Random forest classification and local region-based, level-set segmentation for quantitative ultrasound of human lymph nodes

Bui, Thanh Minh; Coron, Alain; Bridal, S. Lori; Mamou, Jonathan; Feleppa, Ernest J.; Saegusa‐Beecroft, Emi; Machi, Junji

doi:10.1109/ultsym.2015.0106

Cited by 4 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DSC evaluates the similarity between two segmentation results X and Y . Table I shows the segmentation results for the 42 Colorrectal LNs used in [14], which is a subset of the images in the complete dataset. We compare the performance of the RFC+STS-LS, NGC with depth-dependent profiles, and the current, described GC-LAE-based method with and without depth-dependent profiles.…”

Section: B Results In Our Databasementioning

confidence: 99%

“…In this study, we compared the result of the current, described method with two other methods: our own prior work, called NGC with depth-dependent profile [11] and the method developed by Bui et al, called statistical transverse slice levelset (STS-LS) with random forest classification (RFC) [14].…”

Section: Resultsmentioning

confidence: 99%

“…Compared to GC-based methods, level-set-based methods can avoid grid bias and can permit faster calculations, but they require proper initialization or initial seeds to avoid converging to a local minimum. In a more-recent work, Bui et al [14] used random-forest classification to pre-segment images and initiate a level-set approach. Intensity-distribution estimation is another challenge in LN segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…Section III introduces the whole framework combining GC-LAE and NGC. Section IV illustrates the segmentation results and compares the performance of NGC with depth-dependent profiles [11], RFC+STS-LS [14], and the proposed method. Section V discusses the clinical significance and the future work and concludes this paper.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Segmentation of 3-D High-Frequency Ultrasound Images of Human Lymph Nodes Using Graph Cut With Energy Functional Adapted to Local Intensity Distribution

Kuo

Mamou

Wang

et al. 2017

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

Self Cite

View full text Add to dashboard Cite

Previous studies by our group have shown that 3-D high-frequency quantitative ultrasound (QUS) methods have the potential to differentiate metastatic lymph nodes (LNs) from cancer-free LNs dissected from human cancer patients. To successfully perform these methods inside the LN parenchyma (LNP), an automatic segmentation method is highly desired to exclude the surrounding thin layer of fat from QUS processing and accurately correct for ultrasound attenuation. In high-frequency ultrasound images of LNs, the intensity distribution of LNP and fat varies spatially because of acoustic attenuation and focusing effects. Thus, the intensity contrast between two object regions (e.g., LNP and fat) is also spatially varying. In our previous work, nested graph cut (GC) demonstrated its ability to simultaneously segment LNP, fat, and the outer phosphate-buffered saline bath even when some boundaries are lost because of acoustic attenuation and focusing effects. This paper describes a novel approach called GC with locally adaptive energy to further deal with spatially varying distributions of LNP and fat caused by inhomogeneous acoustic attenuation. The proposed method achieved Dice similarity coefficients of 0.937±0.035 when compared with expert manual segmentation on a representative data set consisting of 115 3-D LN images obtained from colorectal cancer patients.

show abstract

Section: B Results In Our Databasementioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Segmentation of 3-D High-Frequency Ultrasound Images of Human Lymph Nodes Using Graph Cut With Energy Functional Adapted to Local Intensity Distribution

Kuo

Mamou

Wang

et al. 2017

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The local source was responsible for directing intensities to the non-uniform area while the global source performs a contrary function for uniform intensities. Bui et al [11] have used Random decision forests to obtain a pre-divided classification of images to start processing the level-set method. This will refine the segmentation results for lymph node ultrasound images to tackle the problem of intensity inhomogeneity of images and poor-quality contrasts.…”

Section: Related Workmentioning

confidence: 99%

Contextual Level-Set Method for Breast Tumor Segmentation

Hussain

Ullah

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Breast ultrasound image segmentation is the foundation of the diagnosis and treatment of breast cancer. The level set method is widely used for medical image segmentation. However, it remained a challenge for traditional level set methods because they cannot fully understand the tumor regions with complex characteristics by only low-level features. Considering that contextual features can provide complementary discriminative information to low-level features, this paper proposed a contextual level set method for breast tumor segmentation. Firstly, an encoder-decoder architecture network such as UNet is developed to learn high-level contextual features with semantic information. After that, the contextual level set method has been proposed to incorporate the novel contextual energy term. The proposed term has the ability to embed the high-level contextual knowledge into the level set framework. The learned contextual features with semantic information can provide more discriminative information, which has been directly associated with category labels, instead of the original intensity. Therefore, it is robust to serious intensity inhomogeneity, which is helpful to improve segmentation performance. The experiments had taken place with the help of three databases, which indicates that the proposed method outperformed traditional methods. INDEX TERMS Breast ultrasound images, contextual feature, Level-set method, tumor segmentation.

show abstract

Artificial Intelligence in Quantitative Ultrasound Imaging: A Survey

Zhou

Yang

Lan

2021

J of Ultrasound Medicine

View full text Add to dashboard Cite

Quantitative ultrasound (QUS) imaging is a safe, reliable, inexpensive, and real-time technique to extract physically descriptive parameters for assessing pathologies. Compared with other major imaging modalities such as computed tomography and magnetic resonance imaging, QUS suffers from several major drawbacks: poor image quality and inter-and intra-observer variability. Therefore, there is a great need to develop automated methods to improve the image quality of QUS. In recent years, there has been increasing interest in artificial intelligence (AI) applications in medical imaging, and a large number of research studies in AI in QUS have been conducted. The purpose of this review is to describe and categorize recent research into AI applications in QUS. We first introduce the AI workflow and then discuss the various AI applications in QUS.Finally, challenges and future potential AI applications in QUS are discussed.

show abstract

Random forest classification and local region-based, level-set segmentation for quantitative ultrasound of human lymph nodes

Cited by 4 publications

References 13 publications

Segmentation of 3-D High-Frequency Ultrasound Images of Human Lymph Nodes Using Graph Cut With Energy Functional Adapted to Local Intensity Distribution

Segmentation of 3-D High-Frequency Ultrasound Images of Human Lymph Nodes Using Graph Cut With Energy Functional Adapted to Local Intensity Distribution

Contextual Level-Set Method for Breast Tumor Segmentation

Artificial Intelligence in Quantitative Ultrasound Imaging: A Survey

Contact Info

Product

Resources

About