Automated detection and classification of shoulder arthroplasty models using deep learning

Machine learning in shoulder arthroplasty : a systematic review of predictive analytics applications

Aims

Machine learning (ML) holds significant promise in optimizing various aspects of total shoulder arthroplasty (TSA), potentially improving patient outcomes and enhancing surgical decision-making. The aim of this systematic review was to identify ML algorithms and evaluate their effectiveness, including those for predicting clinical outcomes and those used in image analysis.

Methods

We searched the PubMed, EMBASE, and Cochrane Central Register of Controlled Trials databases for studies applying ML algorithms in TSA. The analysis focused on dataset characteristics, relevant subspecialties, specific ML algorithms used, and their performance outcomes.

Results

Following the final screening process, 25 articles satisfied the eligibility criteria for our review. Of these, 60% focused on tabular data while the remaining 40% analyzed image data. Among them, 16 studies were dedicated to developing new models and nine used transfer learning to leverage existing pretrained models. Additionally, three of these models underwent external validation to confirm their reliability and effectiveness.

Conclusion

ML algorithms used in TSA demonstrated fair to good performance, as evidenced by the reported metrics. Integrating these models into daily clinical practice could revolutionize TSA, enhancing both surgical precision and patient outcome predictions. Despite their potential, the lack of transparency and generalizability in many current models poses a significant challenge, limiting their clinical utility. Future research should prioritize addressing these limitations to truly propel the field forward and maximize the benefits of ML in enhancing patient care.

Medical Imaging Applications Developed Using Artificial Intelligence Demonstrate High Internal Validity Yet Are Limited in Scope and Lack External Validation

PURPOSE

To (1) review definitions and concepts necessary to interpret applications of deep learning (DL; a domain of artificial intelligence that leverages neural networks to make predictions on media inputs such as images) and (2) identify knowledge and translational gaps in the literature to provide insight into specific areas for improvement as adoption of this technology continues.

METHODS

A comprehensive search of the literature was performed in December 2023 for articles regarding the use of DL in sports medicine. For each study, information regarding the joint of focus, specific anatomic structure/pathology to which DL was applied, imaging modality utilized, source of images used for model training and testing, data set size, model performance, and whether the DL model was externally validated was recorded. A numerical scale was used to rate each DL model's clinical impact, with 1 corresponding to proof-of-concept studies with little to no direct clinical impact and 5 corresponding to practice-changing clinical impact and ready for clinical deployment.

RESULTS

Fifty-five studies were identified, all of which were published within the past 5 years, while 82% were published within the past 3 years. Of the DL models identified, 84% were developed for classification tasks, 9% for automated measurements, and 7% for segmentation. A total of 62% of studies utilized magnetic resonance imaging as the imaging modality, 25% radiographs, and 7% ultrasound, while 1 study each used computed tomography, arthroscopic images, or arthroscopic video. Sixty-five percent of studies focused on the detection of tears (anterior cruciate ligament [ACL], rotator cuff [RC], and meniscus). The diagnostic performance of ACL tears, as determined by the area under the receiver operator curve (AUROC), ranged from 0.81 to 0.99 for ACL tears (excellent to near perfect), 0.83 to 0.94 for RC tears (excellent), and from 0.75 to 0.96 for meniscus tears (acceptable to excellent). In addition, 3 studies focused on detection of cartilage lesions had AUROC ranging from 0.90 to 0.92 (excellent performance). However, only 4 (7%) studies externally validated their models, suggesting that they may not be generalizable or may not perform well when applied to populations other than that used to develop the model. Finally, the mean clinical impact score was 2 (range, 1-3) on scale of 1 to 5, corresponding to limited clinical applicability.

CONCLUSIONS

DL models in orthopaedic sports medicine show generally excellent performance (high internal validity) but require external validation to facilitate clinical deployment. In addition, current models have low clinical applicability and fail to advance the field due to a focus on routine tasks and a narrow conceptual framework.

LEVEL OF EVIDENCE

Level IV, scoping review of Level I to IV studies.

