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

General General

Dual-Phase Inspired Soft Electronic Sensors with Programmable and Tunable Mechanical Properties.

In ACS nano ; h5-index 203.0

Wearable and stretchable sensors are important components to strictly monitor the behavior and health of humans and attract extensive attention. However, traditional sensors are designed with pure horseshoes or chiral metamaterials, which restrict the biological tissue engineer applications due to their narrow regulation ranges of the elastic modulus and the poorly adjustable Poisson's ratio. Inspired by the biological spiral microstructure, a dual-phase metamaterial (chiral-horseshoes) is designed and fabricated in this work, which possesses wide and programmable mechanical properties by tailoring the geometrical parameters. Experimental, numerical, and theoretical studies are conducted, which reveal that the designed microstructures can reproduce mechanical properties of most natural animals such as frogs, snakes, and rabbits skin. Furthermore, a flexible strain sensor with the gauge factor reaching 2 under 35% strain is fabricated, which indicates that the dual-phase metamaterials have a stable monitoring ability and can be potentially applied in the electronic skin. Finally, the flexible strain sensor is attached on the human skin, and it can successfully monitor the physiological behavior signals under various actions. In addition, the dual-phase metamaterial could combine with artificial intelligence algorithms to fabricate a flexible stretchable display. The dual-phase metamaterial with negative Poisson's ratio could decrease the lateral shrinkage and image distortion during the stretching process. This study offers a strategy for designing the flexible strain sensors with programmable, tunable mechanical properties, and the fabricated soft and high-precision wearable strain sensor can accurately monitor the skin signals under different human motions and potentially be applied for flexible display.

Deng Yun, Guo Xiaogang, Lin Yongshui, Huang Zhixin, Li Ying

2023-Mar-02

dual-phase design, flexible display, motion monitoring, programmable metamaterial, skin electronic sensor

General General

What is the best method for long-term survival analysis?

In Indian journal of cancer

In the Cox proportional hazards regression model, which is the most commonly used model in survival analysis, the effects of independent variables on survival may not be constant over time and proportionality cannot be achieved, especially when long-term follow-up is required. When this occurs, it would be better to use alternative methods that are more powerful for the evaluation of various effective independent variables, such as milestone survival analysis, restricted mean survival time analysis (RMST), area under the survival curve (AUSC) method, parametric accelerated failure time (AFT), machine learning, nomograms, and offset variable in logistic regression. The aim was to discuss the pros and cons of these methods, especially with respect to long-term follow-up survival studies.

Bekiroglu G Nural, Avci Esin, Ozgur Emrah G

2022

Cox regression, area under the survival curve method, long-term follow-up, restricted mean survival time analysis, survival analysis

General General

Self-supervised learning for inter-laboratory variation minimization in surface-enhanced Raman scattering spectroscopy.

In The Analyst

Surface-enhanced Raman scattering (SERS) spectroscopy is still considered poorly reproducible despite its numerous advantages and is not a sufficiently robust analytical technique for routine implementation outside of academia. In this article, we present a self-supervised deep learning-based information fusion technique to minimize the variance in the SERS measurements of multiple laboratories for the same target analyte. In particular, a variation minimization model, coined the minimum-variance network (MVNet), is designed. Moreover, a linear regression model is trained using the output of the proposed MVNet. The proposed model showed improved performance in predicting the concentration of the unseen target analyte. The linear regression model trained on the output of the proposed model was evaluated by several well-known metrics, such as root mean square error of prediction (RMSEP), BIAS, standard error of prediction (SEP), and coefficient of determination (R2). The leave-one-lab-out cross-validation (LOLABO-CV) results indicate that the MVNet also minimizes the variance of completely unseen laboratory datasets while improving the reproducibility and linear fit of the regression model. The Python implementation of MVNet and the code for the analysis can be found on the GitHub page https://github.com/psychemistz/MVNet.

