Auto-detection of the coronavirus disease by using deep convolutional neural networks and X-ray photographs

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

Published: Jan. 4, 2024

Abstract The most widely used method for detecting Coronavirus Disease 2019 (COVID-19) is real-time polymerase chain reaction. However, this has several drawbacks, including high cost, lengthy turnaround time results, and the potential false-negative results due to limited sensitivity. To address these issues, additional technologies such as computed tomography (CT) or X-rays have been employed diagnosing disease. Chest are more commonly than CT scans widespread availability of X-ray machines, lower ionizing radiation, cost equipment. COVID-19 presents certain radiological biomarkers that can be observed through chest X-rays, making it necessary radiologists manually search biomarkers. process time-consuming prone errors. Therefore, there a critical need develop an automated system evaluating X-rays. Deep learning techniques expedite process. In study, deep learning-based called Custom Convolutional Neural Network (Custom-CNN) proposed identifying infection in Custom-CNN model consists eight weighted layers utilizes strategies like dropout batch normalization enhance performance reduce overfitting. approach achieved classification accuracy 98.19% aims accurately classify COVID-19, normal, pneumonia samples.

Language: Английский

---

Kidney Cancer Diagnosis and Surgery Selection by Machine Learning from CT Scans Combined with Clinical Metadata

Cancers, Journal Year: 2023, Volume and Issue: 15(12), P. 3189 - 3189

Published: June 14, 2023

Kidney cancers are one of the most common malignancies worldwide. Accurate diagnosis is a critical step in management kidney cancer patients and influenced by multiple factors including tumor size or volume, types stages, etc. For malignant tumors, partial radical surgery might be required, but for clinicians, basis making this decision often unclear. Partial nephrectomy could result patient death due to if removal was necessary, whereas less severe cases resign lifelong dialysis need future transplantation without sufficient cause. Using machine learning consider clinical data alongside computed tomography images potentially help resolve some these surgical ambiguities, enabling more robust classification selection optimal approaches. In study, we used publicly available KiTS dataset contrast-enhanced CT corresponding metadata differentiate four major classes cancer: clear cell (ccRCC), chromophobe (chRCC), papillary (pRCC) renal carcinoma, oncocytoma (ONC). We rationalized overcome high field view (FoV), extract regions interest (ROIs), classify using deep machine-learning models, extract/post-process image features combination with data. Regardless marked imbalance, our combined approach achieved level performance (85.66% accuracy, 84.18% precision, 85.66% recall, 84.92% F1-score). When selecting procedures tumors (RCC), method proved even reliable (90.63% 90.83% 90.61% 90.50% feature ranking, confirmed that volume stage relevant predicting procedures. Once fully mature, propose assist surgeons performing nephrectomies guiding choices individual cancer.

Language: Английский

---

Detection of renal cell hydronephrosis in ultrasound kidney images: a study on the efficacy of deep convolutional neural networks

PeerJ Computer Science, Journal Year: 2024, Volume and Issue: 10, P. e1797 - e1797

Published: Jan. 23, 2024

In the realm of medical imaging, early detection kidney issues, particularly renal cell hydronephrosis, holds immense importance. Traditionally, identification such conditions within ultrasound images has relied on manual analysis, a labor-intensive and error-prone process. However, in recent years, emergence deep learning-based algorithms paved way for automation this domain. This study aims to harness power learning models autonomously detect hydronephrosis taken close proximity kidneys. State-of-the-art architectures, including VGG16, ResNet50, InceptionV3, innovative Novel DCNN, were put test subjected rigorous comparisons. The performance each model was meticulously evaluated, employing metrics as F1 score, accuracy, precision, recall. results paint compelling picture. DCNN outshines its peers, boasting an impressive accuracy rate 99.8%. same arena, InceptionV3 achieved notable 90% ResNet50 secured 89%, VGG16 reached 85%. These outcomes underscore DCNN's prowess images. Moreover, offers detailed view model's through confusion matrices, shedding light their abilities categorize true positives, negatives, false negatives. regard, exhibits remarkable proficiency, minimizing both positives conclusion, research underscores supremacy automating With exceptional minimal error rates, stands promising tool healthcare professionals, facilitating early-stage diagnosis treatment. Furthermore, convergence hold potential enhancement further exploration, testing larger more diverse datasets investigating optimization strategies.

