Development of LuxIA, a Cloud-Based AI Diabetic Retinopathy Screening Tool Using a Single Color Fundus Image.

Purpose: Diabetic retinopathy (DR) is the leading cause of vision impairment in working-age adults. Automated screening can increase DR detection at early stages at relatively low costs. We developed and evaluated a cloud-based screening tool that uses artificial intelligence (AI), the LuxIA algorithm, to detect DR from a single fundus image. Methods: Color fundus images that were previously graded by expert readers were collected from the Canarian Health Service (Retisalud) and used to train LuxIA, a deep-learning-based algorithm for the detection of more than mild DR. The algorithm was deployed in the Discovery cloud platform to evaluate each test set. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve were computed using a bootstrapping method to evaluate the algorithm performance and compared through different publicly available datasets. A usability test was performed to assess the integration into a clinical tool. Results: Three separate datasets, Messidor-2, APTOS, and a holdout set from Retisalud were evaluated. Mean sensitivity and specificity with 95% confidence intervals (CIs) reached for these three datasets were 0.901 (0.901-0.902) and 0.955 (0.955-0.956), 0.995 (0.995-0.995) and 0.821 (0.821-0.823), and 0.911 (0.907-0.912) and 0.880 (0.879-0.880), respectively. The usability test confirmed the successful integration of LuxIA into Discovery. Conclusions: Clinical data were used to train the deep-learning-based algorithm LuxIA to an expert-level performance. The whole process (image uploading and analysis) was integrated into the cloud-based platform Discovery, allowing more patients to have access to expert-level screening tools. Translational Relevance: Using the cloud-based LuxIA tool as part of a screening program may give diabetic patients greater access to specialist-level decisions, without the need for consultation.

Evaluation of Load-To-Strength Ratios in Metastatic Vertebrae and Comparison With Age- and Sex-Matched Healthy Individuals.

Vertebrae containing osteolytic and osteosclerotic bone metastases undergo pathologic vertebral fracture (PVF) when the lesioned vertebrae fail to carry daily loads. We hypothesize that task-specific spinal loading patterns amplify the risk of PVF, with a higher degree of risk in osteolytic than in osteosclerotic vertebrae. To test this hypothesis, we obtained clinical CT images of 11 cadaveric spines with bone metastases, estimated the individual vertebral strength from the CT data, and created spine-specific musculoskeletal models from the CT data. We established a musculoskeletal model for each spine to compute vertebral loading for natural standing, natural standing + weights, forward flexion + weights, and lateral bending + weights and derived the individual vertebral load-to-strength ratio (LSR). For each activity, we compared the metastatic spines' predicted LSRs with the normative LSRs generated from a population-based sample of 250 men and women of comparable ages. Bone metastases classification significantly affected the CT-estimated vertebral strength (Kruskal-Wallis, p < 0.0001). Post-test analysis showed that the estimated vertebral strength of osteosclerotic and mixed metastases vertebrae was significantly higher than that of osteolytic vertebrae (p = 0.0016 and p = 0.0003) or vertebrae without radiographic evidence of bone metastasis (p = 0.0010 and p = 0.0003). Compared with the median (50%) LSRs of the normative dataset, osteolytic vertebrae had higher median (50%) LSRs under natural standing (p = 0.0375), natural standing + weights (p = 0.0118), and lateral bending + weights (p = 0.0111). Surprisingly, vertebrae showing minimal radiographic evidence of bone metastasis presented significantly higher median (50%) LSRs under natural standing (p < 0.0001) and lateral bending + weights (p = 0.0009) than the normative dataset. Osteosclerotic vertebrae had lower median (50%) LSRs under natural standing (p < 0.0001), natural standing + weights (p = 0.0005), forward flexion + weights (p < 0.0001), and lateral bending + weights (p = 0.0002), a trend shared by vertebrae with mixed lesions. This study is the first to apply musculoskeletal modeling to estimate individual vertebral loading in pathologic spines and highlights the role of task-specific loading in augmenting PVF risk associated with specific bone metastatic types. Our finding of high LSRs in vertebrae without radiologically observed bone metastasis highlights that patients with metastatic spine disease could be at an increased risk of vertebral fractures even at levels where lesions have not been identified radiologically.

Influence of Metastatic Bone Lesion Type and Tumor Origin on Human Vertebral Bone Architecture, Matrix Quality, and Mechanical Properties.

