This paper addresses weakly supervised object detection with only image-level supervision at training stage. Previous approaches train detection models with entire images all at once, making the models prone to being trapped in sub-optimums due to the introduced false positive examples. Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds. Towards this goal, we first develop a criterion named mean Energy Accumulation Scores (mEAS) to automatically measure and rank localization difficulty of an image containing the target object, and accordingly learn the detector progressively by feeding examples with increasing difficulty. In this way, the model can be well prepared by training on easy examples for learning from more difficult ones and thus gain a stronger detection ability more efficiently. Furthermore, we introduce a novel masking regularization strategy over the high level convolutional feature maps to avoid overfitting initial samples. These two modules formulate a zigzag learning process, where progressive learning endeavors to discover reliable object instances, and masking regularization increases the difficulty of finding object instances properly. We achieve 47.6% mAP on PASCAL VOC 2007, surpassing the state-of-the-arts by a large margin.
Background: Endobronchial ultrasound (EBUS) elastography is a new imaging procedure for describing the elasticity of intrathoracic lesions and providing important additional diagnostic information. Objectives: The aim of this study was to utilize the feasibility of qualitative and quantitative methods to evaluate the ability of EBUS elastography to differentiate between benign and malignant mediastinal and hilar lymph nodes (LNs) during EBUS-guided transbronchial needle aspiration (EBUS-TBNA). Methods: Patients with enlarged intrathoracic LNs required for EBUS-TBNA examination at a clinical center for thoracic medicine from January 2014 to April 2014 were prospectively enrolled. EBUS sonographic characteristics on B-mode, vascular patterns and elastography, EBUS-TBNA procedures, pathological findings, and microbiological results were recorded. Furthermore, elastographic patterns (qualitative method) and the mean gray value inside the region of interest (quantitative method) were analyzed. Both methods were compared with a definitive diagnosis of the involved LNs. Results: Fifty-six patients including 68 LNs (33 benign and 35 malignant nodes) were prospectively enrolled into this study and retrospectively analyzed. Using qualitative and quantitative methods, we were able to differentiate between benign and malignant LNs with high sensitivity, specificity, positive and negative predictive values, and accuracy (85.71, 81.82, 83.33, 84.38, and 83.82% vs. 91.43, 72.73, 78.05, 88.89, and 82.35%, respectively). Conclusions: EBUS elastography is potentially capable of further differentiating between benign and malignant LNs. These proposed qualitative and quantitative methods might be useful tools for describing EBUS elastography during EBUS-TBNA.
Motivation: Genome-wide association studies (GWAS) have been widely used in discovering the association between genotypes and phenotypes. Human genome data contain valuable but highly sensitive information. Unprotected disclosure of such information might put individual's privacy at risk. It is important to protect human genome data. Exact logistic regression is a bias-reduction method based on a penalized likelihood to discover rare variants that are associated with disease susceptibility. We propose the HEALER framework to facilitate secure rare variants analysis with a small sample size. Results: We target at the algorithm design aiming at reducing the computational and storage costs to learn a homomorphic exact logistic regression model (i.e. evaluate P-values of coefficients), where the circuit depth is proportional to the logarithmic scale of data size. We evaluate the algorithm performance using rare Kawasaki Disease datasets. Availability and implementation: Download HEALER at http://research.ucsd-dbmi.org/HEALER/
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.