Automatic Angle Recognition in Hallux Valgus

This paper proposes a software approach using MATLAB to measure the angular deformity as well as recognizing the type of deformity present. This can give a meaningful approach to measure the most accurate deformed angle due the Valgus and Varus knee deformity. The proposed software aids the orthopedic surgeons in knee surgeries, knee implantation and correcting the deformed knees. Thus it will revolutionize the knee surgeries and speed up the process, avoiding delay in treatment and a great relieve to the patient. Based on the deformed angle doctor can decide whether surgery is needed or not.

Lecture Notes in Computational Vision and Biomechanics, 2012

In orthopedic surgery, to decide upon intervention and how it can be optimized, surgeons usually rely on subjective analysis of medical images of the patient, obtained from computed tomography, magnetic resonance imaging, ultrasound or other techniques. Recent advancements in computational performance, image analysis and in silico modeling techniques have started to revolutionize clinical practice through the development of quantitative tools, including patient-specific models aiming at improving clinical diagnosis and surgical treatment. Anatomical and surgical landmarks as well as features extraction can be automated allowing for the creation of general or patient-specific models based on statistical shape models. Preoperative virtual planning and rapid prototyping tools allow the implementation of customized surgical solutions in real clinical environments. In the present chapter we discuss the applications of some of these techniques in orthopedics and present new computer-aided tools that can take us from image analysis to customized surgical treatment.

Neurospine

Adult spinal deformity (ASD) is a complex disease that significantly affects the lives of many patients. Surgical correction has proven to be effective in achieving improvement of spinopelvic parameters as well as improving quality of life (QoL) for these patients. However, given the relatively high complication risk associated with ASD correction, it is of paramount importance to develop robust prognostic tools for predicting risk profile and outcomes. Historically, statistical models such as linear and logistic regression models were used to identify preoperative factors associated with postoperative outcomes. While these tools were useful for looking at simple associations, they represent generalizations across large populations, with little applicability to individual patients. More recently, predictive analytics utilizing artificial intelligence (AI) through machine learning for comprehensive processing of large amounts of data have become available for surgeons to implement. The use of these computational techniques has given surgeons the ability to leverage far more accurate and individualized predictive tools to better inform individual patients regarding predicted outcomes after ASD correction surgery. Applications range from predicting QoL measures to predicting the risk of major complications, hospital readmission, and reoperation rates. In addition, AI has been used to create a novel classification system for ASD patients, which will help surgeons identify distinct patient subpopulations with unique riskbenefit profiles. Overall, these tools will help surgeons tailor their clinical practice to address patients' individual needs and create an opportunity for personalized medicine within spine surgery.

Computerized Medical Imaging and Graphics, 2010

Accurate, simple, and quick measurement of anatomical deformities at preoperative stage is clinically important for decision making in surgery planning. The deformities include excessive torsional, angular, and curvature deformation. This paper presents computer-aided methods for automatically measuring anatomical deformities of long bones of the lower limb. A three-dimensional bone model reconstructed from CT scan data of the patient is used as input. Anatomical landmarks on femur and tibia bone models are automatically identified using geometric algorithms. Medial axes of femur and tibia bones, and anatomical landmarks are used to generate functional and reference axes. These methods have been implemented in a software program and tested on a set of CT scan data. Overall, the performance of the computerized methodology was better or similar to the manual method and its results were reproducible.

