Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Ultrasensitive Linear Capacitive Pressure Sensor with Wrinkled Microstructures for Tactile Perception.

In Advanced science (Weinheim, Baden-Wurttemberg, Germany)

Ultrasensitive flexible pressure sensors with excellent linearity are essential for achieving tactile perception. Although microstructured dielectrics have endowed capacitive sensors with ultrahigh sensitivity, the compromise of sensitivity with increasing pressure is an issue yet to be resolved. Herein, a spontaneously wrinkled MWCNT/PDMS dielectric layer is proposed to realize the excellent sensitivity and linearity of capacitive sensors for tactile perception. The synergistic effect of a high dielectric constant and wrinkled microstructures enables the sensor to exhibit linearity up to 21 kPa with a sensitivity of 1.448 kPa-1 and a detection limit of 0.2 Pa. Owing to these merits, the sensor monitors subtle physiological signals such as various arterial pulses and respiration. This sensor is further integrated into a fully multimaterial 3D-printed soft pneumatic finger to realize material hardness perception. Eight materials with different hardness values are successfully discriminated, and the capacitance of the sensor varies linearly (R2 > 0.975) with increasing hardness. Moreover, the sensitivity to the material hardness can be tuned by controlling the inflation pressure of the soft finger. As a proof of concept, the finger is used to discriminate pork fats with different hardness, paving the way for hardness discrimination in clinical palpation.

Lv Chunyu, Tian Chengcheng, Jiang Jiashun, Dang Yu, Liu Yang, Duan Xuexin, Li Quanning, Chen Xuejiao, Xie Mengying

2023-Mar-15

hardness discrimination, physiological signal monitoring, pressure sensors, soft pneumatic finger, spontaneous microstructures, tactile perception

General General

Avoiding background knowledge: literature based discovery from important information.

In BMC bioinformatics

BACKGROUND : Automatic literature based discovery attempts to uncover new knowledge by connecting existing facts: information extracted from existing publications in the form of [Formula: see text] and [Formula: see text] relations can be simply connected to deduce [Formula: see text]. However, using this approach, the quantity of proposed connections is often too vast to be useful. It can be reduced by using subject[Formula: see text](predicate)[Formula: see text]object triples as the [Formula: see text] relations, but too many proposed connections remain for manual verification.

RESULTS : Based on the hypothesis that only a small number of subject-predicate-object triples extracted from a publication represent the paper's novel contribution(s), we explore using BERT embeddings to identify these before literature based discovery is performed utilizing only these, important, triples. While the method exploits the availability of full texts of publications in the CORD-19 dataset-making use of the fact that a novel contribution is likely to be mentioned in both an abstract and the body of a paper-to build a training set, the resulting tool can be applied to papers with only abstracts available. Candidate hidden knowledge pairs generated from unfiltered triples and those built from important triples only are compared using a variety of timeslicing gold standards.

CONCLUSIONS : The quantity of proposed knowledge pairs is reduced by a factor of [Formula: see text], and we show that when the gold standard is designed to avoid rewarding background knowledge, the precision obtained increases up to a factor of 10. We argue that the gold standard needs to be carefully considered, and release as yet undiscovered candidate knowledge pairs based on important triples alongside this work.

Preiss Judita

2023-Mar-14

Literature based discovery, Machine learning, Subject–predicate–object triples, Timeslicing gold standard

Pathology Pathology

MetaRegNet: Metamorphic Image Registration Using Flow-Driven Residual Networks

ArXiv Preprint

Deep learning based methods provide efficient solutions to medical image registration, including the challenging problem of diffeomorphic image registration. However, most methods register normal image pairs, facing difficulty handling those with missing correspondences, e.g., in the presence of pathology like tumors. We desire an efficient solution to jointly account for spatial deformations and appearance changes in the pathological regions where the correspondences are missing, i.e., finding a solution to metamorphic image registration. Some approaches are proposed to tackle this problem, but they cannot properly handle large pathological regions and deformations around pathologies. In this paper, we propose a deep metamorphic image registration network (MetaRegNet), which adopts time-varying flows to drive spatial diffeomorphic deformations and generate intensity variations. We evaluate MetaRegNet on two datasets, i.e., BraTS 2021 with brain tumors and 3D-IRCADb-01 with liver tumors, showing promising results in registering a healthy and tumor image pair. The source code is available online.

Ankita Joshi, Yi Hong

2023-03-16

General General

Multi-view feature representation and fusion for drug-drug interactions prediction.

In BMC bioinformatics

BACKGROUND : Drug-drug interactions (DDIs) prediction is vital for pharmacology and clinical application to avoid adverse drug reactions on patients. It is challenging because DDIs are related to multiple factors, such as genes, drug molecular structure, diseases, biological processes, side effects, etc. It is a crucial technology for Knowledge graph to present multi-relation among entities. Recently some existing graph-based computation models have been proposed for DDIs prediction and get good performance. However, there are still some challenges in the knowledge graph representation, which can extract rich latent features from drug knowledge graph (KG).

