Automated unsupervised learning‐based clustering approach for effective anomaly detection in brain magnetic resonance imaging (MRI)

Govindaraj, Vishnuvarthanan; Thiyagarajan, Arunprasath; Rajasekaran, M. Pallikonda; Zhang, Yudong; Rajesh, Krishnasamy

doi:10.1049/iet-ipr.2020.0597

Cited by 6 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automated segmentation plays a crucial role in various image processing applications, including object recognition, by enabling the isolation of distinct areas in an image, thereby cutting down on processing time for relevant information, [14], [15]. Furthermore, [5], [16] delineates five primary strategies for image segmentation: thresholding techniques [17], boundary-based methods [18], region-based techniques, clustering-based approaches [19], and hybrid methods [20]. Seeded Region Growing segmentation who used by [5], [21], [22], is a hybrid technique.…”

Section: B Image Segmentationmentioning

confidence: 99%

“…Deep learning relies on layers of nonlinear transformation functions arranged in intricate structures. Deep learning is applicable to various domains, including supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning, such as tasks like text classification, image recognition, speech recognition, and mor [19], [29].…”

Section: Deep Learning-based Image Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Fuzzy Deep Learning Approach for the Early Detection of Degenerative Disease

Irianto,

Karnila

et al. 2024

IJACSA

View full text Add to dashboard Cite

Degenerative diseases can impact individuals of any age, encompassing children and teenagers; however, they typically tend to affect productive or adult individuals. Globally, conventional and advanced diagnostic methods, including those developed in Indonesia, have emerged to identify and manage these health conditions. Problems in brain tumor detection are the intricate process of precisely and effectively identifying the presence of tumors in the brain. On the other hand, diagnosing brain tumors in the laboratory poses issues related to time consumption, inaccuracy, lack of consistency, and costliness. This study specifically concentrates on the early detection of brain tumors by analyzing images generated through MRI scans. Unlike the traditional method of manual image analysis conducted by seasoned physicians, our approach integrates fuzzy logic to enable the early identification of brain tumors. The principal objective of this research is to enhance understanding and develop an intelligent, swift, and precise application for diagnosing brain tumors using medical imaging. The segmentation technique provides practical technology for the early detection of brain tumors. Utilizing a dataset comprising over 13,000 data points and undergoing a year-long training process with approximately 1,310 MRI images, the research culminates in the creation of a tool or software application system for the analysis of medical images. Despite the impressive precision score of 0.9992, highlighting its exceptional accuracy in correctly identifying positive instances, the recall value of 0.5767 suggests the potential exclusion of a significant number of actual positive instances in its predictions.

show abstract

Section: B Image Segmentationmentioning

confidence: 99%

Section: Deep Learning-based Image Segmentationmentioning

confidence: 99%

Fuzzy Deep Learning Approach for the Early Detection of Degenerative Disease

Irianto,

Karnila

et al. 2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…In anomaly datasets, anomalies (a.k.a., outliers, novelties) are significantly different from most data. The anomaly detection and segmentation [1,2] tasks include the process of detecting anomalies that deviate from the majority of instances and getting the specific location of them.…”

Section: Introductionmentioning

confidence: 99%

“…Previous works on anomaly or OOD detection [1,2] mainly focus on classifying low resolution images and getting the approximate location of anomalies, while the primary goal of anomaly segmentation is to assign each pixel a category label in known classes or OOD label then get more detailed location of anomalies. When the size of the training data set is small, the model trained on this dataset is difficult to distinguish anomalies in the testing process.…”

Section: Introductionmentioning

confidence: 99%

Prototype Guided Network for Anomaly Segmentation

Hao¹,

Jiang²,

An³

2022

Preprint

View full text Add to dashboard Cite

Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD) objects and output the anomaly probability for pixels. In this paper, a Prototype Guided Anomaly segmentation Network (PGAN) is proposed to extract semantic prototypes for in-distribution training data from limited annotated images. In the model, prototypes are used to model the hierarchical category semantic information and distinguish OOD pixels. The proposed PGAN model includes a semantic segmentation network and a prototype extraction network. Similarity measures are adopted to optimize the prototypes. The learned semantic prototypes are used as category semantics to compare the similarity with features extracted from test images and then to generate semantic segmentation prediction. The proposed prototype extraction network can also be integrated into most semantic segmentation networks and recognize OOD pixels. On the StreetHazards dataset, the proposed PGAN model produced mIoU of 53.4% for anomaly segmentation. The experimental results demonstrate PGAN may achieve the SOTA performance in the anomaly segmentation tasks.

show abstract

“…In addition, intensity inhomogeneity is called as bias field due to the property of slowly varying pixels in the same tissue [ 6 ]. Image segmentation has been extensively and deeply studied in computer vision due to its widespread application [ 7 , 8 , 9 , 10 ]. In the aspect of biomedical image analysis, it is a fundamental and complex task, which aims at assigning each pixel or voxel to the region with the same anatomical or biological meaning [ 11 , 12 , 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

Magnetic Resonance Imaging Segmentation via Weighted Level Set Model Based on Local Kernel Metric and Spatial Constraint

Song

Zhang

2021

Entropy

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) segmentation is a fundamental and significant task since it can guide subsequent clinic diagnosis and treatment. However, images are often corrupted by defects such as low-contrast, noise, intensity inhomogeneity, and so on. Therefore, a weighted level set model (WLSM) is proposed in this study to segment inhomogeneous intensity MRI destroyed by noise and weak boundaries. First, in order to segment the intertwined regions of brain tissue accurately, a weighted neighborhood information measure scheme based on local multi information and kernel function is designed. Then, the membership function of fuzzy c-means clustering is used as the spatial constraint of level set model to overcome the sensitivity of level set to initialization, and the evolution of level set function can be adaptively changed according to different tissue information. Finally, the distance regularization term in level set function is replaced by a double potential function to ensure the stability of the energy function in the evolution process. Both real and synthetic MRI images can show the effectiveness and performance of WLSM. In addition, compared with several state-of-the-art models, segmentation accuracy and Jaccard similarity coefficient obtained by WLSM are increased by 0.0586, 0.0362 and 0.1087, 0.0703, respectively.

show abstract

Automated unsupervised learning‐based clustering approach for effective anomaly detection in brain magnetic resonance imaging (MRI)

Cited by 6 publications

References 29 publications

Fuzzy Deep Learning Approach for the Early Detection of Degenerative Disease

Fuzzy Deep Learning Approach for the Early Detection of Degenerative Disease

Prototype Guided Network for Anomaly Segmentation

Magnetic Resonance Imaging Segmentation via Weighted Level Set Model Based on Local Kernel Metric and Spatial Constraint

Contact Info

Product

Resources

About