Metastatic spine disease is incurable, causing increased vertebral fracture risk and severe patient morbidity. Here, we demonstrate that osteolytic, osteosclerotic, and mixed bone metastasis uniquely modify human vertebral bone architecture and quality, affecting vertebral strength and stiffness. Multivariable analysis showed bone metastasis type dominates vertebral strength and stiffness changes, with neither age nor gender having an independent effect. In osteolytic vertebrae, bone architecture rarefaction, lower tissue mineral content and connectivity, and accumulation of advanced glycation end-products (AGEs) affected low vertebral strength and stiffness. In osteosclerotic vertebrae, high trabecular number and thickness but low AGEs, suggesting a high degree of bone remodeling, yielded high vertebral strength. Our study found that bone metastasis from prostate and breast primary cancers differentially impacted the osteosclerotic bone microenvironment, yielding altered bone architecture and accumulation of AGEs. These findings indicate that therapeutic approaches should target the restoration of bone structural integrity. © 2022 American Society for Bone and Mineral Research (ASBMR).

Improved estimates of strength and stiffness in pathologic vertebrae with bone metastases using CT-derived bone density compared with radiographic bone lesion quality classification.

OBJECTIVE: The aim of this study was to compare the ability of 1) CT-derived bone lesion quality (classification of vertebral bone metastases [BM]) and 2) computed CT-measured volumetric bone mineral density (vBMD) for evaluating the strength and stiffness of cadaver vertebrae from donors with metastatic spinal disease. METHODS: Forty-five thoracic and lumbar vertebrae were obtained from cadaver spines of 11 donors with breast, esophageal, kidney, lung, or prostate cancer. Each vertebra was imaged using microCT (21.4 µm), vBMD, and bone volume to total volume were computed, and compressive strength and stiffness experimentally measured. The microCT images were reconstructed at 1-mm voxel size to simulate axial and sagittal clinical CT images. Five expert clinicians blindly classified the images according to bone lesion quality (osteolytic, osteoblastic, mixed, or healthy). Fleiss' kappa test was used to test agreement among 5 clinical raters for classifying bone lesion quality. Kruskal-Wallis ANOVA was used to test the difference in vertebral strength and stiffness based on bone lesion quality. Multivariable regression analysis was used to test the independent contribution of bone lesion quality, computed vBMD, age, gender, and race for predicting vertebral strength and stiffness. RESULTS: A low interrater agreement was found for bone lesion quality (κ = 0.19). Although the osteoblastic vertebrae showed significantly higher strength than osteolytic vertebrae (p = 0.0148), the multivariable analysis showed that bone lesion quality explained 19% of the variability in vertebral strength and 13% in vertebral stiffness. The computed vBMD explained 75% of vertebral strength (p < 0.0001) and 48% of stiffness (p < 0.0001) variability. The type of BM affected vBMD-based estimates of vertebral strength, explaining 75% of strength variability in osteoblastic vertebrae (R2 = 0.75, p < 0.0001) but only 41% in vertebrae with mixed bone metastasis (R2 = 0.41, p = 0.0168), and 39% in osteolytic vertebrae (R2 = 0.39, p = 0.0381). For vertebral stiffness, vBMD was only associated with that of osteoblastic vertebrae (R2 = 0.44, p = 0.0024). Age and race inconsistently affected the model's strength and stiffness predictions. CONCLUSIONS: Pathologic vertebral fracture occurs when the metastatic lesion degrades vertebral strength, rendering it unable to carry daily loads. This study demonstrated the limitation of qualitative clinical classification of bone lesion quality for predicting pathologic vertebral strength and stiffness. Computed CT-derived vBMD more reliably estimated vertebral strength and stiffness. Replacing the qualitative clinical classification with computed vBMD estimates may improve the prediction of vertebral fracture risk.

Conventional finite element models estimate the strength of metastatic human vertebrae despite alterations of the bone's tissue and structure.

