Content‐based retrieval of brain tumor in contrast‐enhanced MRI images using tumor margin information and learned distance metric

Yang, Wei; Feng, Qianjin; Yu, Mei; Lu, Zhentai; Xu, Yikai; Chen, Wufan

doi:10.1118/1.4754305

Cited by 44 publications

(35 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the evaluation measures for CBIR systems are very different from those for classification. In our previous study [6], a distance metric learning method called maximum mean average precision projection (MPP) was proposed to optimize retrieval measures directly. We also verified that the MPP method yields good performance compared with other approaches [6].…”

Section: Methodsmentioning

confidence: 99%

“…In our previous study [6], a distance metric learning method called maximum mean average precision projection (MPP) was proposed to optimize retrieval measures directly. We also verified that the MPP method yields good performance compared with other approaches [6]. In this study, we propose a novel metric learning method based on the minimization of rank error to achieve the projection L .…”

Section: Methodsmentioning

confidence: 99%

“…Conversely, lesions of different pathological categories may show visual similarity [Figures 1(C) and 1(D)]. Given that low-level visual features, such as color (intensity), texture [12]–[17], and shape [18], [19], are not adequately discriminative to describe high-level semantic concepts [20], additional distinctive features are highly desirable [6], [7]. Second, learned distance metrics, which are capable of reducing the semantic gap between visual features and semantic concepts [21], have been investigated intensively and widely used for CBIR [6], [22], [23].…”

Section: Introductionmentioning

confidence: 99%

“…We previously used a marginal information descriptor and region-specific BoVW to obtain structural information on tumors and their surrounding regions [6], [7]. Tumor regions were partitioned into several sub-regions, and the image contents in each sub-region were represented using the BoVW-based approach.…”

Section: Introductionmentioning

confidence: 99%

“…However, compared with the symmetrical partitioning in the spatial pyramid method, the partition can be learned to make the feature more discriminative [28] when the contents of the images from a specific category are distributed with intrinsic regularity. Brain tumor T1-weghted CE-MR Images show that the layouts of the tumor, edema, and surrounding normal tissue have strong correlations [6]. For instance, meningiomas and pituitary tumors are homogeneous lesions [Figures 2(A) and 2(B)]; these two tumor types are usually not associated with edema.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Content-Based Image Retrieval Using Spatial Layout Information in Brain Tumor T1-Weighted Contrast-Enhanced MR Images

Huang

Yang

et al. 2014

PLoS ONE

Self Cite

View full text Add to dashboard Cite

This study aims to develop content-based image retrieval (CBIR) system for the retrieval of T1-weighted contrast-enhanced MR (CE-MR) images of brain tumors. When a tumor region is fed to the CBIR system as a query, the system attempts to retrieve tumors of the same pathological category. The bag-of-visual-words (BoVW) model with partition learning is incorporated into the system to extract informative features for representing the image contents. Furthermore, a distance metric learning algorithm called the Rank Error-based Metric Learning (REML) is proposed to reduce the semantic gap between low-level visual features and high-level semantic concepts. The effectiveness of the proposed method is evaluated on a brain T1-weighted CE-MR dataset with three types of brain tumors (i.e., meningioma, glioma, and pituitary tumor). Using the BoVW model with partition learning, the mean average precision (mAP) of retrieval increases beyond 4.6% with the learned distance metrics compared with the spatial pyramid BoVW method. The distance metric learned by REML significantly outperforms three other existing distance metric learning methods in terms of mAP. The mAP of the CBIR system is as high as 91.8% using the proposed method, and the precision can reach 93.1% when the top 10 images are returned by the system. These preliminary results demonstrate that the proposed method is effective and feasible for the retrieval of brain tumors in T1-weighted CE-MR Images.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Content-Based Image Retrieval Using Spatial Layout Information in Brain Tumor T1-Weighted Contrast-Enhanced MR Images

Huang

Yang

et al. 2014

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

Machine Learning in Meningioma MRI: Past to Present. A Narrative Review

Neromyliotis

Κalamatianos

Paschalis

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Meningioma is one of the most frequent primary central nervous system tumors. While magnetic resonance imaging (MRI), is the standard radiologic technique for provisional diagnosis and surveillance of meningioma, it nevertheless lacks the prima facie capacity in determining meningioma biological aggressiveness, growth, and recurrence potential. An increasing body of evidence highlights the potential of machine learning and radiomics in improving the consistency and productivity and in providing novel diagnostic, treatment, and prognostic modalities in neuroncology imaging. The aim of the present article is to review the evolution and progress of approaches utilizing machine learning in meningioma MRI‐based sementation, diagnosis, grading, and prognosis. We provide a historical perspective on original research on meningioma spanning over two decades and highlight recent studies indicating the feasibility of pertinent approaches, including deep learning in addressing several clinically challenging aspects. We indicate the limitations of previous research designs and resources and propose future directions by highlighting areas of research that remain largely unexplored. Level of Evidence 5 Technical Efficacy Stage 2

show abstract

Invariant Moments, Textural and Deep Features for Diagnostic MR and CT Image Retrieval

Putzu

Loddo

Ruberto

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Content‐based retrieval of brain tumor in contrast‐enhanced MRI images using tumor margin information and learned distance metric

Abstract: Incorporating tumor margin information represented by MID with the distance metric learned by the MPP algorithm can substantially improve the retrieval performance for brain tumors in CE-MRI.

Cited by 44 publications

References 42 publications

Content-Based Image Retrieval Using Spatial Layout Information in Brain Tumor T1-Weighted Contrast-Enhanced MR Images

Content-Based Image Retrieval Using Spatial Layout Information in Brain Tumor T1-Weighted Contrast-Enhanced MR Images

Machine Learning in Meningioma MRI: Past to Present. A Narrative Review

Invariant Moments, Textural and Deep Features for Diagnostic MR and CT Image Retrieval

Contact Info

Product

Resources

About