Trustworthy deep learning framework for the detection of abnormalities in X-ray shoulder images

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(3), P. e0299545 - e0299545

Published: March 11, 2024

Musculoskeletal conditions affect an estimated 1.7 billion people worldwide, causing intense pain and disability. These lead to 30 million emergency room visits yearly, the numbers are only increasing. However, diagnosing musculoskeletal issues can be challenging, especially in emergencies where quick decisions necessary. Deep learning (DL) has shown promise various medical applications. previous methods had poor performance a lack of transparency detecting shoulder abnormalities on X-ray images due training data better representation features. This often resulted overfitting, generalisation, potential bias decision-making. To address these issues, new trustworthy DL framework been proposed detect (such as fractures, deformities, arthritis) using images. The consists two parts: same-domain transfer (TL) mitigate imageNet mismatch feature fusion reduce error rates improve trust final result. Same-domain TL involves pre-trained models large number labelled from body parts fine-tuning them target dataset Feature combines extracted features with seven train several ML classifiers. achieved excellent accuracy rate 99.2%, F1 Score Cohen’s kappa 98.5%. Furthermore, results was validated three visualisation tools, including gradient-based class activation heat map (Grad CAM), visualisation, locally interpretable model-independent explanations (LIME). outperformed orthopaedic surgeons invited classify test set, who obtained average 79.1%. proven effective robust, improving generalisation increasing results.

Language: Английский

---

Improved early detection accuracy for breast cancer using a deep learning framework in medical imaging

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 187, P. 109751 - 109751

Published: Jan. 29, 2025

Language: Английский

---

Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning

Bioengineering, Journal Year: 2023, Volume and Issue: 10(8), P. 981 - 981

Published: Aug. 20, 2023

Background: Lung cancer is one of the most fatal cancers worldwide, and malignant tumors are characterized by growth abnormal cells in tissues lungs. Usually, symptoms lung do not appear until it already at an advanced stage. The proper segmentation cancerous lesions CT images primary method detection towards achieving a completely automated diagnostic system. Method: In this work, we developed improved hybrid neural network via fusion two architectures, MobileNetV2 UNET, for semantic from images. transfer learning technique was employed pre-trained utilized as encoder conventional UNET model feature extraction. proposed efficient approach that performs lightweight filtering to reduce computation pointwise convolution building more features. Skip connections were established with Relu activation function improving convergence connect layers MobileNetv2 decoder allow concatenation maps different resolutions decoder. Furthermore, trained fine-tuned on training dataset acquired Medical Segmentation Decathlon (MSD) 2018 Challenge. Results: tested evaluated 25% obtained MSD, achieved dice score 0.8793, recall 0.8602 precision 0.93. It pertinent mention our outperforms current available networks, which have several phases testing.

Language: Английский

---

Comparison of fine-tuning strategies for transfer learning in medical image classification

Image and Vision Computing, Journal Year: 2024, Volume and Issue: 146, P. 105012 - 105012

Published: April 3, 2024

Language: Английский

---

Transfer Learning with Convolutional Neural Networks for Hydrological Streamline Delineation

Environmental Modelling & Software, Journal Year: 2024, Volume and Issue: 181, P. 106165 - 106165

Published: July 24, 2024

Language: Английский

---

Raman spectroscopy combined with convolutional neural network for the sub-types classification of breast cancer and critical feature visualization

Computer Methods and Programs in Biomedicine, Journal Year: 2024, Volume and Issue: 255, P. 108361 - 108361

Published: Aug. 3, 2024

Language: Английский

---

Optimized deep learning model for comprehensive medical image analysis across multiple modalities

Neurocomputing, Journal Year: 2024, Volume and Issue: 619, P. 129182 - 129182

Published: Dec. 12, 2024

Language: Английский

---

Effective BCDNet-based breast cancer classification model using hybrid deep learning with VGG16-based optimal feature extraction

BMC Medical Imaging, Journal Year: 2025, Volume and Issue: 25(1)

Published: Jan. 8, 2025

Abstract Problem Breast cancer is a leading cause of death among women, and early detection crucial for improving survival rates. The manual breast diagnosis utilizes more time subjective. Also, the previous CAD models mostly depend on manmade visual details that are complex to generalize across ultrasound images utilizing distinct techniques. Distinct imaging tools have been utilized in works such as mammography MRI. However, these costly less portable than imaging. non-invasive method commonly used screening. Hence, paper presents novel deep learning model, BCDNet, classifying tumors benign or malignant using images. Aim primary aim study design an effective model can accurately classify their stages, thus reducing mortality aims optimize weight parameters RPAOSM-ESO algorithm enhance accuracy minimize false negative Methods BCDNet transfer from pre-trained VGG16 network feature extraction employs AHDNAM classification approach, which includes ASPP, DTCN, 1DCNN, attention mechanism. fine-tune weights parameters. Results RPAOSM-ESO-BCDNet-based provided 94.5 This value relatively higher DTCN (88.2), 1DCNN (89.6), MobileNet (91.3), ASPP-DTC-1DCNN-AM (93.8). it guaranteed designed RPAOSM-ESO-BCDNet produces accurate solutions models. Conclusion with its sophisticated techniques optimized by algorithm, shows promise suggests could be valuable tool cancer, potentially saving lives burden healthcare systems.

Language: Английский

---

Applying YOLOv6 as an ensemble federated learning framework to classify breast cancer pathology images

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 30, 2025

The most common carcinoma-related cause of death among women is breast cancer. Early detection crucial, and the manual screening method may lead to a delayed diagnosis, which would delay treatment put lives at risk. Mammography imaging advised for routine diagnose cancer an early stage. To improve generalizability, this study examines implementation Federated Learning (FedL) detect Its performance compared centralized training technique that diagnoses Although FedL has been famous as safeguarding privacy algorithm, its similarities ensemble learning methods, such federated averaging (FEDAvrg), still need be thoroughly investigated. This explicitly how YOLOv6 model trained with performs across several clients. A new homomorphic encryption decryption algorithm also proposed retain data privacy. novel pruned introduced in differentiate benign malignant tissues. on pathological dataset BreakHis BUSI. achieved validation accuracy 98% 97% BUSI dataset. results are VGG-19, ResNet-50, InceptionV3 algorithms, showing better results. tests reveal feasible, FedAvrg trains models outstanding quality only few communication rounds, shown by range topologies ResNet50, InceptionV3, Ensembled YOLOv6.

Language: Английский

---

Integrated Model (IM- LTS) for Lung Tumor Segmentation using Neural Networks and IoMT].

MethodsX, Journal Year: 2025, Volume and Issue: 14, P. 103201 - 103201

Published: Feb. 7, 2025

Language: Английский

---