Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy

Tian, Yu; Maicas, Gabriel; Pu, Leonardo Zorrón Cheng Tao; Singh, Rajvinder; Verjans, Johan; Carneiro, Gustavo

doi:10.1007/978-3-030-59725-2_27

Cited by 30 publications

(29 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventionally, the reviewed GNN models were learned on a large number of brain graphs which hinders their application to a few-shot learning (FSL) setting where the goal is to seek a better model generalization on problems with very limited data. While several image-based works have demonstrated the feasibility of learning given few samples (84,85,86), FSL remains overlooked in brain graph-based works (87). Therefore, a promising direction is to consider the use of FSL in network neuroscience works.…”

Section: Ldis Lgen Lamentioning

confidence: 99%

Graph Neural Networks in Network Neuroscience

Bessadok¹,

Mahjoub²,

Rekik³

2021

Preprint

View full text Add to dashboard Cite

Noninvasive medical neuroimaging has yielded many discoveries about the brain connectivity. Several substantial techniques mapping morphological, structural and functional brain connectivities were developed to create a comprehensive road map of neuronal activities in the human brain -namely brain graph. Relying on its non-Euclidean data type, graph neural network (GNN) provides a clever way of learning the deep graph structure and it is rapidly becoming the state-of-the-art leading to enhanced performance in various network neuroscience tasks. Here we review current GNN-based methods, highlighting the ways that they have been used in several applications related to brain graphs such as missing brain graph synthesis and disease classification. We conclude by charting a path toward a better application of GNN models in network neuroscience field for neurological disorder diagnosis and population graph integration.

show abstract

Section: Ldis Lgen Lamentioning

confidence: 99%

Graph Neural Networks in Network Neuroscience

Bessadok¹,

Mahjoub²,

Rekik³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning has shown outstanding results in medical image analysis problems [11,16,19,21,22,29,30]. However, this performance usually depends on the availability of labelled datasets, which is expensive to obtain given that the labelling process requires expert radiologists.…”

Section: Introductionmentioning

confidence: 99%

Self-supervised Mean Teacher for Semi-supervised Chest X-Ray Classification

Liu

Tian

Cordeiro

et al. 2021

Machine Learning in Medical Imaging

Self Cite

View full text Add to dashboard Cite

The training of deep learning models generally requires a large amount of annotated data for effective convergence and generalisation. However, obtaining high-quality annotations is a laboursome and expensive process due to the need of expert radiologists for the labelling task. The study of semi-supervised learning in medical image analysis is then of crucial importance given that it is much less expensive to obtain unlabelled images than to acquire images labelled by expert radiologists.Essentially, semi-supervised methods leverage large sets of unlabelled data to enable better training convergence and generalisation than if we use only the small set of labelled images.In this paper, we propose the Self-supervised Mean Teacher for Semi-supervised (S 2 MTS 2 ) learning that combines self-supervised mean-teacher pre-training with semi-supervised finetuning. The main innovation of S 2 MTS 2 is the self-supervised mean-teacher pretraining based on the joint contrastive learning, which uses an infinite number of pairs of positive query and key features to improve the mean-teacher representation. The model is then fine-tuned using the exponential moving average teacher framework trained with semi-supervised learning.We validate S 2 MTS 2 on the thorax disease multi-label classification problem from the dataset Chest X-ray14, where we show that it outperforms the previous SOTA semi-supervised learning methods by a large margin. Our code is available at https://github.com/ fengbeiliu/semi-chest.

show abstract

“…disease present or not) and are able to detect and delineate anomalous regions solely from such weakly labeled data, without the need for detailed pixel or patch-level labels [Campanella et al, 2019]. On the contrary, few-shot approaches reduce the number of required labeled samples to the least possible amount [Tian et al, 2020].…”

Section: Introductionmentioning

confidence: 99%

Image-to-Image Translation as a Pretext for Unsupervised Detection of Cancerous Regions in Histology Imagery

Štepec¹,

Skočaj²

2021

View full text Add to dashboard Cite

Detection of visual anomalies refers to the problem of finding patterns in different imaging data that do not conform to the expected visual appearance, and is a widely studied problem in different domains. Due to the nature of anomaly occurrences and underlying generating processes, it is hard to characterize them and obtain labelled data. Obtaining labelled data is especially difficult in biomedical applications, where only trained domain experts can provide labels, which are often diverse and complex to a large degree. The recently presented approaches for unsupervised detection of visual anomalies omit the need for labelled data and demonstrate promising results in domains where anomalous samples significantly deviate from the normal appearance. Despite promising results, the performance of such approaches still lags behind supervised approaches and does not provide a universal solution. In this work, we present an image-to-image translation-based framework that significantly surpasses the performance of existing unsupervised methods and approaches the performance of supervised methods in a challenging domain of cancerous region detection in histology imagery.

show abstract

Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy

Cited by 30 publications

References 17 publications

Graph Neural Networks in Network Neuroscience

Graph Neural Networks in Network Neuroscience

Self-supervised Mean Teacher for Semi-supervised Chest X-Ray Classification

Image-to-Image Translation as a Pretext for Unsupervised Detection of Cancerous Regions in Histology Imagery

Contact Info

Product

Resources

About