Annotated Data Research Articles

Knowledge Extraction from LLMs for Scalable Historical Data Annotation

This paper introduces a novel approach to extract knowledge from large language models and generate structured historical datasets. We investigate the feasibility and limitations of this technique by comparing the generated data against two human-annotated historical datasets spanning from 10,000 BC to 2000 CE. Our findings demonstrate that generative AI can successfully produce historical annotations for a wide range of variables, including political, economic, and social factors. However, the model’s performance varies across different regions, influenced by factors such as data granularity, historical complexity, and model limitations. We highlight the importance of high-quality instructions and effective prompt engineering to mitigate issues like hallucinations and improve the accuracy of generated annotations. The successful application of this technique can significantly accelerate the development of reliable structured historical datasets, with a potentially high impact on comparative and computational history.

SegmOnto: A Controlled Vocabulary to Describe and Process Digital Facsimiles

Our initiative aims at designing a controlled vocabulary for the description of the layout of textual sources: SegmOnto. Following a more physical approach rather than a strictly semantic one, it is designed as a pragmatic and generic typology, coping with most of the Western historical documents rather than answering specific needs. The harmonisation of the layout description has a double objective: on the one hand it facilitates the mutualisation of annotated data and therefore the training of better models for page segmentation (a crucial preliminary step for text recognition), on the other hand it allows the development of a shared post-processing workflow and pipeline for the transformation of ALTO or PAGE files into DH standard formats, which preserves as much as possible the link between the extracted information and the digital facsimile. To demonstrate the capacity of SegmOnto to answer both these objectives, we aggregate data from multiple projects to train a layout analysis model, and we propose a prototype of a generic pipeline for converting ALTO-XMLs into XML-TEI.

Use Self-Training Random Forest for Predicting Winter Wheat Yield

The effectiveness of supervised ML heavily depends on having a large, accurate, and diverse annotated dataset, which poses a challenge in applying ML for yield prediction. To address this issue, we developed a self-training random forest algorithm capable of automatically expanding the annotated dataset. Specifically, we trained a random forest regressor model using a small amount of annotated data. This model was then utilized to generate new annotations, thereby automatically extending the training dataset through self-training. Our experiments involved collecting data from over 30 winter wheat varieties during the 2019–2020 and 2021–2022 growing seasons. The testing results indicated that our model achieved an R2 of 0.84, RMSE of 627.94 kg/ha, and MAE of 516.94 kg/ha in the test dataset, while the validation dataset yielded an R2 of 0.81, RMSE of 692.96 kg/ha, and MAE of 550.62 kg/ha. In comparison, the standard random forest resulted in an R2 of 0.81, RMSE of 681.02 kg/ha, and MAE of 568.97 kg/ha in the test dataset, with validation results of an R2 of 0.79, RMSE of 736.24 kg/ha, and MAE of 585.85 kg/ha. Overall, these results demonstrate that our self-training random forest algorithm is a practical and effective solution for expanding annotated datasets, thereby enhancing the prediction accuracy of ML models in winter wheat yield forecasting.

Improved self-training-based distant label denoising method for cybersecurity entity extractions.

The task of named entity recognition (NER) plays a crucial role in extracting cybersecurity-related information. Existing approaches for cybersecurity entity extraction predominantly rely on manual labelling data, resulting in labour-intensive processes due to the lack of a cybersecurity-specific corpus. In this paper, we propose an improved self-training-based distant label denoising method for cybersecurity entity extraction. Firstly, we create two domain dictionaries of cybersecurity. Then, an algorithm that combines reverse maximum matching and part-of-speech tagging restrictions is proposed, for generating distant labels for the cybersecurity domain corpus. Lastly, we propose a high-confidence text selection method and an improved self-training algorithm that incorporates a teacher-student model and weight update constraints, for exploring the true labels of low-confidence text using a model trained on high-confidence text, thereby reducing the noise in the distant annotation data. Experimental results demonstrate that the cybersecurity distantly-labelled data we obtained is of high quality. Additionally, the proposed constrained self-training algorithm effectively improves the F1 score of several state-of-the-art NER models on this dataset, yielding a 3.5% improvement for the Vendor class and a 3.35% improvement for the Product class.