Automated detection and classification of the rotator cuff tear on plain shoulder radiograph using deep learning

BACKGROUND

The diagnosis of rotator cuff tears (RCTs) using radiographs alone is clinically challenging; thus, the utility of deep learning algorithms based on convolutional neural networks has been remarkable in the field of medical imaging recognition. We aimed to evaluate the diagnostic performance of artificial intelligence (a deep learning algorithm; a convolutional neural network) to detect and classify RCTs using shoulder radiographs, and compare its diagnostic performance with that of orthopedic surgeons.

METHODS

A total of 1169 plain shoulder anteroposterior radiographs (1 image per shoulder) were included in the total dataset and divided into four groups: intact, small, medium, and large to massive tear groups. The sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and area under the receiver operating curve were measured for the detection of RCTs through binary classification. The average accuracy, recall, precision, and F1-score were divided into four groups by cuff tear size for multiclass classification.

RESULTS

The convolutional neural network demonstrated a high performance, with 92% sensitivity, 69% specificity, 86% accuracy, and an area under the receiver operating curve of 0.88 for the detection of RCTs. The average accuracy, recall, precision, and F1-score of the convolutional neural network for classification were 60%, 0.42, 0.49, and 0.45, respectively. The accuracy of the convolutional neural network for the detection and classification of RCTs was significantly better than that of orthopedic surgeons.

CONCLUSION

The convolutional neural network demonstrated the diagnostic ability to detect and classify RCTs using plain shoulder radiographs, and the diagnostic performance exhibited equal to superior accuracy when compared with those of shoulder experts.

Artificial intelligence in shoulder and elbow surgery: overview of current and future applications

Artificial intelligence (AI) is amongst the most rapidly growing technologies in orthopedic surgery. With the exponential growth in healthcare data, computing power, and complex predictive algorithms, this technology is poised to aid providers in data processing and clinical decision support throughout the continuum of orthopedic care. Understanding the utility and limitations of this technology is vital to practicing orthopedic surgeons, as these applications will become more common place in everyday practice. AI has already demonstrated its utility in shoulder and elbow surgery for imaging-based diagnosis, predictive modeling of clinical outcomes, implant identification, and automated image segmentation. The future integration of AI and robotic surgery represents the largest potential application of AI in shoulder and elbow surgery with the potential for significant clinical and financial impact. This editorial's purpose is to summarize common AI terms, provide a framework to understand and interpret AI model results, and discuss current applications and future directions within shoulder and elbow surgery.

Deep-learning for automated detection of MSU deposits on DECT: evaluating impact on efficiency and reader confidence

Introduction

Dual-energy CT (DECT) is a non-invasive way to determine the presence of monosodium urate (MSU) crystals in the workup of gout. Color-coding distinguishes MSU from calcium following material decomposition and post-processing. Manually identifying these foci (most commonly labeled green) is tedious, and an automated detection system could streamline the process. This study aims to evaluate the impact of a deep-learning (DL) algorithm developed for detecting green pixelations on DECT on reader time, accuracy, and confidence.

Methods

We collected a sample of positive and negative DECTs, reviewed twice-once with and once without the DL tool-with a 2-week washout period. An attending musculoskeletal radiologist and a fellow separately reviewed the cases, simulating clinical workflow. Metrics such as time taken, confidence in diagnosis, and the tool's helpfulness were recorded and statistically analyzed.

Results

We included thirty DECTs from different patients. The DL tool significantly reduced the reading time for the trainee radiologist (p = 0.02), but not for the attending radiologist (p = 0.15). Diagnostic confidence remained unchanged for both (p = 0.45). However, the DL model identified tiny MSU deposits that led to a change in diagnosis in two cases for the in-training radiologist and one case for the attending radiologist. In 3/3 of these cases, the diagnosis was correct when using DL.

Conclusions

The implementation of the developed DL model slightly reduced reading time for our less experienced reader and led to improved diagnostic accuracy. There was no statistically significant difference in diagnostic confidence when studies were interpreted without and with the DL model.

