METHODS: One hundred computed tomography scans of disease-free knees were analyzed. A 3-dimensional reconstructed image of the tibia was generated and aligned to its anatomic axis in the coronal and sagittal planes. The tibia was then rotationally aligned to the tibial plateau (tibial centroid axis) and PTS was measured from best-fit planes on the surface of the proximal tibia and individually for the medial and lateral plateaus. This was then repeated with the tibia rotationally aligned to the ankle (transmalleolar axis).
RESULTS: When rotationally aligned to the tibial plateau, the mean PTS, medial PTS, and lateral PTS were 11.2° ± 3.0 (range, 4.7°-17.7°), 11.3° ± 3.2 (range, 2.7°-19.7°), and 10.9° ± 3.7 (range, 3.5°-19.4°), respectively. When rotationally aligned to the ankle, the mean PTS, medial PTS, and lateral PTS were 11.4° ± 3.0 (range, 5.3°-19.3°), 13.9° ± 3.7 (range, 3.1°-24.4°), and 9.7° ± 3.6 (range, 0.8°-17.7°), respectively.
CONCLUSION: The PTS in the normal Asian knee is on average 11° (mean) with a reference range of 5°-17° (mean ± 2 standard deviation). This has implications to surgery and implant design.
DESIGN: Artificial intelligence (neural network) study.
METHODS: We assessed 1400 OCT scans of patients with neovascular AMD. Fifteen physical features for each eligible OCT, as well as patient age, were used as input data and corresponding recorded visual acuity as the target data to train, validate, and test a supervised neural network. We then applied this network to model the impact on acuity of defined OCT changes in subretinal fluid, subretinal hyperreflective material, and loss of external limiting membrane (ELM) integrity.
RESULTS: A total of 1210 eligible OCT scans were analyzed, resulting in 1210 data points, which were each 16-dimensional. A 10-layer feed-forward neural network with 1 hidden layer of 10 neurons was trained to predict acuity and demonstrated a root mean square error of 8.2 letters for predicted compared to actual visual acuity and a mean regression coefficient of 0.85. A virtual model using this network demonstrated the relationship of visual acuity to specific, programmed changes in OCT characteristics. When ELM is intact, there is a shallow decline in acuity with increasing subretinal fluid but a much steeper decline with equivalent increasing subretinal hyperreflective material. When ELM is not intact, all visual acuities are reduced. Increasing subretinal hyperreflective material or subretinal fluid in this circumstance reduces vision further still, but with a smaller gradient than when ELM is intact.
CONCLUSIONS: The supervised machine learning neural network developed is able to generate an estimated visual acuity value from OCT images in a population of patients with AMD. These findings should be of clinical and research interest in macular degeneration, for example in estimating visual prognosis or highlighting the importance of developing treatments targeting more visually destructive pathologies.