Detection of Helmet Violations among Electric Bicycle Riders Through Multi-Network

The use of helmets plays a crucial role in mitigating head injuries resulting from traffic accidents. However, manual supervision of helmet usage is both costly and prone to missing target objects. With the advancement of technology and widespread use of surveillance cameras, it has become technically feasible to automatically detect riders’ helmet wearing based on roadside videos. This capability holds significant potential in effectively guiding riders to wear helmets and enhancing driving safety. This paper presents a multi-network-based approach for automated detection of helmet wearing among electric bicycle riders. The object detection model is employed to detect electric bicycles and helmets. Additionally, the overall approach utilizes a human pose estimator to detect keypoints of human skeletons for selecting the region of interest (RoI) corresponding to the head region location. We propose location rules to extract the rider region within the electric bicycle box for distinguishing riders and locate the head region based on human skeleton keypoints for helmet wearing matching. The mean average precision (mAP) of the detection model trained on public datasets reaches 91.8%. To evaluate matching accuracy, we randomly selected 150 correctly detected images from the open-sourced two-wheeler helmet dataset (TWHD), achieving a matching accuracy of 95.6%. The detection model is trained and tested on public datasets which effectively facilitates the processes of data collection and annotation. Based on multi-network information fusion, we can accurately detect helmet violations among electric bicycle riders in multi-person interaction scenarios.

Classification of real and bogus transients using active learning and semi-supervised learning

The mounting data stream of large time-domain surveys renders the visual inspections of a huge set of transient candidates impractical. Techniques based on deep learning-based are popular solutions for minimizing human intervention in the time domain community. The classification of real and bogus transients is a fundamental component in real-time data processing systems and is critical to enabling rapid follow-up observations. Most existing methods (supervised learning) require sufficiently large training samples with corresponding labels, which involve costly human labeling and are challenging in the early stages of a time-domain survey. One method that can make use of training samples with access to only a limited amount of labels is highly desirable for future large time-domain surveys. These include the forthcoming 2.5-meter Wide-Field Survey Telescope (WFST) six-year survey and the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST). Deep-learning-based methods have been favored in astrophysics owing to their adaptability and remarkable performance. They have been applied to the task of the classification of real and bogus transients. Unlike most existing approaches, which necessitate massive and expensive annotated data, we aim to leverage training samples with only 1000 labels and discover real sources that vary in brightness over time in the early stages of the WFST six-year survey. We present a novel deep learning method that combines active learning and semi-supervised learning to construct a competitive real-bogus classifier. Our method incorporates an active learning stage, where we actively select the most informative or uncertain samples for annotation. This stage aims to achieve higher model performance by leveraging fewer labeled samples, thus reducing annotation costs and improving the overall learning process efficiency. Furthermore, our approach involves a semi-supervised learning stage that exploits the unlabeled data to enhance the model's performance and achieve superior results, compared to using only the limited labeled data. Our proposed methodology capitalizes on the potential of active learning and semi-supervised learning. To demonstrate the efficacy of our approach, we constructed three newly compiled datasets from the Zwicky Transient Facility (ZTF), achieving average accuracies of 98.8<!PCT!>, 98.8<!PCT!>, and 98.6<!PCT!> across these three datasets. It is important to note that our newly compiled datasets only work in terms of testing our deep learning methodology and there may be a potential bias between our datasets and the complete data stream. Therefore, the observed performance on these datasets cannot be assumed to directly translate to the general alert stream for general transient detection in actual scenarios. The algorithm will be integrated into the WFST pipeline, enabling an efficient and effective classification of transients in the early period of a time-domain survey.