RESULTS : In this work, we propose a novel multi-view feature representation and fusion (MuFRF) architecture to realize DDIs prediction. It consists of two views of feature representation and a multi-level latent feature fusion. For the feature representation from the graph view and KG view, we use graph isomorphism network to map drug molecular structures and use RotatE to implement the vector representation on bio-medical knowledge graph, respectively. We design concatenate-level and scalar-level strategies in the multi-level latent feature fusion to capture latent features from drug molecular structure information and semantic features from bio-medical KG. And the multi-head attention mechanism achieves the optimization of features on binary and multi-class classification tasks. We evaluate our proposed method based on two open datasets in the experiments. Experiments indicate that MuFRF outperforms the classic and state-of-the-art models.

CONCLUSIONS : Our proposed model can fully exploit and integrate the latent feature from the drug molecular structure graph (graph view) and rich bio-medical knowledge graph (KG view). We find that a multi-view feature representation and fusion model can accurately predict DDIs. It may contribute to providing with some guidance for research and validation for discovering novel DDIs.

Wang Jing, Zhang Shuo, Li Runzhi, Chen Gang, Yan Siyu, Ma Lihong

2023-Mar-14

Drug molecular structure, Drug-drug interactions, Feature fusion, Graph representation, Semantic information extraction

General General

Gate Recurrent Unit Network based on Hilbert-Schmidt Independence Criterion for State-of-Health Estimation

ArXiv Preprint

State-of-health (SOH) estimation is a key step in ensuring the safe and reliable operation of batteries. Due to issues such as varying data distribution and sequence length in different cycles, most existing methods require health feature extraction technique, which can be time-consuming and labor-intensive. GRU can well solve this problem due to the simple structure and superior performance, receiving widespread attentions. However, redundant information still exists within the network and impacts the accuracy of SOH estimation. To address this issue, a new GRU network based on Hilbert-Schmidt Independence Criterion (GRU-HSIC) is proposed. First, a zero masking network is used to transform all battery data measured with varying lengths every cycle into sequences of the same length, while still retaining information about the original data size in each cycle. Second, the Hilbert-Schmidt Independence Criterion (HSIC) bottleneck, which evolved from Information Bottleneck (IB) theory, is extended to GRU to compress the information from hidden layers. To evaluate the proposed method, we conducted experiments on datasets from the Center for Advanced Life Cycle Engineering (CALCE) of the University of Maryland and NASA Ames Prognostics Center of Excellence. Experimental results demonstrate that our model achieves higher accuracy than other recurrent models.

Ziyue Huang, Lujuan Dang, Yuqing Xie, Wentao Ma, Badong Chen

2023-03-16

Public Health Public Health

Improving bowel preparation for colonoscopy with a smartphone application driven by artificial intelligence.

In NPJ digital medicine

Optimal bowel preparation is a prerequisite for a successful colonoscopy; however, the rate of inadequate bowel preparation remains relatively high. In this study, we establish a smartphone app that assesses patient bowel preparation using an artificial intelligence (AI)-based prediction system trained on labeled photographs of feces in the toilet and evaluate its impact on bowel preparation quality in colonoscopy outpatients. We conduct a prospective, single-masked, multicenter randomized clinical trial, enrolling outpatients who own a smartphone and are scheduled for a colonoscopy. We screen 578 eligible patients and randomize 524 in a 1:1 ratio to the control or AI-driven app group for bowel preparation. The study endpoints are the percentage of patients with adequate bowel preparation and the total BBPS score, compliance with dietary restrictions and purgative instructions, polyp detection rate, and adenoma detection rate (secondary). The prediction system has an accuracy of 95.15%, a specificity of 97.25%, and an area under the curve of 0.98 in the test dataset. In the full analysis set (n = 500), adequate preparation is significantly higher in the AI-driven app group (88.54 vs. 65.59%; P < 0.001). The mean BBPS score is 6.74 ± 1.25 in the AI-driven app group and 5.97 ± 1.81 in the control group (P < 0.001). The rates of compliance with dietary restrictions (93.68 vs. 83.81%, P = 0.001) and purgative instructions (96.05 vs. 84.62%, P < 0.001) are significantly higher in the AI-driven app group, as is the rate of additional purgative intake (26.88 vs. 17.41%, P = 0.011). Thus, our AI-driven smartphone app significantly improves the quality of bowel preparation and patient compliance.

Zhu Yan, Zhang Dan-Feng, Wu Hui-Li, Fu Pei-Yao, Feng Li, Zhuang Kun, Geng Zi-Han, Li Kun-Kun, Zhang Xiao-Hong, Zhu Bo-Qun, Qin Wen-Zheng, Lin Sheng-Li, Zhang Zhen, Chen Tian-Yin, Huang Yuan, Xu Xiao-Yue, Liu Jing-Zheng, Wang Shuo, Zhang Wei, Li Quan-Lin, Zhou Ping-Hong

2023-Mar-14