Park Seongyong, Wahab Abdul, Kim Minseok, Khan Shujaat

2023-Mar-02

Pathology Pathology

Label-free cleared tissue microscopy and machine learning for 3D histopathology of biomaterial implants.

In Journal of biomedical materials research. Part A

Tissue clearing of whole intact organs has enhanced imaging by enabling the exploration of tissue structure at a subcellular level in three-dimensional space. Although clearing and imaging of the whole organ have been used to study tissue biology, the microenvironment in which cells evolve to adapt to biomaterial implants or allografts in the body is poorly understood. Obtaining high-resolution information from complex cell-biomaterial interactions with volumetric landscapes represents a key challenge in the fields of biomaterials and regenerative medicine. To provide a new approach to examine how tissue responds to biomaterial implants, we apply cleared tissue light-sheet microscopy and three-dimensional reconstruction to utilize the wealth of autofluorescence information for visualizing and contrasting anatomical structures. This study demonstrates the adaptability of the clearing and imaging technique to provide sub-cellular resolution (0.6 μm isotropic) 3D maps of various tissue types, using samples from fully intact peritoneal organs to volumetric muscle loss injury specimens. Specifically, in the volumetric muscle loss injury model, we provide 3D visualization of the implanted extracellular matrix biomaterial in the wound bed of the quadricep muscle groups and further apply computational-driven image classification to analyze the autofluorescence spectrum at multiple emission wavelengths to categorize tissue types at the injured site interacting with the biomaterial scaffolds.

Ngo Tran B, DeStefano Sabrina, Liu Jiamin, Su Yijun, Shroff Hari, Vishwasrao Harshad D, Sadtler Kaitlyn

2023-Mar-02

3D imaging, biomaterials, image segmentation, light-sheet microscopy, optical tissue clearing, pathology, tissue-biomaterial interactions

General General

From Basic Sciences and Engineering to Epileptology: A Translational Approach.

In Epilepsia

Collaborative efforts between basic scientists, engineers, and clinicians are enabling translational epileptology. In this paper, we summarize recent advances presented at the International Conference for Technology and Analysis of Seizures (ICTALS 2022): 1) novel developments of structural magnetic resonance imaging; 2) latest electroencephalography signal processing applications; 3) big data for the development of clinical tools; 4) the emerging field of hyperdimensional computing; 5) the new generation of AI-enabled neuroprostheses; and 6) the use of collaborative platforms to facilitate epilepsy research translation. We highlight the promise of artificial intelligence reported in recent investigations and the need for multicenter data sharing initiatives.

Bou Assi Elie, Schindler Kaspar, de Bézenac Christophe, Denison Timothy, Desai Sharanya, Keller Simon S, Lemoine Émile, Rahimi Abbas, Shoaran Mahsa, Rummel Christian

2023-Mar-02

Electroencephalography, hyperdimensional computing, intelligent neural prostheses, magnetic resonance imaging, scientific platforms

General General

Machine learning within the Parkinson's progression markers initiative: Review of the current state of affairs.

In Frontiers in aging neuroscience ; h5-index 64.0

The Parkinson's Progression Markers Initiative (PPMI) has collected more than a decade's worth of longitudinal and multi-modal data from patients, healthy controls, and at-risk individuals, including imaging, clinical, cognitive, and 'omics' biospecimens. Such a rich dataset presents unprecedented opportunities for biomarker discovery, patient subtyping, and prognostic prediction, but it also poses challenges that may require the development of novel methodological approaches to solve. In this review, we provide an overview of the application of machine learning methods to analyzing data from the PPMI cohort. We find that there is significant variability in the types of data, models, and validation procedures used across studies, and that much of what makes the PPMI data set unique (multi-modal and longitudinal observations) remains underutilized in most machine learning studies. We review each of these dimensions in detail and provide recommendations for future machine learning work using data from the PPMI cohort.

Gerraty Raphael T, Provost Allison, Li Lin, Wagner Erin, Haas Magali, Lancashire Lee

2023

PD progression, Parkinson’s Disease, data analysis methods, machine learning, multi-omic analyses