BiFTransNet: A unified and simultaneous segmentation network for gastrointestinal images of CT & MRI

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 165, P. 107326 - 107326

Published: Aug. 9, 2023

Language: Английский

---

CNN-IKOA: convolutional neural network with improved Kepler optimization algorithm for image segmentation: experimental validation and numerical exploration

Journal Of Big Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: Jan. 10, 2024

Abstract Chest diseases, especially COVID-19, have quickly spread throughout the world and caused many deaths. Finding a rapid accurate diagnostic tool was indispensable to combating these diseases. Therefore, scientists thought of combining chest X-ray (CXR) images with deep learning techniques rapidly detect people infected COVID-19 or any other disease. Image segmentation as preprocessing step has an essential role in improving performance techniques, it could separate most relevant features better train techniques. several approaches were proposed tackle image problem accurately. Among methods, multilevel thresholding-based methods won significant interest due their simplicity, accuracy, relatively low storage requirements. However, increasing threshold levels, traditional failed achieve segmented reasonable amount time. researchers recently used metaheuristic algorithms this problem, but existing still suffer from slow convergence speed stagnation into local minima number levels increases. study presents alternative technique based on enhanced version Kepler optimization algorithm (KOA), namely IKOA, segment CXR at small, medium, high levels. Ten are assess IKOA ten (T-5, T-7, T-8, T-10, T-12, T-15, T-18, T-20, T-25, T-30). To observe its effectiveness, is compared terms indicators. The experimental outcomes disclose superiority over all algorithms. Furthermore, IKOA-based eight different newly CNN model called CNN-IKOA find out effectiveness step. Five indicators, overall precision, recall, F1-score, specificity, CNN-IKOA’s effectiveness. CNN-IKOA, according outcomes, outstanding for where reach 94.88% 96.57% 95.40% recall.

Language: Английский

---

WHRIME: A weight-based recursive hierarchical RIME optimizer for breast cancer histopathology image segmentation

Displays, Journal Year: 2024, Volume and Issue: 82, P. 102648 - 102648

Published: Jan. 11, 2024

Language: Английский

---

Super‐evolutionary mechanism and Nelder‐Mead simplex enhanced salp swarm algorithm for photovoltaic model parameter estimation

IET Renewable Power Generation, Journal Year: 2024, Volume and Issue: 18(14), P. 2209 - 2237

Published: Feb. 24, 2024

Abstract In the pursuit of enhancing efficiency solar cells, accurate estimation unspecified parameters in photovoltaic (PV) cell model is imperative. An advanced salp swarm algorithm called Super‐Evolutionary Nelder‐Mead Salp Swarm Algorithm (SENMSSA) proposed to achieve this objective. The SENMSSA addresses limitations SSA by incorporating a super‐evolutionary mechanism based on Gaussian‐Cauchy mutation and vertical horizontal crossover mechanism. This enhances both global optimization capabilities local search performance convergence speed algorithm. It enables secondary refinement optimum, unlocking untapped potential solution space near optimum elevating algorithm's precision exploitation higher levels. simplex method further introduced enhance accuracy. versatile that improves iteratively adjusting geometric shape (simplex) points. operates without needing derivatives, making it suitable for non‐smooth or complex objective functions. To assess efficacy SENMSSA, comparative analysis conducted against other available algorithms, namely SSA, IWOA, SCADE, LWOA, CBA, RCBA, using CEC2014 benchmark function set. Subsequently, was employed determine unknown PV under fixed conditions three different diode models. Additionally, utilized estimate commercially models (ST40, SM55, KC200GT) varying conditions. experimental results indicate study displays remarkably competitive all test cases compared algorithms. As such, we consider constitutes reliable efficient challenge parameter estimation.

Language: Английский

---

FP-CNN: Fuzzy pooling-based convolutional neural network for lung ultrasound image classification with explainable AI

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 165, P. 107407 - 107407

Published: Sept. 1, 2023

The COVID-19 pandemic wreaks havoc on healthcare systems all across the world. In scenarios like COVID-19, applicability of diagnostic modalities is crucial in medical diagnosis, where non-invasive ultrasound imaging has potential to be a useful biomarker. This research develops computer-assisted intelligent methodology for lung image classification by utilizing fuzzy pooling-based convolutional neural network FP-CNN with underlying evidence particular decisions. fuzzy-pooling method finds better representative features classification. FPCNN model categorizes images into one three classes: covid, disease-free (normal), and pneumonia. Explanations decisions are ensure fairness an system. used Shapley Additive Explanation (SHAP) explain prediction models. black-box illustrated using SHAP explanation intermediate layers model. To determine most effective model, we have tested different state-of-the-art architectures various training strategies, including fine-tuned models, single-layer pooling at layers. Among architectures, Xception having achieves best results 97.2% accuracy. We hope our proposed will helpful clinical diagnosis covid-19 from (LUS) images.

Language: Английский

---

Otsu Multi-Threshold Image Segmentation Based on Adaptive Double-Mutation Differential Evolution

Biomimetics, Journal Year: 2023, Volume and Issue: 8(5), P. 418 - 418

Published: Sept. 8, 2023

A quick and effective way of segmenting images is the Otsu threshold method. However, complexity time grows exponentially as number thresolds rises. The aim this study to address issues with standard image segmentation method's low effect high complexity. two mutations differential evolution based on adaptive control parameters presented, twofold mutation approach parameter search mechanism are used. Superior double-mutation views picture an optimization issue, uses maximum interclass variance technique objective function, determines ideal threshold, then implements multi-threshold segmentation. experimental findings demonstrate robustness enhanced parameters. Compared other benchmark algorithms, our algorithm excels in both accuracy complexity, offering superior performance.

Language: Английский

---

A new population initialization of metaheuristic algorithms based on hybrid fuzzy rough set for high-dimensional gene data feature selection

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 166, P. 107538 - 107538

Published: Oct. 4, 2023

Language: Английский

---

EU-Net: Automatic U-Net neural architecture search with differential evolutionary algorithm for medical image segmentation

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 167, P. 107579 - 107579

Published: Oct. 21, 2023

Language: Английский

---

An improved RIME optimization algorithm for lung cancer image segmentation

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 174, P. 108219 - 108219

Published: March 11, 2024

Language: Английский

---

CDRIME-MTIS: An enhanced rime optimization-driven multi-threshold segmentation for COVID-19 X-ray images

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 169, P. 107838 - 107838

Published: Dec. 15, 2023

Language: Английский

---