Deep Learning for Medical Image-Based Cancer Diagnosis

Cancers, Journal Year: 2023, Volume and Issue: 15(14), P. 3608 - 3608

Published: July 13, 2023

(1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one the research hotspots in field artificial intelligence and computer vision. Due rapid development methods, requires very high accuracy timeliness as well inherent particularity complexity imaging. A comprehensive review relevant studies necessary help readers better understand current status ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission (PET), histopathological are reviewed this paper. basic architecture classical pretrained models comprehensively reviewed. In particular, advanced neural networks emerging recent years, transfer learning, ensemble (EL), graph network, vision transformer (ViT), introduced. overfitting prevention methods summarized: batch normalization, dropout, weight initialization, data augmentation. image-based analysis sorted out. (3) Results: Deep has achieved great success diagnosis, showing good results image classification, reconstruction, detection, segmentation, registration, synthesis. However, lack high-quality labeled datasets limits role faces challenges rare multi-modal fusion, model explainability, generalization. (4) Conclusions: There a need for more public standard databases cancer. pre-training potential be improved, special attention should paid multimodal fusion supervised paradigm. Technologies such ViT, few-shot will bring surprises images.

Language: Английский

---

Computer vision and machine learning for medical image analysis: recent advances, challenges, and way forward

Artificial Intelligence Surgery, Journal Year: 2022, Volume and Issue: unknown

Published: Jan. 1, 2022

The recent development in the areas of deep learning and convolutional neural networks has significantly progressed advanced field computer vision (CV) image analysis understanding. Complex tasks such as classifying segmenting medical images localising recognising objects interest have become much less challenging. This progress potential accelerating research deployment multitudes applications that utilise CV. However, reality, there are limited practical examples being physically deployed into front-line health facilities. In this paper, we examine current state art CV applied to domain. We discuss main challenges intelligent data-driven suggest future directions accelerate research, development, practices. First, critically review existing literature domain addresses complex tasks, including: classification; shape object recognition from images; segmentation. Second, present an in-depth discussion various considered barriers methods real-life hospitals. Finally, conclude by discussing directions.

Language: Английский

---

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 30(5), P. 3173 - 3233

Published: April 4, 2023

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Processing, Anomaly Detection video Speech Recognition. CNN is a special type of Neural Network, which compelling effective learning ability to learn features at several steps during augmentation the data. Recently, interesting inspiring ideas Deep Learning (DL) such as activation functions, hyperparameter optimization, regularization, momentum loss functions improved performance, operation execution Different internal architecture innovation representational style significantly performance. This survey focuses taxonomy deep learning, models vonvolutional network, depth width in addition components, applications current challenges learning.

Language: Английский

---

Exploring the Impact of Artificial Intelligence on Global Health and Enhancing Healthcare in Developing Nations

Journal of Primary Care & Community Health, Journal Year: 2024, Volume and Issue: 15

Published: Jan. 1, 2024

Background: Artificial intelligence (AI), which combines computer science with extensive datasets, seeks to mimic human-like intelligence. Subsets of AI are being applied in almost all fields medicine and surgery. Aim: This review focuses on the applications healthcare settings developing countries, designed underscore its significance by comprehensively outlining advancements made thus far, shortcomings encountered applications, present status integration, persistent challenges, innovative strategies surmount them. Methodology: Articles from PubMed, Google Scholar, Cochrane were searched 2000 2023 keywords including healthcare, focusing multiple medical specialties. Results: The increasing role diagnosis, prognosis prediction, patient management, as well hospital management community has overall system more efficient, especially high load setups resource-limited areas countries where care is often compromised. However, low adoption rates absence standardized guidelines, installation maintenance costs equipment, poor transportation connectivvity issues hinder AI’s full use healthcare. Conclusion: Despite these holds a promising future Adequate knowledge expertise professionals for technology imperative nations.

