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

Radiology Radiology

Interoperable slide microscopy viewer and annotation tool for imaging data science and computational pathology.

In Nature communications ; h5-index 260.0

The exchange of large and complex slide microscopy imaging data in biomedical research and pathology practice is impeded by a lack of data standardization and interoperability, which is detrimental to the reproducibility of scientific findings and clinical integration of technological innovations. We introduce Slim, an open-source, web-based slide microscopy viewer that implements the internationally accepted Digital Imaging and Communications in Medicine (DICOM) standard to achieve interoperability with a multitude of existing medical imaging systems. We showcase the capabilities of Slim as the slide microscopy viewer of the NCI Imaging Data Commons and demonstrate how the viewer enables interactive visualization of traditional brightfield microscopy and highly-multiplexed immunofluorescence microscopy images from The Cancer Genome Atlas and Human Tissue Atlas Network, respectively, using standard DICOMweb services. We further show how Slim enables the collection of standardized image annotations for the development or validation of machine learning models and the visual interpretation of model inference results in the form of segmentation masks, spatial heat maps, or image-derived measurements.

Gorman Chris, Punzo Davide, Octaviano Igor, Pieper Steven, Longabaugh William J R, Clunie David A, Kikinis Ron, Fedorov Andrey Y, Herrmann Markus D

2023-Mar-22

oncology Oncology

Immune gene patterns and characterization of the tumor immune microenvironment associated with cancer immunotherapy efficacy.

In Heliyon

Although immunotherapy has revolutionized cancer management, most patients do not derive benefits from it. Aiming to explore an appropriate strategy for immunotherapy efficacy prediction, we collected 6251 patients' transcriptome data from multicohort population and analyzed the data using a machine learning algorithm. In this study, we found that patients from three immune gene clusters had different overall survival when treated with immunotherapy (P < 0.001), and that these clusters had differential states of hypoxia scores and metabolism functions. The immune gene score showed good immunotherapy efficacy prediction (AUC was 0.737 at 20 months), which was well validated. The immune gene score, tumor mutation burden, and long non-coding RNA score were further combined to build a tumor immune microenvironment signature, which correlated more strongly with overall survival (AUC, 0.814 at 20 months) than when using a single variable. Thus, we recommend using the characterization of the tumor immune microenvironment associated with immunotherapy efficacy via a multi-omics analysis of cancer.

Lin Lili, Zhang Wenda, Chen Yongjian, Ren Wei, Zhao Jianli, Ouyang Wenhao, He Zifan, Su Weifeng, Yao Herui, Yu Yunfang

2023-Mar

AUC, Area under the curve, CIs, Confidence intervals, CTL, Cytotoxic T-lymphocyte infiltration, Cancer, GEO, Gene Expression Omnibus, GO, Gene Ontology, GSEA, Gene set enrichment analysis, GSVA, Gene set variation analysis, HLAs, Human leukocyte antigens, HRs, Hazard ratios, Immunotherapy, KEGG, Kyoto Encyclopedia of Genes and Genomes, LASSO, Penalized logistic least absolute shrinkage and selector operation, Machine learning, NSCLC, Non-small cell lung cancer, OS, Overall survival, PCA, Principal componentanalysis, PD-L1, Programmed death ligand-1, PFS, Profession-free survival, RNA-seq, Transcriptome RNA sequencing, ROC, receiver operating characteristic curves, TCGA, The Cancer Genome Atlas, TMB, Tumor mutation burden, TME, Tumor immunemicroenvironment, Tumor immune microenvironment, WGCNA, Weighted gene co-expression network analysis, lncRNA, Long non-coding RNA

General General

Assessing the influence of industry 4.0 technologies on occupational health and safety.

In Heliyon

The aim of this article is to know the impact that the different Industry 4.0 technologies have on occupational health and safety risks, with special attention to the new emerging risks generated. To achieve this objective, an analysis of the literature was carried out. It allowed us to design a survey that was answered by 130 managers and/or technicians of pioneering companies in the development of Industry 4.0 technologies. Next, 32 of these projects were selected and a multiple case study was conducted through 37 in-depth interviews. Moreover, other source of information were analysed (project reports, technical reports, websites..). The findings highlight that the analysed technologies (Additive Manufacturing, Artificial Intelligence, Artificial Vision, Big Data and/or Advanced Analytics, Cybersecurity, Internet of Things, Robotics and Virtual and Augmented Reality) help to reduce occupational health and safety risks (physical and mechanical). However, its impact depends on the type of technology and the method of application. Influences in new emerging risks (mainly psychosocial and mechanical) have been detected in all technologies except in Internet of Things. In addition, additive manufacturing, artificial intelligence, machine vision, the internet of things, robotics and virtual and augmented reality help to reduce ergonomic risks and artificial intelligence, big data and cybersecurity psychosocial risks. The results obtained have implications for policy makers, managers, consultants and those in charge of managing occupational health and safety risks in industrial companies.

