Comparison of diagnostic performance of a deep learning algorithm, emergency physicians, junior radiologists and senior radiologists in the detection of appendicular fractures in children

Article Pediatrics

Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology

Amaka C. Offiah

Summary: In pediatric radiology, AI is mainly used for bone age assessment, with most research still being in the research domain and not replacing the role of radiologists.

PEDIATRIC RADIOLOGY (2022)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Improving Radiographic Fracture Recognition Performance and Efficiency Using Artificial Intelligence

Ali Guermazi et al.

Summary: This study aimed to evaluate the impact of assistance by artificial intelligence (AI) on the diagnosis of fractures on radiographs. The results showed that AI assistance improved the sensitivity of physicians in detecting fractures by 10.4% without affecting specificity. Additionally, AI reduced the average reading time by 6.3 seconds.

RADIOLOGY (2022)

Add to Collection

Article Orthopedics

Automated detection of acute appendicular skeletal fractures in pediatric patients using deep learning

Daichi Hayashi et al.

Summary: This study validated a commercial AI software program for detecting acute appendicular fractures in pediatric patients and found that the deep learning algorithm provided high overall diagnostic performance.

SKELETAL RADIOLOGY (2022)

Add to Collection

Article Pediatrics

Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists

Toan Nguyen et al.

Summary: The study aims to investigate the ability of artificial intelligence to improve the detection of fractures by radiologists in children and young adults. With the help of AI, the sensitivity in fracture detection increased significantly by an average of 10% without significantly affecting specificity in a predominantly pediatric population.

PEDIATRIC RADIOLOGY (2022)

Add to Collection

Article Multidisciplinary Sciences

A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs

Chi-Tung Cheng et al.

Summary: Pelvic radiographs are crucial for detecting proximal femur and pelvis injuries in trauma patients, yet current algorithms are limited in accurately detecting all trauma-related radiographic findings. This study introduces PelviXNet, a deep learning algorithm trained with weakly supervised point annotation, which demonstrates high accuracy and sensitivity in a clinical population test set.

NATURE COMMUNICATIONS (2021)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Assessment of an AI Aid in Detection of Adult Appendicular Skeletal Fractures by Emergency Physicians and Radiologists: A Multicenter Cross-sectiona Diagnostic Study

Loic Duron et al.

Summary: The study evaluated the performance of an artificial intelligence system in aiding radiologists and emergency physicians in detecting and localizing fractures. Results showed that AI assistance improved sensitivity and specificity, reduced false-positive fractures, and lowered average reading time in patients without fractures.

RADIOLOGY (2021)

Add to Collection

Article Multidisciplinary Sciences

Critical evaluation of deep neural networks for wrist fracture detection

Abu Mohammed Raisuddin et al.

Summary: The study revealed that while the Deep Learning model for wrist fracture detection performs near perfectly on a general test set, it shows lower performance on a challenging test set requiring confirmation by CT imaging. This underscores the importance of meticulous analysis of DL-based models before clinical implementation and the necessity for more challenging settings in testing medical AI systems.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Imaging Science & Photographic Technology

How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?

Guillaume Reichert et al.

Summary: The study demonstrates that utilizing deep learning algorithms for diagnosing fractures in emergency room X-rays is effective and can play a crucial role in the training of junior radiologists.

JOURNAL OF IMAGING (2021)

Add to Collection

Article Health Care Sciences & Services

Do as AI say: susceptibility in deployment of clinical decision-aids

Susanne Gaube et al.

Summary: This study found that radiologists rated diagnostic advice as lower quality when it appeared to come from an AI system, while less experienced physicians did not have this bias. Diagnostic accuracy significantly decreased when participants received inaccurate advice, regardless of the purported source being AI or human experts. Therefore, important considerations need to be made when deploying advice in clinical environments, whether it is coming from AI or non-AI sources.

NPJ DIGITAL MEDICINE (2021)

Add to Collection

Review Oncology

Designing deep learning studies in cancer diagnostics

Andreas Kleppe et al.

Summary: The number of publications on deep learning for cancer diagnostics is increasing rapidly, but clinical translation progress is slow. It is advocated to estimate performance in external cohorts, define a primary analysis in a standardized protocol stored online, and establish recommended protocol items in the field to facilitate transition to the clinic.

NATURE REVIEWS CANCER (2021)

Add to Collection

Article Computer Science, Artificial Intelligence