Automatic Segmentation for Favourable Delineation of Ten Wrist Bones on Wrist Radiographs Using Convolutional Neural Network

Article Medicine, Legal

Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network

Li-Qin Peng et al.

Summary: Segmentation networks can improve the accuracy of pelvic bone age estimation in forensic assessment by automatically locating key pelvic areas and minimizing the influence of constraints like overlapping organs in X-ray images.

INTERNATIONAL JOURNAL OF LEGAL MEDICINE (2022)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Detecting Distal Radial Fractures from Wrist Radiographs Using a Deep Convolutional Neural Network with an Accuracy Comparable to Hand Orthopedic Surgeons

Takeshi Suzuki et al.

Summary: The study evaluated the ability of a convolutional neural network (CNN) to diagnose distal radius fractures using frontal and lateral wrist radiographs, showing high accuracy compared to three hand orthopedic surgeons. The CNN model exhibited high accuracy in diagnosing distal radius fractures with plain radiographs.

JOURNAL OF DIGITAL IMAGING (2022)

添加到收藏夹

Article Oncology

A blind randomized validated convolutional neural network for auto-segmentation of clinical target volume in rectal cancer patients receiving neoadjuvant radiotherapy

Yijun Wu et al.

Summary: This study introduces a CNN-based model for fast auto-segmentation of CTV in cancer patients, showing high performance in clinical evaluation and improving the efficiency and consistency of radiation clinicians' work.

CANCER MEDICINE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Automatic Carpal Site Detection Method for Evaluation of Rheumatoid Arthritis Using Deep Learning

Kohei Nakatsu et al.

Summary: This study proposes a fully automatic detection method of rheumatoid arthritis score evaluation points using deep learning, which can significantly shorten the diagnosis time and improve the diagnosis quality.

JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS (2022)

添加到收藏夹

Article Computer Science, Information Systems

X-ray carpal bone segmentation and area measurement

Amir Faisal et al.

Summary: This study introduces a method for segmentation and area measurement of carpal bones in X-ray images, which achieved satisfying segmentation outcomes using the locally weighted K-means variational level set technique on multiple datasets.

MULTIMEDIA TOOLS AND APPLICATIONS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks

Narinder Singh Punn et al.

Summary: The novel coronavirus 2019 (COVID-19) presents a respiratory syndrome resembling pneumonia, with the current diagnostic procedure being less sensitive at the initial stage. To improve diagnosis efficiency, publicly available datasets of corona positive patients are being utilized for faster and automated diagnosis using deep learning approaches. Various state-of-the-art deep learning models are being fine-tuned using random oversampling and weighted class loss function techniques for improved classification of COVID-19 cases in chest X-ray images. NASNetLarge shows better performance compared to other architectures, as demonstrated through evaluation metrics such as accuracy, precision, recall, loss, and area under the curve (AUC).

APPLIED INTELLIGENCE (2021)

添加到收藏夹

Article Emergency Medicine

Application of convolutional neural networks for distal radio-ulnar fracture detection on plain radiographs in the emergency room

Min Woong Kim et al.

Summary: The study demonstrated the satisfactory performance of DenseNet-161 and ResNet-152 models in detecting wrist fractures in the emergency room. Both models showed high sensitivity, specificity, and accuracy in the test dataset, with area under the ROC curve values of 0.962 and 0.947, respectively.

CLINICAL AND EXPERIMENTAL EMERGENCY MEDICINE (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A Novel Combined Level Set Model for Carpus Segmentation from Magnetic Resonance Images with Prior Knowledge aligned in Polar Coordinate System

Jianzhang Li et al.

Summary: A shape prior enhanced level set model was proposed in this study to address segmentation issues in wrist images. By simplifying parameters and utilizing shape priors, the algorithm efficiency was greatly improved, showing abilities against noise and intensity inhomogeneity.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Development and Validation of a Convolutional Neural Network for Automated Detection of Scaphoid Fractures on Conventional Radiographs

Nils Hendrix et al.

Summary: The developed CNN achieved radiologist-level performance in detecting scaphoid bone fractures on conventional radiographs of the hand, wrist, and scaphoid. The CNN showed no significant difference in performance compared to 11 radiologists in terms of the area under the receiver operating characteristic curve (AUC).

RADIOLOGY-ARTIFICIAL INTELLIGENCE (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging