Enhanced deep-joint segmentation with deep learning networks of glioma tumor for multi-grade classification using MR images

Divya, S.; Suresh, L. Padma; John, Alexander

doi:10.1007/s10044-022-01064-5

Cited by 5 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Glioma is an invasive growth, which has no obvious boundary with normal brain tissue, is difficult to completely resect, is not very sensitive to radiotherapy and chemotherapy, and is very easy to relapse. Benign and malignant tumors growing in important parts of the brain are difficult to resect or cannot be operated on at all [13,14]. Due to the influence of blood-brain barrier and other factors, the efficacy of chemical drugs and general anti-tumor Chinese medicine is not ideal, so glioma is still one of the worst prognosis tumors in the whole body.…”

Section: Discussionmentioning

confidence: 99%

The Expression Level of CD47 in Glioma and its Impact on Invasiveness

Zhou,

Guo,

et al. 2023

IJCEMR

View full text Add to dashboard Cite

Objective:To investigate the expression level of CD47 in glioma and assess its influence on the invasiveness of tumor cells. Methods: A total of 30 glioma brain tissue specimens and 10 normal brain tissue control specimens were selected. Real-time fluorescence quantitative PCR (RT-PCR), Western Blot analysis and invasion assay were used to analyze the effects of low and high expression levels of CD47 on the aggressiveness of glioma cells. Results: The expression of CD47 in glioma cells was found to be significantly high. Conversely, a notable decrease in CD47 expression resulted in a significant inhibition of tumor cell aggressiveness. On the other hand, an increased expression of CD47 was observed to significantly promote tumor cell aggressiveness (P<0.05). Conclusion: CD47 is highly expressed in glioma cells, and a decrease in CD47 expression of CD47 significantly inhibits the aggressiveness of tumor cells. CD47 serves as a significant prognostic factor and potential therapeutic target in glioma.

show abstract

Section: Discussionmentioning

confidence: 99%

The Expression Level of CD47 in Glioma and its Impact on Invasiveness

Zhou,

Guo,

et al. 2023

IJCEMR

View full text Add to dashboard Cite

show abstract

“…The sophisticated architecture of Inception v3, distinguished by parallel convolutional layers of different sizes, works well at extracting a wide range of features and patterns from brain tumor pictures. The scalability of this design makes it possible to analyze information effectively at different scales and accurately distinguish between different types of tumors [22]. By enabling accurate diagnosis and treatment plans, Inception v3 ability to categorize brain tumors is enhanced by extensive training.…”

Section: Inception V3mentioning

confidence: 99%

Multi-modal fusion deep transfer learning for accurate brain tumor classification using magnetic resonance imaging images

Gottipati,

Thumbur

2024

IJEECS

View full text Add to dashboard Cite

Early identification and treatment of brain tumors depend critically on accurate classification. Accurate brain tumor classification in medical imaging is essential for clinical decisions and individualized treatment plans. This paper introduces a novel method for classifying brain tumors called multimodal fusion deep transfer learning (MMFDTL) using original, contoured, and annotated magnetic resonance imaging (MRI) images to showcase its capabilities. The MMFDTL can capture complex tumor features frequently missed in analyzing individual modalities. The MMFDTL model employs three deep learning models for extracting features VGG16, Inception V3, and ResNet 50. The accuracy rate improves when combined with decision based multimodal fusion. It produces impressive outcomes of sensitivity 92.96%, specificity 98.54%, precision 93.60%, accuracy 98.80%, F1-score 93.26%, and kappa 91.86%. This research can improve medical imaging and brain tumor analysis through its multi modal fusion approach. It could give healthcare practitioners vital insights for personalized treatment plans and informed decision making.

show abstract

“…Therefore, to alleviate this situation, an automatic tumor segmentation method has been proposed. Some automatic segmentation models for medical images have achieved good results using deep learning (Divya et al 2022, Thayumanavan and Ramasamy 2022, Diao et al 2022, Zhang et al 2023. However, the lung nodules and the tissues such as blood vessels in lung tumor CT images are usually misclassified as tumors (Byun et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Mutually enhanced multi-view information learning for segmentation of lung tumor in CT images

Xuan,

Xu,

Cui

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

The accurate automatic segmentation of tumors from computed tomography (CT) volumes facilitates early diagnosis and treatment of patients. A significant challenge in tumor segmentation is the integration of the spatial correlations among multiple parts of the CT volume and the context relationship across multiple channels. We proposed a mutually enhanced multi-view information model (MEMI) to propagate and fuse the spatial correlations and the context relationship and then apply it to lung tumor segmentation from CT volumes. First, an attention mechanism from the region node perspective was presented to determine the impact of all the other nodes on a specific node, which aims to enhance the node attribute embedding. A gated convolution-based strategy was also designed to integrate the enhanced attributes and the original node features. Second, transformer across multiple channels was constructed to learn the context relationship between these channels and to fuse the information across the channels. Third, since the encoded node attributes from the gated convolution view and those from the channel transformer view were complementary, an interaction attention mechanism was proposed to propagate and fuse the mutual information from multiple views. Finally, the node embeddings with the spatial correlations, the channel context embeddings, and the original features of region nodes were adaptively integrated before sending through the segmentation decoder for final output. The segmentation performance was evaluated on both public lung tumor dataset and private dataset collected from a hospital. The experimental results demonstrated that MEMI was superior to other compared segmentation methods. Ablation studies showed the contributions of node correlation learning, channel context relationship learning, and mutual information interaction across multiple views to the improved segmentation performance. The experimental results of using MEMI on multiple segmentation backbones also demonstrated MEMI’s generalization ability.

show abstract

Enhanced deep-joint segmentation with deep learning networks of glioma tumor for multi-grade classification using MR images

Cited by 5 publications

References 25 publications

The Expression Level of CD47 in Glioma and its Impact on Invasiveness

The Expression Level of CD47 in Glioma and its Impact on Invasiveness

Multi-modal fusion deep transfer learning for accurate brain tumor classification using magnetic resonance imaging images

Mutually enhanced multi-view information learning for segmentation of lung tumor in CT images

Contact Info

Product

Resources

About