Unveiling the Spectrum of UV-Induced DNA Damage in Melanoma: Insights from AI-Based Analysis of Environmental Factors, Repair Mechanisms, and Skin Pigment Interactions

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 64837 - 64860

Published: Jan. 1, 2024

Language: Английский

---

Deep learning-based medical image analysis with explainable transfer learning

Published: June 29, 2023

Along with the remarkable progress of deep learning-based medical image analysis (DLB-MIA), learning models are widely deployed for computer-aided diagnosis (CAD). However, Data scarcity and model interpretability pose noteworthy challenges to DLB-MIA application. Explainable artificial intelligence (XAI) can be applied in transfer address aforementioned problems, which makes explainable a promising methodology. The utilization combined XAI techniques is therefore surveyed. current status summarized. application investigated respectively on convolutional neural networks (CNNs) transformers.

Language: Английский

---

Image Compression and Protection Systems Based on Atomic Functions

International Journal of Computing, Journal Year: 2023, Volume and Issue: unknown, P. 283 - 291

Published: Oct. 1, 2023

Digital images are a particular type of data. They have numerous applications. Taking into account current challenges and trends, image compression protection to be ensured. Data format, which provides fast analysis the compressed, is needed. In order satisfy combination these requirements, an appropriate information system should developed. this paper, we design such based on atomic functions (AF) that solutions special functional differential equations and, in terms function theory, as good constructive tools trigonometric polynomials. AF-based processing (AFIPS), satisfies requirements considered, A core discrete transform (DAT). feature AFIPS provided by possibility vary structure procedure DAT. Constructive approximation properties AF ensure high lossy lossless compression, well representation DAT-coefficients. Software implementation investigated. The results test data given.

Language: Английский

---

A transfer learning approach for the classification of liver cancer

Journal of Intelligent Systems, Journal Year: 2023, Volume and Issue: 32(1)

Published: Jan. 1, 2023

Abstract Problem The frequency of liver cancer is rising worldwide, and it a common, deadly condition. For successful treatment patient survival, early precise diagnosis essential. automated classification using medical imaging data has shown potential outcome when employing machine deep learning (DL) approaches. To train neural networks, still quite difficult to obtain large diverse dataset, especially in the field. Aim This article classifies tumors identifies whether they are malignant, benign tumor, or normal liver. Methods study mainly focuses on computed tomography scans from Radiology Institute Baghdad Medical City, Iraq, provides novel transfer (TL) approach for categorization images. Our findings show that TL-based model performs better at classifying data, as our method, high-level characteristics images extracted pre-trained convolutional networks compared conventional techniques DL models do not use TL. Results proposed method TL technology (VGG-16, ResNet-50, MobileNetV2) successfully achieves high accuracy, sensitivity, specificity identifying cancer, making an important tool radiologists other healthcare professionals. experiment results diagnostic accuracy VGG-16 up 99%, ResNet-50 100%, 99% total was attained with MobileNetV2 model. Conclusion proves improvement working small dataset. new layers also showed performance classifiers, which accelerated process.

Language: Английский

---

Enhancing Pneumonia Detection in Pediatric Chest X-Rays Using CGAN-Augmented Datasets and Lightweight Deep Transfer Learning Models

Journal of Data Analysis and Information Processing, Journal Year: 2024, Volume and Issue: 12(01), P. 1 - 23

Published: Jan. 1, 2024

Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays report their findings physicians, task susceptible human error. The application Deep Transfer Learning (DTL) for the identification pneumonia through is hindered by shortage available images, which has led less than optimal DTL performance issues with overfitting. Overfitting characterized model’s learning that too closely fitted training data, reducing its effectiveness on unseen data. problem overfitting especially prevalent medical image processing due high costs extensive time required annotation, well challenge collecting substantial datasets also respect patient privacy concerning infectious diseases such pneumonia. To mitigate these challenges, paper introduces use conditional generative adversarial networks (CGAN) enrich dataset 2690 synthesized X-ray images minority class, aiming even out distribution improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer models Xception, MobileNetV2, MobileNet, EfficientNetB0. These have been fine-tuned evaluated, demonstrating remarkable detection accuracies 99.26%, 98.23%, 97.06%, 94.55%, respectively, across fifty epochs. experimental results validate proposed achieve accuracy rates, best model reaching up 99.26% effectiveness, outperforming other diagnosis from images.

Language: Английский

---