AI applications in musculoskeletal imaging: a narrative review

This narrative review focuses on clinical applications of artificial intelligence (AI) in musculoskeletal imaging. A range of musculoskeletal disorders are discussed using a clinical-based approach, including trauma, bone age estimation, osteoarthritis, bone and soft-tissue tumors, and orthopedic implant-related pathology. Several AI algorithms have been applied to fracture detection and classification, which are potentially helpful tools for radiologists and clinicians. In bone age assessment, AI methods have been applied to assist radiologists by automatizing workflow, thus reducing workload and inter-observer variability. AI may potentially aid radiologists in identifying and grading abnormal findings of osteoarthritis as well as predicting the onset or progression of this disease. Either alone or combined with radiomics, AI algorithms may potentially improve diagnosis and outcome prediction of bone and soft-tissue tumors. Finally, information regarding appropriate positioning of orthopedic implants and related complications may be obtained using AI algorithms. In conclusion, rather than replacing radiologists, the use of AI should instead help them to optimize workflow, augment diagnostic performance, and keep up with ever-increasing workload.Relevance statement This narrative review provides an overview of AI applications in musculoskeletal imaging. As the number of AI technologies continues to increase, it will be crucial for radiologists to play a role in their selection and application as well as to fully understand their potential value in clinical practice. Key points • AI may potentially assist musculoskeletal radiologists in several interpretative tasks.• AI applications to trauma, age estimation, osteoarthritis, tumors, and orthopedic implants are discussed.• AI should help radiologists to optimize workflow and augment diagnostic performance.

Artificial Intelligence for Automated Implant Identification in Knee Arthroplasty: A Multicenter External Validation Study Exceeding 3.5 Million Plain Radiographs

BACKGROUND

Surgical management of complications following knee arthroplasty demands accurate and timely identification of implant manufacturer and model. Automated image processing using deep machine learning has been previously developed and internally validated; however, external validation is essential prior to scaling clinical implementation for generalizability.

METHODS

We trained, validated, and externally tested a deep learning system to classify knee arthroplasty systems as one of the 9 models from 4 manufacturers derived from 4,724 original, retrospectively collected anteroposterior plain knee radiographs across 3 academic referral centers. From these radiographs, 3,568 were used for training, 412 for validation, and 744 for external testing. Augmentation was applied to the training set (n = 3,568,000) to increase model robustness. Performance was determined by the area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated. The training and testing sets were drawn from statistically different populations of implants (P < .001).

RESULTS

After 1,000 training epochs by the deep learning system, the system discriminated 9 implant models with a mean area under the receiver operating characteristic curve of 0.989, accuracy of 97.4%, sensitivity of 89.2%, and specificity of 99.0% in the external testing dataset of 744 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image.

CONCLUSION

An artificial intelligence-based software for identifying knee arthroplasty implants demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents a responsible and meaningful clinical application of artificial intelligence with immediate potential to globally scale and assist in preoperative planning prior to revision knee arthroplasty.

Artificial Intelligence for Automated Implant Identification in Total Hip Arthroplasty: A Multicenter External Validation Study Exceeding Two Million Plain Radiographs

BACKGROUND

The surgical management of complications after total hip arthroplasty (THA) necessitates accurate identification of the femoral implant manufacturer and model. Automated image processing using deep learning has been previously developed and internally validated; however, external validation is necessary prior to responsible application of artificial intelligence (AI)-based technologies.

METHODS

We trained, validated, and externally tested a deep learning system to classify femoral-sided THA implants as one of the 8 models from 2 manufacturers derived from 2,954 original, deidentified, retrospectively collected anteroposterior plain radiographs across 3 academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n = 2,117,000) to increase model robustness. Performance was evaluated by area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated.

RESULTS

The training and testing sets were drawn from statistically different populations of implants (P < .001). After 1,000 training epochs by the deep learning system, the system discriminated 8 implant models with a mean area under the receiver operating characteristic curve of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external testing dataset of 588 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image.

CONCLUSION

An AI-based software demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.

Artificial intelligence for automated identification of total shoulder arthroplasty implants

BACKGROUND

Accurate and rapid identification of implant manufacturer and model is critical in the evaluation and management of patients requiring revision total shoulder arthroplasty (TSA). Failure to correctly identify implant designs in these circumstances may lead to delay in care, unexpected intraoperative challenges, increased morbidity, and excess health care costs. Deep learning (DL) permits automated image processing and holds the potential to mitigate such challenges while improving the value of care rendered. The purpose of this study was to develop an automated DL algorithm to identify shoulder arthroplasty implants from plain radiographs.

METHODS

A total of 3060 postoperative images from patients who underwent TSA between 2011 and 2021 performed by 26 fellowship-trained surgeons at 2 independent tertiary academic hospitals in the Pacific Northwest and Mid-Atlantic Northeast were included. A DL algorithm was trained using transfer learning and data augmentation to classify 22 different reverse TSA and anatomic TSA prostheses from 8 implant manufacturers. Images were split into training and testing cohorts (2448 training and 612 testing images). Optimized model performance was assessed using standardized metrics including the multiclass area under the receiver operating characteristic curve (AUROC) and compared with a reference standard of implant data from operative reports.

RESULTS

The algorithm classified implants at a mean speed of 0.079 seconds (±0.002 seconds) per image. The optimized model discriminated between 8 manufacturers (22 unique implants) with AUROCs of 0.994-1.000, accuracy of 97.1%, and sensitivities between 0.80 and 1.00 on the independent testing set. In the subset of single-institution implant predictions, a DL model identified 6 specific implants with AUROCs of 0.999-1.000, accuracy of 99.4%, and sensitivity >0.97 for all implants. Saliency maps revealed key differentiating features across implant manufacturers and designs recognized by the algorithm for classification.

CONCLUSION

A DL model demonstrated excellent accuracy in identifying 22 unique TSA implants from 8 manufacturers. This algorithm may provide a clinically meaningful adjunct in assisting with preoperative planning for the failed TSA and allows for scalable expansion with additional radiographic data and validation efforts.

Automated Shoulder Implant Manufacturer Detection using Encoder Decoder based Classifier from X-ray Images

Total shoulder arthroplasty is the process of replacing the damaged ball and socket joint in the shoulder with a prosthesis made with polyethylene and metal components. The prosthesis helps to restore the normal range of motion and reduce pain, enabling the patient to return to their daily activities. These implants may need to be replaced over the years due to damage or wear and tear. It is a tedious and time-consuming process to identify the type of implant if medical records are not properly maintained. Artificial intelligence systems can speed up the treatment process by classifying the manufacturer and model of the prosthesis. We have proposed an encoder-decoder based classifier along with the supervised contrastive loss function that can identify the implant manufacturer effectively with increased accuracy of 92% from X-ray images overcoming the class imbalance problem.

Artificial intelligence-based applications in shoulder surgery leaves much to be desired: a systematic review

Background

Artificial intelligence (AI) aims to simulate human intelligence using automated computer algorithms. There has been a rapid increase in research applying AI to various subspecialties of orthopedic surgery, including shoulder surgery. The purpose of this review is to assess the scope and validity of current clinical AI applications in shoulder surgery literature.

Methods

A systematic literature review was conducted using PubMed for all articles published between January 1, 2010 and June 10, 2022. The search query used the terms as follows: (artificial intelligence OR machine learning OR deep learning) AND (shoulder OR shoulder surgery OR rotator cuff). All studies that examined AI application models in shoulder surgery were included and evaluated for model performance and validation (internal, external, or both).

Results

A total of 45 studies were included in the final analysis. Eighteen studies involved shoulder arthroplasty, 13 rotator cuff, and 14 other areas. Studies applying AI to shoulder surgery primarily involved (1) automated imaging analysis including identifying rotator cuff tears and shoulder implants (2) risk prediction analyses including perioperative complications, functional outcomes, and patient satisfaction. Highest model performance area under the curve ranged from 0.681 (poor) to 1.00 (perfect). Only 2 studies reported external validation.

