Head and Neck Cancer Tumor Segmentation Using Support Vector Machine in Dynamic Contrast-Enhanced MRI

Deng, Wei; Luo, Liangping; Lin, Xiaoyi; Fang, Tianqi; Liu, Dexiang; Guo, Dan; Chen, Hanwei

doi:10.1155/2017/8612519

Cited by 22 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In similar studies, authors obtained a HR of 86% and MR of 0.79, which was considered satisfactory. (24)(25)(26) In this study, the HR was 89.23% and the MR was 0.70, i.e., quantitatively similar to those of previous authors, which indicates good accuracy of the proposed segmentation method. The best HR results were obtained for T2 and FSPGR-T1c sequences.…”

Section: Comparative Performance Analysis Of Automatic Segmentationsupporting

confidence: 89%

“…Quantitative results of the automatic segmentation were calculated by comparison between the gold standard and the proposed segmentation method. The metrics commonly used in the literature (24)(25)(26) to assess performance are the hit rate (HR), calculated by the number of true positive (TP) of the method compared with the gold standard; and the matching rate (MR), based on the number of false positive results (FP). In the cited studies, the HR and MR are respectively defined as:…”

Section: Evaluation Of Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic segmentation of brain tumors in magnetic resonance imaging

Mascarenhas¹,

Júnior²,

Ramos³

2020

Einstein (São Paulo)

View full text Add to dashboard Cite

Objective: To develop a computational algorithm applied to magnetic resonance imaging for automatic segmentation of brain tumors. Methods: A total of 130 magnetic resonance images were used in the T1c, T2 and FSPRG T1C sequences and in the axial, sagittal and coronal planes of patients with brain cancer. The algorithms employed contrast correction, histogram normalization and binarization techniques to disconnect adjacent structures from the brain and enhance the region of interest. Automatic segmentation was performed through detection by coordinates and arithmetic mean of the area. Morphological operators were used to eliminate undesirable elements and reconstruct the shape and texture of the tumor. The results were compared with manual segmentations by two radiologists to determine the efficacy of the algorithms implemented. Results: The correlated correspondence between the segmentation obtained and the gold standard was 89.23%. Conclusion: It is possible to locate and define the tumor region automatically with no the need for user interaction, based on two innovative methods to detect brain extreme sites and exclude non-tumor tissues on magnetic resonance images. ❚ RESUMOObjetivo: Desenvolver um algoritmo computacional aplicado a imagens de ressonância magnética, para segmentação automática de tumores cerebrais. Métodos: Foram utilizadas 130 imagens de ressonância magnética nas sequências T1c, T2 e FSPRG T1c e nos planos axial, sagital e coronal de pacientes acometidos com câncer cerebral. Os algoritmos empregaram técnicas de correção de contraste, normalização de histograma e binarização, para desconectar estruturas adjacentes do cérebro e realçar a região de interesse. A segmentação automática foi realizada por meio da detecção por coordenadas e por média aritmética da área. Operadores morfológicos foram utilizados para eliminar elementos indesejáveis e reconstruir a forma e a textura do tumor. Os resultados foram comparados com as segmentações manuais de dois médicos radiologistas, para determinar a eficácia dos algoritmos implementados. Resultados: Os acertos foram de 89,23% na correspondência entre a segmentação obtida e o padrão-ouro. Conclusão: É possível localizar e delimitar a região tumoral de forma automática, sem necessidade de interação com o usuário baseado em dois métodos inovadores de detecção dos extremos do cérebro e de exclusão dos tecidos não tumorais em imagens de ressonância magnética.Descritores: Diagnóstico por imagem; Neoplasias encefálicas; Processamento de imagem assistida por computador; Imagem por ressonância magnética; Simulação por computador How to cite this article: Mascarenhas LR, Ribeiro Júnior AS, Ramos RP. Automatic segmentation of brain tumors in magnetic resonance imaging. einstein (São Paulo). 2020;18:eAO4948. http://dx.

show abstract

Section: Comparative Performance Analysis Of Automatic Segmentationsupporting

confidence: 89%

Section: Evaluation Of Resultsmentioning

confidence: 99%

Automatic segmentation of brain tumors in magnetic resonance imaging

Mascarenhas¹,

Júnior²,

Ramos³

2020

Einstein (São Paulo)

