Brain Image Segmentation in Recent Years: A Narrative Review

Fawzi, Ali; Achuthan, Anusha; Belaton, Bahari

doi:10.3390/brainsci11081055

Cited by 37 publications

(33 citation statements)

References 66 publications

(140 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3D reconstruction has diverse applications in the medical field like complex intracranial structures (10) , craniofacial abnormalities (11) , microcalcifications in breast cancer (12) , artery visualization for cardiac applications (13) . Reconstruction of the tumor with its boundary completely depends on the accurate extraction of the irregularly shaped tumor from the corresponding MR images.…”

Section: Methodsmentioning

confidence: 99%

“…Accuracy can be estimated from the proportion of TP and TN in all evaluated cases. Mathematically, accuracy can be calculated by, Accuracy = (TN + TP)/ (TN+TP+FN+FP) (10) When accuracy of all 3 subjects is compared with the two different algorithms, FWISVM outperforms the existing SVM in all the 3 cases. The result shows that the FWISVM gives the highest overall accuracy.…”

Section: Segmentation Efficiencymentioning

confidence: 99%

See 1 more Smart Citation

Mass Sphering Approach for Three-Dimensional Reconstruction of Brain Tumor using MRI

Radhakrishnan¹,

Vanaja²,

Devi³

et al. 2022

IJST

View full text Add to dashboard Cite

Objective: The objective of the research work is to reconstruct the brain tumor three-dimensionally with high degree of accuracy. Methods: This study describes 3D reconstruction of brain tumor using Mass Sphering Approach (MSA) algorithm. 39 weighted features are extracted from the non-tumor and tumor pixels. These weighted features are used to train the Support Vector Machine (SVM) algorithm. Number of training samples taken to train SVM algorithm are 268 and the testing sample are 64. The complete MR image set of a subject (64 axial slices) are detected for tumor pixels and these slices are concatenated to get volumetric tumor information. Findings: 5-step MSA algorithm is proposed which includes filtering, segmentation, classification, optimization and reconstruction. MR images are subjected to Rician noise which can be removed by a simple correction scheme, initiated to change the bias due to the Rician distribution of the noisy magnitude data. The filtered MR image slices are segmented and classified to detect the tumor areas and the tumor pixels are subjected for 3D reconstruction. The improvement in performance of MSA is depicted by comparing the algorithm with traditional SVM. Novelty: The accuracy achieved in detecting glioma and glioblastoma using MSA are 95.24% and 99% respectively which is highly remarkable.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Segmentation Efficiencymentioning

confidence: 99%

Mass Sphering Approach for Three-Dimensional Reconstruction of Brain Tumor using MRI

Radhakrishnan¹,

Vanaja²,

Devi³

et al. 2022

IJST

View full text Add to dashboard Cite

show abstract

“…Various automated techniques using atlas-based or deep-learning (DL) techniques have been developed to overcome these problems. Although automated image segmentation models for the brain show limitations [15,16], FreeSurfer (FS) [17] can extract brain structures with relatively high accuracy. Therefore, FS has been widely adopted as a non-DL automated segmentation method [17,18,19,20,21].…”

Section: Introductionmentioning

confidence: 99%

“…An automated model for fast segmentation and diagnosis without involving intricate methods should be developed for clinical use. Although DL segmentation has been used in various fields, including medicine [16], the segmentation of brain structures in MRI for the diagnosis of neurodegenerative diseases has made little progress. In addition, no study has introduced artificial-intelligence-based analysis or demonstrated the usefulness of DL (i.e., complexity or disease discrimination performance) compared with existing non-DL automated segmentation of brain structures (e.g., FS).…”

Section: Introductionmentioning

confidence: 99%

Comparative Validation of AI and non-AI Methods in MRI Volumetry to Diagnose Parkinsonian Syndromes

