DeeplabV3+ Driven Polyp Segmentation: Advancing Colonoscopy Diagnosis DOI

Nabil Ahmed,

MD. Naimujjaman,

Mahbuba Akhter

et al.

Published: Dec. 13, 2023

Colorectal cancer, marked by abnormal cell growth in the colon or rectum, poses a significant health risk, with potential origins precancerous polyps. The process used to identify and diagnose polyps from is called colonoscopy. Physicians may be able increase identification rate of problematic using an automatic picture segmentation technique. In recent years, significance polyp has grown substantially order attain competitive outcomes, numerous methods utilizing CNN, Vision Transformer, Transformer methodologies have been developed. DeepLabV3+ Architecture ResNet-50, MobileNetV2, ResNet-152 this paper as backbone network for Polyp Segmentation because it achieved praiseworthy results different real-world applications. Five publicly accessible datasets conduct thorough studies are validated. model implemented outperformed other existing achieving better mIOU 0.9874 loss function, Dice Coefficient, network, RestNet-152. implementation can found here: https://www.github.com/nabil0220/DeeplabV3-

Language: Английский

Polyp Segmentation Using a Hybrid Vision Transformer and a Hybrid Loss Function DOI
Evgin Göçeri

Deleted Journal, Journal Year: 2024, Volume and Issue: 37(2), P. 851 - 863

Published: Jan. 12, 2024

Accurate and early detection of precursor adenomatous polyps their removal at the stage can significantly decrease mortality rate occurrence disease since most colorectal cancer evolve from polyps. However, accurate segmentation by doctors are difficult mainly these factors: (i) quality screening with colonoscopy depends on imaging experience doctors; (ii) visual inspection is time-consuming, burdensome, tiring; (iii) prolonged inspections lead to being missed even when physician experienced. To overcome problems, computer-aided methods have been proposed. they some disadvantages or limitations. Therefore, in this work, a new architecture based residual transformer layers has designed used for polyp segmentation. In proposed segmentation, both high-level semantic features low-level spatial utilized. Also, novel hybrid loss function The focal Tversky loss, binary cross-entropy, Jaccard index reduces image-wise pixel-wise differences as well improves regional consistencies. Experimental works indicated effectiveness approach terms dice similarity (0.9048), recall (0.9041), precision (0.9057), F2 score (0.8993). Comparisons state-of-the-art shown its better performance.

Language: Английский

Citations

46
Neighbouring-slice Guided Multi-View Framework for brain image segmentation DOI
Xuemeng Hu, Zhongyu Li, Yi Wu

et al.

Neurocomputing, Journal Year: 2024, Volume and Issue: 575, P. 127315 - 127315

Published: Jan. 22, 2024

Language: Английский

Citations

6
Adaptive t-vMF dice loss: An effective expansion of dice loss for medical image segmentation DOI Creative Commons
Sota Kato, Kazuhiro Hotta

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 168, P. 107695 - 107695

Published: Nov. 27, 2023

Language: Английский

Citations

12
Polyp Segmentation With the FCB-SwinV2 Transformer DOI Creative Commons
Kerr Fitzgerald, Jorge Bernal, Aymeric Histace

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 38927 - 38943

Published: Jan. 1, 2024

Polyp segmentation within colonoscopy video frames using deep learning models has the potential to automate screening procedures. This could help improve early lesion detection rate and in vivo characterization of polyps which develop into colorectal cancer. Recent state-of-the-art polyp have combined Convolutional Neural Network (CNN) architectures Transformer (TN) architectures. Motivated by aim improving performance their robustness data variations beyond those covered during training, we propose a new CNN-TN hybrid model named FCB-SwinV2 Transformer. was created making extensive modifications recent FCN-Transformer, including replacing TN branch architecture with SwinV2 U-Net. The is evaluated on popular benchmarking datasets Kvasir-SEG, CVC-ClinicDB ETIS-LaribPolypDB. Generalizability tests are also conducted determine if can maintain accuracy when outside training distribution. consistently achieves higher mean Dice IoU scores compared other reported literature therefore represents performance. importance understanding subtleties evaluation metrics dataset partitioning demonstrated discussed.

Language: Английский

Citations

5
Foundation models in gastrointestinal endoscopic AI: Impact of architecture, pre-training approach and data efficiency DOI Creative Commons
Tim G. W. Boers,

Kiki Fockens,

Joost van der Putten

et al.

