DropConnect is effective in modeling uncertainty of Bayesian deep networks.

Deep neural networks (DNNs) have achieved state-of-the-art performance in many important domains, including medical diagnosis, security, and autonomous driving. In domains where safety is highly critical, an erroneous decision can result in serious consequences. While a perfect prediction accuracy is not always achievable, recent work on Bayesian deep networks shows that it is possible to know when DNNs are more likely to make mistakes. Knowing what DNNs do not know is desirable to increase the safety of deep learning technology in sensitive applications; Bayesian neural networks attempt to address this challenge. Traditional approaches are computationally intractable and do not scale well to large, complex neural network architectures. In this paper, we develop a theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights. This method called Monte Carlo DropConnect (MC-DropConnect) gives us a tool to represent the model uncertainty with little change in the overall model structure or computational cost. We extensively validate the proposed algorithm on multiple network architectures and datasets for classification and semantic segmentation tasks. We also propose new metrics to quantify uncertainty estimates. This enables an objective comparison between MC-DropConnect and prior approaches. Our empirical results demonstrate that the proposed framework yields significant improvement in both prediction accuracy and uncertainty estimation quality compared to the state of the art.

Whole-brain tissue mapping toolkit using large-scale highly multiplexed immunofluorescence imaging and deep neural networks.

Mapping biological processes in brain tissues requires piecing together numerous histological observations of multiple tissue samples. We present a direct method that generates readouts for a comprehensive panel of biomarkers from serial whole-brain slices, characterizing all major brain cell types, at scales ranging from subcellular compartments, individual cells, local multi-cellular niches, to whole-brain regions from each slice. We use iterative cycles of optimized 10-plex immunostaining with 10-color epifluorescence imaging to accumulate highly enriched image datasets from individual whole-brain slices, from which seamless signal-corrected mosaics are reconstructed. Specific fluorescent signals of interest are isolated computationally, rejecting autofluorescence, imaging noise, cross-channel bleed-through, and cross-labeling. Reliable large-scale cell detection and segmentation are achieved using deep neural networks. Cell phenotyping is performed by analyzing unique biomarker combinations over appropriate subcellular compartments. This approach can accelerate pre-clinical drug evaluation and system-level brain histology studies by simultaneously profiling multiple biological processes in their native anatomical context.

Memory-Augmented Capsule Network for Adaptable Lung Nodule Classification.

Computer-aided diagnosis (CAD) systems must constantly cope with the perpetual changes in data distribution caused by different sensing technologies, imaging protocols, and patient populations. Adapting these systems to new domains often requires significant amounts of labeled data for re-training. This process is labor-intensive and time-consuming. We propose a memory-augmented capsule network for the rapid adaptation of CAD models to new domains. It consists of a capsule network that is meant to extract feature embeddings from some high-dimensional input, and a memory-augmented task network meant to exploit its stored knowledge from the target domains. Our network is able to efficiently adapt to unseen domains using only a few annotated samples. We evaluate our method using a large-scale public lung nodule dataset (LUNA), coupled with our own collected lung nodules and incidental lung nodules datasets. When trained on the LUNA dataset, our network requires only 30 additional samples from our collected lung nodule and incidental lung nodule datasets to achieve clinically relevant performance (0.925 and 0.891 area under receiving operating characteristic curves (AUROC), respectively). This result is equivalent to using two orders of magnitude less labeled training data while achieving the same performance. We further evaluate our method by introducing heavy noise, artifacts, and adversarial attacks. Under these severe conditions, our network's AUROC remains above 0.7 while the performance of state-of-the-art approaches reduce to chance level.

Kidney Level Lupus Nephritis Classification Using Uncertainty Guided Bayesian Convolutional Neural Networks.

The kidney biopsy based diagnosis of Lupus Nephritis (LN) is characterized by low inter-observer agreement, with misdiagnosis being associated with increased patient morbidity and mortality. Although various Computer Aided Diagnosis (CAD) systems have been developed for other nephrohistopathological applications, little has been done to accurately classify kidneys based on their kidney level Lupus Glomerulonephritis (LGN) scores. The successful implementation of CAD systems has also been hindered by the diagnosing physician's perceived classifier strengths and weaknesses, which has been shown to have a negative effect on patient outcomes. We propose an Uncertainty-Guided Bayesian Classification (UGBC) scheme that is designed to accurately classify control, class I/II, and class III/IV LGN (3 class) at both the glomerular-level classification task (26,634 segmented glomerulus images) and the kidney-level classification task (87 MRL/lpr mouse kidney sections). Data annotation was performed using a high throughput, bulk labeling scheme that is designed to take advantage of Deep Neural Network's (or DNNs) resistance to label noise. Our augmented UGBC scheme achieved a 94.5% weighted glomerular-level accuracy while achieving a weighted kidney-level accuracy of 96.6%, improving upon the standard Convolutional Neural Network (CNN) architecture by 11.8% and 3.5% respectively.