Toward generalizable phenotype prediction from single-cell morphology representations

BackgroundFunctional cell processes (e.g., molecular signaling, response to stimuli, mitosis, etc.) impact cell phenotypes, which scientists can measure with cell morphology. However, linking these measurements with phenotypes remains challenging because it requires manually annotated labels. We propose that nuclear morphology can be a predictive marker for cell phenotypes that are generalizable across contexts.MethodsWe reanalyzed a pre-labeled, publicly-available nucleus microscopy dataset from the MitoCheck consortium. We extracted single-cell morphology features using CellProfiler and DeepProfiler, which provide robust processing pipelines. We trained multinomial, multi-class elastic-net logistic regression models to classify nuclei into one of 15 phenotypes such as ‘Anaphase,’ ‘Apoptosis’, and ‘Binuclear’. We rigorously assessed performance using F1 scores, precision-recall curves, and a leave-one-image-out (LOIO) cross-validation analysis. In LOIO, we retrained models using cells from every image except one and predicted phenotype in the held-out image, repeating this procedure for all images. We evaluated each morphology feature space, a concatenated feature space, and several feature space subsets (e.g., nuclei AreaShape features only). We applied models to the Joint Undertaking in Morphological Profiling (JUMP) data to assess performance using a different dataset.ResultsIn a held-out test set, we observed an overall F1 score of 0.84. Individual phenotype scores ranged from 0.64 (moderate performance) to 0.99 (high performance). Phenotypes such as ‘Elongated’, ‘Metaphase’, and ‘Apoptosis’ showed high performance. While CellProfiler and DeepProfiler features were generally equally effective, concatenation yielded the best results for 9/15 phenotypes. LOIO showed a performance decline, indicating our model could not reliably predict phenotypes in new images. Poor performance was unrelated to illumination correction or model selection. Applied to the JUMP data, models trained using nuclear AreaShape features only increased alignment with the annotated MitoCheck data (based on UMAP space). This approach implicated many chemical and genetic perturbations known to be associated with specific phenotypes.DiscussionPoor LOIO performance demonstrates challenges of single-cell phenotype prediction in new datasets. We propose several strategies that could pave the way for more generalizable methods in single-cell phenotype prediction, which is a step toward morphology representation ontologies that would aid in cross-dataset interpretability.

Optimizing Privacy in Set-Valued Data: Comparing Certainty Penalty and Information Gain

The increase in set-valued data such as transaction records and medical histories has introduced new challenges in data anonymization. Traditional anonymization techniques targeting structured microdata comprising single-attribute- rather than set-valued records are often insufficient to ensure privacy protection in complex datasets, particularly when re-identification attacks leverage partial background knowledge. To address these limitations, this study proposed the Local Generalization and Reallocation (LGR) + algorithm to replace the Normalized Certainty Penalty loss measure (hereafter, NCP) used in traditional LGR algorithms with the Information Gain Heuristic metric (hereafter, IGH). IGH, an entropy-based metric, evaluates information loss based on uncertainty and provides users with the advantage of balancing privacy protection and data utility. For instance, when IGH causes greater information-scale data annotation loss than NCP, it ensures stronger privacy protection for datasets that contain sensitive or high-risk information. Conversely, when IGH induces less information loss, it provides better data utility for less sensitive or low-risk datasets. The experimental results based on using the BMS-WebView-2 and BMS-POS datasets showed that the IGH-based LGR + algorithm caused up to 100 times greater information loss than NCP, indicating significantly improved privacy protection. Although the opposite case also exists, the use of IGH introduces the issue of increased computational complexity. Future research will focus on optimizing efficiency through parallel processing and sampling techniques. Ultimately, LGR+ provides the only viable solution for improving the balance between data utility and privacy protection, particularly in scenarios that prioritize strong privacy or utility guarantees.

