Abstract. Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve ðAUCÞ ¼ 0.81]. Further, the performance of ensemble classifiers based on both types was significantly better than that of either classifier type alone (AUC ¼ 0.86 versus 0.81, p ¼ 0.022). We conclude that transfer learning can improve current CADx methods while also providing standalone classifiers without large datasets, facilitating machine-learning methods in radiomics and precision medicine.

No abstract

Text spotting in natural scene images is of great importance for many image understanding tasks. It includes two sub-tasks: text detection and recognition. In this work, we propose a unified network that simultaneously localizes and recognizes text with a single forward pass, avoiding intermediate processes such as image cropping and feature re-calculation, word separation, and character grouping.In contrast to existing approaches that consider text detection and recognition as two distinct tasks and tackle them one by one, the proposed framework settles these two tasks concurrently. The whole framework can be trained end-to-end and is able to handle text of arbitrary shapes. The convolutional features are calculated only once and shared by both detection and recognition modules. Through multi-task training, the learned features become more discriminate and improve the overall performance. By employing the 2D attention model in word recognition, the irregularity of text can be robustly addressed. It provides the spatial location for each character, which not only helps local feature extraction in word recognition, but also indicates an orientation angle to refine text localization. We show that our proposed method can achieve state-of-the-art performance on several widely-used text spotting benchmarks, including both regular and irregular datasets.

We report a method that uses the process of selective withdrawal of one fluid through a second immiscible fluid to coat small particles with polymer films. Fluid is withdrawn through a tube with its orifice slightly above a water-oil interface. Upon increasing the flow rate, there is a transition from a state where only oil is withdrawn to a state where the water, containing the particles to be coated and appropriate prepolymer reagents, is entrained in a thin spout along with the oil. The entrained particles eventually cause the spout interface to break, producing a thin coat of controllable thickness around each particle, which can be subsequently polymerized using chemical reagents, light, or heat. This method allows flexibility in the chemical composition and thickness of the conformal coatings.