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

Balancing Performance and Interpretability in Medical Image Analysis: Case study of Osteopenia

Multiple studies within the medical field have highlighted the remarkable effectiveness of using convolutional neural networks for predicting medical conditions, sometimes even surpassing that of medical professionals. Despite their great performance, convolutional neural networks operate as black boxes, potentially arriving at correct conclusions for incorrect reasons or areas of focus. Our work explores the possibility of mitigating this phenomenon by identifying and occluding confounding variables within images. Specifically, we focused on the prediction of osteopenia, a serious medical condition, using the publicly available GRAZPEDWRI-DX dataset. After detection of the confounding variables in the dataset, we generated masks that occlude regions of images associated with those variables. By doing so, models were forced to focus on different parts of the images for classification. Model evaluation using F1-score, precision, and recall showed that models trained on non-occluded images typically outperformed models trained on occluded images. However, a test where radiologists had to choose a model based on the focused regions extracted by the GRAD-CAM method showcased different outcomes. The radiologists' preference shifted towards models trained on the occluded images. These results suggest that while occluding confounding variables may degrade model performance, it enhances interpretability, providing more reliable insights into the reasoning behind predictions. The code to repeat our experiment is available on the following link: https://github.com/mikulicmateo/osteopenia .

Building RadiologyNET: an unsupervised approach to annotating a large-scale multimodal medical database

BACKGROUND

The use of machine learning in medical diagnosis and treatment has grown significantly in recent years with the development of computer-aided diagnosis systems, often based on annotated medical radiology images. However, the lack of large annotated image datasets remains a major obstacle, as the annotation process is time-consuming and costly. This study aims to overcome this challenge by proposing an automated method for annotating a large database of medical radiology images based on their semantic similarity.

RESULTS

An automated, unsupervised approach is used to create a large annotated dataset of medical radiology images originating from the Clinical Hospital Centre Rijeka, Croatia. The pipeline is built by data-mining three different types of medical data: images, DICOM metadata and narrative diagnoses. The optimal feature extractors are then integrated into a multimodal representation, which is then clustered to create an automated pipeline for labelling a precursor dataset of 1,337,926 medical images into 50 clusters of visually similar images. The quality of the clusters is assessed by examining their homogeneity and mutual information, taking into account the anatomical region and modality representation.

CONCLUSIONS

The results indicate that fusing the embeddings of all three data sources together provides the best results for the task of unsupervised clustering of large-scale medical data and leads to the most concise clusters. Hence, this work marks the initial step towards building a much larger and more fine-grained annotated dataset of medical radiology images.

Automatic diagnosis of pediatric supracondylar humerus fractures using radiomics-based machine learning

The aim of this study was to construct a classification model for the automatic diagnosis of pediatric supracondylar humerus fractures using radiomics-based machine learning. We retrospectively collected elbow joint Radiographs of children aged 3 to 14 years and manually delineated regions of interest (ROI) using ITK-SNAP. Radiomics features were extracted using pyradiomics, a python-based feature extraction tool. T-tests and the least absolute shrinkage and selection operator (LASSO) algorithm were used to further select the most valuable radiomics features. A logistic regression (LR) model was trained, with an 8:2 split into training and testing sets, and 5-fold cross-validation was performed on the training set. The diagnostic performance of the model was evaluated using receiver operating characteristic curves (ROC) on the testing set. A total of 411 fracture samples and 190 normal samples were included. 1561 features were extracted from each ROI. After dimensionality reduction screening, 40 and 94 features with the most diagnostic value were selected for further classification modeling in anteroposterior and lateral elbow radiographs. The area under the curve (AUC) of anteroposterior and lateral elbow radiographs is 0.65 and 0.72. Radiomics can extract and select the most valuable features from a large number of image features. Supervised machine-learning models built using these features can be used for the diagnosis of pediatric supracondylar humerus fractures.

Multi-Class Deep Learning Model for Detecting Pediatric Distal Forearm Fractures Based on the AO/OTA Classification

Common pediatric distal forearm fractures necessitate precise detection. To support prompt treatment planning by clinicians, our study aimed to create a multi-class convolutional neural network (CNN) model for pediatric distal forearm fractures, guided by the AO Foundation/Orthopaedic Trauma Association (AO/ATO) classification system for pediatric fractures. The GRAZPEDWRI-DX dataset (2008-2018) of wrist X-ray images was used. We labeled images into four fracture classes (FRM, FUM, FRE, and FUE with F, fracture; R, radius; U, ulna; M, metaphysis; and E, epiphysis) based on the pediatric AO/ATO classification. We performed multi-class classification by training a YOLOv4-based CNN object detection model with 7006 images from 1809 patients (80% for training and 20% for validation). An 88-image test set from 34 patients was used to evaluate the model performance, which was then compared to the diagnosis performances of two readers-an orthopedist and a radiologist. The overall mean average precision levels on the validation set in four classes of the model were 0.97, 0.92, 0.95, and 0.94, respectively. On the test set, the model's performance included sensitivities of 0.86, 0.71, 0.88, and 0.89; specificities of 0.88, 0.94, 0.97, and 0.98; and area under the curve (AUC) values of 0.87, 0.83, 0.93, and 0.94, respectively. The best performance among the three readers belonged to the radiologist, with a mean AUC of 0.922, followed by our model (0.892) and the orthopedist (0.830). Therefore, using the AO/OTA concept, our multi-class fracture detection model excelled in identifying pediatric distal forearm fractures.