Contextualized race and ethnicity annotations for clinical text from MIMIC-III

Observational health research often relies on accurate and complete race and ethnicity (RE) patient information, such as characterizing cohorts, assessing quality/performance metrics of hospitals and health systems, and identifying health disparities. While the electronic health record contains structured data such as accessible patient-level RE data, it is often missing, inaccurate, or lacking granular details. Natural language processing models can be trained to identify RE in clinical text which can supplement missing RE data in clinical data repositories. Here we describe the Contextualized Race and Ethnicity Annotations for Clinical Text (C-REACT) Dataset, which comprises 12,000 patients and 17,281 sentences from their clinical notes in the MIMIC-III dataset. Using these sentences, two sets of reference standard annotations for RE data are made available with annotation guidelines. The first set of annotations comprise highly granular information related to RE, such as preferred language and country of origin, while the second set contains RE labels annotated by physicians. This dataset can support health systems’ ability to use RE data to serve health equity goals.

Bi-modal contrastive learning for crop classification using Sentinel-2 and Planetscope

Remote sensing has enabled large-scale crop classification for understanding agricultural ecosystems and estimating production yields. In recent years, machine learning has become increasingly relevant for automated crop classification. However, the existing algorithms require a huge amount of annotated data. Self-supervised learning, which enables training on unlabeled data, has great potential to overcome the problem of annotation. Contrastive learning, a self-supervised approach based on instance discrimination, has shown promising results in the field of natural as well as remote sensing images. Crop data often consists of field parcels or sets of pixels from small spatial regions. Additionally, one needs to account for temporal patterns to correctly label crops. Hence, the standard approaches for landcover classification cannot be applied. In this work, we propose two contrastive self-supervised learning approaches to obtain a pre-trained model for crop classification without the need for labeled data. First, we adopt the uni-modal contrastive method (SCARF) and, second, we use a bi-modal approach based on Sentinel-2 and Planetscope data instead of standard transformations developed for natural images to accommodate the spectral characteristics of crop pixels. Evaluation in three regions of Germany and France shows that crop classification with the pre-trained multi-modal model is superior to the pre-trained uni-modal method as well as the supervised baseline models in the majority of test cases.

Automatic segmentation of pericardial adipose tissue from cardiac MR images via semi-supervised method with difference-guided consistency.

Accurate and automatic segmentation of pericardial adipose tissue (PEAT) in cardiac magnetic resonance (MR) images is essential for the diagnosis and treatment of cardiovascular diseases. Precise segmentation is challenging due to high costs and the need for specialized knowledge, as a large amount of accurately annotated data is required, demanding significant time and medicalresources. In order to reduce the burden of data annotation while maintaining the high accuracy of segmentation tasks, this paper introduces a semi-supervised learning method to solve the limitations of current PEAT segmentationmethods. In this paper, we propose a difference-guided collaborative mean teacher (DCMT) semi-supervised method, designed for the segmentation of PEAT from DCMT consists of two main components: a semi-supervised framework with a difference fusion strategy and a backbone network MCM-UNet using Mamba-CNN mixture (MCM) blocks. The differential fusion strategy effectively utilizes the uncertain areas in unlabeled data, encouraging the model to reach a consensus in predictions across these difficult-to-segment yet information-rich areas. In addition, considering the sparse and scattered distribution of PEAT in cardiac MR images, which makes it challenging to segment, we propose MCM-UNet as the backbone network in our semi-supervised framework. This not only enhances the processing ability of global information, but also accurately captures the detailed local features of the image, which greatly improves the accuracy of PEATsegmentation. Our experiments conducted on the MRPEAT dataset show that our DCMT method outperforms existing state-of-the-art semi-supervised methods in terms of segmentation accuracy. These findings underscore the effectiveness of our approach in handling the specific challenges associated with PEATsegmentation. The DCMT method significantly improves the accuracy of PEAT segmentation in cardiac MR images. By effectively utilizing uncertain areas in the data and enhancing feature capture with the MCM-UNet, our approach demonstrates superior performance and offers a promising solution for semi-supervised learning in medical image segmentation. This method can alleviate the extensive annotation requirements typically necessary for training accurate segmentation models in medicalimaging.

