HydraViT: Adaptive multi-branch transformer for multi-label disease classification from Chest X-ray images

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 100, С. 106959 - 106959

Опубликована: Сен. 30, 2024

Язык: Английский

---

Revolutionizing Medical Diagnosis with Novel Teaching-Learning-Based Optimization

2021 International Conference on Emerging Smart Computing and Informatics (ESCI), Год журнала: 2024, Номер unknown

Опубликована: Март 5, 2024

In medical diagnosis, the precise and prompt identification of diseases is crucial for effective treatment optimal patient care. As data grows increasingly complex, there's an urgent need efficient diagnostic tools. Researchers are turning to innovative optimization techniques enhance accuracy speed these diagnoses. This paper applied a novel Teaching-Learning-Based Optimization (TLBO) technique its potential implications in diagnosis. Diagnoses require interpretation each point categorization specific pathology. Tools such as computer-aided diagnostics artificial neural networks exemplify AI technologies that aim refine processes minimize human error. These algorithms have versatility process broad spectrum data. Our investigation delves into theory using Results indicate while various methods predicting diagnostics, TLBOMLP ER-WCAMLP outperform with rates AUC=0.971, compared CART-MLP's AUC=0.961 0.962.

Язык: Английский

---

Deep learning-assisted medical image compression challenges and opportunities: systematic review

Neural Computing and Applications, Год журнала: 2024, Номер 36(17), С. 10067 - 10108

Опубликована: Апрель 30, 2024

Язык: Английский

---

Transform Drug Discovery and Development With Generative Artificial Intelligence

Опубликована: Янв. 3, 2025

In the past decade, artificial intelligence (AI) has significantly reshaped drug discovery, offering a wide range of tools to expedite identification new therapeutics. This review meticulously examines AI's pivotal role, detailing common data resources, molecule representations, and benchmark platforms crucial for molecular property prediction generation. addition, it provides comprehensive analysis AI techniques, categorizing them by model architectures learning paradigms. Success stories underscore transformative impact on clinical candidate advancement. Despite progress, formidable challenges persist, demanding innovative solutions. By addressing these charting future directions, aims deepen understanding foster innovation in AI-driven discovery development, serving as valuable resource researchers practitioners.

Язык: Английский

---

Continual Learning in Medicine: A Systematic Literature Review

Neural Processing Letters, Год журнала: 2025, Номер 57(1)

Опубликована: Янв. 7, 2025

Abstract Continual Learning (CL) is a novel AI paradigm in which tasks and data are made available over time; thus, the trained model computed on basis of stream data. CL-based approaches able to learn new skills knowledge without forgetting previous ones, with no guaranteed access previously encountered data, mitigating so-called “catastrophic forgetting” phenomenon. Interestingly, by making systems improve time need for large amounts or computational resources, CL can help at reducing impact computationally-expensive energy-intensive activities; hence, play key role path towards more green AIs, enabling efficient sustainable uses resources. In this work, we describe different methods proposed literature solve tasks; survey applications, highlighting strengths weaknesses, particular focus biomedical context. Furthermore, discuss how make robust suitable wider range applications.

Язык: Английский

---

BrainNeXt: novel lightweight CNN model for the automated detection of brain disorders using MRI images

Cognitive Neurodynamics, Год журнала: 2025, Номер 19(1)

Опубликована: Март 22, 2025

Abstract The main aim of this study is to propose a novel convolutional neural network, named BrainNeXt, for the automated brain disorders detection using magnetic resonance images (MRI) images. Furthermore, we investigate performance our proposed network on various medical applications. To achieve high/robust image classification performance, gathered new MRI dataset belonging four classes: (1) Alzheimer's disease, (2) chronic ischemia, (3) multiple sclerosis, and (4) control. Inspired by ConvNeXt, designed BrainNeXt as lightweight model incorporating structural elements Swin Transformers Tiny model. By training collected dataset, pretrained was obtained. Additionally, have suggested feature engineering (FE) approach based which extracted features from fixed-sized patches. select most discriminative/informative features, employed neighborhood component analysis selector in selection phase. As classifier patch-based FE approach, utilized support vector machine classifier. Our recommended achieved an accuracy 100% 91.35% validation. obtained test 94.21%. further improve DFE 99.73%. results, surpassing 90% demonstrate effectiveness high models.

Язык: Английский

---

Imaging in Interventional Radiology: 2043 and Beyond

Radiology, Год журнала: 2023, Номер 308(1)

Опубликована: Июль 1, 2023

Since its inception in the early 20th century, interventional radiology (IR) has evolved tremendously and is now a distinct clinical discipline with own training pathway. The arsenal of modalities at work IR includes x-ray radiography fluoroscopy, CT, MRI, US, molecular multimodality imaging within hybrid environments. This article briefly reviews major developments technology over past summarizes technologies representative standard care, reflects on emerging advances that could shape field century ahead. role emergent enabling high-precision interventions also reviewed, including image-guided ablative therapies. © RSNA, 2023 See review "Interventional Oncology: 2043 Beyond" by Elsayed Solomon this issue.

Язык: Английский

---

Generative AI for medical imaging analysis and applications

Future Medicine AI, Год журнала: 2023, Номер unknown

Опубликована: Сен. 6, 2023

Generative AI plays a pivotal role in medical imaging analysis, enabling precise diagnosis, treatment planning and disease monitoring. Techniques like generative adversarial networks (GANs) variational autoencoders (VAEs) enhance by generating synthetic images, improving reconstruction, segmentation facilitating diagnosis planning. Nonetheless, ethical, legal regulatory concerns arise regarding patient privacy, data protection fairness. This paper offers an overview of highlighting applications, challenges case studies. It compares results with traditional methods examines potential implications on healthcare policies. The concludes recommendations for responsible implementation suggests future research development directions.

Язык: Английский

---

Application of Generative Artificial Intelligence AIGC Technology Under Neural Network Algorithm in Game Character Art Design

Journal of the Knowledge Economy, Год журнала: 2024, Номер unknown

Опубликована: Июнь 19, 2024

Язык: Английский

---

New era after ChatGPT in ophthalmology: advances from data-based decision support to patient-centered generative artificial intelligence

Annals of Translational Medicine, Год журнала: 2023, Номер 11(10), С. 337 - 337

Опубликована: Авг. 1, 2023

Язык: Английский

---