Search for: All records

With each passing year, the state-of-the-art deep learning neural networks grow larger in size, requiring larger computing and power resources. The high compute resources required by these large networks are alienating the majority of the world population that lives in low-resource settings and lacks the infrastructure to benefit from these advancements in medical AI. Current state-of-the-art medical AI, even with cloud resources, is a bit difficult to deploy in remote areas where we don’t have good internet connectivity. We demonstrate a cost-effective approach to deploying medical AI that could be used in limited resource settings using Edge Tensor Processing Unit (TPU). We trained and optimized a classification model on the Chest X-ray 14 dataset and a segmentation model on the Nerve ultrasound dataset using INT8 Quantization Aware Training. Thereafter, we compiled the optimized models for Edge TPU execution. We find that the inference performance on edge TPUs is 10x faster compared to other embedded devices. The optimized model is 3x and 12x smaller for the classification and segmentation respectively, compared to the full precision model. In summary, we show the potential of Edge TPUs for two medical AI tasks with faster inference times, which could potentially be used in low-resource settings for medical AI-based diagnostics. We finally discuss some potential challenges and limitations of our approach for real-world deployments. 

Abstract Real-time execution of machine learning (ML) pipelines on radiology images is difficult due to limited computing resources in clinical environments, whereas running them in research clusters requires efficient data transfer capabilities. We developed Niffler, an open-source Digital Imaging and Communications in Medicine (DICOM) framework that enables ML and processing pipelines in research clusters by efficiently retrieving images from the hospitals’ PACS and extracting the metadata from the images. We deployed Niffler at our institution (Emory Healthcare, the largest healthcare network in the state of Georgia) and retrieved data from 715 scanners spanning 12 sites, up to 350 GB/day continuously in real-time as a DICOM data stream over the past 2 years. We also used Niffler to retrieve images bulk on-demand based on user-provided filters to facilitate several research projects. This paper presents the architecture and three such use cases of Niffler. First, we executed an IVC filter detection and segmentation pipeline on abdominal radiographs in real-time, which was able to classify 989 test images with an accuracy of 96.0%. Second, we applied the Niffler Metadata Extractor to understand the operational efficiency of individual MRI systems based on calculated metrics. We benchmarked the accuracy of the calculated exam time windows by comparing Niffler against the Clinical Data Warehouse (CDW). Niffler accurately identified the scanners’ examination timeframes and idling times, whereas CDW falsely depicted several exam overlaps due to human errors. Third, with metadata extracted from the images by Niffler, we identified scanners with misconfigured time and reconfigured five scanners. Our evaluations highlight how Niffler enables real-time ML and processing pipelines in a research cluster. 

The management of blood glucose levels is critical in the care of Type 1 diabetes subjects. In extremes, high or low levels of blood glucose are fatal. To avoid such adverse events, there is the development and adoption of wearable technologies that continuously monitor blood glucose and administer insulin. This technology allows subjects to easily track their blood glucose levels with early intervention without the need for hospital visits. The data collected from these sensors is an excellent candidate for the application of machine learning algorithms to learn patterns and predict future values of blood glucose levels. In this study, we developed artificial neural network algorithms based on the OhioT1DM training dataset that contains data on 12 subjects. The dataset contains features such as subject identifiers, continuous glucose monitoring data obtained in 5 minutes intervals, insulin infusion rate, etc. We developed individual models, including LSTM, BiLSTM, Convolutional LSTMs, TCN, and sequence-to-sequence models. We also developed transfer learning models based on the most important features of the data, as identified by a gradient boosting algorithm. These models were evaluated on the OhioT1DM test dataset that contains 6 unique subject’s data. The model with the lowest RMSE values for the 30- and 60-minutes was selected as the best performing model. Our result shows that sequence-to-sequence BiLSTM performed better than the other models. This work demonstrates the potential of artificial neural networks algorithms in the management of Type 1 diabetes.