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

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 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.

Язык: Английский

---

Enhancing heart disease classification based on greylag goose optimization algorithm and long short-term memory

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 8, 2025

Heart disease is a category of various conditions that affect the heart, which includes multiple diseases influence its structure and operation. Such may consist coronary artery disease, characterized by narrowing or clotting arteries supply blood to heart muscle, with resulting threat attacks. rhythm disorders (arrhythmias), valve problems, congenital defects present at birth, muscle (cardiomyopathies) are other types disease. The objective this work introduce Greylag Goose Optimization (GGO) algorithm, seeks improve accuracy classification. GGO algorithm's binary format specifically intended choose most effective set features can classification when compared six optimization algorithms. bGGO algorithm for selecting optimal enhance accuracy. phase utilizes many classifiers, findings indicated Long Short-Term Memory (LSTM) emerged as classifier, achieving an rate 91.79%. hyperparameter LSTM model tuned using GGO, outcome alternative optimizers. obtained highest performance, 99.58%. statistical analysis employed Wilcoxon signed-rank test ANOVA assess feature selection outcomes. Furthermore, visual representations results was provided confirm robustness effectiveness proposed hybrid approach (GGO + LSTM).

Язык: Английский

---

Breast cancer classification based on hybrid CNN with LSTM model

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 5, 2025

Breast cancer (BC) is a global problem, largely due to shortage of knowledge and early detection. The speed-up process detection classification crucial for effective treatment. Medical image analysis methods computer-aided diagnosis can enhance this process, providing training assistance less experienced clinicians. Deep Learning (DL) models play great role in accurately detecting classifying the huge dataset, especially when dealing with large medical images. This paper presents novel hybrid model DL combined Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) binary breast on two datasets available at Kaggle repository. CNNs extract mammographic features, including spatial hierarchies malignancy patterns, whereas LSTM networks characterize sequential dependencies temporal interactions. Our method combines these structures improve accuracy resilience. We compared proposed other models, such as CNN, LSTM, Gated Recurrent Units (GRUs), VGG-16, RESNET-50. CNN-LSTM achieved superior performance accuracies 99.17% 99.90% respective datasets. uses prediction evaluation metrics accuracy, sensitivity, specificity, F-score, AUC curve. results showed that our classifiers others second dataset.

Язык: Английский

---

Strategies to Improve the Robustness and Generalizability of Deep Learning Segmentation and Classification in Neuroimaging

BioMedInformatics, Год журнала: 2025, Номер 5(2), С. 20 - 20

Опубликована: Апрель 14, 2025

Artificial Intelligence (AI) and deep learning models have revolutionized diagnosis, prognostication, treatment planning by extracting complex patterns from medical images, enabling more accurate, personalized, timely clinical decisions. Despite its promise, challenges such as image heterogeneity across different centers, variability in acquisition protocols scanners, sensitivity to artifacts hinder the reliability integration of models. Addressing these issues is critical for ensuring accurate practical AI-powered neuroimaging applications. We reviewed summarized strategies improving robustness generalizability segmentation classification neuroimages. This review follows a structured protocol, comprehensively searching Google Scholar, PubMed, Scopus studies on neuroimaging, task-specific applications, model attributes. Peer-reviewed, English-language brain imaging were included. The extracted data analyzed evaluate implementation effectiveness techniques. study identifies key enhance including regularization, augmentation, transfer learning, uncertainty estimation. These approaches address major domain shifts, consistent performance diverse settings. technical this can improve their real-world practice.

Язык: Английский

---

AInsectID Version 1.1: An Insect Species Identification Software Based on the Transfer Learning of Deep Convolutional Neural Networks

Опубликована: Март 25, 2025

AInsectID Version 1.1 is a Graphical User Interface (GUI)‐operable open‐source insect species identification, color processing, and image analysis software. The software has current database of 150 insects integrates artificial intelligence approaches to streamline the process with focus on addressing prediction challenges posed by mimics. This paper presents methods algorithmic development, coupled rigorous machine training used enable high levels validation accuracy. Our work transfer learning prominent convolutional neural network (CNN) architectures, including VGG16, GoogLeNet, InceptionV3, MobileNetV2, ResNet50, ResNet101. Here, we employ both fine tuning hyperparameter optimization improve performance. After extensive computational experimentation, ResNet101 evidenced as being most effective CNN model, achieving accuracy 99.65%. dataset utilized for sourced from National Museum Scotland, Natural History London, open source datasets Zenodo (CERN's Data Center), ensuring diverse comprehensive collection species.

Язык: Английский

---

A novel similarity navigated graph neural networks and crayfish optimization algorithm for accurate brain tumor detection

Research on Biomedical Engineering, Год журнала: 2025, Номер 41(2)

Опубликована: Апрель 5, 2025

Язык: Английский

---