Heterogenous thinning of peripapillary tissues occurs early during high myopia development in juvenile tree shrews.

Myopia is an independent risk factor for glaucoma, but the link between both conditions remains unknown. Both conditions induce connective tissue remodeling at the optic nerve head (ONH), including the peripapillary tissues. The purpose of this study was to investigate the thickness changes of the peripapillary tissues during experimental high myopia development in juvenile tree shrews. Six juvenile tree shrews experienced binocular normal vision, while nine received monocular -10D lens treatment starting at 24 days of visual experience (DVE) to induce high myopia in one eye and the other eye served as control. Daily refractive and biometric measurements and weekly optical coherence tomography scans of the ONH were obtained for five weeks. Peripapillary sclera (Scl), choroid-retinal pigment epithelium complex (Ch-RPE), retinal nerve fiber layer (RNFL), and remaining retinal layers (RRL) were auto-segmented using a deep learning algorithm after nonlinear distortion correction. Peripapillary thickness values were quantified from 3D reconstructed segmentations. All lens-treated eyes developed high myopia (-9.8 ± 1.5 D), significantly different (P < 0.001) from normal (0.69 ± 0.45 D) and control eyes (0.76 ± 1.44 D). Myopic eyes showed significant thinning of all peripapillary tissues compared to both, normal and control eyes (P < 0.001). At the experimental end point, the relative thinning from baseline was heterogeneous across tissues and significantly more pronounced in the Scl (-8.95 ± 3.1%) and Ch-RPE (-16.8 ± 5.8%) when compared to the RNFL (-5.5 ± 1.6%) and RRL (-6.7 ± 1.8%). Furthermore, while axial length increased significantly throughout the five weeks of lens wear, significant peripapillary tissue thinning occurred only during the first week of the experiment (until a refraction of -2.5 ± 1.9 D was reached) and ceased thereafter. A sectorial analysis revealed no clear pattern. In conclusion, our data show that in juvenile tree shrews, experimental high myopia induces significant and heterogeneous thinning of the peripapillary tissues, where the retina seems to be protected from profound thickness changes as seen in Ch-RPE and Scl. Peripapillary tissue thinning occurs early during high myopia development despite continued progression of axial elongation. The observed heterogeneous thinning may contribute to the increased risk for pathological optic nerve head remodeling and glaucoma later in life.

Demystifying Statistics and Machine Learning in Analysis of Structured Tabular Data.

Electronic health records have facilitated the extraction and analysis of a vast amount of data with many variables for clinical care and research. Conventional regression-based statistical methods may not capture all the complexities in high-dimensional data analysis. Therefore, researchers are increasingly using machine learning (ML)-based methods to better handle these more challenging datasets for the discovery of hidden patterns in patients' data and for classification and predictive purposes. This article describes commonly used ML methods in structured data analysis with examples in orthopedic surgery. We present practical considerations in starting an ML project and appraising published studies in this field.

An Overview of Machine Learning in Orthopedic Surgery: An Educational Paper.

The growth of artificial intelligence combined with the collection and storage of large amounts of data in the electronic medical record collection has created an opportunity for orthopedic research and translation into the clinical environment. Machine learning (ML) is a type of artificial intelligence tool well suited for processing the large amount of available data. Specific areas of ML frequently used by orthopedic surgeons performing total joint arthroplasty include tabular data analysis (spreadsheets), medical imaging processing, and natural language processing (extracting concepts from text). Previous studies have discussed models able to identify fractures in radiographs, identify implant type in radiographs, and determine the stage of osteoarthritis based on walking analysis. Despite the growing popularity of ML, there are limitations including its reliance on "good" data, potential for overfitting, long life cycle for creation, and ability to only perform one narrow task. This educational article will further discuss a general overview of ML, discussing these challenges and including examples of successfully published models.

Application of Natural Language Processing in Total Joint Arthroplasty: Opportunities and Challenges.

Total joint arthroplasty is becoming one of the most common surgeries within the United States, creating an abundance of analyzable data to improve patient experience and outcomes. Unfortunately, a large majority of this data is concealed in electronic health records only accessible by manual extraction, which takes extensive time and resources. Natural language processing (NLP), a field within artificial intelligence, may offer a viable alternative to manual extraction. Using NLP, a researcher can analyze written and spoken data and extract data in an organized manner suitable for future research and clinical use. This article will first discuss common subtasks involved in an NLP pipeline, including data preparation, modeling, analysis, and external validation, followed by examples of NLP projects. Challenges and limitations of NLP will be discussed, closing with future directions of NLP projects, including large language models.

Educational Overview of the Concept and Application of Computer Vision in Arthroplasty.

Image data has grown exponentially as systems have increased their ability to collect and store it. Unfortunately, there are limits to human resources both in time and knowledge to fully interpret and manage that data. Computer Vision (CV) has grown in popularity as a discipline for better understanding visual data. Computer Vision has become a powerful tool for imaging analytics in orthopedic surgery, allowing computers to evaluate large volumes of image data with greater nuance than previously possible. Nevertheless, even with the growing number of uses in medicine, literature on the fundamentals of CV and its implementation is mainly oriented toward computer scientists rather than clinicians, rendering CV unapproachable for most orthopedic surgeons as a tool for clinical practice and research. The purpose of this article is to summarize and review the fundamental concepts of CV application for the orthopedic surgeon and musculoskeletal researcher.

Artificial intelligence assisted whole organ pancreatic fat estimation on magnetic resonance imaging and correlation with pancreas attenuation on computed tomography.

BACKGROUND: Fatty pancreas is associated with inflammatory and neoplastic pancreatic diseases. Magnetic resonance imaging (MRI) is the diagnostic modality of choice for measuring pancreatic fat. Measurements typically use regions of interest limited by sampling and variability. We have previously described an artificial intelligence (AI)-aided approach for whole pancreas fat estimation on computed tomography (CT). In this study, we aimed to assess the correlation between whole pancreas MRI proton-density fat fraction (MR-PDFF) and CT attenuation. METHODS: We identified patients without pancreatic disease who underwent both MRI and CT between January 1, 2015 and June 1, 2020. 158 paired MRI and CT scans were available for pancreas segmentation using an iteratively trained convolutional neural network (CNN) with manual correction. Boxplots were generated to visualize slice-by-slice variability in 2D-axial slice MR-PDFF. Correlation between whole pancreas MR-PDFF and age, BMI, hepatic fat and pancreas CT-Hounsfield Unit (CT-HU) was assessed. RESULTS: Mean pancreatic MR-PDFF showed a strong inverse correlation (Spearman -0.755) with mean CT-HU. MR-PDFF was higher in males (25.22 vs 20.87; p = 0.0015) and in subjects with diabetes mellitus (25.95 vs 22.17; p = 0.0324), and was positively correlated with age and BMI. The pancreatic 2D-axial slice-to-slice MR-PDFF variability increased with increasing mean whole pancreas MR-PDFF (Spearman 0.51; p < 0.0001). CONCLUSION: Our study demonstrates a strong inverse correlation between whole pancreas MR-PDFF and CT-HU, indicating that both imaging modalities can be used to assess pancreatic fat. 2D-axial pancreas MR-PDFF is variable across slices, underscoring the need for AI-aided whole-organ measurements for objective and reproducible estimation of pancreatic fat.

Longitudinal Changes of Bruch's Membrane Opening, Anterior Scleral Canal Opening, and Border Tissue in Experimental Juvenile High Myopia.

Purpose: To investigate the relative positional changes between the Bruch's membrane opening (BMO) and the anterior scleral canal opening (ASCO), and border tissue configuration changes during experimental high myopia development in juvenile tree shrews. Methods: Juvenile tree shrews were assigned randomly to two groups: binocular normal vision (n = 9) and monocular -10 D lens treatment starting at 24 days of visual experience to induce high myopia in one eye while the other eye served as control (n = 12). Refractive and biometric measurements were obtained daily, and 48 radial optical coherence tomography B-scans through the center of the optic nerve head were obtained weekly for 6 weeks. ASCO and BMO were segmented manually after nonlinear distortion correction. Results: Lens-treated eyes developed high degree of axial myopia (-9.76 ± 1.19 D), significantly different (P < 0.001) from normal (0.34 ± 0.97 D) and control eyes (0.39 ± 0.88 D). ASCO-BMO centroid offset gradually increased and became significantly larger in the experimental high myopia group compared with normal and control eyes (P < 0.0001) with an inferonasal directional preference. The border tissue showed a significantly higher tendency of change from internally to externally oblique configuration in the experimental high myopic eyes in four sectors: nasal, inferonasal, inferior, and inferotemporal (P < 0.005). Conclusions: During experimental high myopia development, progressive relative deformations of ASCO and BMO occur simultaneously with changes in border tissue configuration from internally to externally oblique in sectors that are close to the posterior pole (nasal in tree shrews). These asymmetric changes may contribute to pathologic optic nerve head remodeling and an increased risk of glaucoma later in life.

Mitigating Bias in Radiology Machine Learning: 2. Model Development.

There are increasing concerns about the bias and fairness of artificial intelligence (AI) models as they are put into clinical practice. Among the steps for implementing machine learning tools into clinical workflow, model development is an important stage where different types of biases can occur. This report focuses on four aspects of model development where such bias may arise: data augmentation, model and loss function, optimizers, and transfer learning. This report emphasizes appropriate considerations and practices that can mitigate biases in radiology AI studies. Keywords: Model, Bias, Machine Learning, Deep Learning, Radiology © RSNA, 2022.

Mitigating Bias in Radiology Machine Learning: 3. Performance Metrics.

The increasing use of machine learning (ML) algorithms in clinical settings raises concerns about bias in ML models. Bias can arise at any step of ML creation, including data handling, model development, and performance evaluation. Potential biases in the ML model can be minimized by implementing these steps correctly. This report focuses on performance evaluation and discusses model fitness, as well as a set of performance evaluation toolboxes: namely, performance metrics, performance interpretation maps, and uncertainty quantification. By discussing the strengths and limitations of each toolbox, our report highlights strategies and considerations to mitigate and detect biases during performance evaluations of radiology artificial intelligence models. Keywords: Segmentation, Diagnosis, Convolutional Neural Network (CNN) © RSNA, 2022.