No abstract

Computer-aided diagnosis systems with deep learning frameworks have been used to identify benign and malignant pulmonary nodules in lung cancer diagnosis. It's commonly known that a premise of training complex deep neural nets is the large-scale labeled datasets. However, the abundance of labeled datasets is usually unavailable in many medical image domains. This factor can lead to the poor generalization performance of deep learning models. In this paper, we propose a novel multi-discriminator generative adversarial network model combined with an encoder for the classification of benign and malignant pulmonary nodules. To the best of our knowledge, we are the first to apply unsupervised learning to identify benign and malignant lung nodules. Firstly, we use a multi-discriminator generative adversarial network to build a generative model trained with unlabeled benign lung nodule images. Then an encoder is combined with the trained generative model to establish a mapping of benign pulmonary nodule images to the latent space. The benign and malignant lung nodules are scored by calculating the GAN discriminator feature loss and image reconstruction loss. The model yields high anomaly scores on malignant images and low anomaly scores on benign images. Experimental results show that our method with only a small number of unlabeled datasets could achieve more competitive results compared with other supervised deep learning approaches. INDEX TERMS Computer-aided diagnosis (CAD), lung nodule, malignancy classification, unsupervised learning, generative adversarial networks.

No abstract

With the increasing popularity of graph-based learning, Graph Neural Networks (GNNs) win lots of attention from research and industry field because of their high accuracy. However, existing GNNs suffer from high memory footprints (e.g., node embedding features). This high memory footprint hurdles the potential applications towards memory-constrained devices, such as the widely-deployed IoT devices. To this end, we propose a specialized GNN quantization scheme, SGQuant, to systematically reduce the GNN memory consumption. Specifically, we first propose a GNN-tailored quantization algorithm design and a GNN quantization fine-tuning scheme to reduce memory consumption while maintaining accuracy. Then, we investigate the multi-granularity quantization strategy that operates at different levels (components, graph topology, and layers) of GNN computation. Moreover, we offer an automatic bit-selecting (ABS) to pinpoint the most appropriate quantization bits for the above multi-granularity quantizations. Intensive experiments show that SGQuant can effectively reduce the memory footprint from 4.25× to 31.9× compared with the original full-precision GNNs while limiting the accuracy drop to 0.4% on average.• We propose a GNN-tailored quantization algorithm design to reduce memory consumption and a GNN quantization finetuning to maintain the accuracy.

Adverse drug event (ADE) is a significant challenge in clinical practice. Many ADEs have not been identified timely after the approval of the corresponding drugs. Despite the use of drug similarity network demonstrates early success on improving ADE detection, false discovery rate (FDR) control remains unclear in its application. Additionally, performance of early ADE detection has not been explicitly investigated under the time-to-event framework. In this manuscript, we propose to use the drug similarity based posterior probability of null hypothesis for early ADE detection. The proposed approach is also able to control FDR for monitoring a large number of ADEs of multiple drugs. The proposed approach outperforms existing approaches on mining labeled ADEs in the US FDA Adverse Event Reporting System (FAERS) data, especially in the first few years after the drug initial reporting time. Additionally, the proposed approach is able to identify more labeled ADEs and has significantly lower time to ADE detection. In simulation study, the proposed approach demonstrates proper FDR control, as well as has better true positive rate and an excellent true negative rate. In our exemplified FAERS analysis, the proposed approach detects new ADE signals and identifies ADE signals in a timelier fashion than existing approach. In conclusion, the proposed approach is able to both reduce the time and improve the FDR control for ADE detection.