Threshold-Based New Segmentation Model to Separate the Liver from CT Scan Images

Siri, Sangeeta K.; Kumar, S. Pramod; Latte, Mrityunjaya V.

doi:10.1080/03772063.2020.1795938

Cited by 16 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such methods require human-computer interaction and set prior values based on experience to adapt to different methods and results. Siri et al [13] determined multiple thresholds for liver segmentation from histogram slope profiles. Arica et al [14] selected a seed point in each selected region for region growth, and then merged the liver regions in combination with region binding to obtain the complete liver region.…”

Section: Model-driven-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

MDR‐Net: Multiscale dense residual networks for liver image segmentation

Xie

Zhu

2023

IET Image Processing

View full text Add to dashboard Cite

Liver image segmentation is an attractive topic in the diagnosis and surgical planning of liver diseases. Although deep learning methods have significantly advanced liver segmentation, existing frameworks fail to clearly determine liver boundaries, especially in medical images where various organs have similar grey levels. In this paper, the authors design a multi-scale dense residual network (MDR-Net) for liver segmentation, which consists of two blocks: a liver segmentation network and an edge-aware network. In the segmentation network, the authors introduce a multi-scale residual pooling module combining channel attention (CA) mechanism and depth-wise separable convolution to accommodate liver scale variation. Furthermore, the authors employ an edge-aware loss network to refine edge information and enhance feature representation, which is beneficial to guide the network to iterate towards the ground truth. The authors' method achieves the best visualization results in qualitative evaluation. In addition, the authors' method achieves 96.189% on 3D-IRCADb and 96.889% on the CHAOS dataset in quantitative evaluation with respect to the dice index.

show abstract

Section: Model-driven-based Methodsmentioning

confidence: 99%

“…Siri et al. [13] determined multiple thresholds for liver segmentation from histogram slope profiles. Arica et al.…”

Section: Related Workmentioning

confidence: 99%

MDR‐Net: Multiscale dense residual networks for liver image segmentation

Xie

Zhu

2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…For example, Siri et al (2020) proposed a novel multi-threshold liver segmentation model based on the ‘Slope Difference Distribution’ of image histogram, and the segmentation of the CT images of the liver is satisfactory. The Jaccard Coefficient results with the popular method demonstrated that this model could be more accurate for lung CT images.…”

Section: Related Workmentioning

confidence: 99%

Multi-threshold image segmentation for melanoma based on Kapur’s entropy using enhanced ant colony optimization

Xiao

Ye²,

Zhao³

et al. 2022

Front. Neuroinform.

View full text Add to dashboard Cite

Melanoma is a malignant tumor formed by the cancerous transformation of melanocytes, and its medical images contain much information. However, the percentage of the critical information in the image is small, and the noise is non-uniformly distributed. We propose a new multi-threshold image segmentation model based on the two-dimensional histogram approach to the above problem. We present an enhanced ant colony optimization for continuous domains (EACOR) in the proposed model based on the soft besiege and chase strategies. Further, EACOR is combined with two-dimensional Kapur’s entropy to search for the optimal thresholds. An experiment on the IEEE CEC2014 benchmark function was conducted to measure the reliable global search capability of the EACOR algorithm in the proposed model. Moreover, we have also conducted several sets of experiments to test the validity of the image segmentation model proposed in this paper. The experimental results show that the segmented images from the proposed model outperform the comparison method in several evaluation metrics. Ultimately, the model proposed in this paper can provide high-quality samples for subsequent analysis of melanoma pathology images.

show abstract

“…The structure of the liver is impacted by a variety of disorders, including cirrhosis, cancer, hepatitis, and fatty liver. These may cause major health problems, and if the appropriate steps are not done on time, they may even result in death [1]. The World Health Organization (WHO) ranks liver cancer as the second most common cause of cancer.…”

Section: Introductionmentioning

confidence: 99%

Deep Ensemble Stacked Technique for the Classification of Liver Disease Using Artificial Neural Networks at the Base Level and Random Forest at the Meta Level

Bhusnurmath,

Betageri

2023

Preprint

View full text Add to dashboard Cite

Liver is the most noticeable and metabolically active organs in the human body. Damage to this organ might result in liver failure and a loss of life. The early detection of liver infection is critical for effective therapy. The main goal of the research is to identify liver illness using machine learning and deep learning classification algorithms. The proposed "Deep ensemble stacked model" is implemented on the “Indian liver Patient Dataset”. An attempt is made to analyze the data through various pre-processing and visualization techniques to understand which factors affect the liver. An artificial neural network is used as the model's primary training and testing tool. The new training set is created for the meta-level consisting of base-level predictions. The random forest classifier is used at the meta level which serves as a meta classifier for the final prediction. The deep ensemble stacked model performed better than the most recent research with 98.29% of classification accuracy, 97.43% of precision, 100% of recall rate, and 98.69% of f1-score. To evaluate the effectiveness of the suggested approach, the outcomes are also contrasted with well-known machine and deep learning models.

show abstract

Threshold-Based New Segmentation Model to Separate the Liver from CT Scan Images

Cited by 16 publications

References 28 publications

MDR‐Net: Multiscale dense residual networks for liver image segmentation

MDR‐Net: Multiscale dense residual networks for liver image segmentation

Multi-threshold image segmentation for melanoma based on Kapur’s entropy using enhanced ant colony optimization

Deep Ensemble Stacked Technique for the Classification of Liver Disease Using Artificial Neural Networks at the Base Level and Random Forest at the Meta Level

Contact Info

Product

Resources

About