Language: Английский

---

ProsGradNet: An effective and structured CNN approach for prostate cancer grading from histopathology images

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 105, P. 107626 - 107626

Published: Feb. 8, 2025

Language: Английский

---

Kidney Diseases Classification using Hybrid Transfer-Learning DenseNet201-Based and Random Forest Classifier

Kurdistan Journal of Applied Research, Journal Year: 2023, Volume and Issue: unknown, P. 131 - 144

Published: Jan. 15, 2023

There are several disease kinds in global populations that may be related to human lifestyles, social, genetic, economic, and other factors the nature of country they live in. Most recent studies have focused on investigating prevalent diseases spread population order minimize mortality risks, choose best method for treatment, improve community healthcare. Kidney is one most widespread health problems modern society. This study focuses kidney stones, cysts, tumors, three common types renal illness, using a dataset 12,446 CT urogram whole abdomen images, aiming move toward an AI-based diagnosis system while contributing wider field artificial intelligence research. In this study, hybrid technique used by utilizing both pre-train models feature extraction classification machine learning algorithms task image diagnosis. The pre-trained model Densenet-201 model. As well as Random Forest classification, Densenet-201-Random-Forest approach has outperformed many previous studies, having accuracy rate 99.719 percent.

Language: Английский

---

Deep Federated Machine Learning-Based Optimization Methods for Liver Tumor Diagnosis: A Review

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 30(5), P. 3359 - 3378

Published: March 21, 2023

Language: Английский

---

An optimized fusion of deep learning models for kidney stone detection from CT images

Journal of King Saud University - Computer and Information Sciences, Journal Year: 2024, Volume and Issue: 36(7), P. 102130 - 102130

Published: July 18, 2024

Accurate diagnosis of kidney disease is crucial, as it a significant health concern that demands precise identification for effective and appropriate treatment. Deep learning methods are increasingly recognized valuable tools in the biomedical field. However, current models utilizing deep networks often encounter challenges overfitting low accuracy, necessitating further refinement optimal performance. To overcome these challenges, this paper proposes introduction two ensemble designed stone detection CT images. The first model, called StackedEnsembleNet, two-level stack model effectively integrates predictions from four base models: InceptionV3, InceptionResNetV2, MobileNet, Xception. By leveraging collective knowledge models, StackedEnsembleNet improves accuracy reliability detection. second PSOWeightedAvgNet, leverages Particle Swarm Optimization (PSO) algorithm to determine weights weighted average ensemble. Through PSO, approach assigns optimized each during ensembling process, enhancing performance by optimizing combination their predictions. Experimental results conducted on large dataset 1799 images demonstrate both PSOWeightedAvgNet outperform individual achieving high rates Furthermore, additional experiments an unseen validate models' ability generalize. comparison with previous confirms superior proposed models. also presents Grad-CAM visualizations error case analysis provide insights into decision-making processes overcoming limitations existing offer promising accurate detection, contributing improved treatment outcomes field nephrology.

Language: Английский

---

Kidney Tumor Classification on CT images using Self-supervised Learning

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 176, P. 108554 - 108554

Published: May 3, 2024

Language: Английский

---

A framework to distinguish healthy/cancer renal CT images using the fused deep features

Frontiers in Public Health, Journal Year: 2023, Volume and Issue: 11

Published: Jan. 30, 2023

Introduction Cancer happening rates in humankind are gradually rising due to a variety of reasons, and sensible detection management essential decrease the disease rates. The kidney is one vital organs human physiology, cancer medical emergency needs accurate diagnosis well-organized management. Methods proposed work aims develop framework classify renal computed tomography (CT) images into healthy/cancer classes using pre-trained deep-learning schemes. To improve accuracy, this suggests threshold filter-based pre-processing scheme, which helps removing artefact CT slices achieve better detection. various stages scheme involve: (i) Image collection, resizing, removal, (ii) Deep features extraction, (iii) Feature reduction fusion, (iv) Binary classification five-fold cross-validation. Results discussion This experimental investigation executed separately for: with without artefact. As result outcome study, K-Nearest Neighbor (KNN) classifier able 100% accuracy by pre-processed slices. Therefore, can be considered for purpose examining clinical grade images, as it clinically significant.

Language: Английский

---

A multi-class deep learning model for early lung cancer and chronic kidney disease detection using computed tomography images

Frontiers in Oncology, Journal Year: 2023, Volume and Issue: 13

Published: June 2, 2023

Lung cancer is a fatal disease caused by an abnormal proliferation of cells in the lungs. Similarly, chronic kidney disorders affect people worldwide and can lead to renal failure impaired function. Cyst development, stones, tumors are frequent diseases impairing Since these conditions generally asymptomatic, early, accurate identification lung necessary prevent serious complications. Artificial Intelligence plays vital role early detection lethal diseases. In this paper, we proposed modified Xception deep neural network-based computer-aided diagnosis model, consisting transfer learning based image net weights model fine-tuned network for automatic computed tomography multi-class classification. The obtained 99.39% accuracy, 99.33% precision, 98% recall, 98.67% F1-score Whereas, it attained 100% F1 score, recall precision Also, outperformed original existing methods. Hence, serve as support tool radiologists nephrologists disease, respectively.

Language: Английский

---