INTRODUCTION: Pathologic vertebral fractures are a major clinical concern in the management of cancer patients with metastatic spine disease. These fractures are a direct consequence of the effect of bone metastases on the anatomy and structure of the vertebral bone. The goals of this study were twofold. First, we evaluated the effect of lytic, blastic and mixed (both lytic and blastic) metastases on the bone structure, on its material properties, and on the overall vertebral strength. Second, we tested the ability of bone mineral content (BMC) measurements and standard FE methodologies to predict the strength of real metastatic vertebral bodies. METHODS: Fifty-seven vertebral bodies from eleven cadaver spines containing lytic, blastic, and mixed metastatic lesions from donors with breast, esophageal, kidney, lung, or prostate cancer were scanned using micro-computed tomography (µCT). Based on radiographic review, twelve vertebrae were selected for nanoindentation testing, while the remaining forty-five vertebrae were used for assessing their compressive strength. The µCT reconstruction was exploited to measure the vertebral BMC and to establish two finite element models. 1) a micro finite element (µFE) model derived at an image resolution of 24.5 µm and 2) homogenized FE (hFE) model derived at a resolution of 0.98 mm. Statistical analyses were conducted to measure the effect of the bone metastases on BV/TV, indentation modulus (Eit), ratio of plastic/total work (WPl/Wtot), and in vitro vertebral strength (Fexp). The predictive value of BMC, µFE stiffness, and hFE strength were evaluated against the in vitro measurements. RESULTS: Blastic vertebral bodies exhibit significantly higher BV/TV compared to the mixed (p = 0.0205) and lytic (p = 0.0216) vertebral bodies. No significant differences were found between lytic and mixed vertebrae (p = 0.7584). Blastic bone tissue exhibited a 5.8% lower median Eit (p< 0.001) and a 3.3% lower median Wpl/Wtot (p<0.001) compared to non-involved bone tissue. No significant differences were measured between lytic and non-involved bone tissues. Fexp ranged from 1.9 to 13.8 kN, was strongly associated with hFE strength (R2=0.78, p< 0.001) and moderately associated with BMC (R2=0.66, p< 0.001) and µFE stiffness (R2=0.66, p< 0.001), independently of the lesion type. DISCUSSION: Our findings show that tumour-induced osteoblastic metastases lead to slightly, but significantly lower bone tissue properties compared to controls, while osteolytic lesions appear to have a negligible impact. These effects may be attributed to the lower mineralization and woven nature of bone forming in blastic lesions whilst the material properties of bone in osteolytic vertebrae appeared little changed. The moderate association between BMC- and FE-based predictions to fracture strength suggest that vertebral strength is affected by the changes of bone mass induced by the metastatic lesions, rather than altered tissue properties. In a broader context, standard hFE approaches generated from CTs at clinical resolution are robust to the lesion type when predicting vertebral strength. These findings open the door for the development of FE-based prediction tools that overcomes the limitations of BMC in accounting for shape and size of the metastatic lesions. Such tools may help clinicians to decide whether a patient needs the prophylactic fixation of an impending fracture.

Finite element models can reproduce the effect of nucleotomy on the multi-axial compliance of human intervertebral discs.

Finite element (FE) models can unravel the link between intervertebral disc (IVD) degeneration and its mechanical behaviour. Nucleotomy may provide the data required for model verification. Three human IVDs were scanned with MRI and tested in multiple loading scenarios, prior and post nucleotomy. The resulting data was used to generate, calibrate, and verify the FE models. Nucleotomy increased the experimental range of motion by 26%, a result reproduced by the FE simulation within a 5% error. This work demonstrates the ability of FE models to reproduce the mechanical compliance of human IVDs prior and post nucleotomy.

Integrating MRI-based geometry, composition and fiber architecture in a finite element model of the human intervertebral disc.

Intervertebral disc degeneration is a common disease that is often related to impaired mechanical function, herniations and chronic back pain. The degenerative process induces alterations of the disc's shape, composition and structure that can be visualized in vivo using magnetic resonance imaging (MRI). Numerical tools such as finite element analysis (FEA) have the potential to relate MRI-based information to the altered mechanical behavior of the disc. However, in terms of geometry, composition and fiber architecture, current FE models rely on observations made on healthy discs and might therefore not be well suited to study the degeneration process. To address the issue, we propose a new, more realistic FE methodology based on diffusion tensor imaging (DTI). For this study, a human disc joint was imaged in a high-field MR scanner with proton-density weighted (PD) and DTI sequences. The PD image was segmented and an anatomy-specific mesh was generated. Assuming accordance between local principal diffusion direction and local mean collagen fiber alignment, corresponding fiber angles were assigned to each element. Those element-wise fiber directions and PD intensities allowed the homogenized model to smoothly account for composition and fibrous structure of the disc. The disc's in vitro mechanical behavior was quantified under tension, compression, flexion, extension, lateral bending and rotation. The six resulting load-displacement curves could be replicated by the FE model, which supports our approach as a first proof of concept towards patient-specific disc modeling.