Conclusion

Applications of AI in the field of shoulder surgery are expanding rapidly and offer patient-specific risk stratification for shared decision-making and process automation for resource preservation. However, model performance is modest and external validation remains to be demonstrated, suggesting increased scientific rigor is warranted prior to deploying AI-based clinical applications.

Development of a machine learning algorithm to identify total and reverse shoulder arthroplasty implants from X-ray images

Introduction

Demand for total shoulder arthroplasty (TSA) has risen significantly and is projected to continue growing. From 2012 to 2017, the incidence of reverse total shoulder arthroplasty (rTSA) rose from 7.3 cases per 100,000 to 19.3 per 100,000. Anatomical TSA saw a growth from 9.5 cases per 100,000 to 12.5 per 100,000. Failure to identify implants in a timely manner can increase operative time, cost and risk of complications. Several machine learning models have been developed to perform medical image analysis. However, they have not been widely applied in shoulder surgery. The authors developed a machine learning model to identify shoulder implant manufacturers and type from anterior-posterior X-ray images.

Methods

The model deployed was a convolutional neural network (CNN), which has been widely used in computer vision tasks. 696 radiographs were obtained from a single institution. 70% were used to train the model, while evaluation was done on 30%.

Results

On the evaluation set, the model performed with an overall accuracy of 93.9% with positive predictive value, sensitivity and F-1 scores of 94% across 10 different implant types (4 reverse, 6 anatomical). Average identification time was 0.110 s per implant.

Conclusion

This proof of concept study demonstrates that machine learning can assist with preoperative planning and improve cost-efficiency in shoulder surgery.

Radiomics and Deep Learning for Disease Detection in Musculoskeletal Radiology: An Overview of Novel MRI- and CT-Based Approaches

ABSTRACT

Radiomics and machine learning-based methods offer exciting opportunities for improving diagnostic performance and efficiency in musculoskeletal radiology for various tasks, including acute injuries, chronic conditions, spinal abnormalities, and neoplasms. While early radiomics-based methods were often limited to a smaller number of higher-order image feature extractions, applying machine learning-based analytic models, multifactorial correlations, and classifiers now permits big data processing and testing thousands of features to identify relevant markers. A growing number of novel deep learning-based methods describe magnetic resonance imaging- and computed tomography-based algorithms for diagnosing anterior cruciate ligament tears, meniscus tears, articular cartilage defects, rotator cuff tears, fractures, metastatic skeletal disease, and soft tissue tumors. Initial radiomics and deep learning techniques have focused on binary detection tasks, such as determining the presence or absence of a single abnormality and differentiation of benign versus malignant. Newer-generation algorithms aim to include practically relevant multiclass characterization of detected abnormalities, such as typing and malignancy grading of neoplasms. So-called delta-radiomics assess tumor features before and after treatment, with temporal changes of radiomics features serving as surrogate markers for tumor responses to treatment. New approaches also predict treatment success rates, surgical resection completeness, and recurrence risk. Practice-relevant goals for the next generation of algorithms include diagnostic whole-organ and advanced classification capabilities. Important research objectives to fill current knowledge gaps include well-designed research studies to understand how diagnostic performances and suggested efficiency gains of isolated research settings translate into routine daily clinical practice. This article summarizes current radiomics- and machine learning-based magnetic resonance imaging and computed tomography approaches for musculoskeletal disease detection and offers a perspective on future goals and objectives.