Automated Classification of Apoptosis in Phase Contrast Microscopy Using Capsule Network.

Automatic and accurate classification of apoptosis, or programmed cell death, will facilitate cell biology research. The state-of-the-art approaches in apoptosis classification use deep convolutional neural networks (CNNs). However, these networks are not efficient in encoding the part-whole relationships, thus requiring a large number of training samples to achieve robust generalization. This paper proposes an efficient variant of capsule networks (CapsNets) as an alternative to CNNs. Extensive experimental results demonstrate that the proposed CapsNets achieve competitive performances in target cell apoptosis classification, while significantly outperforming CNNs when the number of training samples is small. To utilize temporal information within microscopy videos, we propose a recurrent CapsNet constructed by stacking a CapsNet and a bi-directional long short-term recurrent structure. Our experiments show that when considering temporal constraints, the recurrent CapsNet achieves 93.8% accuracy and makes significantly more consistent prediction than NNs.

Risk-Aware Machine Learning Classifier for Skin Lesion Diagnosis.

Knowing when a machine learning system is not confident about its prediction is crucial in medical domains where safety is critical. Ideally, a machine learning algorithm should make a prediction only when it is highly certain about its competency, and refer the case to physicians otherwise. In this paper, we investigate how Bayesian deep learning can improve the performance of the machine-physician team in the skin lesion classification task. We used the publicly available HAM10000 dataset, which includes samples from seven common skin lesion categories: Melanoma (MEL), Melanocytic Nevi (NV), Basal Cell Carcinoma (BCC), Actinic Keratoses and Intraepithelial Carcinoma (AKIEC), Benign Keratosis (BKL), Dermatofibroma (DF), and Vascular (VASC) lesions. Our experimental results show that Bayesian deep networks can boost the diagnostic performance of the standard DenseNet-169 model from 81.35% to 83.59% without incurring additional parameters or heavy computation. More importantly, a hybrid physician-machine workflow reaches a classification accuracy of 90 % while only referring 35 % of the cases to physicians. The findings are expected to generalize to other medical diagnosis applications. We believe that the availability of risk-aware machine learning methods will enable a wider adoption of machine learning technology in clinical settings.

Assaying neural activity of children during video game play in public spaces: a deep learning approach.

OBJECTIVE: Understanding neural activity patterns in the developing brain remains one of the grand challenges in neuroscience. Developing neural networks are likely to be endowed with functionally important variability associated with the environmental context, age, gender, and other variables. Therefore, we conducted experiments with typically developing children in a stimulating museum setting and tested the feasibility of using deep learning techniques to help identify patterns of brain activity associated with different conditions. APPROACH: A four-channel dry EEG-based Mobile brain-body imaging data of children at rest and during videogame play (VGP) was acquired at the Children's Museum of Houston. A data-driven approach based on convolutional neural networks (CNN) was used to describe underlying feature representations in the EEG and their ability to discern task and gender. The variability of the spectral features of EEG during the rest condition as a function of age was also analyzed. MAIN RESULTS: Alpha power (7-13 Hz) was higher during rest whereas theta power (4-7 Hz) was higher during VGP. Beta (13-18 Hz) power was the most significant feature, higher in females, when differentiating between males and females. Using data from both temporoparietal channels to classify between VGP and rest condition, leave-one-subject-out cross-validation accuracy of 67% was obtained. Age-related changes in EEG spectral content during rest were consistent with previous developmental studies conducted in laboratory settings showing an inverse relationship between age and EEG power. SIGNIFICANCE: These findings are the first to acquire, quantify and explain brain patterns observed during VGP and rest in freely behaving children in a museum setting using a deep learning framework. The study shows how deep learning can be used as a data driven approach to identify patterns in the data and explores the issues and the potential of conducting experiments involving children in a natural and engaging environment.