Learning robust uniform features for cross-media social data by using cross autoencoders

The Gap in the Thickness: Estimating Effectiveness of Pulmonary Nodule Detection in Thick- and Thin-Section CT Images with 3D Deep Neural Networks

BACKGROUND AND OBJECTIVES

There is a noticeable gap in diagnostic evidence strength between the thick and thin scans of Low-Dose CT (LDCT) for pulmonary nodule detection. When the thin scans are needed is unknown, especially when aided with an artificial intelligence nodule detection system.

METHODS

A case study is conducted with a set of 1,000 pulmonary nodule screening LDCT scans with both thick (5.0mm), and thin (1.0mm) section scans available. Pulmonary nodule detection is performed by human and artificial intelligence models for nodule detection developed using 3D convolutional neural networks (CNNs). The intra-sample consistency is evaluated with thick and thin scans, for both clinical doctor and NN (neural network) models. Free receiver operating characteristic (FROC) is used to measure the accuracy of humans and NNs.

RESULTS

Trained NNs outperform humans with small nodules < 6.0mm, which is a good complement to human ability. For nodules > 6.0mm, human and NNs perform similarly while human takes a fractional advantage. By allowing a few more FPs, a significant sensitivity improvement can be achieved with NNs.

CONCLUSIONS

There is a performance gap between the thick and thin scans for pulmonary nodule detection regarding both false negatives and false positives. NNs can help reduce false negatives when the nodules are small and trade off the false negatives for sensitivity. A combination of human and trained NNs is a promising way to achieve a fast and accurate diagnosis.

Deep Multimodal Neural Network Based on Data-Feature Fusion for Patient-Specific Quality Assurance

Patient-specific quality assurance (QA) for Volumetric Modulated Arc Therapy (VMAT) plans is routinely performed in the clinical. However, it is labor-intensive and time-consuming for medical physicists. QA prediction models can address these shortcomings and improve efficiency. Current approaches mainly focus on single cancer and single modality data. They are not applicable to clinical practice. To assess the accuracy of QA results for VMAT plans, this paper presents a new model that learns complementary features from the multi-modal data to predict the gamma passing rate (GPR). According to the characteristics of VMAT plans, a feature-data fusion approach is designed to fuse the features of imaging and non-imaging information in the model. In this study, 690 VMAT plans are collected encompassing more than ten diseases. The model can accurately predict the most VMAT plans at all three gamma criteria: 2%/2 mm, 3%/2 mm and 3%/3 mm. The mean absolute error between the predicted and measured GPR is 2.17%, 1.16% and 0.71%, respectively. The maximum deviation between the predicted and measured GPR is 3.46%, 4.6%, 8.56%, respectively. The proposed model is effective, and the features of the two modalities significantly influence QA results.

Permutationally Invariant Deep Learning Approach to Molecular Fingerprinting with Application to Compound Mixtures

Recent advancements in deep learning have led to widespread applications of its algorithms to synthetic planning and reaction predictions in the field of chemistry. One major area, known as supervised learning, is being explored for predicting certain properties such as reaction yields and types. Many chemical descriptors known as fingerprints are being explored as potential candidates for reaction properties prediction. However, there are few studies that describe the permutational invariance of chemical fingerprints, which are concatenated at some stage before being fed to deep learning architecture. In this work, we show that by utilizing permutational invariance, we consistently see improved results in terms of accuracy relative to previously published studies. Furthermore, we are able to accurately predict hydrogen peroxide loss with our own dataset, which consists of more than 20 ingredients in each chemical formulation.

A New Delay Connection for Long Short-Term Memory Networks

Connections play a crucial role in neural network (NN) learning because they determine how information flows in NNs. Suitable connection mechanisms may extensively enlarge the learning capability and reduce the negative effect of gradient problems. In this paper, a new delay connection is proposed for Long Short-Term Memory (LSTM) unit to develop a more sophisticated recurrent unit, called Delay Connected LSTM (DCLSTM). The proposed delay connection brings two main merits to DCLSTM with introducing no extra parameters. First, it allows the output of the DCLSTM unit to maintain LSTM, which is absent in the LSTM unit. Second, the proposed delay connection helps to bridge the error signals to previous time steps and allows it to be back-propagated across several layers without vanishing too quickly. To evaluate the performance of the proposed delay connections, the DCLSTM model with and without peephole connections was compared with four state-of-the-art recurrent model on two sequence classification tasks. DCLSTM model outperformed the other models with higher accuracy and F1[Formula: see text]score. Furthermore, the networks with multiple stacked DCLSTM layers and the standard LSTM layer were evaluated on Penn Treebank (PTB) language modeling. The DCLSTM model achieved lower perplexity (PPL)/bit-per-character (BPC) than the standard LSTM model. The experiments demonstrate that the learning of the DCLSTM models is more stable and efficient.