Dataset Information

Task design for crowdsourced glioma cell annotation in microscopy images.

ABSTRACT: Crowdsourcing has been used in computational pathology to generate cell and cell nuclei annotations for machine learning. Herein, we broaden its scope to the previously unsolved challenging task of glioma cell detection. This requires multiplexed immunofluorescence microscopy due to diffuse invasiveness and exceptional similarity between glioma cells and reactive astrocytes. In four pilot experiments, we iteratively developed a task design enabling high-quality annotations by crowdworkers on Amazon Mechanical Turk. We applied majority or weighted vote and validated them against ground truth in the final setting. On the base of a YOLO convolutional neural network architecture, we used these consensus labels for training with different image representations regarding colors, intensities, and immmunohistochemical marker combinations. A crowd of 712 workers defined aggregated point annotations in 235 images with an average [Formula: see text] score of 0.627 for majority vote. The networks resulted in acceptable [Formula: see text] scores up to 0.69 for YOLOv8 on average and indicated first evidence for transferability to images lacking tumor markers, especially in IDH-wildtype glioblastoma. Our work confirms feasibility of crowdsourcing to generate labels suitable for training of machine learning tools in the challenging and clinically relevant use case of glioma microenvironment.

SUBMITTER: Schwarze S

PROVIDER: S-EPMC10805723 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Task design for crowdsourced glioma cell annotation in microscopy images.

Schwarze Svea S Schaadt Nadine S NS Sobotta Viktor M G VMG Spicher Nicolai N Skripuletz Thomas T Esmaeilzadeh Majid M Krauss Joachim K JK Hartmann Christian C Deserno Thomas M TM Feuerhake Friedrich F

Scientific reports 20240123 1

Crowdsourcing has been used in computational pathology to generate cell and cell nuclei annotations for machine learning. Herein, we broaden its scope to the previously unsolved challenging task of glioma cell detection. This requires multiplexed immunofluorescence microscopy due to diffuse invasiveness and exceptional similarity between glioma cells and reactive astrocytes. In four pilot experiments, we iteratively developed a task design enabling high-quality annotations by crowdworkers on Ama ...[more]

PMID: 38263411

Similar Datasets

Project description:SignificanceAccurate identification of epidermal cells on reflectance confocal microscopy (RCM) images is important in the study of epidermal architecture and topology of both healthy and diseased skin. However, analysis of these images is currently done manually and therefore time-consuming and subject to human error and inter-expert interpretation. It is also hindered by low image quality due to noise and heterogeneity.AimWe aimed to design an automated pipeline for the analysis of the epidermal structure from RCM images.ApproachTwo attempts have been made at automatically localizing epidermal cells, called keratinocytes, on RCM images: the first is based on a rotationally symmetric error function mask, and the second on cell morphological features. Here, we propose a dual-task network to automatically identify keratinocytes on RCM images. Each task consists of a cycle generative adversarial network. The first task aims to translate real RCM images into binary images, thus learning the noise and texture model of RCM images, whereas the second task maps Gabor-filtered RCM images into binary images, learning the epidermal structure visible on RCM images. The combination of the two tasks allows one task to constrict the solution space of the other, thus improving overall results. We refine our cell identification by applying the pre-trained StarDist algorithm to detect star-convex shapes, thus closing any incomplete membranes and separating neighboring cells.ResultsThe results are evaluated both on simulated data and manually annotated real RCM data. Accuracy is measured using recall and precision metrics, which is summarized as the F1 -score.ConclusionsWe demonstrate that the proposed fully unsupervised method successfully identifies keratinocytes on RCM images of the epidermis, with an accuracy on par with experts' cell identification, is not constrained by limited available annotated data, and can be extended to images acquired using various imaging techniques without retraining.

Project description:The primary purpose of this study was to examine whether 2D:4D ratios (a putative measure of prenatal androgen exposure) could be determined using participant-submitted hand images. The secondary purpose was to examine whether 2D:4D ratio was associated with pro-environmental behaviors, attitudes, and empathy, given the recent literature linking sex to environmental attitudes and actions. Participants (N = 1065) were asked via an online survey to submit a clear photograph of their right hand, palm side up. Participants also completed a questionnaire to assess (a) demographics, (b) dispositional empathy, and (c) environmental attitudes and behavior. A 2D:4D ratio was calculated for each participant, and the quality of each image was classified as poor, moderate, or good. We then examined the reliability of the 2D:4D image measurements, and the relationship between 2D:4D and our environmental measures. 2D:4D ratios fell somewhat outside of previously reported ranges, but the measurements did show acceptable intra-rater consistency. Although we did not find a sex difference in 2D:4D, we did find a sex by ratio interaction for both empathy and the number of pro-environmental behaviors in which individuals had engaged. Specifically, as 2D:4D ratio increased, males reported lower empathy and less engagement in pro-environmental behaviors, whereas females reported more engagement in pro-environmental behaviors (but no differences in empathy). These findings were contrary to expectations, as we anticipated that greater digit ratios (i.e., feminized) would be associated with greater empathy and pro-environmental behaviors. Overall, the findings of this study present a preliminary examination of the utility of measuring digit ratio with online samples. Furthermore, our results provide information regarding the complex relationship between sex and pro-environmental behaviors.Supplementary informationThe online version contains supplementary material available at 10.1007/s10211-022-00401-5.

Dataset Information

Task design for crowdsourced glioma cell annotation in microscopy images.

Publications

Task design for crowdsourced glioma cell annotation in microscopy images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets