Endoscopic ultrasound avoids diagnostic ERCP among the ASGE high-risk group - Experience in an Asian population.

BACKGROUND: A prediction system for common bile duct (CBD) stones was originally published by the American Society for Gastrointestinal Endoscopy (ASGE) in 2010 and was last revised in 2019. We wanted to investigate its application in an Asian population, who have different etiologies of bile duct stone formation and accessibility to medical service compared to the West. METHODS: This is a single center retrospective study. Patients who received endoscopic ultrasound (EUS) for suspected CBD stones were collected from our endoscopic record system over a 10-year period. The accuracy of the revised ASGE criteria was estimated according to the results of EUS. A minimum follow-up of 6 months was required to detect false negative results. RESULTS: 142 patients were enrolled, 87 (61%) patients had CBD stones. The sensitivity, specificity, positive predictive value, negative predictive value and accuracy of the revised ASGE criteria for high-risk patients were 69%, 38%, 64%, 44%, and 57%. 36% of the ASGE-defined high-risk patients negative for CBD stones on EUS. The two significant predictors for CBD stone were CBD dilatation (adjusted OR 3.06, 95% C.I. 1.31-7.17, p = 0.010) and ascending cholangitis (adjusted OR 2.28, 95% C.I. 1.01-5.15, p = 0.047). CONCLUSION: ASGE recommends that patients defined as high-risk for choledocholithiasis be considered for direct ERCP without prior need for confirmation imaging. However, our findings indicate a high rate (36%) of patients in that group negative for CBD stones on EUS. Hence, EUS is still be suggested first in selective high-risk patients so that diagnostic ERCP can be avoided in our Asian society.

Randomized trial of contrast-enhanced harmonic guidance versus fanning technique for EUS-guided fine-needle biopsy sampling of solid pancreatic lesions.

BACKGROUND AND AIMS: For EUS-guided fine-needle biopsy sampling (EUS-FNB) of solid pancreatic lesions (SPLs), the role of sampling strategy between targeted biopsy sampling and wide sampling has not been reported. This study aimed to investigate the benefits of the 2 sampling techniques on EUS-FNB using rapid on-site evaluation. METHODS: Patients with SPLs were prospectively enrolled and randomly assigned (1:1) to undergo EUS-FNB using either contrast guidance or the fanning technique. The primary outcome was the total number of passes required to establish a diagnosis, and secondary outcomes were overall diagnostic accuracy and adverse event rates. RESULTS: One hundred eighteen patients were enrolled from February 2019 to January 2021, with 59 patients assigned to each group. There was no significant difference in the total number of passes required to establish a diagnosis between the contrast and fanning groups (median, 1 [interquartile range, 1-1] vs 1 [interquartile range, 1-2], respectively; P = .629). The sensitivity, specificity, and diagnostic accuracy in the contrast group was 100%, 66.7%, and 98.3% and in the fanning group 100%, 100%, and 100%, respectively (P = 1). An SPL <4 cm (odds ratio, 2.47; 95% confidence interval, 1.05-5.81; P = .037) and macroscopic visible core length >1 cm (odds ratio, 2.89; 95% confidence interval, 1.07-7.84; P = .037) were independently associated with increased cytologic and histologic accuracy. CONCLUSIONS: The diagnostic accuracy of EUS-FNB with the fanning technique for SPLs was comparable with the contrast guidance technique. Without additional cost, EUS-FNB with the fanning technique may be preferred for SPLs. (Clinical trial registration number: NCT04924725.).

OBET: On-the-Fly Byte-Level Error Tracking for Correcting and Detecting Faults in Unreliable DRAM Systems.

With technology scaling, maintaining the reliability of dynamic random-access memory (DRAM) has become more challenging. Therefore, on-die error correction codes have been introduced to accommodate reliability issues in DDR5. However, the current solution still suffers from high overhead when a large DRAM capacity is used to deliver high performance. We present a DRAM chip architecture that can track faults at byte-level DRAM cell errors to address this problem. DRAM faults are classified as temporary or permanent in our proposed architecture, with no additional pins and with minor DRAM chip modifications. Hence, we achieve reliability comparable to that of other state-of-the-art solutions while incurring negligible performance and energy overhead. Furthermore, the faulty locations are efficiently exposed to the operating system (OS). Thus, we can significantly reduce the required scrubbing cycle by scrubbing only faulty DRAM pages while reducing the system failure probability up to 5000∼7000 times relative to conventional operation.

Approximate probabilistic analysis of biopathway dynamics.

MOTIVATION: Biopathways are often modeled as systems of ordinary differential equations (ODEs). Such systems will usually have many unknown parameters and hence will be difficult to calibrate. Since the data available for calibration will have limited precision, an approximate representation of the ODEs dynamics should suffice. One must, however, be able to efficiently construct such approximations for large models and perform model calibration and subsequent analysis. RESULTS: We present a graphical processing unit (GPU) based scheme by which a system of ODEs is approximated as a dynamic Bayesian network (DBN). We then construct a model checking procedure for DBNs based on a simple probabilistic linear time temporal logic. The GPU implementation considerably extends the reach of our previous PC-cluster-based implementation (Liu et al., 2011b). Further, the key components of our algorithm can serve as the GPU kernel for other Monte Carlo simulations-based analysis of biopathway dynamics. Similarly, our model checking framework is a generic one and can be applied in other systems biology settings. We have tested our methods on three ODE models of bio-pathways: the epidermal growth factor-nerve growth factor pathway, the segmentation clock network and the MLC-phosphorylation pathway models. The GPU implementation shows significant gains in performance and scalability whereas the model checking framework turns out to be convenient and efficient for specifying and verifying interesting pathways properties. AVAILABILITY: The source code is freely available at http://www.comp.nus.edu.sg/~rpsysbio/pada-gpu/

CQ + Training: Minimizing Accuracy Loss in Conversion From Convolutional Neural Networks to Spiking Neural Networks.

Spiking neural networks (SNNs) are attractive for energy-constrained use-cases due to their binarized activation, eliminating the need for weight multiplication. However, its lag in accuracy compared to traditional convolutional network networks (CNNs) has limited its deployment. In this paper, we propose CQ+ training (extended "clamped" and "quantized" training), an SNN-compatible CNN training algorithm that achieves state-of-the-art accuracy for both CIFAR-10 and CIFAR-100 datasets. Using a 7-layer modified VGG model (VGG-*), we achieved 95.06% accuracy on the CIFAR-10 dataset for equivalent SNNs. The accuracy drop from converting the CNN solution to an SNN is only 0.09% when using a time step of 600. To reduce the latency, we propose a parameterized input encoding method and a threshold training method, which further reduces the time window size to 64 while still achieving an accuracy of 94.09%. For the CIFAR-100 dataset, we achieved an accuracy of 77.27% using the same VGG-* structure and a time window of 500. We also demonstrate the transformation of popular CNNs, including ResNet (basic, bottleneck, and shortcut block), MobileNet v1/2, and Densenet, to SNNs with near-zero conversion accuracy loss and a time window size smaller than 60. The framework was developed in PyTorch and is publicly available.

Optimizing for In-Memory Deep Learning With Emerging Memory Technology.

In-memory deep learning executes neural network models where they are stored, thus avoiding long-distance communication between memory and computation units, resulting in considerable savings in energy and time. In-memory deep learning has already demonstrated orders of magnitude higher performance density and energy efficiency. The use of emerging memory technology (EMT) promises to increase density, energy, and performance even further. However, EMT is intrinsically unstable, resulting in random data read fluctuations. This can translate to nonnegligible accuracy loss, potentially nullifying the gains. In this article, we propose three optimization techniques that can mathematically overcome the instability problem of EMT. They can improve the accuracy of the in-memory deep learning model while maximizing its energy efficiency. Experiments show that our solution can fully recover most models' state-of-the-art (SOTA) accuracy and achieves at least an order of magnitude higher energy efficiency than the SOTA.

Synthesis of the Dynamical Properties of Feedback Loops in Bio-Pathways.

Feedback loops regulate various biological functions such as oscillations, bistability, and robustness. They play a significant role in developmental signalling and failure of feedback can lead to disease. Systematic analysis of feedback loops could be useful in understanding their properties and biological effects. We propose here a method to automatically analyze feedback loops in bio-pathways and synthesize temporal logic properties which describe their dynamics. Starting with an ordinary differential equations (ODEs) based model of a bio-pathway, for a chosen feedback loop present in the pathway, we use a convolutional neural network to classify the behaviours of the key components of the feedback according to templates specified in bounded linear temporal logic (BLTL). Once a template has been identified, we instantiate the symbolic variables appearing in the template and synthesize properties using a parameter estimation procedure based on sequential hypothesis testing. We have applied this framework to a number of bio-pathway models and validated that the synthesized properties faithfully describe the behaviours of the feedback loops.