Acoustic target recognition has always played a central role in marine sensing. Traditional signal processing techniques that have been used for target recognition have shown limitations in accuracy, particularly with commodity hardware. To address such limitations, we present the results of our experiments to assess the capabilities of AI-enabled acoustic buoys using OpenEar™, a commercial, off-the-shelf, software-defined hydrophone sensor, for detecting and tracking fast-moving vessels. We used a triangular sparse sensor network to investigate techniques necessary to estimate the detection, classification, localization, and tracking of boats transiting through the network. Emphasis was placed on evaluating the sensor’s operational detection range and feasibility of onboard AI for cloud-based data fusion. Results indicated effectiveness for enhancing maritime domain awareness and gaining insight into illegal, unreported, and unregulated activities. Additionally, this study provides a framework for scaling autonomous sensor networks to support persistent maritime surveillance.

The ability to predict which pairs of amino acid residues in a protein are in contact with each other offers many advantages for various areas of research that focus on proteins. For example, contact prediction can be used to reduce the computational complexity of predicting the structure of proteins and even to help identify functionally important regions of proteins. These predictions are becoming especially important given the relatively low number of experimentally determined protein structures compared to the amount of available protein sequence data. Here we have developed and benchmarked a set of machine learning methods for performing residue-residue contact prediction, including random forests, direct-coupling analysis, support vector machines, and deep networks (stacked denoising autoencoders). These methods are able to predict contacting residue pairs given only the amino acid sequence of a protein. According to our own evaluations performed at a resolution of +/− two residues, the predictors we trained with the random forest algorithm were our top performing methods with average top 10 prediction accuracy scores of 85.13% (short range), 74.49% (medium range), and 54.49% (long range). Our ensemble models (stacked denoising autoencoders combined with support vector machines) were our best performing deep network predictors and achieved top 10 prediction accuracy scores of 75.51% (short range), 60.26% (medium range), and 43.85% (long range) using the same evaluation. These tests were blindly performed on targets from the CASP11 dataset; and the results suggested that our models achieved comparable performance to contact predictors developed by groups that participated in CASP11. Due to the challenging nature of contact prediction, it is beneficial to develop and benchmark a variety of different prediction methods. Our work has produced useful tools with a simple interface that can provide contact predictions to users without requiring a lengthy installation process. In addition to this, we have released our C++ implementation of the direct-coupling analysis method as a standalone software package. Both this tool and our RFcon web server are freely available to the public at http://dna.cs.miami.edu/RFcon /.

Purpose: Breast cancer is the most common major public health problems of women in the world. Until now, analyzing mammogram images is still the main method used by doctors to diagnose and detect breast cancers. However, this process usually depends on the experience of radiologists and is always very time consuming. Patients and Methods: We propose to introduce deep learning technology into the process for the facilitation of computer-aided diagnosis (CAD), and address the challenges of class imbalance, enhance the detection of small masses and multiple targets, and reduce false positives and negatives in mammogram analysis. Therefore, we adopted and enhanced RetinaNet to detect masses in mammogram images. Specifically, we introduced a novel modification to the network structure, where the feature map M5 is processed by the ReLU function prior to the original convolution kernel. This strategic adjustment was designed to prevent the loss of resolution for small mass features. Additionally, we introduced transfer learning techniques into training process through leveraging pre-trained weights from other RetinaNet applications, and fine-tuned our improved model using the INbreast dataset. Results: The aforementioned innovations facilitate superior performance of the enhanced RetiaNet model on the public dataset INbreast, as evidenced by a mAP (mean average precision) of 1.0000 and TPR (true positive rate) of 1.00 at 0.00 FPPI (false positive per image) on the INbreast dataset. Conclusion: The experimental results demonstrate that our enhanced RetinaNet model defeats the existing models by having more generalization performance than other published studies, and it can also be applied to other types of patients to assist doctors in making a proper diagnosis.

Background: Accurate and robust pathological image analysis for colorectal cancer (CRC) diagnosis is time-consuming and knowledge-intensive, but is essential for CRC patients’ treatment. The current heavy workload of pathologists in clinics/hospitals may easily lead to unconscious misdiagnosis of CRC based on their daily image analyses. Methods: Based on a state-of-the-art transfer-learned deep convolutional neural network in artificial intelligence (AI), we proposed a novel patch aggregation strategy for clinic CRC prediction/diagnosis using weakly labeled pathological whole slide image (WSI) patches. This approach was trained and validated using an unprecedented and enormously large number of 170,099 patches, >14,680 WSIs, from >9,631 subjects that covered diverse and representative clinical cases from multi-independent-sources across China, U.S., and Germany. Results: Our innovative AI tool was consistently nearly perfectly agreed with (average Kappa-statistic 0.896) and even often better than most of the experienced expert pathologists when tested in diagnosing CRC WSIs from multi-centers. The average area under the receiver operating characteristics curve (AUC) of AI was greater than that of the pathologists (0.981 vs 0.970) and achieved the best performance among the application of other AI methods to CRC diagnosis. Our AI-generated heatmap highlights the image regions of cancer tissue/cells. Conclusions: This first-ever generalizable AI system can handle large amounts of WSIs consistently and robustly without potential bias due to fatigue commonly experienced by clinical pathologists. Hence, it will drastically alleviate the heavy clinical burden of daily pathology diagnosis, and improve the treatment for CRC patients. This tool is generalizable to other cancer diagnosis based on image recognition.