Explainable artificial intelligence with UNet based segmentation and Bayesian machine learning for classification of brain tumors using MRI images

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 3, 2025

Detecting brain tumours (BT) early improves treatment possibilities and increases patient survival rates. Magnetic resonance imaging (MRI) scanning offers more comprehensive information, such as better contrast clarity, than any alternative process. Manually separating BTs from several MRI images gathered in medical practice for cancer analysis is challenging time-consuming. Tumours scans of the are exposed utilizing methods machine learning technologies, simplifying process doctors. can sometimes appear normal even when a has tumour or malignancy. Deep approaches have recently depended on deep convolutional neural networks to analyze with promising outcomes. It supports saving lives faster rectifying some errors. With this motivation, article presents new explainable artificial intelligence semantic segmentation Bayesian tumors (XAISS-BMLBT) technique. The presented XAISS-BMLBT technique mainly concentrates classification BT images. approach initially involves bilateral filtering-based image pre-processing eliminate noise. Next, performs MEDU-Net+ define impacted regions. For feature extraction process, ResNet50 model utilized. Furthermore, regularized network (BRANN) used identify presence BTs. Finally, an improved radial movement optimization employed hyperparameter tuning BRANN To highlight performance technique, series simulations were accomplished by benchmark database. experimental validation portrayed superior accuracy value 97.75% over existing models.

Language: Английский

---

Visualization and classification of mushroom species with multi-feature fusion of metaheuristics-based convolutional neural network model

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 164, P. 111936 - 111936

Published: July 4, 2024

Language: Английский

---

MDC-RHT: Multi-Modal Medical Image Fusion via Multi-Dimensional Dynamic Convolution and Residual Hybrid Transformer

Sensors, Journal Year: 2024, Volume and Issue: 24(13), P. 4056 - 4056

Published: June 21, 2024

The fusion of multi-modal medical images has great significance for comprehensive diagnosis and treatment. However, the large differences between various modalities make image a challenge. This paper proposes novel multi-scale network based on multi-dimensional dynamic convolution residual hybrid transformer, which better capability feature extraction context modeling improves performance. Specifically, proposed exploits that introduces four attention mechanisms corresponding to different dimensions convolutional kernel extract more detailed information. Meanwhile, transformer is designed, activates pixels participate in process by channel attention, window overlapping cross thereby strengthening long-range dependence modes enhancing connection global A loss function, including perceptual structural similarity loss, where former enhances visual reality details fused image, latter enables model learn textures. whole adopts architecture uses an unsupervised end-to-end method realize fusion. Finally, our tested qualitatively quantitatively mainstream datasets. results indicate achieves high scores most quantitative indicators satisfactory performance qualitative analysis.

Language: Английский

---

Multi-Modal Feature Extraction Network for Medical Image Fusion

Published: April 19, 2025

Medical image fusion is to synthesize multiple medical images from single or different imaging devices. This paper aims improve quality with accurate preserving for diagnosis and treatment. work plays an important role in the fields of surgical navigation, routine staging, radio-therapy planning malignant disease. Nowadays, computerized tomography (CT), magnetic resonance (MRI), single-photo emission computed (SPECT) modalities, positron (PET) are focused using fusion. Bones implants clearly reflected by CT Image. High-resolution anatomical details soft tissues recorded MRL images. However, MRI not sensitive fractures compared image. SPECT utilized study blood flow organs nuclear technique. Our proposed Multi-Modal Based Image directly learning features original a powerful tool that enhances clinical value individual leading better patient outcomes. As technology advances computational techniques evolve, modern medicine continues grow.

Language: Английский

---

Pushing the Boundaries of Brain-Computer Interfacing (BCI) and Neuron-Electronics

Journal of Neuroscience Methods, Journal Year: 2024, Volume and Issue: 411, P. 110274 - 110274

Published: Aug. 30, 2024

Language: Английский

---