Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering

Kim, Wonjik; Kanezaki, Asako; Tanaka, Masayuki

doi:10.1109/tip.2020.3011269

Cited by 193 publications

(162 citation statements)

References 46 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…To highlight our method's soundness, we compare it with other commonly used unsupervised methods in the literature and its 2D implementation [12]. In particular, our results were evaluated against the kidney graft segmentations obtained by Otsu thresholding [15] and watershed 3D [6] methods that are commonly used for unsupervised segmentation in a variety of studies.…”

Section: Resultsmentioning

confidence: 99%

“…The proposed unsupervised segmentation model then processes the boundary boxes of various sizes containing the region of interest. Our method is based on differentiable feature clustering [12]. A simple straight-forward 3D convolutional neural network (CNN) is used to extract features and optimize two loss functions without any need for ground truth annotations.…”

Section: Unsupervised Segmentation Modelmentioning

confidence: 99%

“…The second step corresponds to the pixelwise segmentation of the kidney graft. Our method is based on [12] extending the formulation to 3D to explore all the available information from the MRI modalities. Moreover, it proposes a multimodal formulation where multiple MRI sequences are integrated towards a robust kidney graft segmentation tool.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3d Unsupervised Kidney Graft Segmentation Based On Deep Learning And Multi-Sequence Mri

Milecki

Bodard

Corréas

et al. 2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

Image segmentation is one of the most popular problems in medical image analysis. Recently, with the success of deep neural networks, these powerful methods provide state of the art performance on various segmentation tasks. However, one of the main challenges relies on the high number of annotations that they need to be trained, which is crucial in medical applications. In this paper, we propose an unsupervised method based on deep learning for the segmentation of kidney grafts. Our method is composed of two different stages, the detection of the area of interest and the segmentation model that is able, through an iterative process, to provide accurate kidney draft segmentation without the need for annotations. The proposed framework works in the 3D space to explore all the available information and extract meaningful representations from Dynamic Contrast-Enhanced and T2 MRI sequences. Our method reports a dice of 89.8 ± 3.1%, Hausdorff distance at percentile 95% of 5.8±0.41mm and percentage of kidney volume difference of 5.9 ± 5.7% on a test dataset of 29 patients subject to a kidney transplant.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Unsupervised Segmentation Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

3d Unsupervised Kidney Graft Segmentation Based On Deep Learning And Multi-Sequence Mri

Milecki

Bodard

Corréas

et al. 2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

show abstract

“…The reason for assigning separate labels (annotations) to the surrounding non-follicular tissue and the non-tissue region is motivated by the future perspective of using this dataset for a separate analysis of the non-follicular tissue regions. Annotations were performed using a two step approach: initially, an unsupervised segmentation method as described in 12 was used to produce a rough segmentation of the three classes described above. In the second step the segmentations were manually refined to obtain the final annotations.…”

Section: Methodsmentioning

confidence: 99%

Deep-learning for thyroid microstructure segmentation in 2D OCT images

Tampu

Eklund

Haj‐Hosseini

2021

Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXV

View full text Add to dashboard Cite

Optical coherence tomography (OCT) can provide exquisite details of tissue microstructure without traditional tissue sectioning, with potential diagnostic and intraoperative applications in a variety of clinical areas. In thyroid surgery, OCT could provide information to reduce the risk of damaging normal tissue. Thyroid tissue's follicular structure alters in case of various pathologies including the non-malignant ones which can be imaged using OCT. The success of deep learning for medical image analysis encourages its application on OCT thyroid images for quantitative analysis of tissue microstructure. To investigate the potential of a deep learning approach to segment the follicular structure in OCT images, a 2D U-Net was trained on b-scan OCT images acquired from ex vivo adult human thyroid samples affected by a range of pathologies. Results on a pool of 104 annotated images showed a mean Dice score of 0.74±0.19 and 0.92±0.09 when segmenting the follicular structure and the surrounding tissue on the test dataset (n=10 images). This study shows that a deep learning approach for tissue microstructure segmentation in OCT images is possible. The achieved performance without requiring manual intervention encourages the application of a deep-learning method for real-time analysis of OCT data.

show abstract

“…Due to the various resolutions of X-ray images in the dataset, it is necessary to locate object regions to enhance informative areas and suppress noise. Therefore, an unsupervised learning framework, which was inspired by a novel unsupervised learning image-segmentation approach proposed in [ 19 ], was exploited to accomplish it. Supervised methods require the original image and ground truth with pixel-level semantic labels.…”

Section: Dataset and Image-processingmentioning

confidence: 99%

A deep learning-based computer-aided diagnosis method of X-ray images for bone age assessment

Li¹,

Liu

Li³

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Bone age assessment using hand-wrist X-ray images is fundamental when diagnosing growth disorders of a child or providing a more patient-specific treatment. However, as clinical procedures are a subjective assessment, the accuracy depends highly on the doctor’s experience. Motivated by this, a deep learning-based computer-aided diagnosis method was proposed for performing bone age assessment. Inspired by clinical approaches and aimed to reduce expensive manual annotations, informative regions localization based on a complete unsupervised learning method was firstly performed and an image-processing pipeline was proposed. Subsequently, an image model with pre-trained weights as a backbone was utilized to enhance the reliability of prediction. The prediction head was implemented by a Multiple Layer Perceptron with one hidden layer. In compliance with clinical studies, gender information was an additional input to the prediction head by embedded into the feature vector calculated from the backbone model. After the experimental comparison study, the best results showed a mean absolute error of 6.2 months on the public RSNA dataset and 5.1 months on the additional dataset using MobileNetV3 as the backbone.

show abstract

Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering

Abstract: The usage of convolutional neural networks (CNNs)

Cited by 193 publications

References 46 publications

3d Unsupervised Kidney Graft Segmentation Based On Deep Learning And Multi-Sequence Mri

3d Unsupervised Kidney Graft Segmentation Based On Deep Learning And Multi-Sequence Mri

Deep-learning for thyroid microstructure segmentation in 2D OCT images

A deep learning-based computer-aided diagnosis method of X-ray images for bone age assessment

Contact Info

Product

Resources

About