Data processing and learning has become a spearhead for the advancement of medicine, with pathology and laboratory medicine has no exception. The incorporation of scientific research through clinical ...informatics, including genomics, proteomics, bioinformatics, and biostatistics, into clinical practice unlocks innovative approaches for patient care. Computational pathology is burgeoning subspecialty in pathology that promises a better-integrated solution to whole-slide images, multi-omics data, and clinical informatics. However, computational pathology faces several challenges, including the ability to integrate raw data from different sources, limitation of hardware processing capacity, and a lack of specific training programs, as well as issues on ethics and larger societal acceptable practices that are still solidifying. The establishment of the entire industry of computational pathology requires far-reaching changes of the three essential elements connecting patients and doctors: the local laboratory, the scan center, and the central cloud hub/portal for data processing and retrieval. Computational pathology, unlocked through information integration and advanced digital communication networks, has the potential to improve clinical workflow efficiency, diagnostic quality, and ultimately create personalized diagnosis and treatment plans for patients. This review describes clinical perspectives and discusses the statistical methods, clinical applications, potential obstacles, and future directions of computational pathology.
Image quality assessment (IQA) aims to use computational models to measure the image quality consistently with subjective evaluations. The well-known structural similarity index brings IQA from ...pixel- to structure-based stage. In this paper, a novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features. Specifically, the phase congruency (PC), which is a dimensionless measure of the significance of a local structure, is used as the primary feature in FSIM. Considering that PC is contrast invariant while the contrast information does affect HVS' perception of image quality, the image gradient magnitude (GM) is employed as the secondary feature in FSIM. PC and GM play complementary roles in characterizing the image local quality. After obtaining the local quality map, we use PC again as a weighting function to derive a single quality score. Extensive experiments performed on six benchmark IQA databases demonstrate that FSIM can achieve much higher consistency with the subjective evaluations than state-of-the-art IQA metrics.
Conventional extreme learning machines (ELMs) solve a Moore-Penrose generalized inverse of hidden layer activated matrix and analytically determine the output weights to achieve generalized ...performance, by assuming the same loss from different types of misclassification. The assumption may not hold in cost-sensitive recognition tasks, such as face recognition-based access control system, where misclassifying a stranger as a family member may result in more serious disaster than misclassifying a family member as a stranger. Though recent cost-sensitive learning can reduce the total loss with a given cost matrix that quantifies how severe one type of mistake against another, in many realistic cases, the cost matrix is unknown to users. Motivated by these concerns, this paper proposes an evolutionary cost-sensitive ELM, with the following merits: 1) to the best of our knowledge, it is the first proposal of ELM in evolutionary cost-sensitive classification scenario; 2) it well addresses the open issue of how to define the cost matrix in cost-sensitive learning tasks; and 3) an evolutionary backtracking search algorithm is induced for adaptive cost matrix optimization. Experiments in a variety of cost-sensitive tasks well demonstrate the effectiveness of the proposed approaches, with about 5%-10% improvements.
Targeted immunomodulation of dendritic cells (DCs) in vivo will enable manipulation of T-cell priming and amplification of anticancer immune responses, but a general strategy has been lacking. Here ...we show that DCs concentrated by a biomaterial can be metabolically labelled with azido groups in situ, which allows for their subsequent tracking and targeted modulation over time. Azido-labelled DCs were detected in lymph nodes for weeks, and could covalently capture dibenzocyclooctyne (DBCO)-bearing antigens and adjuvants via efficient Click chemistry for improved antigen-specific CD8
T-cell responses and antitumour efficacy. We also show that azido labelling of DCs allowed for in vitro and in vivo conjugation of DBCO-modified cytokines, including DBCO-IL-15/IL-15Rα, to improve priming of antigen-specific CD8
T cells. This DC labelling and targeted modulation technology provides an unprecedented strategy for manipulating DCs and regulating DC-T-cell interactions in vivo.
Developments in selective laser melting (SLM) have enabled the fabrication of periodic cellular lattice structures characterized by suitable properties matching the bone tissue well and by fluid ...permeability from interconnected structures. These multifunctional performances are significantly affected by cell topology and constitutive properties of applied materials. In this respect, a diamond unit cell was designed in particular volume fractions corresponding to the host bone tissue and optimized with a smooth surface at nodes leading to fewer stress concentrations. There were 33 porous titanium samples with different volume fractions, from 1.28 to 18.6%, manufactured using SLM. All of them were performed under compressive load to determine the deformation and failure mechanisms, accompanied by an in-situ approach using digital image correlation (DIC) to reveal stress-strain evolution. The results showed that lattice structures manufactured by SLM exhibited comparable properties to those of trabecular bone, avoiding the effects of stress-shielding and increasing longevity of implants. The curvature of optimized surface can play a role in regulating the relationship between density and mechanical properties. Owing to the release of stress concentration from optimized surface, the failure mechanism of porous titanium has been changed from the pattern of bottom-up collapse by layer (or cell row) to that of the diagonal (45°) shear band, resulting in the significant enhancement of the structural strength.
We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier ...for visual categorization. This paper proposes a new extreme learning machine (ELM)-based cross-domain network learning framework, that is called ELM-based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the ℓ 2,1 -norm of the network output weights and the learning error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross-domain learning. It minimizes the matching error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as the base classifiers. The network output weights cannot only be analytically determined, but also transferrable. In addition, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semisupervised learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition demonstrate that our EDA methods outperform the existing cross-domain learning methods.