Song¹,

Hahm²,

Lee³

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Automated segmentation and volumetry of brain magnetic resonance imaging (MRI) scans are essential for the diagnosis of Parkinson's disease (PD) and Parkinson's plus syndromes (P-plus).Objective: To enhance the diagnostic performance, we adopt deep learning (DL) models in brain segmentation and compared their performance with the gold-standard non-DL method.Methods: We collected brain MRI scans of healthy controls (n = 105) and patients with PD (n = 105), multiple systemic atrophy (n = 132), and progressive supranuclear palsy (n = 69) at Samsung Medical Center from January 2017 to December 2020. Using the gold-standard non-DL model, FreeSurfer (FS), we segmented six brain structures: midbrain, pons, caudate, putamen, pallidum, and third ventricle, and considered them as annotating data for DL models, the representative V-Net and UNETR. The Dice scores and area under the curve (AUC) for differentiating normal, PD, and P-plus cases were calculated.Results: The segmentation times of V-Net and UNETR for the six brain structures per patient were 3.48 ± 0.17 and 48.14 ± 0.97 s, respectively, being at least 300 times faster than FS (15,735 ± 1.07 s). Dice scores of both DL models were sufficiently high (>0.85), and their AUCs for disease classification were superior to that of FS. For classification of normal vs. P-plus and PD vs. multiple systemic atrophy (cerebellar type), the DL models and FS showed AUCs above 0.8.Conclusions: DL significantly reduces the analysis time without compromising the performance of brain segmentation and differential diagnosis. Our findings may contribute to the adoption of DL brain MRI segmentation in clinical settings and advance brain research.

show abstract

“…Images produced in such an environment display a restricted range of gray-level distribution and lower intensity frequencies, leading to intensity inhomogeneity, low contrast, and low-quality images [1]. Non-uniform gray-level distribution and low contrast may degrade the performance of subsequent image processing, such as image segmentation [2]. Enhancing image intensity boosts information richness in images, particularly in terms of edges, information, contrast, and regions boundaries, which facilitate human visual perception and computerized image analysis [3].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Clip Limit Tile Size Histogram Equalization for Non-Homogenized Intensity Images

Fawzi¹,

Achuthan

Belaton

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Intensity inhomogeneity, hidden details, poor image contrast due to low capturing device quality, limited user experience, and inappropriate environment setting during data acquisition are major issues reported during the image enhancement process. Histogram Equalization (HE) approaches have been commonly deployed to overcome the above-listed problems, apart from improving image contrast. Nevertheless, the resulting images retrieved after undergoing these approaches are often affected by undesired artifacts, unnatural looks, and unpleasant washed-out effects. As such, this study introduces a new approach called Adaptive Clip Limit Tile Size Histogram Equalization (ACLTSHE). The ACLTSHE initially assigns the optimum clip limit (CL) and tile size minimum or maximum values. Then, a new fitness function called DataSignal is deployed to produce a set of non-dominated solutions by adaptively computing the optimum CL value. The performance of the proposed ACLTSHE approach was assessed and compared with conventional Clip Limit HE (CLHE) and several state-of-the-art approaches, such as Dynamic Clipped HE (DCLHE), Iterated Adaptive Entropy Clip Limit HE (IAECHE), Mean and Variance Sub-image HE (MVSIHE), and Adaptive Entropy Index HE (AEIHE). The outcomes were assessed both qualitatively and quantitatively by using six evaluation metrics, Discrete Entropy (DE), Absolute Mean Brightness Error (AMBE), Peak Signalto-Noise Ratio (PSNR), Contrast Improvement Index (CII), Root Mean Square Error (RMSE), Structure Similarity Index (SSI) and Standard Deviation (SD). The quantitative evaluation of three dataset images (Pasadena-houses 2000, faces 1999, and BraTS 2019) verified that the proposed approach outperformed the compared approaches in terms of improved DE, enhanced contrast, and highlighted local details without losing the original image structures. INDEX TERMS Histogram equalization-based technique, histogram entropy, histogram clip limit, tile size.

show abstract

Brain Image Segmentation in Recent Years: A Narrative Review

Cited by 37 publications

References 66 publications

Mass Sphering Approach for Three-Dimensional Reconstruction of Brain Tumor using MRI

Mass Sphering Approach for Three-Dimensional Reconstruction of Brain Tumor using MRI

Comparative Validation of AI and non-AI Methods in MRI Volumetry to Diagnose Parkinsonian Syndromes

Adaptive Clip Limit Tile Size Histogram Equalization for Non-Homogenized Intensity Images

Contact Info

Product

Resources

About