Applications of artificial intelligence in orthopaedic surgery

The practice of medicine is rapidly transforming as a result of technological breakthroughs. Artificial intelligence (AI) systems are becoming more and more relevant in medicine and orthopaedic surgery as a result of the nearly exponential growth in computer processing power, cloud based computing, and development, and refining of medical-task specific software algorithms. Because of the extensive role of technologies such as medical imaging that bring high sensitivity, specificity, and positive/negative prognostic value to management of orthopaedic disorders, the field is particularly ripe for the application of machine-based integration of imaging studies, among other applications. Through this review, we seek to promote awareness in the orthopaedics community of the current accomplishments and projected uses of AI and ML as described in the literature. We summarize the current state of the art in the use of ML and AI in five key orthopaedic disciplines: joint reconstruction, spine, orthopaedic oncology, trauma, and sports medicine.

A Novel Hybrid Machine Learning Based System to Classify Shoulder Implant Manufacturers

It is necessary to know the manufacturer and model of a previously implanted shoulder prosthesis before performing Total Shoulder Arthroplasty operations, which may need to be performed repeatedly in accordance with the need for repair or replacement. In cases where the patient’s previous records cannot be found, where the records are not clear, or the surgery was conducted abroad, the specialist should identify the implant manufacturer and model during preoperative X-ray controls. In this study, an auxiliary expert system is proposed for classifying manufacturers of shoulder implants on the basis of X-ray images that is automated, objective, and based on hybrid machine learning models. In the proposed system, ten different hybrid models consisting of a combination of deep learning and machine learning algorithms were created and statistically tested. According to the experimental results, an accuracy of 95.07% was achieved using the DenseNet201 + Logistic Regression model, one of the proposed hybrid machine learning models (p < 0.05). The proposed hybrid machine learning algorithms achieve the goal of low cost and high performance compared to other studies in the literature. The results lead the authors to believe that the proposed system could be used in hospitals as an automatic and objective system for assisting orthopedists in the rapid and effective determination of shoulder implant types before performing revision surgery.

Automatic Localization and Brand Detection of Cervical Spine Hardware on Radiographs Using Weakly Supervised Machine Learning

Purpose

To develop an end-to-end pipeline to localize and identify cervical spine hardware brands on routine cervical spine radiographs.

Materials and Methods

In this single-center retrospective study, patients who received cervical spine implants between 2014 and 2018 were identified. Information on the implant model was retrieved from the surgical notes. The dataset was filtered for implants present in at least three patients, which yielded five anterior and five posterior hardware models for classification. Images for training were manually annotated with bounding boxes for anterior and posterior hardware. An object detection model was trained and implemented to localize hardware on the remaining images. An image classification model was then trained to differentiate between five anterior and five posterior hardware models. Model performance was evaluated on a holdout test set with 1000 iterations of bootstrapping.

Results

A total of 984 patients (mean age, 62 years ± 12 [standard deviation]; 525 women) were included for model training, validation, and testing. The hardware localization model achieved an intersection over union of 86.8% and an F1 score of 94.9%. For brand classification, an F1 score, sensitivity, and specificity of 98.7% ± 0.5, 98.7% ± 0.5, and 99.2% ± 0.3, respectively, were attained for anterior hardware, with values of 93.5% ± 2.0, 92.6% ± 2.0, and 96.1% ± 2.0, respectively, attained for posterior hardware.

Conclusion

The developed pipeline was able to accurately localize and classify brands of hardware implants using a weakly supervised learning framework.Keywords: Spine, Convolutional Neural Network, Deep Learning Algorithms, Machine Learning Algorithms, Prostheses, Semisupervised Learning Supplemental material is available for this article. © RSNA, 2022See also commentary by Huisman and Lessmann in this issue.

Artificial intelligence in orthopedic implant model classification: a systematic review