Synthetic antigen-presenting cells (APCs) are used to mediate scalable ex vivo T-cell expansion for adoptive cell therapy. Recently, we developed APC-mimetic scaffolds (APC-ms), which present signals ...to T cells in a physiological manner to mediate rapid and controlled T-cell expansion. APC-ms are composed of individual high-aspect-ratio silica microrods loaded with soluble mitogenic cues and coated with liposomes of defined compositions, to form supported lipid bilayers. Membrane-bound ligands for stimulation and co-stimulation of T-cell receptors are presented via the fluid, synthetic membranes, while mitogenic cues are released slowly from the microrods. In culture, interacting T cells assemble the individual APC-ms microrods into a biodegradable 3D matrix. Compared to conventional methods, APC-ms facilitates several-fold greater polyclonal T-cell expansion and improved antigen-specific enrichment of rare T-cell subpopulations. Here we provide a detailed protocol for APC-ms synthesis and use for human T-cell activation, and discuss important considerations for material design and T-cell co-culture. This protocol describes the facile assembly of APC-ms in ~4 h and rapid expansion or enrichment of relevant T-cell clones in <2 weeks, and is applicable for T-cell manufacturing and assay development.
The employed dictionary plays an important role in sparse representation or sparse coding based image reconstruction and classification, while learning dictionaries from the training data has led to ...state-of-the-art results in image classification tasks. However, many dictionary learning models exploit only the discriminative information in either the representation coefficients or the representation residual, which limits their performance. In this paper we present a novel dictionary learning method based on the Fisher discrimination criterion. A structured dictionary, whose atoms have correspondences to the subject class labels, is learned, with which not only the representation residual can be used to distinguish different classes, but also the representation coefficients have small within-class scatter and big between-class scatter. The classification scheme associated with the proposed Fisher discrimination dictionary learning (FDDL) model is consequently presented by exploiting the discriminative information in both the representation residual and the representation coefficients. The proposed FDDL model is extensively evaluated on various image datasets, and it shows superior performance to many state-of-the-art dictionary learning methods in a variety of classification tasks.
Display omitted
Sustained, localized protein delivery can enhance the safety and activity of protein drugs in diverse disease settings. While hydrogel systems are widely studied as vehicles for ...protein delivery, they often suffer from rapid release of encapsulated cargo, leading to a narrow duration of therapy, and protein cargo can be denatured by incompatibility with the hydrogel crosslinking chemistry. In this work, we describe injectable nanocomposite hydrogels that are capable of sustained, bioactive, release of a variety of encapsulated proteins. Injectable and porous cryogels were formed by bio-orthogonal crosslinking of alginate using tetrazine-norbornene coupling. To provide sustained release from these hydrogels, protein cargo was pre-adsorbed to charged Laponite nanoparticles that were incorporated within the walls of the cryogels. The presence of Laponite particles substantially hindered the release of a number of proteins that otherwise showed burst release from these hydrogels. By modifying the Laponite content within the hydrogels, the kinetics of protein release could be precisely tuned. This versatile strategy to control protein release simplifies the design of hydrogel drug delivery systems.
Here we present an injectable nanocomposite hydrogel for simple and versatile controlled release of therapeutic proteins. Protein release from hydrogels often requires first entrapping the protein in particles and embedding these particles within the hydrogel to allow controlled protein release. This pre-encapsulation process can be cumbersome, can damage the protein’s activity, and must be optimized for each protein of interest. The strategy presented in this work simply premixes the protein with charged nanoparticles that bind strongly with the protein. These protein-laden particles are then placed within a hydrogel and slowly release the protein into the surrounding environment. Using this method, tunable release from an injectable hydrogel can be achieved for a variety of proteins. This strategy greatly simplifies the design of hydrogel systems for therapeutic protein release applications.
The triply periodic minimal surface (TPMS) method is a novel approach for lattice design in a range of fields, such as impact protection and structural lightweighting. In this paper, we used the TPMS ...formula to rapidly and accurately generate the most common lattice structure, named the body centered cubic (BCC) structure, with certain volume fractions. TPMS-based and computer aided design (CAD) based BCC lattice structures with volume fractions in the range of 10⁻30% were fabricated by selective laser melting (SLM) technology with Ti⁻6Al⁻4V and subjected to compressive tests. The results demonstrated that local geometric features changed the volume and stress distributions, revealing that the TPMS-based samples were superior to the CAD-based ones, with elastic modulus, yield strength and compression strength increasing in the ranges of 18.9⁻42.2%, 19.2⁻29.5%, and 2⁻36.6%, respectively. The failure mechanism of the TPMS-based samples with a high volume fraction changed to brittle failure observed by scanning electron microscope (SEM), as their struts were more affected by the axial force and fractured on struts. It was also found that the TPMS-based samples have a favorable capacity to absorb energy, particularly with a 30% volume fraction, the energy absorbed up to 50% strain was approximately three times higher than that of the CAD-based sample with an equal volume fraction. Furthermore, the theoretic Gibson⁻Ashby mode was established in order to predict and design the mechanical properties of the lattice structures. In summary, these results can be used to rapidly create BCC lattice structures with superior compressive properties for engineering applications.