Arana-Landín Germán, Laskurain-Iturbe Iker, Iturrate Mikel, Landeta-Manzano Beñat

2023-Mar

ISO 45001, Industry 4.0 technologies, Occupational health and safety, Occupational risks

Radiology Radiology

Amplitude of low-frequency fluctuation-based regional radiomics similarity network: Biomarker for Parkinson's disease.

In Heliyon

Parkinson's disease (PD) is a highly heterogeneous disorder that is difficult to diagnose. Therefore, reliable biomarkers are needed. We implemented a method constructing a regional radiomics similarity network (R2SN) based on the amplitude of low-frequency fluctuation (ALFF). We classified patients with PD and healthy individuals by using a machine learning approach in accordance with the R2SN connectome. The ALFF-based R2SN exhibited great reproducibility with different brain atlases and datasets. Great classification performances were achieved both in primary (AUC = 0.85 ± 0.02 and accuracy = 0.81 ± 0.03) and independent external validation (AUC = 0.77 and accuracy = 0.70) datasets. The discriminative R2SN edges correlated with the clinical evaluations of patients with PD. The nodes of discriminative R2SN edges were primarily located in the default mode, sensorimotor, executive control, visual and frontoparietal network, cerebellum and striatum. These findings demonstrate that ALFF-based R2SN is a robust potential neuroimaging biomarker for PD and could provide new insights into connectome reorganization in PD.

Shi Dafa, Ren Zhendong, Zhang Haoran, Wang Guangsong, Guo Qiu, Wang Siyuan, Ding Jie, Yao Xiang, Li Yanfei, Ren Ke

2023-Mar

Amplitude of low-frequency fluctuation (ALFF), Biomarker, Machine learning, Network, Parkinson’s disease

Internal Medicine Internal Medicine

Deep learning-assisted diagnosis of chronic atrophic gastritis in endoscopy.

In Frontiers in oncology

BACKGROUND : Chronic atrophic gastritis (CAG) is a precancerous condition. It is not easy to detect CAG in endoscopy. Improving the detection rate of CAG under endoscopy is essential to reduce or interrupt the occurrence of gastric cancer. This study aimed to construct a deep learning (DL) model for CAG recognition based on endoscopic images to improve the CAG detection rate during endoscopy.

METHODS : We collected 10,961 endoscopic images and 118 video clips from 4,050 patients. For model training and testing, we divided them into two groups based on the pathological results: CAG and chronic non-atrophic gastritis (CNAG). We compared the performance of four state-of-the-art (SOTA) DL networks for CAG recognition and selected one of them for further improvement. The improved network was called GAM-EfficientNet. Finally, we compared GAM-EfficientNet with three endoscopists and analyzed the decision basis of the network in the form of heatmaps.

RESULTS : After fine-tuning and transfer learning, the sensitivity, specificity, and accuracy of GAM-EfficientNet reached 93%, 94%, and 93.5% in the external test set and 96.23%, 89.23%, and 92.37% in the video test set, respectively, which were higher than those of the three endoscopists.

CONCLUSIONS : The CAG recognition model based on deep learning has high sensitivity and accuracy, and its performance is higher than that of endoscopists.

Shi Yanting, Wei Ning, Wang Kunhong, Wu Jingjing, Tao Tao, Li Na, Lv Bing

2023

chronic atrophic gastritis (CAG), deep learning - artificial intelligence, endoscopy, gastric cancer, transfer learning

General General

A versatile and fast-sampling rate wearable analog data logger.

In MethodsX

We propose a wearable, versatile, and open-source data logger that harvests the capacities of a low-cost microcontroller and enables fast-sampling recording of Analog signals into a microSD card. We describe here the circuit design and an exhaustive list of instructions to build a small, lightweight, and fast sampling rate data logger (up to 5 kHz for simultaneous recording of 3 channels and up to 40 kHz when using a single channel). We provide data analysis instructions, including publicly available scripts to facilitate its replication and customization. As a straightforward proof-of-concept, we tested our device embedded with a three-axial Analog accelerometer and were able to record triple axis acceleration of body movements in high resolution. A Fourier transform followed by a principal component analysis discriminated accurately between body motions of two participants and two types of movement recorded (walking VS running). Our wearable and fast-sampling rate data logger overcomes limits that we identified in previous studies, by being low-cost, capable of fast sampling rate, and easily replicated. Moreover, it can be customized to fit with a wide variety of applications in biomedical research by substituting the three-axial Analog accelerometer with virtually any type of Analog sensors or devices that output Analog signals. •We present a method to build and use a low-cost, fast-sampling rate and wearable Analog data logger, where having an engineering background is not required.•The data logger we present can collect Analog signals from 3 channels simultaneously at 5kHz and up to 40 kHz when using a single channel.•We demonstrate that our data logger can record data from a triple axis Analog accelerometer at 5 kHz, however, signals from virtually any Analog sensor or device that outputs Analog signals can be collected.

Bouchekioua Youcef, Matsui Hiroshi, Watanabe Shigeru

2023

Accelerometer, Analog, Data logger, Microcontroller, Movement disorders, Sensor, Versatile and Fast-Sampling Rate Wearable Analog Data Logger