Semi-Supervised Deep Learning Semantic Segmentation for 3D Volumetric Computed Tomographic Scoring of Chronic Rhinosinusitis: Clinical Correlations and Comparison with Lund-Mackay Scoring

Review Otorhinolaryngology

A systematic review to examine the relationship between objective and patient-reported outcome measures in sinonasal disorders: recommendations for use in research and clinical practice

Ngan Hong Ta et al.

Summary: This systematic review found that there is limited correlation between objective outcome measures and patient-reported outcome measures for sinonasal conditions, recommending the use of validated PROMs in different settings.

INTERNATIONAL FORUM OF ALLERGY & RHINOLOGY (2021)

添加到收藏夹

Article Medicine, Legal

Computer-aided superimposition of the frontal sinus via 3D reconstruction for comparative forensic identification

Yuan Li et al.

Summary: The study proposes a computer-aided frontal sinus comparative paradigm based on 3D technology, and validates the anatomical uniqueness of frontal sinuses using a large Chinese Han sample for human identification. The results show a significant difference in the average root mean square distance between the matched and unmatched groups.

INTERNATIONAL JOURNAL OF LEGAL MEDICINE (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Recognition of honeycomb lung in CT images based on improved MobileNet model

Li Gang et al.

Summary: The study aims to improve the efficiency and accuracy of honeycomb lung recognition in CT images. By combining MobileNetV1 network, multiscale feature fusion method (MSFF), and dilated convolution, a novel recognition method for honeycomb lung in CT image classification is explored. Experimental results show that the improved MobileNet model achieves the best performance in recognizing honeycomb lung image datasets, with an accuracy of 99.52%.

MEDICAL PHYSICS (2021)

添加到收藏夹

Article Biology

A robust real-time deep learning based automatic polyp detection system

Ishak Pacal et al.

Summary: Colorectal cancer is the third most common type of cancer globally, and colonoscopy is the gold standard for screening. Deep learning architectures show promise in detecting polyps, but real-time detection success has not been achieved. By improving the YOLOv4 algorithm structure, the proposed method demonstrates superior performance on public datasets.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Semi-Supervised Multi-View Deep Discriminant Representation Learning

Xiaodong Jia et al.

Summary: This paper proposes a semi-supervised multi-view deep discriminant representation learning approach, which utilizes the consensus and complementary properties of multi-view data to learn shared and specific representations, while reducing redundancy through orthogonality and adversarial similarity constraints. Experimental results demonstrate its effectiveness in typical multi-view learning tasks.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Chemistry, Analytical

An Improved Deep Residual Network Prediction Model for the Early Diagnosis of Alzheimer's Disease

Haijing Sun et al.

Summary: The study proposed a model based on deep residual networks, utilizing spatial transformer networks and non-local attention mechanism, for the early diagnosis of Alzheimer's disease. In the MRI images of AD patients, this model can extract more information, retain key information, and find the relationship between lesion areas and normal areas.

SENSORS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Automated segmentation of macular edema for the diagnosis of ocular disease using deep learning method

Zhenhua Wang et al.

Summary: A novel deep learning model (OCT-DeepLab) was developed for the segmentation of macular edema in OCT images. This model showed superior performance compared to traditional hand-crafted methods and end-to-end methods, with higher precision, sensitivity, specificity, and F1-score. The OCT-DeepLab model is suitable for assisting ophthalmologists in managing ocular diseases.

SCIENTIFIC REPORTS (2021)

添加到收藏夹

Review Anatomy & Morphology