RESUMEN
Buzzwire tasks are often used as benchmarks and as training environments for fine motor skills and high precision path following. These tasks require moving a wire loop along an arbitrarily shaped wire obstacle in a collision-free manner. While there have been some demonstrations of buzzwire tasks with robotic manipulators using reinforcement learning and admittance control, there does not seem to be any examples with humanoid robots. In this work, we consider the scenario where we control one arm of the REEM-C humanoid robot, with other joints fixed, as groundwork for eventual full-body control. In pursuit of this, we contribute by designing an optimal control problem that generates trajectories to solve the buzzwire in a time optimized manner. This is composed of task-space constraints to prevent collisions with the buzzwire obstacle, the physical limits of the robot, and an objective function to trade-off reducing time and increasing margins from collision. The formulation can be applied to a very general set of wire shapes and the objective and task constraints can be adapted to other hardware configurations. We evaluate this formulation using the arm of a REEM-C humanoid robot and provide an analysis of how the generated trajectories perform both in simulation and on hardware.
RESUMEN
PURPOSE: Multiparametric MRI (mp-MRI) is a widely used tool for diagnosing and staging prostate cancer. The purpose of this study was to evaluate whether transfer learning, unsupervised pre-training and test-time augmentation significantly improved the performance of a convolutional neural network (CNN) for pixel-by-pixel prediction of cancer vs. non-cancer using mp-MRI datasets. METHODS: 154 subjects undergoing mp-MRI were prospectively recruited, 16 of whom subsequently underwent radical prostatectomy. Logistic regression, random forest and CNN models were trained on mp-MRI data using histopathology as the gold standard. Transfer learning, unsupervised pre-training and test-time augmentation were used to boost CNN performance. Models were evaluated using Dice score and area under the receiver operating curve (AUROC) with leave-one-subject-out cross validation. Permutation feature importance testing was performed to evaluate the relative value of each MR contrast to CNN model performance. Statistical significance (p<0.05) was determined using the paired Wilcoxon signed rank test with Benjamini-Hochberg correction for multiple comparisons. RESULTS: Baseline CNN outperformed logistic regression and random forest models. Transfer learning and unsupervised pre-training did not significantly improve CNN performance over baseline; however, test-time augmentation resulted in significantly higher Dice scores over both baseline CNN and CNN plus either of transfer learning or unsupervised pre-training. The best performing model was CNN with transfer learning and test-time augmentation (Dice score of 0.59 and AUROC of 0.93). The most important contrast was apparent diffusion coefficient (ADC), followed by Ktrans and T2, although each contributed significantly to classifier performance. CONCLUSIONS: The addition of transfer learning and test-time augmentation resulted in significant improvement in CNN segmentation performance in a small set of prostate cancer mp-MRI data. Results suggest that these techniques may be more broadly useful for the optimization of deep learning algorithms applied to the problem of semantic segmentation in biomedical image datasets. However, further work is needed to improve the generalizability of the specific model presented herein.
Asunto(s)
Neoplasias de la Próstata , Semántica , Humanos , Procesamiento de Imagen Asistido por Computador , Aprendizaje Automático , Imagen por Resonancia Magnética , Masculino , Redes Neurales de la Computación , Neoplasias de la Próstata/diagnóstico por imagenRESUMEN
Dynamic contrast enhanced (DCE) magnetic resonance imaging (MRI) is a method of temporal imaging that is commonly used to aid in prostate cancer (PCa) diagnosis and staging. Typically, machine learning models designed for the segmentation and detection of PCa will use an engineered scalar image called Ktrans to summarize the information in the DCE time-series images. This work proposes a new model that amalgamates the U-net and the convGRU neural network architectures for the purpose of interpreting DCE time-series in a temporal and spatial basis for segmenting PCa in MR images. Ultimately, experiments show that the proposed model using the DCE time-series images can outperform a baseline U-net segmentation model using Ktrans. However, when other types of scalar MR images are considered by the models, no significant advantage is observed for the proposed model.