Search

Oral leukoplakia (OL) has an inherent disposition to develop oral cancer. OL with epithelial dysplasia (OED) is significantly likely to undergo malignant transformation; however, routine OED assessment is invasive and challenging. This study investigated whether a deep learning (DL) model can predict dysplasia probability among patients with leukoplakia using oral photographs. In addition, we assessed the performance of the DL model in comparison with clinicians' ratings and in providing decision support on dysplasia assessment. Retrospective images of leukoplakia taken before biopsy/histopathology were obtained to construct the DL model (n = 2,073). OED status following histopathology was used as the gold standard for all images. We first developed, fine-tuned, and internally validated a DL architecture with an EfficientNet-B2 backbone that outputs the predicted probability of OED, OED status, and regions-of-interest heat maps. Then, we tested the performance of the DL model on a temporal cohort before geographical validation. We also assessed the model's performance at external validation with opinions provided by human raters on OED status. Performance evaluation included discrimination, calibration, and potential net benefit. The DL model achieved good Brier scores, areas under the curve, and balanced accuracies of 0.124 (0.079–0.169), 0.882 (0.838–0.926), and 81.8% (76.5–87.1) at testing and 0.146 (0.112–0.18), 0.828 (0.792–0.864), and 76.4% (72.3–80.5) at external validation, respectively. In addition, the model had a higher potential net benefit in selecting patients with OL for biopsy/histopathology during OED assessment than when biopsies were performed for all patients. External validation also showed that the DL model had better accuracy than 92.3% (24/26) of human raters in classifying the OED status of leukoplakia from oral images (balanced accuracy: 54.8%–79.7%). Overall, the photograph-based intelligent model can predict OED probability and status in leukoplakia with good calibration and discrimination, which shows potential for decision support to select patients for biopsy/histopathology, obviate unnecessary biopsy, and assist in patient self-monitoring. [ABSTRACT FROM AUTHOR]

Based on the fact that numerical integration can provide more stable and accurate results than numerical differentiation in the presence of noise, a constructive nonlinear velocity estimator (NVE) with simple computation is developed for high-quality instantaneous velocity estimation, based on the position measurement only. The attraction of the new velocity estimator is that it is very effective as well in the low-velocity ranges, it has high robustness against noise and design parameters, and it is easy to implement. Furthermore, the developed approach is model free. Both simulation and experimental tests have been run to verify its effectiveness and efficiency. The proposed new simple NVE has built a solid base for high-performance control of servo systems. Index Terms--Extended state observer, low-velocity range, motion control, velocity estimator.

A highly robust automatic disturbances rejection controller (ADRC) is developed to implement high-precision motion control of permanent-magnet synchronous motors. The proposed ADRC consists of a tracking differentiator (TD) in the feedforward path, an extended state observer (ESO), and a nonlinear proportional derivative control in the feedback path. The TD solves the difficulties posed by low-order reference trajectories which are quantized at the sensor resolution, and the ESO provides the estimate of the unmeasured system's state and the real action of the unknown disturbances only based on a measurement output of the system. Simulations and experimental results show that the proposed ADRC achieves a better position response and is robust to parameter variation and load disturbance. Furthermore, the ADRC is designed directly in discrete time with a simple structure and fast computation, which make it widely applicable to all other types of derives. Index Terms--Disturbance rejection, friction compensation, nonlinear proportional derivative (NPD) control, observers, permanent-magnet synchronous (PMAC) motor.