CFANet: Context fusing attentional network for preoperative CT image segmentation in robotic surgery DOI

Yao Lin,

Jiazheng Wang, Qinghao Liu

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 171, P. 108115 - 108115

Published: Feb. 6, 2024

Language: Английский

Radiomics and Its Feature Selection: A Review DOI Open Access
Wenchao Zhang, Yu Guo, Qiyu Jin

et al.

Symmetry, Journal Year: 2023, Volume and Issue: 15(10), P. 1834 - 1834

Published: Sept. 27, 2023

Medical imaging plays an indispensable role in evaluating, predicting, and monitoring a range of medical conditions. Radiomics, specialized branch imaging, utilizes quantitative features extracted from images to describe underlying pathologies, genetic information, prognostic indicators. The integration radiomics with artificial intelligence presents innovative avenues for cancer diagnosis, prognosis evaluation, therapeutic choices. In the context oncology, offers significant potential. Feature selection emerges as pivotal step, enhancing clinical utility precision radiomics. It achieves this by purging superfluous unrelated features, thereby augmenting model performance generalizability. goal review is assess fundamental process progress feature methods, explore their applications challenges research, provide theoretical methodological support future investigations. Through extensive literature survey, articles pertinent were garnered, synthesized, appraised. paper provides detailed descriptions how applied challenged different types various stages. also comparative insights into strategies, including filtering, packing, embedding methodologies. Conclusively, broaches limitations prospective trajectories

Language: Английский

Citations

43
Artificial Intelligence in Gastrointestinal Cancer Research: Image Learning Advances and Applications DOI Creative Commons
Shengyuan Zhou, Yi Xie,

Xujiao Feng

et al.

Cancer Letters, Journal Year: 2025, Volume and Issue: 614, P. 217555 - 217555

Published: Feb. 12, 2025

Language: Английский

Citations

2
A survey on cancer detection via convolutional neural networks: Current challenges and future directions DOI
Pallabi Sharma, Deepak Ranjan Nayak, Bunil Kumar Balabantaray

et al.

Neural Networks, Journal Year: 2023, Volume and Issue: 169, P. 637 - 659

Published: Nov. 7, 2023

Language: Английский

Citations

32
Grey Wolf optimized SwinUNet based transformer framework for liver segmentation from CT images DOI

S. S. Kumar,

Ravi Kumar,

V. Ranjith

et al.

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 117, P. 109248 - 109248

Published: April 18, 2024

Language: Английский

Citations

7
ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation DOI Creative Commons
Zhanlin Ji,

Juncheng Mu,

Jianuo Liu

et al.

Medical & Biological Engineering & Computing, Journal Year: 2024, Volume and Issue: 62(6), P. 1673 - 1687

Published: Feb. 8, 2024

Early intervention in tumors can greatly improve human survival rates. With the development of deep learning technology, automatic image segmentation has taken a prominent role field medical analysis. Manually segmenting kidneys on CT images is tedious task, and due to diversity these varying technical skills professionals, results be inconsistent. To address this problem, novel ASD-Net network proposed paper for kidney tumor tasks. First, employs newly designed Adaptive Spatial-channel Convolution Optimization (ASCO) blocks capture anisotropic information images. Then, other blocks, i.e., Dense Dilated Enhancement (DDEC) are utilized enhance feature propagation reuse it across network, thereby improving its accuracy. allow segment complex small more effectively, Atrous Spatial Pyramid Pooling (ASPP) module incorporated middle layer. generalized pyramid feature, enables better understand context at various scales within In addition this, concurrent spatial channel squeeze & excitation (scSE) attention mechanism adopted comprehend manage Additional encoding layers also added base (U-Net) connected original layer through skip connections. The resultant enhanced U-Net structure allows extraction merging high-level low-level features, further boosting network's ability restore details. addition, combined Binary Cross Entropy (BCE)-Dice loss as function. Experiments, conducted KiTS19 dataset, demonstrate that outperforms existing networks according all evaluation metrics used, except recall case segmentation, where takes second place after Attention-UNet.

Language: Английский

Citations

6
Digital healthcare framework for patients with disabilities based on deep federated learning schemes DOI
Abdullah Lakhan, Hassen Hamouda, Karrar Hameed Abdulkareem

et al.

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 169, P. 107845 - 107845

Published: Dec. 18, 2023

Language: Английский

Citations

16
En–DeNet Based Segmentation and Gradational Modular Network Classification for Liver Cancer Diagnosis DOI Creative Commons

G Suganeshwari,

Jothi Prabha Appadurai,

Balasubramanian Prabhu Kavin

et al.

Biomedicines, Journal Year: 2023, Volume and Issue: 11(5), P. 1309 - 1309

Published: April 28, 2023

Liver cancer ranks as the sixth most prevalent among all cancers globally. Computed tomography (CT) scanning is a non-invasive analytic imaging sensory system that provides greater insight into human structures than traditional X-rays, which are typically used to make diagnosis. Often, final product of CT scan three-dimensional image constructed from series interlaced two-dimensional slices. Remember not slices deliver useful information for tumor detection. Recently, images liver and its tumors have been segmented using deep learning techniques. The primary goal this study develop learning-based automatically segmenting pictures, also reduce amount time labor required by speeding up process diagnosing cancer. At core, an Encoder-Decoder Network (En-DeNet) uses neural network built on UNet serve encoder, pre-trained EfficientNet decoder. In order improve segmentation, we developed specialized preprocessing techniques, such production multichannel de-noising, contrast enhancement, ensemble, union model predictions. Then, proposed Gradational modular (GraMNet), unique estimated efficient technique. GraMNet, smaller networks called SubNets construct larger more robust variety alternative configurations. Only one new SubNet modules updated at each level. This helps in optimization minimizes computational resources needed training. segmentation classification performance compared Tumor Segmentation Benchmark (LiTS) 3D Image Rebuilding Comparison Algorithms Database (3DIRCADb01). By breaking down components learning, state-of-the-art level can be attained scenarios evaluation. comparison conventional architectures, GraMNets generated here low difficulty. When associated with benchmark methods, straight forward GraMNet trained faster, consumes less memory, processes rapidly.

Language: Английский

Citations

15
Image color rendering based on frequency channel attention GAN DOI

Hong-an Li,

Diao Wang, Min Zhang

et al.

Signal Image and Video Processing, Journal Year: 2024, Volume and Issue: 18(4), P. 3179 - 3186

Published: Jan. 20, 2024

Language: Английский

Citations

5
Literature survey on deep learning methods for liver segmentation from CT images: a comprehensive review DOI

S. S. Kumar,

Vinod Kumar R. S.

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(28), P. 71833 - 71862

Published: Feb. 8, 2024

Language: Английский

Citations

4
BGF-Net: Boundary guided filter network for medical image segmentation DOI
Yanlin He, Yugen Yi,

Caixia Zheng

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 171, P. 108184 - 108184

Published: Feb. 20, 2024

Language: Английский

Citations

4