Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 4 appraisals
PloS one
Automated concrete crack detection enhanced by deep learning and generative adversarial networks
Cracks on the surface of concrete structures are an obvious indication of their condition. However, traditional visual inspection methods are significantly influenced by human factors. They are accurate for larger cracks. However, they introduce subjective judgment when detecting smaller cracks. They also pose safety risks. Automated detection methods face challenges in achieving lightweight implementation due to limited annotated data and difficulties in complex environments. This paper proposes a method for detecting and measuring concrete cracks. The method uses a generative adversarial network (GAN) to augment data and a U-Net segmentation network. Conditional GAN (cGAN) is proposed to generate high-fidelity crack images using training-set data only, avoiding data leakage and effectively solving insufficient sample issues. A U-Net segmentation network that has been enhanced performs crack segmentation. This network incorporates channel attention modules and dilated residual blocks. A hybrid loss function that combines the Dice coefficient and binary cross-entropy resolves class imbalance. Fractal theory quantifies the geometric features of the detected cracks. The crack segmentation model that was trained on cGAN-augmented datasets achieved an average precision (AP) of 82.03% and an F1 score of 83.24%, as demonstrated by experimental results. The fractal dimension-based crack measurement method achieves an accuracy of ≤4% error for complex crack networks (fractal dimension >1.6). The proposed method provides a reproducible, automated, high-precision solution for concrete crack detection and quantification, with verified stability and engineering applicability.
21 July 2026
Read appraisal →PloS one
Research on the semantic segmentation of Thangka images via an improved PIDNet.
In the digital preservation, restoration, and research of Thangka paintings, real-time semantic segmentation plays a crucial role in rapid image analysis. However, Thangka images exhibit intricate compositions, where principal figures often blend with backgrounds, ritual objects, and intricate ornaments, leading to blurred boundaries and fine details that challenge conventional segmentation methods in balancing accuracy and efficiency. To address this, we propose an improved PIDNet-based model incorporating ECA-Pag (Efficient Channel Attention-Path Aggregation) and LGFM (Local-Global Feature Fusion Module) modules, along with PConv3 (Partial Convolution 3), enhancing feature extraction and segmentation precision. Experimental results demonstrate that our model achieves 73.28% mIoU and mB-Fscore (mean Boundary F-score) of 40.01% on a custom Thangka dataset while maintaining 109.03 FPS (Frames Per Second), ensuring both high accuracy and real-time performance. Furthermore, evaluations on the Cityscapes benchmark confirm the model's generalization capability, outperforming baseline methods. This work provides an efficient and reliable solution for Thangka image segmentation, with potential applications in cultural heritage preservation and broader computer vision tasks.
17 May 2026
Read appraisal →PloS one
SSH-YOLO: YOLOv8 improved model based on Object Detection in Complex Road Scenes
To address the problem of insufficient detection accuracy for dense targets, small targets and partially occluded objects in complex road scenarios, an improved object detection model, SSH-YOLO, is proposed. On the basis of YOLOv8n, the model optimizes and improves performance through a three-level collaborative architecture: 1) introduce the spatial and deep conversion (SPDConv) module in the backbone network to replace the traditional step downsampling with nonstep convolution, retain the fine-grained features of small targets, and solve the feature loss problem of low-resolution images; 2) embed the spatial and channel collaborative attention module (SCSA), through cross-scale feature fusion (SMSA) and channel weight progressive optimization (PCSA), focus on the key visible areas of the occluded target and suppress background interference such as roadside vegetation; and 3) add a new 160 × 160 resolution small object detection head, combined with the original P3‒P5 layer to form a four-level detection system, covering long-distance small targets < 32 × 32 pixels. The experimental results show that the improved model performs well on the self-built RoadScene-Complex dataset and four public datasets BDD100K: 0.729 (12.4% higher than YOLOv8n) on the RoadScene-Complex dataset [email protected] (12.4% higher than YOLOv8n) and 0.868 (7.6% higher than the KITTI dataset) [email protected]). COCO small target subset [email protected] to 0.585 (up 16.5%), and CityPersons occluded scene [email protected] to 0.739 (up 22.8%). At the same time, it maintains lightweight characteristics and has an inference speed of up to 60 FPS to meet the needs of real-time on-board detection. The research results provide a balanced solution of "accuracy-speed-lightweight" for high-precision target detection in complex traffic scenarios, especially in small target and occlusion scenarios.
17 Apr 2026
Read appraisal →PloS one
Attention and residual mechanism-based CNN architecture (ARC-Net) with enhanced fairness generalization for deepfake facial image detection.
Deepfake (DF) content poses a major challenge to digital media authentication, that can mimic facial movements, creating realistic replicas that risk spreading misinformation and enabling harassment, as can be seen in Bangladesh. Previous studies applied residual convolutional blocks or attention mechanisms for DF detection; however, these approaches often treat these components in isolation and lack explicit consideration of fairness, out-of-distribution generalization, statistical analysis or artifact-focused detection. Our study introduces an approach, called ARC-Net, which uses a combination of attention and residual convolutional layers along with the EfficientNet B0 base, the attention mechanism of which allows the model to pay more attention to details that could resemble the ones seen in non-perfectly executed DF, which enhances the model's potential to distinguish them, addressing limitations in pre-trained and also advanced DL models. A dataset of 500 real images from Bangladesh combined with a 140k real and fake faces dataset was used to train and test our model alongside four pre-trained DL models. ARC-Net performed much better than the other traditional and state of art methods with 99% accuracy, 1.0 precision, 0.97 recall and 0.98 F1 score, reaching the highest level of reliability in spotting DF images. To assess the external reliability and generalizability of ARC-Net, the model was evaluated on the Deepfake Dataset and the Deepfake Database datasets, achieving consistently high and balanced performance across different scales. Three out-of-distribution (OOD) experiments were conducted, where the first one evaluated South Asian images, showing that incorporating fewer than one percent real Bangladeshi images reduced the false positive rate by more than half and improved probability calibration, while the remaining two cross-dataset experiments demonstrated strong transferability. An ablation study further showed the impact of different components within a model by systematically removing or modifying them and statistical significance between competing classifiers was assessed using McNemar's Statistical test. In addition, we've applied Explainable AI (XAI) techniques, Grad-CAM and LIME to offer transparency of the results, as giving attention to the facial region is also important for DF detection. This study will help advance DF detection by integrating ARC-Net's attention-residual mechanisms and XAI, offering insights for developing models in security and media forensics.
7 Apr 2026
Read appraisal →