Medical Image Analysis, Journal Year: 2024, Volume and Issue: 98, P. 103298 - 103298

Published: Aug. 12, 2024

Pre-training deep learning models with large data sets of natural images, such as ImageNet, has become the standard for endoscopic image analysis. This approach is generally superior to training from scratch, due scarcity high-quality medical imagery and labels. However, it still unknown whether learned features on provide an optimal starting point downstream imaging tasks. Intuitively, pre-training closer target domain could lead better-suited feature representations. study evaluates leveraging in-domain in gastrointestinal analysis potential benefits compared images. To this end, we present a dataset comprising 5,014,174 images eight different centers (GastroNet-5M), exploit self-supervised SimCLRv2, MoCov2 DINO learn relevant The are derived multiple methods, variable amounts and/or labels (e.g. Billion-scale semi-weakly supervised ImageNet-21k). effects evaluation performed five sets, particularly designed variety tasks, example, GIANA angiodyplsia detection Kvasir-SEG polyp segmentation. findings indicate that domain-specific pre-training, specifically using framework, results into better performing any On ResNet50 Vision-Transformer-small architectures, utilizing leads average performance boost 1.63% 4.62%, respectively, datasets. improvement measured against best achieved through within evaluated frameworks. Moreover, pre-trained also exhibit increased robustness distortion perturbations (noise, contrast, blur, etc.), where 1.28% 3.55% higher metrics, found Overall, highlights importance improving generic nature, scalability GastroNet-5M weights made publicly available our repository: huggingface.co/tgwboers/GastroNet-5M_Pretrained_Weights.

Language: Английский

Citations

5
Polyp image segmentation based on improved planet optimization algorithm using reptile search algorithm DOI Creative Commons
Mohamed Abd Elaziz, Mohammed A. A. Al‐qaness, Mohammed Azmi Al‐Betar

et al.

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 12, 2025

Abstract To recognize the potential for colon polyps to develop into cancer over time, early diagnosis is crucial preventative healthcare. Timely identification significantly improves prognosis and treatment outcomes colorectal patients. Image segmentation in medical image analysis accurate planning. Therefore, this study, we present an alternative multilevel thresholding polyp method (MPOA) enhance of images. The proposed based on enhancing planet optimization algorithm (POA) by integrating operators from reptile search (RSA). evaluation developed MPOA tested with different images compared other approaches. results highlight superior capability MPOA, as evidenced various performance measures effectively segmenting Furthermore, metrics such peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), fitness values demonstrate that outperforms basic version POA methods. underscore significant impact RSA

Language: Английский

Citations

0
SCABNet: A Novel Polyp Segmentation Network With Spatial‐Gradient Attention and Channel Prioritization DOI Creative Commons
Khaled ELKarazle, Valliappan Raman,

Caslon Chua

et al.

International Journal of Imaging Systems and Technology, Journal Year: 2025, Volume and Issue: 35(2)

Published: Feb. 6, 2025

ABSTRACT Current colorectal polyps detection methods often struggle with efficiency and boundary precision, especially when dealing of complex shapes sizes. Traditional techniques may fail to precisely define the boundaries these polyps, leading suboptimal rates. Furthermore, flat small blend into background due their low contrast against mucosal wall, making them even more challenging detect. To address challenges, we introduce SCABNet, a novel deep learning architecture for efficient polyps. SCABNet employs an encoder‐decoder structure three blocks: Feature Enhancement Block (FEB), Channel Prioritization (CPB), Spatial‐Gradient Boundary Attention (SGBAB). The FEB applies dilation spatial attention high‐level features, enhancing discriminative power improving model's ability capture patterns. CPB, alternative traditional channel blocks, assigns prioritization weights diverse feature channels. SGBAB replaces conventional mechanisms solution that focuses on map. It Jacobian‐based approach construct learned convolutions both vertical horizontal components This allows effectively understand changes in map across different locations, which is crucial detecting complex‐shaped These blocks are strategically embedded within network's skip connections, capabilities without imposing excessive computational demands. They exploit enhance features at levels: high, mid, low, thereby ensuring wide range has been trained Kvasir‐SEG CVC‐ClinicDB datasets evaluated multiple datasets, demonstrating superior results. code available on: https://github.com/KhaledELKarazle97/SCABNet .

Language: Английский

Citations

0
PVTAdpNet: polyp segmentation using pyramid vision transformer with a novel adapter block DOI

Arshia Yousefi Nezhad,

Helia Aghaei,

Hedieh Sajedi

et al.

International Journal of Information Technology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 20, 2025

Language: Английский

Citations

0
SAM2U-Net: A U-Shaped Medical Image Segmentation Model Based on SAM2 and U-Net DOI

俊伟 候

Modeling and Simulation, Journal Year: 2025, Volume and Issue: 14(03), P. 337 - 347

Published: Jan. 1, 2025

Language: Английский

Citations

0
A Multi-stage Noise Suppression Network for Segmenting Polyp Images Containing Noise Interference DOI

Mianduan Lin,

Kaoru Hirota, Yaping Dai

et al.

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 93 - 106

Published: Jan. 1, 2025

Language: Английский

Citations

0