Morphological residual convolutional neural network (M-RCNN) for intelligent recognition of wear particles from artificial joints
Ontology highlight
ABSTRACT: Electronic Supplementary Material
Supplementary Material is available in the online version of this article at 10.1007/s40544-021-0516-2.
SUBMITTER: Hu X
PROVIDER: S-EPMC8372229 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Wear debris, of deferent sizes, shapes and quantities, generated in artificial hip and knees is largely confined to the bone and joint interface. This debris interacts with periprosthetic tissue and may cause aseptic loosening. The purpose of this review is to summarize and collate findings of the recent demonstrations on debris characterization and their biological response that influences the occurrence in implant migration. A systematic review of peer-reviewed literature is performed, based on inclusion and exclusion criteria addressing mainly debris isolation, characterization, and biologic responses. Results show that debris characterization largely depends on their appropriate and accurate isolation protocol. The particles are found to be non-uniform in size and non-homogeneously distributed into the periprosthetic tissues. In addition, the sizes, shapes, and volumes of the particles are influenced by the types of joints, bearing geometry, material combination, and lubricant. Phagocytosis of wear debris is size dependent; high doses of submicron-sized particles induce significant level of secretion of bone resorbing factors. However, articles on wear debris from engineered surfaces (patterned and coated) are lacking. The findings suggest considering debris morphology as an important parameter to evaluate joint simulator and newly developed implant materials.
| S-EPMC5453097 | biostudies-other
Project description:Currently, digital transformation has occurred in most countries in the world to varying degrees, but digitizing business processes are complex in terms of understanding the various aspects of manual documentation. The use of digital devices and intelligent systems is vital in the digital transformation of manual documentation from hardcopy to digital formats. The transformation of handwritten documents into electronic files is one of the principal aspects of digitization and represents a common need shared by today's businesses. Generally, handwriting recognition poses a complex digitization challenge, and Arabic handwriting recognition, specifically, proves inordinately challenging due to the nature of Arabic scripts and the excessive diversity in human handwriting. This study presents an intelligent approach for recognizing handwritten Arabic letters. In this approach, a convolution neural network (CNN) model is proposed to recognize handwritten Arabic letters. The model is regularized using batch normalization and dropout operations. Moreover, the model was tested with and without dropout, resulting in a significant difference in the performance. Hence, the model overfitting has been prevented using dropout regularization. The proposed model was applied to the prominent, publicly-available Arabic handwritten characters (AHCD) dataset with 16,800 letters, and the performance was measured using several evaluation measures. The experimental results show the best fit of the proposed model in terms of higher accuracy results that reached 96.78%; additionally, other evaluation measures compared to popular domain-relevant approaches in the literature.
| S-EPMC9202630 | biostudies-literature
Project description:MotivationSequence-based protein-protein interaction (PPI) prediction represents a fundamental computational biology problem. To address this problem, extensive research efforts have been made to extract predefined features from the sequences. Based on these features, statistical algorithms are learned to classify the PPIs. However, such explicit features are usually costly to extract, and typically have limited coverage on the PPI information.ResultsWe present an end-to-end framework, PIPR (Protein-Protein Interaction Prediction Based on Siamese Residual RCNN), for PPI predictions using only the protein sequences. PIPR incorporates a deep residual recurrent convolutional neural network in the Siamese architecture, which leverages both robust local features and contextualized information, which are significant for capturing the mutual influence of proteins sequences. PIPR relieves the data pre-processing efforts that are required by other systems, and generalizes well to different application scenarios. Experimental evaluations show that PIPR outperforms various state-of-the-art systems on the binary PPI prediction problem. Moreover, it shows a promising performance on more challenging problems of interaction type prediction and binding affinity estimation, where existing approaches fall short.Availability and implementationThe implementation is available at https://github.com/muhaochen/seq_ppi.git.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6681469 | biostudies-literature
Project description:Artificial intelligence (AI) tools have been applied to diagnose or predict disease risk from medical images with recent data disclosure actions, but few of them are designed for mobile terminals due to the limited computational power and storage capacity of mobile devices. In this work, a novel AI diagnostic system is proposed for cholelithiasis recognition on mobile devices with Android platform. To this aim, a data set of CT images of cholelithiasis is firstly collected from The Third Hospital of Shandong Province, China, and then we technically use histogram equalization to preprocess these CT images. As results, a lightweight convolutional neural network is obtained in a constructive way to extract cholelith features and recognize gallstones. In terms of implementation, we compile Java and C++ to adapt to the application of deep learning algorithm on mobile devices with Android platform. Noted that, the training task is completed offline on PC, but cholelithiasis recognition tasks are performed on mobile terminals. We evaluate and compare the performance of our MobileNetV2 with MobileNetV1, Single Shot Detector (SSD), YOLOv2 and original SSD (with VGG-16) as feature extractors for object detection. It is achieved that our MobileNetV2 achieve similar accuracy rate, about 91% with the other four methods, but the number of parameters used is reduced from 36.1M (SSD 300, SSD512), 50.7M (Yolov2) and 5.1M (MobileNetV1) to 4.3M (MobileNetV2). The complete process on testing mobile devices, including Virtual machine, Xiaomi 7 and Htc One M8 can be controlled within 4 seconds in recognizing cholelithiasis as well as the degree of the disease.
