Search

BACKGROUND: Artificial Intelligence(AI)-based solutions for Gleason grading hold promise for pathologists, while image quality inconsistency, continuous data integration needs, and limited generalizability hinder their adoption and scalability. METHODS: We present a comprehensive digital pathology workflow for AI-assisted Gleason grading. It incorporates A!MagQC (image quality control), A!HistoClouds (cloud-based annotation), Pathologist-AI Interaction (PAI) for continuous model improvement, Trained on Akoya-scanned images only, the model utilizes color augmentation and image appearance migration to address scanner variations. We evaluate it on Whole Slide Images (WSI) from another five scanners and conduct validations with pathologists to assess AI efficacy and PAI. RESULTS: Our model achieves an average F1 score of 0.80 on annotations and 0.71 Quadratic Weighted Kappa on WSIs for Akoya-scanned images. Applying our generalization solution increases the average F1 score for Gleason pattern detection from 0.73 to 0.88 on images from other scanners. The model accelerates Gleason scoring time by 43% while maintaining accuracy. Additionally, PAI improve annotation efficiency by 2.5 times and led to further improvements in model performance. CONCLUSIONS: This pipeline represents a notable advancement in AI-assisted Gleason grading for improved consistency, accuracy, and efficiency. Unlike previous methods limited by scanner specificity, our model achieves outstanding performance across diverse scanners. This improvement paves the way for its seamless integration into clinical workflows.

MOTIVATION: Pediatric kidney disease is a widespread, progressive condition that severely impacts growth and development of children. Chronic kidney disease is often more insidious in children than in adults, usually requiring a renal biopsy for diagnosis. Biopsy evaluation requires copious examination by trained pathologists, which can be tedious and prone to human error. In this study, we propose an artificial intelligence (AI) method to assist pathologists in accurate segmentation and classification of pediatric kidney structures, named as AI-based Pediatric Kidney Diagnosis (APKD). RESULTS: We collected 2935 pediatric patients diagnosed with kidney disease for the development of APKD. The dataset comprised 93 932 histological structures annotated manually by three skilled nephropathologists. APKD scored an average accuracy of 94% for each kidney structure category, including 99% in the glomerulus. We found strong correlation between the model and manual detection in detected glomeruli (Spearman correlation coefficient r = 0.98, P

The elucidation of the structural characteristics of deoxyribonucleic acid (DNA) by Watson and Crick, the advent of polymerase chain reaction technology, and the development of primer-synthesis methods, enable DNA to be replicated and transformed in an increasingly easy manner, such that it is among the most directed and evolving nanomaterials in molecular biology. Traditional cancer diagnosis methods are somewhat limited and are unable to meet existing needs; consequently, DNA nanostructures with wide ranging properties are receiving increasingly more attention because a number of DNA materials have been shown to exhibit diagnostic properties. Some DNA materials can functionally alter the biological behavior of cells, such as cell migration, cell proliferation, cell differentiation, autophagy, and anti-inflammatory effects. Some single-stranded DNA or ribonucleic acid with secondary structure through self-pairing, called aptamer, systematic evolution of ligands by exponential enrichment (SELEX), have targeting capabilities and can be applied to tumor targeted diagnosis and therapy. Several DNA nanomaterials with three-dimensional nanostructures and stable structures are being investigated as drug carrier systems to act on a variety of antitumor drugs or gene therapy agents. This article reviews the use of functionalized DNA nanostructures in cancer diagnosis and treatment applications. Various biosensors and carriers based on DNA nanostructures are introduced and chemical reactions related to the preparation of the carrier and the signal transduction mechanism of the sensor are discussed. Efficient carrier/biosensor platforms based on various structural developments and current DNA nanomaterial developments are also presented.

DNA is commonly employed as a substrate for the building of artificial logic networks due to its excellent biocompatibility and programmability. Till now, DNA logic circuits are rapidly evolving to accomplish advanced operations. Nonetheless, nowadays, most DNA circuits remain to be disposable and lack of field programmability and thereby limits their practicability. Herein, inspired by the Configurable Logic Block (CLB), the CLB‐based erasable field‐programmable DNA circuit that uses clip strands as its operation‐controlling signals is presented. It enables users to realize diverse functions with limited hardware. CLB‐based basic logic gates (OR and AND) are first constructed and demonstrated their erasability and field programmability. Furthermore, by adding the appropriate operation‐controlling strands, multiple rounds of programming are achieved among five different logic operations on a two‐layer circuit. Subsequently, a circuit is successfully built to implement two fundamental binary calculators: half‐adder and half‐subtractor, proving that the design can imitate silicon‐based binary circuits. Finally, a comprehensive CLB‐based circuit is built that enables multiple rounds of switch among seven different logic operations including half‐adding and half‐subtracting. Overall, the CLB‐based erasable field‐programmable circuit immensely enhances their practicability. It is believed that design can be widely used in DNA logic networks due to its efficiency and convenience. [ABSTRACT FROM AUTHOR]

Considerable efforts have been made for link prediction by researchers from various disciplines because of its important value in a wide range of applications. Heuristics methods, which predict links based on some assumptions, can attain commendable accuracy when their assumptions are met. Otherwise, their effectiveness may be unsatisfactory. On the other hand, the methods that leverage Graph Neural Networks to learn the representations of node pairs have been confirmed to be effective for link prediction. However, they are usually very time-consuming. To circumvent these issues, we put forth the HELF method, a new link prediction technique built on fully connected neural networks (FCNNs) with fundamental heuristic elements. By investigating the formulas of a collection of heuristic methods, we extract a series of fundamental heuristic elements from them, which cover the core structural profiles of node pairs. Then, we encode target node pairs into feature vectors using these fundamental heuristic elements and feed the feature vectors to a FCNN to gauge the existence of links. Extensive experiments are conducted on several networks to evaluate the performance of our HELF method. The results demonstrate that HELF outperforms the well-known heuristic methods and state-of-the-art neural network-based methods subject to AUC and AP. Additionally, HELF runs much faster than these neural network-based methods. [ABSTRACT FROM AUTHOR]