Automated segmentation and analysis of retinal microglia within ImageJ

μGlia-Flow, an automatic workflow for microglia segmentation and classification

BACKGROUND

Microglia are important immune cells in the central nervous system, playing a key role in various pathological processes. The morphological diversity of microglia is closely linked to the development of brain diseases, yet accurate segmentation and automatic classification of microglia remain challenging.

NEW METHOD

We proposed a workflow, μGlia-Flow, which integrates both segmentation and classification for microglia analysis. The Frangi filtering algorithm was employed for branch segmentation, and an edge-guided attention TransUNet (EGA-Net) was used for soma segmentation. A Vision Transformer (ViT) network was applied to classify different morphologies.

RESULTS

The Frangi filtering algorithm produces more complete branches with smoother edges and clearer structures. The EGA-Net improves Dice and IoU scores by 4.02 % and 6.75 %, respectively. ViT achieves over 99 % precision in classification. Post-processing reveals decreasing complexity during activation, validating the accuracy of μGlia-Flow.

COMPARISON WITH EXISTING METHODS

μGlia-Flow introduces deep learning, significantly improving segmentation accuracy and addressing the parameter dependency of existing classification methods.

CONCLUSION

we present an automatic workflow for segmenting and classifying microglia, providing a powerful tool for different morphology analysis.

Leveraging Deep Learning for Immune Cell Quantification and Prognostic Evaluation in Radiotherapy-Treated Oropharyngeal Squamous Cell Carcinomas

The tumor microenvironment plays a critical role in cancer progression and therapeutic responsiveness, with the tumor immune microenvironment (TIME) being a key modulator. In head and neck squamous cell carcinomas (HNSCCs), immune cell infiltration significantly influences the response to radiotherapy (RT). A better understanding of the TIME in HNSCCs could help identify patients most likely to benefit from combining RT with immunotherapy. Standardized, cost-effective methods for studying TIME in HNSCCs are currently lacking. This study aims to leverage deep learning (DL) to quantify immune cell densities using immunohistochemistry in untreated oropharyngeal squamous cell carcinoma (OPSCC) biopsies of patients scheduled for curative RT and assess their prognostic value. We analyzed 84 pretreatment formalin-fixed paraffin-embedded tumor biopsies from OPSCC patients. Immunohistochemistry was performed for CD3, CD8, CD20, CD163, and FOXP3, and whole slide images were digitized for analysis using a U-Net-based DL model. Two quantification approaches were applied: a cell-counting method and an area-based method. These methods were applied to stained regions. The DL model achieved high accuracy in detecting stained cells across all biomarkers. Strong correlations were found between our DL pipeline, the HALO Image Analysis Platform, and the open-source QuPath software for estimating immune cell densities. Our DL pipeline provided an accurate and reproducible approach for quantifying immune cells in OPSCC. The area-based method demonstrated superior prognostic value for recurrence-free survival, when compared with the cell-counting method. Elevated densities of CD3, CD8, CD20, and FOXP3 were associated with improved recurrence-free survival, whereas CD163 showed no significant prognostic association. These results highlight the potential of DL in digital pathology for assessing TIME and predicting patient outcomes.

A review of open-source image analysis tools for mammalian cell culture: algorithms, features and implementations

Cell culture is undeniably important for multiple scientific applications, including pharmaceuticals, transplants, and cosmetics. However, cell culture involves multiple manual steps, such as regularly analyzing cell images for their health and morphology. Computer scientists have developed algorithms to automate cell imaging analysis, but they are not widely adopted by biologists, especially those lacking an interactive platform. To address the issue, we compile and review existing open-source cell image processing tools that provide interactive interfaces for management and prediction tasks. We highlight the prediction tools that can detect, segment, and track different mammalian cell morphologies across various image modalities and present a comparison of algorithms and unique features of these tools, whether they work locally or in the cloud. This would guide non-experts to determine which is best suited for their purposes and, developers to acknowledge what is worth further expansion. In addition, we provide a general discussion on potential implementations of the tools for a more extensive scope, which guides the reader to not restrict them to prediction tasks only. Finally, we conclude the article by stating new considerations for the development of interactive cell imaging tools and suggesting new directions for future research.