| S-EPMC6742400 | biostudies-literature
Project description:Stick-slip friction was observed in articular cartilage under certain loading and sliding conditions and systematically studied. Using the Surface Forces Apparatus, we show that stick-slip friction can induce permanent morphological changes (a change in the roughness indicative of wear/damage) in cartilage surfaces, even under mild loading and sliding conditions. The different load and speed regimes can be represented by friction maps--separating regimes of smooth and stick-slip sliding; damage generally occurs within the stick-slip regimes. Prolonged exposure of cartilage surfaces to stick-slip sliding resulted in a significant increase of surface roughness, indicative of severe morphological changes of the cartilage superficial zone. To further investigate the factors that are conducive to stick-slip and wear, we selectively digested essential components of cartilage: type II collagen, hyaluronic acid (HA), and glycosaminoglycans (GAGs). Compared with the normal cartilage, HA and GAG digestions modified the stick-slip behavior and increased surface roughness (wear) during sliding, whereas collagen digestion decreased the surface roughness. Importantly, friction forces increased up to 2, 10, and 5 times after HA, GAGs, and collagen digestion, respectively. Also, each digestion altered the friction map in different ways. Our results show that (i) wear is not directly related to the friction coefficient but (ii) more directly related to stick-slip sliding, even when present at small amplitudes, and that (iii) the different molecular components of joints work synergistically to prevent wear. Our results also suggest potential noninvasive diagnostic tools for sensing stick-slip in joints.
| S-EPMC3574935 | biostudies-literature
Project description:The inflammatory response to prosthetic implant-derived wear particles is the primary cause of bone loss and aseptic loosening of implants, but the mechanisms by which macrophages recognize and respond to particles remain unknown. Studies of innate immunity demonstrate that Toll-like receptors (TLRs) recognize pathogen-associated molecular patterns (PAMPs) and danger-associated molecular patterns (DAMPS). All TLRs signal through myeloid differentiation factor 88 (MyD88), except TLR3 which signals through TIR domain containing adapter inducing interferon-beta (TRIF), and TLR4 which signals through both MyD88 and TRIF. We hypothesized that wear-debris particles may act as PAMPs/DAMPs and activate macrophages via TLRs. To test this hypothesis, we first demonstrated that inhibition of MyD88 decreases polymethylmethacrylate (PMMA) particle-induced production of TNF-? in RAW 264.7 macrophages. Next we compared particle-induced production of TNF-? among MyD88 knockout (MyD88(-/-)), TRIF knockout (TRIF(-/-)), and wild type (WT) murine macrophages. Relative to WT, disruption of MyD88 signaling diminished, and disruption of TRIF amplified the particle-induced production of TNF-?. Gene expression data indicated that this latter increase in TNF-? was due to a compensatory increase in expression of MyD88 associated components of the TLR pathway. Finally, using an in vivo model, MyD88(-/-) mice developed less particle-induced osteolysis than WT mice. These results indicate that the response to PMMA particles is partly dependent on MyD88, presumably as part of TLR signaling; MyD88 may represent a therapeutic target for prevention of wear debris-induced periprosthetic osteolysis.
