Efficient Soft-Constrained Clustering for Group-Based Labeling

Bise, Ryoma; Abe, Kentaro; Hayashi, H.; Tanaka, Kiyohito; Uchida, Seiichi

doi:10.1007/978-3-030-32254-0_47

Cited by 3 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used DenseNet [32] as the CNN. DenseNet has been widely used in various medical-image classification and analysis tasks due to its state-of-the-art performance (e.g., [33], [34]).…”

Section: Methodsmentioning

confidence: 99%

Automatic Estimation of Ulcerative Colitis Severity by Learning to Rank With Calibration

et al. 2022

Self Cite

View full text Add to dashboard Cite

For automatic disease-severity-level estimation, a large-scale medical image dataset with level annotations is generally necessary. However, attaching absolute-level annotations (such as levels 0, 1, and 3) is very costly and even inaccurate due to the level ambiguity. In this study, we proved experimentally that using a ranking function for level estimation can relax this difficulty. We propose a multi-task learning method for automatically estimating disease-severity levels that combine learning to rank with regression. The ranking function of the proposed method is trainable by relative-level and a small number of absolutelevel annotations. For relative-level annotation, an annotator only needs to specify that one image has a higher disease level than another-this is much easier than absolute-level annotation. The proposed method enables disease-severity classification by calibrating the ranking function based on relative-level annotation through regression. The effectiveness of the method was proved through a large-scale experiment of ulcerative colitis-severity estimation with colonoscopy images.

show abstract

“…We used DenseNet [32] as the CNN. DenseNet has been widely used in various medical-image classification and analysis tasks due to its state-of-the-art performance (e.g., [33], [34]).…”

Section: Methodsmentioning

confidence: 99%

Automatic Estimation of Ulcerative Colitis Severity by Learning to Rank With Calibration

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep Clustering In recent years, several approaches perform clustering on top of features extracted by deep neural network (DNN) [3], [8], [9]. Tian et al [10] proposed a two-stage framework that runs K-means clustering on the feature space extracted by a DNN in the first stage.…”

Section: Related Work and Backgroundmentioning

confidence: 99%

“…JULE [14] is an end-to-end deep clustering framework that jointly learns Convnet features and clusters within a recurrent framework. Bise et al [8] proposed a soft-constrained clustering method on top of CNN's features and applied it for clustering of endoscopy images. Deep Generative Clustering Deep generative models are the powerful class of machine learning which are able to capture the data distribution of the training data and generate artificial samples.…”

Section: Related Work and Backgroundmentioning

confidence: 99%

Deep Variational Clustering Framework for Self-labeling of Large-scale Medical Images

Soleymani¹,

Eslami²,

Elze³

et al. 2021

Preprint

View full text Add to dashboard Cite

One of the most promising approaches for unsupervised learning is combining deep representation learning and deep clustering. Recent studies propose to simultaneously learn representation using deep neural networks and perform clustering by defining a clustering loss on top of embedded features. Unsupervised image clustering naturally requires good feature representations to capture the distribution of the data and subsequently differentiate data points from one another. Among existing deep learning models, the generative variational autoencoder explicitly learns data generating distribution in a latent space. We propose a Deep Variational Clustering (DVC) framework for unsupervised representation learning and clustering of large-scale medical images. DVC simultaneously learns the multivariate Gaussian posterior through the probabilistic convolutional encoder, and the likelihood distribution with the probabilistic convolutional decoder; and optimizes cluster labels assignment. Here, the learned multivariate Gaussian posterior captures the latent distribution of a large set of unlabeled images. Then, we perform unsupervised clustering on top of the variational latent space using a clustering loss. In this approach, the probabilistic decoder helps to prevent the distortion of data points in the latent space, and to preserve local structure of data generating distribution.The training process can be considered as a self-training process to refine the latent space and simultaneously optimizing cluster assignments iteratively. We evaluated our proposed framework on three public datasets that represented different medical imaging modalities. Our experimental results show that our proposed framework generalizes better across different datasets. It achieves compelling results on several medical imaging benchmarks. Thus, our approach offers potential advantages over conventional deep unsupervised learning in real-world applications. The source code of the method and of all the experiments are available publicly at: https://github.com/csfarzin/DVC

show abstract

Semi-supervised Learning in Computer-aided Diagnosis

2021

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)

View full text Add to dashboard Cite

Efficient Soft-Constrained Clustering for Group-Based Labeling

Cited by 3 publications

References 9 publications

Automatic Estimation of Ulcerative Colitis Severity by Learning to Rank With Calibration

Automatic Estimation of Ulcerative Colitis Severity by Learning to Rank With Calibration

Deep Variational Clustering Framework for Self-labeling of Large-scale Medical Images

Semi-supervised Learning in Computer-aided Diagnosis

Contact Info

Product

Resources

About