Journal of Digital Imaging

Leg length discrepancies are common orthopedic problems with the potential for poor functional outcomes. These are frequently assessed using bilateral leg length radiographs. The objective was to determine whether an artificial intelligence (AI)-based image analysis system can accurately interpret long leg length radiographic images. We built an end-to-end system to analyze leg length radiographs and generate reports like radiologists, which involves measurement of lengths (femur, tibia, entire leg) and angles (mechanical axis and pelvic tilt), describes presence and location of orthopedic hardware, and reports laterality discrepancies. After IRB approval, a dataset of 1,726 extremities (863 images) from consecutive examinations at a tertiary referral center was retrospectively acquired and partitioned into train/validation and test sets. The training set was annotated and used to train a fasterRCNN-ResNet101 object detection convolutional neural network. A second-stage classifier using a EfficientNet-D0 model was trained to recognize the presence or absence of hardware within extracted joint image patches. The system was deployed in a custom web application that generated a preliminary radiology report. Performance of the system was evaluated using a holdout 220 image test set, annotated by 3 musculoskeletal fellowship trained radiologists. At the object detection level, the system demonstrated a recall of 0.98 and precision of 0.96 in detecting anatomic landmarks. Correlation coefficients between radiologist and AI-generated measurements for femur, tibia, and whole-leg lengths were > 0.99, with mean error of < 1%. Correlation coefficients for mechanical axis angle and pelvic tilt were 0.98 and 0.86, respectively, with mean absolute error of < 1°. AI hardware detection demonstrated an accuracy of 99.8%. Automatic quantitative and qualitative analysis of leg length radiographs using deep learning is feasible and holds potential in improving radiologist workflow.

In orthopedic surgery, to decide upon intervention and how it can be optimized, surgeons usually rely on subjective analysis of medical images of the patient, obtained from computed tomography, magnetic resonance imaging, ultrasound or other techniques. Recent advancements in computational performance, image analysis and in silico modeling techniques have started to revolutionize clinical practice through the development of quantitative tools, including patient-specific models aiming at improving clinical diagnosis and surgical treatment. Anatomical and surgical landmarks as well as features extraction can be automated allowing for the creation of general or patient-specific models based on statistical shape models. Preoperative virtual planning and rapid prototyping tools allow the implementation of customized surgical solutions in real clinical environments. In the present chapter we discuss the applications of some of these techniques in orthopedics and present new computer-aided tools that can take us from image analysis to customized surgical treatment.

Clinical research on foot & ankle, 2015

Background: Evaluation of hallux valgus deformity was traditionally made on a printed X-ray image. In the last two decades, digital X-ray systems have begun to replace the analog images, and images are not routinely printed anymore. Clinicians have to evaluate X-rays on digital images viewed on the computer monitors. This study compares the intra-and inter-observer reliability of foot deformity evaluation on printed images with measurements on computer monitors with the guidance of dedicated software. Methods: Fifteen pre-operative X-rays reports of patients who were candidates for a surgical correction of hallux valgus deformity, were evaluated by ten orthopedic surgeons. Each surgeon had two evaluation sessions on each modality, printed and computer monitor with the guidance of dedicated software. Results: We found that the hallux valgus deformity evaluations on computer monitors had significantly lower inter-and intra-observer variations than the evaluations performed on printed images. This study validates the use of digital X-ray measurements on computer monitors with the guidance of dedicated software. for evaluation of hallux valgus deformity. Conclusion: Clinician can use digital images with the guidance of dedicated software to evaluate for deformities without a need to print the images.