A Semi-Supervised Multi-Region Segmentation Framework of Bladder Wall and Tumor with Wall-Enhanced Self-Supervised Pre-Training

Bladder cancer is a prevalent and highly recurrent malignancy within the urinary tract. The accurate segmentation of the bladder wall and tumor in magnetic resonance imaging (MRI) is a crucial step in distinguishing between non-muscle-invasive and muscle-invasive types of bladder cancer, which plays a pivotal role in guiding clinical treatment decisions and influencing postoperative quality of life. The performance of data-driven methods is highly dependent on the quality of the annotations and datasets, however the amount of high-quality annotated data is very limited given the difficulty of professional radiologists to distinguish the mixed regions between the bladder wall and the tumor. The performance of the data-driven approach is highly dependent on the quality of the annotation and datasets, Therefore, in order to alleviate these problems and take full advantage of the potential of limited annotated and unlabeled data, we designed a semi-supervised multi-region framework for bladder wall and tumor segmentation. Our framework incorporates wall-enhanced self-supervised pre-training, designed to enhance discrimination of the bladder wall, and a semi-supervised segmentation network that utilizes both limited high-quality annotated data and unlabeled data. Contrast consistency and reconstruction observation losses are introduced to constrain the model to enhance the bladder walls, and adaptive learning rate and post-processing techniques are implemented to further improve segmentation performance. Extensive experimental validation demonstrated that our proposed method achieves promising results in the segmentation of both the bladder wall and the tumor. The average Dice Similarity Coefficients (DSCs) of the proposed method for the bladder wall and tumor were 0.8351 and 0.9175, respectively. Visualization results indicated that our method can effectively reduce excessive segmentation artifacts outside the bladder, and improve the clinical significance of the segmentation results.

Interpreting single-cell and spatial omics data using deep neural network training dynamics.

Single-cell and spatial omics datasets can be organized and interpreted by annotating single cells to distinct types, states, locations or phenotypes. However, cell annotations are inherently ambiguous, as discrete labels with subjective interpretations are assigned to heterogeneous cell populations on the basis of noisy, sparse and high-dimensional data. Here we developed Annotatability, a framework for identifying annotation mismatches and characterizing biological data structure by monitoring the dynamics and difficulty of training a deep neural network over such annotated data. Following this, we developed a signal-aware graph embedding method that enables downstream analysis of biological signals. This embedding captures cellular communities associated with target signals. Using Annotatability, we address key challenges in the interpretation of genomic data, demonstrated over eight single-cell RNA sequencing and spatial omics datasets, including identifying erroneous annotations and intermediate cell states, delineating developmental or disease trajectories, and capturing cellular heterogeneity. These results underscore the broad applicability of annotation-trainability analysis via Annotatability for unraveling cellular diversity and interpreting collective cell behaviors in health and disease.

Development and validation of a fluency rating scale for Swiss German Sign Language

IntroductionSign language fluency is an area that has received very little attention within research on sign language education and assessment. Therefore, we wanted to develop and validate a rating scale of fluency for Swiss German Sign Language (Deutschschweizerische Gebärdensprache, DSGS).MethodsDifferent kinds of data were collected to inform the rating scale development. The data were from (1) focus group interviews with sign language teachers (N = 3); (2) annotated DSGS data from users/learners with various levels of proficiency (i.e., deaf native signers of DSGS, hearing sign language interpreters, and beginning learners of DSGS, approximately CEFR level A1-A2) (N = 28) who completed different signing tasks that were manipulated by preparation time; (3) feedback from raters (N = 3); and (4) complimented with theory from spoken and sign language fluency.ResultsIn the focus group interview, sign language teachers identified a number of fluency aspects. The annotated DSGS data were analyzed using different regression models to see how language background and preparation time for the tasks can predict aspects of fluency (e.g., number and duration of pauses). Whereas preparation time showed only a slight effect in the annotated data, language background predicted the occurrence of fluency features that also informed the scale development. The resulting rating scale consisted of six criteria, each on a six-point scale. DSGS performances (N = 162) (same as the annotated data) from the different groups of DSGS users/learners were rated by three raters. The rated data were analyzed using multi-facet Rasch measurement. Overall, the rating scale functioned well, with each score category being modal at some point on the continuum. Results from correlation and regression analysis of the annotated data and rated DSGS performances complemented validity evidence of the rating scale.DiscussionWe argue that the different sources of data serve as a sound empirical basis for the operationalized “DSGS fluency construct” in the rating scale. The results of the analyses relating performance data to ratings show strong validity evidence of the second version of the rating scale. Together, the objective fluency measures explained 88% of the variance in the rating scores.