Language: Английский

---

Worth of prior knowledge for enhancing deep learning

Deleted Journal, Journal Year: 2024, Volume and Issue: 1(1), P. 100003 - 100003

Published: March 1, 2024

Knowledge constitutes the accumulated understanding and experience that humans use to gain insight into world. In deep learning, prior knowledge is essential for mitigating shortcomings of data-driven models, such as data dependence, generalization ability, compliance with constraints. Here, we present a framework enable efficient evaluation worth by derived rule importance. Through quantitative experiments, assess influence volume estimation range on knowledge. Our findings elucidate complex relationship between knowledge, including synergistic, substitution effects. model-agnostic can be applied variety common network architectures, providing comprehensive role in learning models. It also offers practical utility identification model construction within interdisciplinary research improving performance informed machine distinguishing improper

Language: Английский

---

Comparative analysis of vision transformers and convolutional neural networks in osteoporosis detection from X-ray images

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 3, 2024

Within the scope of this investigation, we carried out experiments to investigate potential Vision Transformer (ViT) in field medical image analysis. The diagnosis osteoporosis through inspection X-ray radio-images is a substantial classification problem that were able address with assistance models. In order provide basis for comparison, conducted parallel analysis which sought solve same by employing traditional convolutional neural networks (CNNs), are well-known and commonly used techniques solution categorization issues. findings our research led us conclude ViT capable achieving superior outcomes compared CNN. Furthermore, provided methods have access sufficient quantity training data, probability increases both arrive at more appropriate solutions critical

Language: Английский

---

Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(8), P. 11187 - 11212

Published: May 20, 2024

Abstract The early and accurate diagnosis of brain tumors is critical for effective treatment planning, with Magnetic Resonance Imaging (MRI) serving as a key tool in the non-invasive examination such conditions. Despite advancements Computer-Aided Diagnosis (CADx) systems powered by deep learning, challenge accurately classifying from MRI scans persists due to high variability tumor appearances subtlety early-stage manifestations. This work introduces novel adaptation EfficientNetv2 architecture, enhanced Global Attention Mechanism (GAM) Efficient Channel (ECA), aimed at overcoming these hurdles. enhancement not only amplifies model’s ability focus on salient features within complex images but also significantly improves classification accuracy tumors. Our approach distinguishes itself meticulously integrating attention mechanisms that systematically enhance feature extraction, thereby achieving superior performance detecting broad spectrum Demonstrated through extensive experiments large public dataset, our model achieves an exceptional high-test 99.76%, setting new benchmark MRI-based classification. Moreover, incorporation Grad-CAM visualization techniques sheds light decision-making process, offering transparent interpretable insights are invaluable clinical assessment. By addressing limitations inherent previous models, this study advances field medical imaging analysis highlights pivotal role enhancing interpretability learning models diagnosis. research sets stage advanced CADx systems, patient care outcomes.

Language: Английский

---

Hybrid Intelligence-Driven Medical Image Recognition for Remote Patient Diagnosis in Internet of Medical Things

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2021, Volume and Issue: 26(12), P. 5817 - 5828

Published: Dec. 31, 2021

In ear of smart cities, intelligent medical image recognition technique has become a promising way to solve remote patient diagnosis in IoMT. Although deep learning-based approaches have received great development during the past decade, explainability always acts as main obstacle promote higher levels. Because it is hard clearly grasp internal principles learning models. contrast, conventional machine (CML)-based methods are well explainable, they give relatively certain meanings parameters. Motivated by above view, this paper combines with CML, and proposes hybrid intelligence-driven framework On one hand, convolution neural network utilized extract abstract features for initial images. other CML-based techniques employed reduce dimensions extracted construct strong classifier that output results. A real dataset about pathologic myopia selected establish simulative scenario, order assess proposed framework. Results reveal proposal improves accuracy two three percent.

Language: Английский

---

Deep learning-based detection of aluminum casting defects and their types

Engineering Applications of Artificial Intelligence, Journal Year: 2022, Volume and Issue: 118, P. 105636 - 105636

Published: Nov. 28, 2022

Language: Английский

---

A deep-learning based multimodal system for Covid-19 diagnosis using breathing sounds and chest X-ray images

Applied Soft Computing, Journal Year: 2021, Volume and Issue: 109, P. 107522 - 107522

Published: May 26, 2021

Language: Английский

---