of honeycomb lung lesions, the shape-edge aware constraint is designed to assist the model in locating lesions. Then, in order to better understand the different levels of information in the images, we develop global contrast and local contrast learning to enhance the model’s learning of semantic-level and pixel-level features. Lastly, aiming to improve the diagnostic accuracy, we propose a gradient thresholding algorithm to integrate the segmentation predictions into the grading diagnosis network. The experiment’s results based on the in-house honeycomb lung dataset demonstrate the superiority of our method. Compared to other methods, our approach achieves a state-of-the-art performance. In particular, in external data testing, our predictions are consistent with physicians in the majority of cases. In addition, the segmentation results based on the public Kvasir-SEG dataset also indicate that our method has good generalization ability.

show abstract

“…Therefore, to reduce dependency on annotated medical image dataset, semi-supervised learning (SSL) techniques are appropriate for medical image analysis tasks. The semisupervised approach is broadly branched into traditional semi-supervised techniques and deep semi-supervised techniques [17][18][19][20][21][22][23][24]. The traditional semi-supervised methods are a blend of both labeled and unlabeled data for the classification process.…”

Section: Introductionmentioning

confidence: 99%

A Critical Analysis of Deep Semi-Supervised Learning Approaches for Enhanced Medical Image Classification

Shakya,

Alavi,

Porteous

et al. 2024

Information

View full text Add to dashboard Cite

Deep semi-supervised learning (DSSL) is a machine learning paradigm that blends supervised and unsupervised learning techniques to improve the performance of various models in computer vision tasks. Medical image classification plays a crucial role in disease diagnosis, treatment planning, and patient care. However, obtaining labeled medical image data is often expensive and time-consuming for medical practitioners, leading to limited labeled datasets. DSSL techniques aim to address this challenge, particularly in various medical image tasks, to improve model generalization and performance. DSSL models leverage both the labeled information, which provides explicit supervision, and the unlabeled data, which can provide additional information about the underlying data distribution. That offers a practical solution to resource-intensive demands of data annotation, and enhances the model’s ability to generalize across diverse and previously unseen data landscapes. The present study provides a critical review of various DSSL approaches and their effectiveness and challenges in enhancing medical image classification tasks. The study categorized DSSL techniques into six classes: consistency regularization method, deep adversarial method, pseudo-learning method, graph-based method, multi-label method, and hybrid method. Further, a comparative analysis of performance for six considered methods is conducted using existing studies. The referenced studies have employed metrics such as accuracy, sensitivity, specificity, AUC-ROC, and F1 score to evaluate the performance of DSSL methods on different medical image datasets. Additionally, challenges of the datasets, such as heterogeneity, limited labeled data, and model interpretability, were discussed and highlighted in the context of DSSL for medical image classification. The current review provides future directions and considerations to researchers to further address the challenges and take full advantage of these methods in clinical practices.

show abstract

Deep semi-supervised learning for medical image segmentation: A review

Cited by 13 publications

References 102 publications

Deep Learning for Elucidating Modifications to RNA—Status and Challenges Ahead

Deep Learning for Elucidating Modifications to RNA—Status and Challenges Ahead

Multitask Learning for Concurrent Grading Diagnosis and Semi-Supervised Segmentation of Honeycomb Lung in CT Images

A Critical Analysis of Deep Semi-Supervised Learning Approaches for Enhanced Medical Image Classification

Contact Info

Product

Resources

About