JBJS Open Access, 2021

The ability to accurately predict postoperative outcomes is of considerable interest in the field of orthopaedic surgery. Machine learning has been used as a form of predictive modeling in multiple health-care settings. The purpose of the current study was to determine whether machine learning algorithms using preoperative data can predict improvement in American Shoulder and Elbow Surgeons (ASES) scores for patients with glenohumeral osteoarthritis (OA) at a minimum of 2 years after shoulder arthroplasty. Methods: This was a retrospective cohort study that included 472 patients (472 shoulders) diagnosed with primary glenohumeral OA (mean age, 68 years; 56% male) treated with shoulder arthroplasty (431 anatomic total shoulder arthroplasty and 41 reverse total shoulder arthroplasty). Preoperative computed tomography (CT) scans were used to classify patients on the basis of glenoid and rotator cuff morphology. Preoperative and final postoperative ASES scores were used to assess the level of improvement. Patients were separated into 3 improvement ranges of approximately equal size. Machine learning methods that related patterns of these variables to outcome ranges were employed. Three modeling approaches were compared: a model with the use of all baseline variables (Model 1), a model omitting morphological variables (Model 2), and a model omitting ASES variables (Model 3). Results: Improvement ranges of £28 points (class A), 29 to 55 points (class B), and >55 points (class C) were established. Using all follow-up time intervals, Model 1 gave the most accurate predictions, with probability values of 0.94, 0.95, and 0.94 for classes A, B, and C, respectively. This was followed by Model 2 (0.93, 0.80, and 0.73) and Model 3 (0.77, 0.72, and 0.71). Conclusions: Machine learning can accurately predict the level of improvement after shoulder arthroplasty for glenohumeral OA. This may allow physicians to improve patient satisfaction by better managing expectations. These predictions were most accurate when latent variables were combined with morphological variables, suggesting that both patients' perceptions and structural pathology are critical to optimizing outcomes in shoulder arthroplasty. Level of Evidence: Therapeutic Level IV. See Instructions for Authors for a complete description of levels of evidence. atient expectations can have a strong influence on postoperative outcomes and patient satisfaction in the field of orthopaedic surgery 1-3 . Studies from the total knee 4-7 , hip 7,8 , and shoulder 9-11 arthroplasty literature illustrate correlations between preoperative patient expectations and postoperative outcomes. Shoulder surgeons have endeavored to quantify preoperative patient factors that may influence outcomes, such as functional assessment measures 12 , soft-tissue integrity , and bone loss/wear symmetry . The myriad of assessment measures highlights both the importance and challenge of creating accurate, comprehensive predictive models for surgeons to anticipate outcomes, counsel patients, and manage expectations. Predictive modeling has attracted considerable interest in health care, particularly since the advent of electronic medical records containing troves of patient data 19 . Strategies for assimilating these vast data into meaningful clinical application Disclosure: DJO Surgical provided funding for this study to the Foundation for Orthopaedic Research and Education (F.O.R.E.). DJO Surgical did not have input into the design, data collection, analysis, or manuscript preparation. On the Disclosure of Potential Conflicts of Interest forms, which are provided with the online version of the article, one or more of the authors checked "yes" to indicate that the author had a relevant financial relationship in the biomedical arena outside the submitted work (including relationships with DJO Surgical) ().

Background: The most common methods for assessing severity of hallux valgus deformity and the effects of an operative procedure are the angular measurements in weightbearing radiographs, specifically the hallux valgus angle and intermetatarsal angle (IMA). Our objective was to analyze the interobserver variability in hallux valgus patients of a new angle called the "angle to be corrected" (ATC), and to compare its capacity to differentiate between different deformities against IMA. Methods: We included 28 symptomatic hallux valgus patients with 48 weightbearing foot x-rays. Three trained observers measured the 1 to 2 IMA and the ATC. We then identified retrospectively 45 hallux valgus patients, which were divided into 3 operative technique groups having used the ATC as reference, and analyzed the capacity of the IMA to differentiate between them. Results: The IMA average value was 13.6 degrees, and there was a significant difference between observer 3 and observer 1 (P = .001). The average value for the ATC was 8.9 degrees, and there was no difference between observers. Both angles showed a high intraclass correlation. Regarding the capacity to differentiate between operative technique groups, the ATC was different between the 3 operative technique groups analyzed, but the IMA showed differences only between 2.

Diagnostics

Artificial intelligence (AI) in medicine is a rapidly growing field. In orthopedics, the clinical implementations of AI have not yet reached their full potential. Deep learning algorithms have shown promising results in computed radiographs for fracture detection, classification of OA, bone age, as well as automated measurements of the lower extremities. Studies investigating the performance of AI compared to trained human readers often show equal or better results, although human validation is indispensable at the current standards. The objective of this narrative review is to give an overview of AI in medicine and summarize the current applications of AI in orthopedic radiography imaging. Due to the different AI software and study design, it is difficult to find a clear structure in this field. To produce more homogeneous studies, open-source access to AI software codes and a consensus on study design should be aimed for.