Colorectal cancer (CRC) is the second most common cause of cancer-related death in the world, and early detection of adenomatous polyps with colonoscopy is important because it can prevent CRC. Nonetheless, traditional colonoscopy is still operator-dependent and with lesion-miss rates of up to 25% for small or flat lesions. Over the past decade, automated polyp detection and segmentation have come a long way with deep learning. CNNs like U-Net, UNet++ and ResUNet++ set strong baselines, however their low receptive field bound hindered generalization. More recently, vision transformers (ViTs) and hybrid CNN–transformer architectures have achieved state-of-the-art results by modeling long-range dependencies and incorporating global context. This systematic review examines more than 50 studies as the representative one available between 2015 and 2025, with specific attention to the results on Kvasir-SEG, CVC-ClinicDB, and ETIS-Larib benchmarks. Experiments demonstrate that while NFL-CNNs reach Dice scores of 0.85–0.90 on easier datasets, ViTs and hybrids almost always outperform motors, with the best models reaching 0.94 (NA-SegFormer) on Kvasir-SEG and 0.81 over ETIS. Our results illustrate the disruptive nature of attention-based approaches, closer to what was desired by clinical colleagues, and signal some of the stubborn open challenges relating to dataset availability, practical computational cost and high-quality clinical evidence. Advances in the future will likely center around the development of lightweight understandable and generalisable AI systems designed to provide real-time, clinically reliable polyp detection.
| Mualliflar | Burhonovna, Lobar Badalova, Rabbimovich , Yusupov Ozod |
|---|---|
| Jurnal | Innovative Multidisciplinary Journal of Applied Technology |
| Nashr sanasi | 2025-12-05 |
| Jild | 3 |
| Son | 12 |
| Betlar | 7-23 |
| Til | Ingliz |
| DOI | 10.51699/j5tb2v47 |
DOI: 10.51699/j5tb2v47 · Maqolaning asl sahifasi
vision transformers, convolutional neural networks, polyp detection, colonoscopy, medical image segmentation, deep learning, endoscopy
The accuracy of the LightGBM model in forecasting oil and gas probability maps had been evaluated based on MapOil analytic system. Integration of geological, geophysical, satellite and topographic map datasets in single…
Data visualization, interoperability, analysis, and business decisions face a significant challenge as a result of the growing volumes of heterogeneous data being produced by agencies and institutions in the education…
Thermal therapies namely, thermal ablation, hyperthermia, and laser play an important role in the treatment of various medical conditions especially, malignancies focusing on tumor/tumor-like tissues. These therapies…
The increasing need for natural textile fibers has reignited interest in wool production in the Republic of Uzbekistan, where today, Karakul, Jaidari, Hisar and Edilbay sheep are the main sources of raw wool. These…
We invest.igate the conc.ept of semi-.strong (s-s.trong) and semi.-weak (s-.weak) sets in topolo.gical spa.ces. We beg.in by giv.ing defini.tions, some exam.ples and fundam.ental characte.ristics for the two sor.ts of…
Ionising radiation and other physical factors have a strong impact on vegetative growth and pest resistance in various plant species. This influences agriculture and ecosystem management by determining the suitability…
Standardization and the Improvement of Non autoclaved Aerated Concrete Quality in Modern Construction: A Review In the introduction, the authors explain that conditions of large-scale production of construction units…
The significant impact of ionizing radiation and physical factors on vegetative growth and pest resistance of various plant species underlies the development of their ability to exist and grow in contaminated areas…
Considering that the world's primary tillage area is 4.2 billion hectares, the development of high-quality, energy-efficient and resource-efficient soil tillage machines and tools is one of the important tasks. This…
Artificial intelligence (AI) is a collection of various technologies and algorithms built to minimize human intervention and maximize results, saving time for businesses and customers. It is transforming ecommerce by…
Innovative Multidisciplinary Journal of Applied Technology — barcha maqolalar