Optimization Based Liver Contour Extraction of Abdominal CT Images

Muthuswamy, Jayanthi; Kanmani, B

doi:10.11591/ijece.v8i6.pp5061-5070

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For quantitative evaluation, the segmented heart region using the proposed algorithm for each dataset was benchmarked against the manual segmentation by the expert attached to the PPDN-UPM Center. Four volume overlap parameters were used, Jaccard coefficient (Jaccard), Dice coefficient (Dice), false positive ratio (RFP) and false negative ratio (RFN) following to the ([24]- [26]). Considering A is the…”

Section: Methodsmentioning

confidence: 99%

Level Set Based Whole Heart Segmentation in Non-Contrast Enhanced CT Images

Mokri¹

2019

IJATCSE

View full text Add to dashboard Cite

Segmentation of the whole heat in CT images prior to lung radiotherapy is crucial to avoid undesirable radiation. In addition, heart segmentation is equally important in cardiovascular disease medical image analysis. However, heart segmentation in non-contrast enhanced CT image is a challenging problem due to the similarity of the grey level intensities of the heart with its surroundings. This paper aims to propose an automated heart segmentation method in non-contrast enhanced CT images. The method first identifies important slices during lung segmentation process to define an elliptical volume of interest (VOI) that approximately confines the heart region. Then 2D distance regularized (DRLSE) method is used to segment the heart slice by slice. The segmentation results are further improved by a refined elliptical VOI constructed from 3 different shapes of ellipses. Then 3 stages of DRLSE are used to obtain the final heart boundary. The segmentation results are validated based on Jaccard and Dice coefficients, false positive ratio (RFP) and false negative ratio (RFN) using 10 patient datasets where the average of Jaccard value of 0.86 and Dice value of 0.93 are obtained. Both values are more than 0.85 that indicates good heart segmentation in thoracic non-contrast enhanced CT image.

show abstract

Section: Methodsmentioning

confidence: 99%

Level Set Based Whole Heart Segmentation in Non-Contrast Enhanced CT Images

Mokri¹

2019

IJATCSE

View full text Add to dashboard Cite

show abstract

“…Figure 2 enlists some research methodologies available in the literature. The literature reports the use of statistic shape model (SSM), machine learning (ML) classifiers [19]- [21], clustering, graph-cut, and other semi-automatic liver tumor segmentation models [22]- [24].…”

Section: Literature Surveymentioning

confidence: 99%

Deep Learning Framework for Liver Tumor Segmentation

Gupta,

Aggarwal,

Jha

et al. 2024

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

INTRODUCTION: Segregating hepatic tumors from the liver in computed tomography (CT) scans is vital in hepatic surgery planning. Extracting liver tumors in CT images is complex due to the low contrast between the malignant and healthy tissues and the hazy boundaries in CT images. Moreover, manually detecting hepatic tumors from CT images is complicated, time-consuming, and needs clinical expertise. OBJECTIVES: An automated liver and hepatic malignancies segmentation is essential to improve surgery planning, therapy, and follow-up evaluation. Therefore, this study demonstrates the creation of an intuitive approach for segmenting tumors from the liver in CT scans. METHODS: The proposed framework uses residual UNet (ResUNet) architecture and local region-based segmentation. The algorithm begins by segmenting the liver, followed by malignancies within the liver envelope. First, ResUNet trained on labeled CT images predicts the coarse liver pixels. Further, the region-level segmentation helps determine the tumor and improves the overall segmentation map. The model is tested on a public 3D-IRCADb dataset. RESULTS: Two metrics, namely dice coefficient and volumetric overlap error (VOE), were used to evaluate the performance of the proposed method. ResUNet model achieved dice of 0.97 and 0.96 in segmenting liver and tumor, respectively. The value of VOE is also reduced to 1.90 and 0.615 for liver and tumor segmentation. CONCLUSION: The proposed ResUNet model performs better than existing methods in the literature. Since the proposed model is built using U-Net, the model ensures quality and precise dimensions of the output.

show abstract

“…The limitation of swaping does not allow more regions to be found in the search space with more optimial clustering assignments. As an optimization algorithm grey wolf optimization (GWO) has been used for different applications domains due to its simplicity to adapt in any optimization algorithm [38]- [43]. It successfully showed promising results such as in wireless sensor [44], resource allocation in cloud environment [45], classification [45], feature selection [46], and other optimization problems [47], [48].…”

Section: Introductionmentioning

confidence: 99%

Grey wolf optimization algorithm for hierarchical document clustering

Jabbar

Ku-Mahamud²

2021

IJEECS

View full text Add to dashboard Cite

In data mining, the application of grey wolf optimization (GWO) algorithm has been used in several learning approaches because of its simplicity in adapting to different application domains. Most recent works that concern unsupervised learning have focused on text clustering, where the GWO algorithm shows promising results. Although GWO has great potential in performing text clustering, it has limitations in dealing with outlier documents and noise data. This research introduces medoid GWO (M-GWO) algorithm, which incorporates a medoid recalculation process to share the information of medoids among the three best wolves and the rest of the population. This improvement aims to find the best set of medoids during the algorithm run and increases the exploitation search to find more local regions in the search space. Experimental results obtained from using well-known algorithms, such as genetic, firefly, GWO, and k-means algorithms, in four benchmarks. The results of external evaluation metrics, such as rand, purity, F-measure, and entropy, indicates that the proposed M-GWO algorithm achieves better document clustering than all other algorithms (i.e., 75% better when using Rand metric, 50% better than all algorithm based on purity metric, 75% better than all algorithms using F-measure metric, and 100% based on entropy metric).

show abstract

Optimization Based Liver Contour Extraction of Abdominal CT Images

Cited by 6 publications

References 14 publications

Level Set Based Whole Heart Segmentation in Non-Contrast Enhanced CT Images

Level Set Based Whole Heart Segmentation in Non-Contrast Enhanced CT Images

Deep Learning Framework for Liver Tumor Segmentation

Grey wolf optimization algorithm for hierarchical document clustering

Contact Info

Product

Resources

About