A pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX) for machine learning

Nagy, Eszter; Janisch, Michael; Hržić, Franko; Sorantin, Erich; Tschauner, Sebastian

doi:10.1038/s41597-022-01328-z

Cited by 24 publications

(23 citation statements)

References 38 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we delved into the examination of a YOLOv7 object detector with a focus on detecting pediatric wrist fractures. The dataset and baseline parameters used here closely followed a study by Nagy et al (15), ensuring a realistic scope and resource context. Accordingly, this paper undertook an ablation study, established a baseline model, and subsequently presents the research findings (10).…”

Section: Discussionmentioning

confidence: 99%

Development and optimization of AI algorithms for wrist fracture detection in children using a freely available dataset

Till,

Tschauner,

Singer

et al. 2023

Front. Pediatr.

Self Cite

View full text Add to dashboard Cite

IntroductionIn the field of pediatric trauma computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems have emerged offering a promising avenue for improved patient care. Especially children with wrist fractures may benefit from machine learning (ML) solutions, since some of these lesions may be overlooked on conventional X-ray due to minimal compression without dislocation or mistaken for cartilaginous growth plates. In this article, we describe the development and optimization of AI algorithms for wrist fracture detection in children.MethodsA team of IT-specialists, pediatric radiologists and pediatric surgeons used the freely available GRAZPEDWRI-DX dataset containing annotated pediatric trauma wrist radiographs of 6,091 patients, a total number of 10,643 studies (20,327 images). First, a basic object detection model, a You Only Look Once object detector of the seventh generation (YOLOv7) was trained and tested on these data. Then, team decisions were taken to adjust data preparation, image sizes used for training and testing, and configuration of the detection model. Furthermore, we investigated each of these models using an Explainable Artificial Intelligence (XAI) method called Gradient Class Activation Mapping (Grad-CAM). This method visualizes where a model directs its attention to before classifying and regressing a certain class through saliency maps.ResultsMean average precision (mAP) improved when applying optimizations pre-processing the dataset images (maximum increases of +25.51% mAP@0.5 and +39.78% mAP@[0.5:0.95]), as well as the object detection model itself (maximum increases of +13.36% mAP@0.5 and +27.01% mAP@[0.5:0.95]). Generally, when analyzing the resulting models using XAI methods, higher scoring model variations in terms of mAP paid more attention to broader regions of the image, prioritizing detection accuracy over precision compared to the less accurate models.DiscussionThis paper supports the implementation of ML solutions for pediatric trauma care. Optimization of a large X-ray dataset and the YOLOv7 model improve the model’s ability to detect objects and provide valid diagnostic support to health care specialists. Such optimization protocols must be understood and advocated, before comparing ML performances against health care specialists.

show abstract

Section: Discussionmentioning

confidence: 99%

Development and optimization of AI algorithms for wrist fracture detection in children using a freely available dataset

Till,

Tschauner,

Singer

et al. 2023

Front. Pediatr.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The GRAZPEDWRI-DX dataset, shown in Figure 2, was collected by a number of paediatric radiologists at the Department of Paediatric Surgery at the University Hospital Graz. A total of 10,643 wrist site studies involving 6,091 unique paediatric patients with 20,327 image samples [24] . The dataset was annotated by a group of paediatric radiologists.…”

Section: Methods Dataset and Image Pre-processingmentioning

confidence: 99%

“…In order to improve the overall efficacy of the proposed model, we incorporated YOLO algorithmic ideas for different model sizes, including Nano, Small and medium. Also to validate the feasibility of the model, we additionally trained the model on the GRAZPEDWRI-DX public dataset [24] . The contributions of this paper are summarized as follows:…”

Section: Introductionmentioning

confidence: 99%

WCAY Object Detection of Fractures for X-ray Images of Multiple Sites

Chen,

Liu,

et al. 2024

Preprint

View full text Add to dashboard Cite

Presented herein is the WCAY (Weighted Channel attention YOLO) model, meticulously crafted to identify fracture features across diverse X-ray image sites. This model integrates novel core operators and an innovative attention mechanism to enhance its efficacy. Initially, leveraging the benefits of DSConv (Dynamic Snake Convolution), adept at capturing elongated tubular structural features, we introduce the DSC-C2f module to augment the model's fracture detection performance by replacing a portion of C2f. Subsequently, we integrate the newly proposed Weighted Channel attention (WCA) mechanism into the architecture to bolster feature fusion and improve fracture detection across various sites. Comparative experiments were conducted, evaluating the performance of several attention mechanisms. These enhancement strategies were validated through experimentation on public X-ray image datasets (FracAtlas and GRAZPEDWRI-DX). Multiple experimental comparisons substantiate the model's efficacy, demonstrating its superior accuracy and real-time detection capabilities. According to the experimental findings, on the FracAtlas dataset, our WCAY model exhibits a notable 8.8% improvement in mean Average Precision (mAP) over the original model. On the GRAZPEDWRI-DX dataset, the mAP reaches 64.4%, with a detection accuracy of 93.9% for the "fracture" category alone. The proposed model represents a substantial advancement over the original algorithm when compared to other state-of-the-art object detection models. The code is publicly available at https://github.com/cccp421/Fracture-Detection-WCAY .

show abstract

“…We also requested the raters to judge and note the subjective difficulty of every X-ray picture on a five-point Likert scale (1 = Very easy, 2 = Easy, 3 = Neither easy nor hard, 4 = Hard, 5 = Very hard). The cumulative 7,000 student-assessed trauma radiographs were part of a comprehensive, already published dataset on pediatric trauma wrist examinations, containing 20,327 images in total [ 26 ].…”

Section: Methodsmentioning

confidence: 99%

Learning rate of students detecting and annotating pediatric wrist fractures in supervised artificial intelligence dataset preparations

Nagy

Marterer²,

Hržić³

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

The use of artificial intelligence (AI) in image analysis is an intensively debated topic in the radiology community these days. AI computer vision algorithms typically rely on large-scale image databases, annotated by specialists. Developing and maintaining them is time-consuming, thus, the involvement of non-experts into the workflow of annotation should be considered. We assessed the learning rate of inexperienced evaluators regarding correct labeling of pediatric wrist fractures on digital radiographs. Students with and without a medical background labeled wrist fractures with bounding boxes in 7,000 radiographs over ten days. Pediatric radiologists regularly discussed their mistakes. We found F1 scores—as a measure for detection rate—to increase substantially under specialist feedback (mean 0.61±0.19 at day 1 to 0.97±0.02 at day 10, p<0.001), but not the Intersection over Union as a parameter for labeling precision (mean 0.27±0.29 at day 1 to 0.53±0.25 at day 10, p<0.001). The times needed to correct the students decreased significantly (mean 22.7±6.3 seconds per image at day 1 to 8.9±1.2 seconds at day 10, p<0.001) and were substantially lower as annotated by the radiologists alone. In conclusion our data showed, that the involvement of undergraduated students into annotation of pediatric wrist radiographs enables a substantial time saving for specialists, therefore, it should be considered.

show abstract

A pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX) for machine learning

Cited by 24 publications

References 38 publications

Development and optimization of AI algorithms for wrist fracture detection in children using a freely available dataset

Development and optimization of AI algorithms for wrist fracture detection in children using a freely available dataset

WCAY Object Detection of Fractures for X-ray Images of Multiple Sites

Learning rate of students detecting and annotating pediatric wrist fractures in supervised artificial intelligence dataset preparations

Contact Info

Product

Resources

About