No abstract

No abstract

There is a pressing need for an automatic road extraction method due to the continuous development of transportation networks. Free from the influence of weather, satellitemounted synthetic-aperture radar (SAR) opens the way for such a road detection application. This study introduces an automatic discrimination method based on a deep neural network (DNN) adjusted for roads from dual-polarimetric (VV and VH) Sentinel-1 SAR imagery. In this proposed method, the U-Net extended the convolutional neural network (CNN), is adjusted for road extraction from SAR images. To investigate the potential of using the U-Net based fully convolutional neural network (FCN) for road extraction, LeNet-5, is applied as a preliminary DNN model. Additionally, several training optimizations are introduced to improve accuracy. To assess the performance of the different polarization modes used in road extraction, both single-polarimetric and dual-polarimetric data were investigated. Moreover, four machine learning algorithms have been compared for accuracy and speed. As a result, the outcome evaluation of Precision, Recall, and F 1 obtained by FCN is better than the original CNN, and the training time has been significantly reduced. The DNN model (CNN and FCN) is superior to machine learning methods in accuracy and elapsed computation time.

No abstract

To design an ensemble learning based prediction model using different breast DCE-MR post-contrast sequence images to distinguish two kinds of breast cancer subtypes (luminal and non-luminal). We retrospectively studied preoperative dynamic contrast enhanced-magnetic resonance imaging and molecular information of 266 breast cancer cases with either luminal subtype (luminal A and luminal B) or non-luminal subtype (human epidermal growth factor receptor 2 and triple negative). Then, multiple bounding boxes covering tumor lesions were acquired from three series of post-contrast DCE-MR sequence images which were determined by radiologists. Afterwards, three baseline convolutional neural networks (CNNs) with same architecture were concurrently trained, followed by preliminary prediction of probabilities from the testing database. Finally, the classification and evaluation of breast subtypes were realized by means of fusing predicted results from three CNNs employed via ensemble learning based on weighted voting. Taking advantage of 5-fold cross validation CV, the average prediction specificity, accuracy, precision and area under the ROC curve on testing dataset for the luminal versus non-luminal are 0.958, 0.852, 0.961, and 0.867, respectively, which empirically demonstrate that our proposed ensemble model has highly reliability and robustness. The breast DCE-MR post-contrast sequence image analysis utilizing the ensemble CNN model based on deep learning could show a valuable and extendible practical application on breast molecular subtype identification.