| S-EPMC3716294 | biostudies-literature
Project description:A protein-based lubricating substance is discovered in the femoro-tibial joint of the darkling beetle Zophobas morio (Insecta). The substance extrudes to the contacting areas within the joint and appears in a form of filiform flows and short cylindrical fragments. The extruded lubricating substance effectively reduces the coefficient of sliding friction to the value of 0.13 in the tribosystem glass/lubricant/glass. This value is significantly lower than 0.35 in the control tribosystem glass/glass and comparable to the value of 0.14 for the tribosystem glass/dry PTFE (polytetrafluoroethylene or Teflon). The study shows for the first time that the friction-reducing mechanism found in Z. morio femoro-tibial joints is based on the lubricant spreading over the contacting surfaces rolling or moving at low loads and deforming at higher loads, preventing direct contact of joint counterparts. Besides Z. morio, the lubricant has been found in the leg joints of the Argentinian wood roach Blaptica dubia.
| S-EPMC8261218 | biostudies-literature
Project description:Hand gesture recognition tasks based on surface electromyography (sEMG) are vital in human-computer interaction, speech detection, robot control, and rehabilitation applications. However, existing models, whether traditional machine learnings (ML) or other state-of-the-arts, are limited in the number of movements. Targeting a large number of gesture classes, more data features such as temporal information should be persisted as much as possible. In the field of sEMG-based recognitions, the recurrent convolutional neural network (RCNN) is an advanced method due to the sequential characteristic of sEMG signals. However, the invariance of the pooling layer damages important temporal information. In the all convolutional neural network (ACNN), because of the feature-mixing convolution operation, a same output can be received from completely different inputs. This paper proposes a concatenate feature fusion (CFF) strategy and a novel concatenate feature fusion recurrent convolutional neural network (CFF-RCNN). In CFF-RCNN, a max-pooling layer and a 2-stride convolutional layer are concatenated together to replace the conventional simple dimensionality reduction layer. The featurewise pooling operation serves as a signal amplitude detector without using any parameter. The feature-mixing convolution operation calculates the contextual information. Complete evaluations are made on both the accuracy and convergence speed of the CFF-RCNN. Experiments are conducted using three sEMG benchmark databases named DB1, DB2 and DB4 from the NinaPro database. With more than 50 gestures, the classification accuracies of the CFF-RCNN are 88.87% on DB1, 99.51% on DB2, and 99.29% on DB4. These accuracies are the highest compared with reported accuracies of machine learnings and other state-of-the-art methods. To achieve accuracies of 86%, 99% and 98% for the RCNN, the training time are 2353.686 s, 816.173 s and 731.771 s, respectively. However, for the CFF-RCNN to reach the same accuracies, it needs only 1727.415 s, 542.245 s and 576.734 s, corresponding to a reduction of 26.61%, 33.56% and 21.19% in training time. We concluded that the CFF-RCNN is an improved method when classifying a large number of hand gestures. The CFF strategy significantly improved model performance with higher accuracy and faster convergence as compared to traditional RCNN.
| S-EPMC8775254 | biostudies-literature
Project description: Not available
| S-EPMC7327358 | biostudies-literature
Project description:Automated manipulation of small particles using external (e.g., magnetic, electric and acoustic) fields has been an emerging technique widely used in different areas. The manipulation typically necessitates a reduced-order physical model characterizing the field-driven motion of particles in a complex environment. Such models are available only for highly idealized settings but are absent for a general scenario of particle manipulation typically involving complex nonlinear processes, which has limited its application. In this work, the authors present a data-driven architecture for controlling particles in microfluidics based on hydrodynamic manipulation. The architecture replaces the difficult-to-derive model by a generally trainable artificial neural network to describe the kinematics of particles, and subsequently identifies the optimal operations to manipulate particles. The authors successfully demonstrate a diverse set of particle manipulations in a numerically emulated microfluidic chamber, including targeted assembly of particles and subsequent navigation of the assembled cluster, simultaneous path planning for multiple particles, and steering one particle through obstacles. The approach achieves both spatial and temporal controllability of high precision for these settings. This achievement revolutionizes automated particle manipulation, showing the potential of data-driven approaches and machine learning in improving microfluidic technologies for enhanced flexibility and intelligence.
| S-EPMC9929134 | biostudies-literature