POLYRETINA restores light responses in vivo in blind Göttingen minipigs

Retinal prostheses hold the potential for artificial vision in blind people affected by incurable diseases of the outer retinal layer. Available technologies provide only a small field of view: a significant limitation for totally blind people. To overcome this problem, we recently proposed a large and high-density photovoltaic epiretinal device, known as POLYRETINA. Here, we report the in vivo assessment of POLYRETINA. First, we characterise a model of chemically-induced blindness in Göttingen minipigs. Then, we develop and test a minimally invasive injection procedure to insert the large epiretinal implant into the eye. Last, we show that POLYRETINA restores light-evoked cortical responses in blind animals at safe irradiance levels. These results indicate that POLYRETINA holds the potential for artificial vision in totally blind patients affected by retinitis pigmentosa.

Automated characterisation of microglia in ageing mice using image processing and supervised machine learning algorithms

The resident macrophages of the central nervous system, microglia, are becoming increasingly implicated as active participants in neuropathology and ageing. Their diverse and changeable morphology is tightly linked with functions they perform, enabling assessment of their activity through image analysis. To better understand the contributions of microglia in health, senescence, and disease, it is necessary to measure morphology with both speed and reliability. A machine learning approach was developed to facilitate automatic classification of images of retinal microglial cells as one of five morphotypes, using a support vector machine (SVM). The area under the receiver operating characteristic curve for this SVM was between 0.99 and 1, indicating strong performance. The densities of the different microglial morphologies were automatically assessed (using the SVM) within wholemount retinal images. Retinas used in the study were sourced from 28 healthy C57/BL6 mice split over three age points (2, 6, and 28-months). The prevalence of 'activated' microglial morphology was significantly higher at 6- and 28-months compared to 2-months (p < .05 and p < .01 respectively), and 'rod' significantly higher at 6-months than 28-months (p < 0.01). The results of the present study propose a robust cell classification SVM, and further evidence of the dynamic role microglia play in ageing.

Full-thickness macular holes after surgical repair of primary rhegmatogenous retinal detachments: incidence, clinical characteristics, and outcomes

PURPOSE

Full-thickness macular hole (FTMH) formation following rhegmatogenous retinal detachment (RRD) repair may limit post-operative visual acuity and often requires a return to the operating room, but little is known about this phenomenon.

METHODS

This study included all patients with a FTMH that developed after RRD repair from January 1, 2015-July 31, 2020. The main outcome was the rate of FTMH formation following RRD repair as well as characteristics of FTMH following RRD repair that spontaneously close.

RESULTS

There were 470 eyes with a diagnosis of both a FTMH and a RRD during the study period. Of these, 27 (0.28%) developed a FTMH following RRD repair. The median time to FTMH diagnosis was 91 days (25th, 75th quartiles 40, 204 days). The mean minimum hole diameter was 514.5 ± 303.6 microns. There were 4 FTMHs (14.8%) that spontaneously closed without surgical intervention. The spontaneous closure was noted from 4 to 12 weeks after the initial diagnosis of the FTMH. These holes were smaller than the holes that did not close spontaneously (mean minimum diameter 161.8 ± 85.2 vs 588.7 ± 279.3 microns, p = 0.0058). Of the 27 post-operative FTMHs, there were 23 eyes (85%) that underwent surgical intervention with pars plana vitrectomy and internal limiting membrane peeling. Nineteen eyes (83%) closed with one surgery, 20 eyes (87%) ultimately closed, while 3 eyes (11.1%) did not close.

CONCLUSIONS

FTMH is relatively uncommon to occur following RRD repair with a prevalence of 0.28% in our series with 87% of these holes achieving closure following surgery or spontaneously. Approximately 15% of FTMHs following RRD repair closed spontaneously and these holes were significantly smaller.