View full text Add to dashboard Cite

show abstract

“…However, it is hard to formulate an objective, robust and straightforward cost function for graph-based methods due to potentially contradicting / conflicting requirements among image. Recently, machine learning based segmentation approaches, such as Support Vector Machine (Deng et al, 2017), Decision tree (Berthon et al, 2017) and k-nearest neighbour (KNN) (Yu et al, 2009;Comelli et al, 2018), are adopted in many head and neck segmentation studies. These classifiers make decisions for each voxel by gradients or texture features extracted from the neighbourhood without any shape constraint.…”

Section: Introductionmentioning

confidence: 99%

Gross tumor volume segmentation for head and neck cancer radiotherapy using deep dense multi-modality network

Guo¹,

Guo

Gong

et al. 2019

Phys. Med. Biol.

View full text Add to dashboard Cite

In radiation therapy, the accurate delineation of gross tumor volume (GTV) is crucial for treatment planning. However, it is challenging for head and neck cancer (HNC) due to the morphology complexity of various organs in the head, low targets to background contrast and potential artifacts on conventional planning CT images. Thus, manual delineation of GTV on anatomical images is extremely time consuming and suffers from inter-observer variability that leads to planning uncertainty. With the wide use of PET/CT imaging in oncology, complementary functional and anatomical information can be utilized for tumor contouring and bring a significant advantage for radiation therapy planning. In this study, by taking advantage of multi-modality PET and CT images, we propose an automatic GTV segmentation framework based on deep learning for HNC. The backbone of this segmentation framework is based on 3D convolution with dense connections which enables a better information propagation and taking full advantage of the features extracted from multi-modality input images. We evaluate our proposed framework on a dataset including 250 HNC patients. Each patient receives both planning CT and PET/CT imaging before radiation therapy. Manually delineated GTV contours by radiation oncologists are used as ground truth in this study. To further investigate the advantage of our proposed Dense-Net framework, we also compared with the framework using 3D U-Net which is the state-of-the-art in segmentation tasks. Meanwhile, for each frame, the performance comparison between single modality input (PET or CT image) and multi-modality input (both PET/CT) is conducted. Dice coefficient, mean surface distance (MSD), 95th-percentile Hausdorff distance (HD 95 ) and displacement of mass centroid are calculated for quantitative evaluation. Based on the results of five-fold cross-validation, our proposed multi-modality Dense-Net (Dice 0.73) shows better performance than the compared network (Dice 0.71). Furthermore, the proposed Dense-Net structure has less trainable parameters than the 3D U-Net, which reduces the prediction variability. In conclusion, our proposed multimodality Dense-Net can enable satisfied GTV segmentation for HNC using multi-modality images and yield superior performance than conventional methods. Our proposed method provides an automatic, fast and consistent solution for GTV segmentation and shows potentials to be generally applied for radiation therapy planning of a variety of cancers.

show abstract

“…They trained on a publicly available data set of 250 patients and were able to achieve a Dice coefficient of 0.73. In another study, Deng et al 57 developed a tumor segmentation algorithm with a training data set of 120 contrast-enhanced head and neck MRI scans. The model was developed using support vector machines (a method of classical ML) and was able to achieve an area overlap measure of 0.76.…”

Section: Head and Neckmentioning

confidence: 99%

Artificial Intelligence and Deep Learning in Neuroradiology: Exploring the New Frontier

2020

View full text Add to dashboard Cite

There have been many recently published studies exploring machine learning (ML) and deep learning applications within neuroradiology. The improvement in performance of these techniques has resulted in an ever-increasing number of commercially available tools for the neuroradiologist. In this narrative review, recent publications exploring ML in neuroradiology are assessed with a focus on several key clinical domains. In particular, major advances are reviewed in the context of: (1) intracranial hemorrhage detection, (2) stroke imaging, (3) intracranial aneurysm screening, (4) multiple sclerosis imaging, (5) neuro-oncology, (6) head and tumor imaging, and (7) spine imaging.

show abstract

Head and Neck Cancer Tumor Segmentation Using Support Vector Machine in Dynamic Contrast-Enhanced MRI

Cited by 22 publications

References 9 publications

Automatic segmentation of brain tumors in magnetic resonance imaging

Automatic segmentation of brain tumors in magnetic resonance imaging

Gross tumor volume segmentation for head and neck cancer radiotherapy using deep dense multi-modality network

Artificial Intelligence and Deep Learning in Neuroradiology: Exploring the New Frontier

Contact Info

Product

Resources

About