Computers & Electrical Engineering, Journal Year: 2025, Volume and Issue: 123, P. 110099 - 110099
Published: Jan. 22, 2025
Language: Английский
Computers & Electrical Engineering, Journal Year: 2025, Volume and Issue: 123, P. 110099 - 110099
Published: Jan. 22, 2025
Language: Английский
Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 234, P. 121007 - 121007
Published: July 21, 2023
Language: Английский
Citations
17Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 125, P. 106749 - 106749
Published: July 14, 2023
Colonoscopy is considered the gold standard for colorectal cancer diagnosis and prognosis. However, existing methods are less accurate prone to overlooking lesions during gastrointestinal endoscopic examinations. Computer-assisted combined with robot-assisted minimally invasive surgery (RMIS) can significantly help medical practitioners detect treat lesions. Therefore, two novel architectures developed polyp surgical instrument segmentation aid diagnosis, assessment, treatment. Colorectal network (CCS-Net) base used in this study. It uses maximum convolutional layers near input image effective feature extraction from low-level information. In addition, CCS-Net an efficient upsampling unit efficiently increase spatial features' map size. Hence, capable of providing a fair performance satisfactory computational efficiency The multi-scale retention aggregation (MFRA-Net) final MFRA-Net improve accuracy further as it retain features transfers them deep stages network. also combines high-strided information high-level boost performance. Finally, all transferred early aggregated levels This mechanism enables maintain better compared other even challenging blur, specular reflection, low contrast, high variation cases. We evaluated both on four datasets: Kvasir-SEG, CVC-ClinicDB, Kvasir-Instrument, UW-Sinus-Surgery-Live dataset. proposed method achieves dice similarity coefficients 95.98%, 94.19%, 92.81%, 88.57% datasets. superior state-of-the-art requires only 4.9 million trainable parameters complete training. networks effectively assist health professionals procedures through instruments segmentation, respectively.
Language: Английский
Citations
16Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 157, P. 106735 - 106735
Published: March 1, 2023
Language: Английский
Citations
14Sensors, Journal Year: 2023, Volume and Issue: 23(10), P. 4688 - 4688
Published: May 12, 2023
In the realm of computer vision, semantic segmentation is task recognizing objects in images at pixel level. This done by performing a classification each pixel. The complex and requires sophisticated skills knowledge about context to identify objects' boundaries. importance many domains undisputed. medical diagnostics, it simplifies early detection pathologies, thus mitigating possible consequences. this work, we provide review literature on deep ensemble learning models for polyp develop new ensembles based convolutional neural networks transformers. development an effective entails ensuring diversity between its components. To end, combined different (HarDNet-MSEG, Polyp-PVT, HSNet) trained with data augmentation techniques, optimization methods, rates, which experimentally demonstrate be useful form better ensemble. Most importantly, introduce method obtain mask averaging intermediate masks after sigmoid layer. our extensive experimental evaluation, average performance proposed over five prominent datasets beat any other solution that know of. Furthermore, also performed than state-of-the-art two datasets, when individually considered, without having been specifically them.
Language: Английский
Citations
14Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 93, P. 106210 - 106210
Published: March 16, 2024
Language: Английский
Citations
5Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 249, P. 123663 - 123663
Published: March 19, 2024
Language: Английский
Citations
5Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 180, P. 108939 - 108939
Published: July 29, 2024
Language: Английский
Citations
5Journal of Imaging, Journal Year: 2023, Volume and Issue: 9(2), P. 35 - 35
Published: Feb. 6, 2023
Skin detection involves identifying skin and non-skin areas in a digital image is commonly used various applications, such as analyzing hand gestures, tracking body parts, facial recognition. The process of distinguishing between regions widely variety ranging from hand-gesture analysis to body-part challenging problem that has received lot attention experts proposals the research community context intelligent systems, but lack common benchmarks unified testing protocols hampered fairness among approaches. Comparisons are very difficult. Recently, success deep neural networks had major impact on field segmentation detection, resulting successful models date. In this work, we survey most recent propose fair comparisons approaches, using several different datasets. main contributions work (i) comprehensive review literature approaches skin-color comparison may help researchers practitioners choose best method for their application; (ii) list datasets report ground truth detection; (iii) protocol evaluating comparing skin-detection Moreover, an ensemble convolutional transformers obtains state-of-the-art performance.
Language: Английский
Citations
13Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 157, P. 106736 - 106736
Published: March 5, 2023
Language: Английский
Citations
11Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 172, P. 108302 - 108302
Published: March 16, 2024
Language: Английский
Citations
4