Supervised representation learning based on various levels of pediatric radiographic views for transfer learning

Transfer learning plays a pivotal role in addressing the paucity of data, expediting training processes, and enhancing model performance. Nonetheless, the prevailing practice of transfer learning predominantly relies on pre-trained models designed for the natural image domain, which may not be well-suited for the medical image domain in grayscale. Recognizing the significance of leveraging transfer learning in medical research, we undertook the construction of class-balanced pediatric radiograph datasets collectively referred to as PedXnets, grounded in radiographic views using the pediatric radiographs collected over 24 years at Asan Medical Center. For PedXnets pre-training, approximately 70,000 X-ray images were utilized. Three different pre-training weights of PedXnet were constructed using Inception V3 for various radiation perspective classifications: Model-PedXnet-7C, Model-PedXnet-30C, and Model-PedXnet-68C. We validated the transferability and positive effects of transfer learning of PedXnets through pediatric downstream tasks including fracture classification and bone age assessment (BAA). The evaluation of transfer learning effects through classification and regression metrics showed superior performance of Model-PedXnets in quantitative assessments. Additionally, visual analyses confirmed that the Model-PedXnets were more focused on meaningful regions of interest.

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

Introduction

In 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.

Methods

A 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.

Results

Mean 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.

Discussion

This 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.

Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm

Hospital emergency departments frequently receive lots of bone fracture cases, with pediatric wrist trauma fracture accounting for the majority of them. Before pediatric surgeons perform surgery, they need to ask patients how the fracture occurred and analyze the fracture situation by interpreting X-ray images. The interpretation of X-ray images often requires a combination of techniques from radiologists and surgeons, which requires time-consuming specialized training. With the rise of deep learning in the field of computer vision, network models applying for fracture detection has become an important research topic. In this paper, we use data augmentation to improve the model performance of YOLOv8 algorithm (the latest version of You Only Look Once) on a pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX), which is a public dataset. The experimental results show that our model has reached the state-of-the-art (SOTA) mean average precision (mAP 50). Specifically, mAP 50 of our model is 0.638, which is significantly higher than the 0.634 and 0.636 of the improved YOLOv7 and original YOLOv8 models. To enable surgeons to use our model for fracture detection on pediatric wrist trauma X-ray images, we have designed the application "Fracture Detection Using YOLOv8 App" to assist surgeons in diagnosing fractures, reducing the probability of error analysis, and providing more useful information for surgery.

Enhancing X-ray-Based Wrist Fracture Diagnosis Using HyperColumn-Convolutional Block Attention Module

Fractures affect nearly 9.45% of the South Korean population, with radiography being the primary diagnostic tool. This research employs a machine-learning methodology that integrates HyperColumn techniques with the convolutional block attention module (CBAM) to enhance fracture detection in X-ray radiographs. Utilizing the EfficientNet-B0 and DenseNet169 models bolstered by the HyperColumn and the CBAM, distinct improvements in fracture site prediction emerge. Significantly, when HyperColumn and CBAM integration is applied, both DenseNet169 and EfficientNet-B0 showed noteworthy accuracy improvements, with increases of approximately 0.69% and 0.70%, respectively. The HyperColumn-CBAM-DenseNet169 model particularly stood out, registering an uplift in the AUC score from 0.8778 to 0.9145. The incorporation of Grad-CAM technology refined the heatmap's focus, achieving alignment with expert-recognized fracture sites and alleviating the deep-learning challenge of heavy reliance on bounding box annotations. This innovative approach signifies potential strides in streamlining training processes and augmenting diagnostic precision in fracture detection.

FracAtlas: A Dataset for Fracture Classification, Localization and Segmentation of Musculoskeletal Radiographs

Digital radiography is one of the most common and cost-effective standards for the diagnosis of bone fractures. For such diagnoses expert intervention is required which is time-consuming and demands rigorous training. With the recent growth of computer vision algorithms, there is a surge of interest in computer-aided diagnosis. The development of algorithms demands large datasets with proper annotations. Existing X-Ray datasets are either small or lack proper annotation, which hinders the development of machine-learning algorithms and evaluation of the relative performance of algorithms for classification, localization, and segmentation. We present FracAtlas, a new dataset of X-Ray scans curated from the images collected from 3 major hospitals in Bangladesh. Our dataset includes 4,083 images that have been manually annotated for bone fracture classification, localization, and segmentation with the help of 2 expert radiologists and an orthopedist using the open-source labeling platform, makesense.ai. There are 717 images with 922 instances of fractures. Each of the fracture instances has its own mask and bounding box, whereas the scans also have global labels for classification tasks. We believe the dataset will be a valuable resource for researchers interested in developing and evaluating machine learning algorithms for bone fracture diagnosis.

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

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.