Although artificial intelligence models have demonstrated high accuracy in identifying specific orthopedic implant models from imaging, which is an important and time-consuming task, the scope of prior works and performance of prior models have not been evaluated. We performed a systematic review to summarize the scope, methodology, and performance of artificial intelligence algorithms in classifying orthopedic implant models. We performed a literature search in PubMed, EMBASE, and the Cochrane Library for studies published up to March 10, 2021, using search terms related to "artificial intelligence", "orthopedic", "implant", and "arthroplasty". Studies were assessed using a modified version of the methodologic index for non-randomized studies. Reported outcomes included area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. The search identified 2689 records, of which 11 were included in the final review. The number of implant models evaluated ranged from 2 to 27. Five studies reported overall AUC across all included models which ranged from 0.94 to 1.0. Overall accuracy values ranged from 0.804 to 1.0. One study compared AI model performance with that of three surgeons, reporting similar performance. There was a large degree of variation in methodology and reporting quality. Artificial intelligence algorithms have demonstrated strong performance in classifying orthopedic implant models from radiographs. Further research is needed to compare artificial intelligence alone and as an adjunct with human experts in implant identification. Future studies should aim to adhere to rigorous artificial intelligence development methods and thorough, transparent reporting of methods and results.

AI MSK clinical applications: orthopedic implants

Artificial intelligence (AI) and deep learning have multiple potential uses in aiding the musculoskeletal radiologist in the radiological evaluation of orthopedic implants. These include identification of implants, characterization of implants according to anatomic type, identification of specific implant models, and evaluation of implants for positioning and complications. In addition, natural language processing (NLP) can aid in the acquisition of clinical information from the medical record that can help with tasks like prepopulating radiology reports. Several proof-of-concept works have been published in the literature describing the application of deep learning toward these various tasks, with performance comparable to that of expert musculoskeletal radiologists. Although much work remains to bring these proof-of-concept algorithms into clinical deployment, AI has tremendous potential toward automating these tasks, thereby augmenting the musculoskeletal radiologist.

Artificial Intelligence-Based Solution in Personalized Computer-Aided Arthroscopy of Shoulder Prostheses

Background: Early recognition of prostheses before reoperation can reduce perioperative morbidity and mortality. Because of the intricacy of the shoulder biomechanics, accurate classification of implant models before surgery is fundamental for planning the correct medical procedure and setting apparatus for personalized medicine. Expert surgeons usually use X-ray images of prostheses to set the patient-specific apparatus. However, this subjective method is time-consuming and prone to errors. Method: As an alternative, artificial intelligence has played a vital role in orthopedic surgery and clinical decision-making for accurate prosthesis placement. In this study, three different deep learning-based frameworks are proposed to identify different types of shoulder implants in X-ray scans. We mainly propose an efficient ensemble network called the Inception Mobile Fully-Connected Convolutional Network (IMFC-Net), which is comprised of our two designed convolutional neural networks and a classifier. To evaluate the performance of the IMFC-Net and state-of-the-art models, experiments were performed with a public data set of 597 de-identified patients (597 shoulder implants). Moreover, to demonstrate the generalizability of IMFC-Net, experiments were performed with two augmentation techniques and without augmentation, in which our model ranked first, with a considerable difference from the comparison models. A gradient-weighted class activation map technique was also used to find distinct implant characteristics needed for IMFC-Net classification decisions. Results: The results confirmed that the proposed IMFC-Net model yielded an average accuracy of 89.09%, a precision rate of 89.54%, a recall rate of 86.57%, and an F1.score of 87.94%, which were higher than those of the comparison models. Conclusion: The proposed model is efficient and can minimize the revision complexities of implants.

Can AI distinguish a bone radiograph from photos of flowers or cars? Evaluation of bone age deep learning model on inappropriate data inputs

OBJECTIVE

To evaluate the behavior of a publicly available deep convolutional neural network (DCNN) bone age algorithm when presented with inappropriate data inputs in both radiological and non-radiological domains.

METHODS

We evaluated a publicly available DCNN-based bone age application. The DCNN was trained on 12,612 pediatric hand radiographs and won the 2017 RSNA Pediatric Bone Age Challenge (concordance of 0.991 with radiologist ground-truth). We used the application to analyze 50 left-hand radiographs (appropriate data inputs) and seven classes of inappropriate data inputs in radiological (i.e., chest radiographs) and non-radiological (i.e., image of street numbers) domains. For each image, we noted if (1) the application distinguished between appropriate and inappropriate data inputs and (2) inference time per image. Mean inference times were compared using ANOVA.

RESULTS

The 16Bit Bone Age application calculated bone age for all pediatric hand radiographs with mean inference time of 1.1 s. The application did not distinguish between pediatric hand radiographs and inappropriate image types, including radiological and non-radiological domains. The application inappropriately calculated bone age for all inappropriate image types, with mean inference time of 1.1 s for all categories (p = 1).

CONCLUSION

A publicly available DCNN-based bone age application failed to distinguish between appropriate and inappropriate data inputs and calculated bone age for inappropriate images. The awareness of inappropriate outputs based on inappropriate DCNN input is important if tasks such as bone age determination are automated, emphasizing the need for appropriate oversight at the data input and verification stage to avoid unrecognized erroneous results.

Deep learning for accurately recognizing common causes of shoulder pain on radiographs

OBJECTIVE

Training a convolutional neural network (CNN) to detect the most common causes of shoulder pain on plain radiographs and to assess its potential value in serving as an assistive device to physicians.

MATERIALS AND METHODS

We used a CNN of the ResNet-50 architecture which was trained on 2700 shoulder radiographs from clinical practice of multiple institutions. All radiographs were reviewed and labeled for six findings: proximal humeral fractures, joint dislocation, periarticular calcification, osteoarthritis, osteosynthesis, and joint endoprosthesis. The trained model was then evaluated on a separate test dataset, which was previously annotated by three independent expert radiologists. Both the training and the test datasets included radiographs of highly variable image quality to reflect the clinical situation and to foster robustness of the CNN. Performance of the model was evaluated using receiver operating characteristic (ROC) curves, the thereof derived AUC as well as sensitivity and specificity.

RESULTS

The developed CNN demonstrated a high accuracy with an area under the curve (AUC) of 0.871 for detecting fractures, 0.896 for joint dislocation, 0.945 for osteoarthritis, and 0.800 for periarticular calcifications. It also detected osteosynthesis and endoprosthesis with near perfect accuracy (AUC 0.998 and 1.0, respectively). Sensitivity and specificity were 0.75 and 0.86 for fractures, 0.95 and 0.65 for joint dislocation, 0.90 and 0.86 for osteoarthrosis, and 0.60 and 0.89 for calcification.

CONCLUSION

CNNs have the potential to serve as an assistive device by providing clinicians a means to prioritize worklists or providing additional safety in situations of increased workload.

Artificial Intelligence-Based Recognition of Different Types of Shoulder Implants in X-ray Scans Based on Dense Residual Ensemble-Network for Personalized Medicine

Re-operations and revisions are often performed in patients who have undergone total shoulder arthroplasty (TSA) and reverse total shoulder arthroplasty (RTSA). This necessitates an accurate recognition of the implant model and manufacturer to set the correct apparatus and procedure according to the patient's anatomy as personalized medicine. Owing to unavailability and ambiguity in the medical data of a patient, expert surgeons identify the implants through a visual comparison of X-ray images. False steps cause heedlessness, morbidity, extra monetary weight, and a waste of time. Despite significant advancements in pattern recognition and deep learning in the medical field, extremely limited research has been conducted on classifying shoulder implants. To overcome these problems, we propose a robust deep learning-based framework comprised of an ensemble of convolutional neural networks (CNNs) to classify shoulder implants in X-ray images of different patients. Through our rotational invariant augmentation, the size of the training dataset is increased 36-fold. The modified ResNet and DenseNet are then combined deeply to form a dense residual ensemble-network (DRE-Net). To evaluate DRE-Net, experiments were executed on a 10-fold cross-validation on the openly available shoulder implant X-ray dataset. The experimental results showed that DRE-Net achieved an accuracy, F1-score, precision, and recall of 85.92%, 84.69%, 85.33%, and 84.11%, respectively, which were higher than those of the state-of-the-art methods. Moreover, we confirmed the generalization capability of our network by testing it in an open-world configuration, and the effectiveness of rotational invariant augmentation.