Retinal Image Augmentation using Composed GANs

Medical image analysis faces a significant challenge in the scarcity of annotated data, which is crucial for developing generalizable Deep Learning (DL) models that require extensive training data. Consequently, the field of medical image generation has garnered substantial interest and potential for further exploration. Besides widely employed data augmentation techniques, such as rotation, reflection, and scaling, Generative Adversarial Networks (GANs) have demonstrated the ability to effectively leverage additional information from datasets by generating synthetic samples from real images. In the context of retinal image synthesis, an image-to-image translation approach is frequently adopted to generate retinal images from available vessel maps, which can be scarce and resource-intensive to obtain. Deviating from prior work reliant on pre-existing vessel maps, this study proposes a learning-based model that is independent of vessel maps, utilizing Progressive Growing GAN (PGGAN) to generate vascular networks from random noise. The visual and quantitative evaluations conducted suggest that the majority of the images generated by the proposed model are substantially distinct from the training set while maintaining a high proportion of true image quality, underscoring the model's potential as a powerful tool for data augmentation.

RESMatch: Referring expression segmentation in a semi-supervised manner

Referring Expression segmentation (RES), a task that involves localizing specific instance-level objects on the basis of free-form linguistic descriptions, has emerged as a crucial frontier in human–AI interactions. It demands an intricate understanding of both the visual and textual contexts, and often requires extensive training data. This paper introduces RESMatch, the first semi-supervised learning (SSL) approach for RES aimed at reducing reliance on exhaustive data annotation. Moreover, our proposed RESMatch can leverage the abundance of image–text paired data available in the current era of training large models, resulting in an improved RES task performance without the need for costly semantic annotation, as evidenced by our experimental results. Moreover, although existing SSL techniques are effective in image segmentation, we find that they fall short in RES. Facing challenges such as the comprehension of free-form linguistic descriptions and the variability in object attributes, RESMatch introduces a trifecta of adaptations: revised strong perturbation, text augmentation, and adjustments for pseudolabel quality and strong–weak supervision. RESMatch has demonstrated its effectiveness by achieving state-of-the-art (SOTA) results in various experimental settings. This pioneering work lays the groundwork for future research in semi-supervised learning for referring expression segmentation.

Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration

In our increasingly interconnected world, where intelligent devices continually amass copious personalized multi-modal data, a pressing need arises to deliver high-quality, personalized device-aware services. However, this endeavor presents a multifaceted challenge to prevailing artificial intelligence (AI) systems primarily rooted in the cloud. As these systems grapple with shifting data distributions between the cloud and devices, the traditional approach of fine-tuning-based adaptation (FTA) exists the following issues: the costly and time-consuming data annotation required by FTA and the looming risk of model overfitting. To surmount these challenges, we introduce a Universal On-Device Multi-modal Model Adaptation Framework, revolutionizing on-device model adaptation by striking a balance between efficiency and effectiveness. The framework features the Fast Domain Adaptor (FDA) hosted in the cloud, providing tailored parameters for the Lightweight Multi-modal Model on devices. To enhance adaptability across multi-modal tasks, the AnchorFrame Distribution Reasoner (ADR) minimizes communication costs. Our contributions, encapsulated in the Cloud-Device Collaboration Multi-modal Parameter Generation (CDC-MMPG) framework, represent a pioneering solution for on-Device Multi-modal Model Adaptation (DMMA). Extensive experiments validate the efficiency and effectiveness of our method, particularly in video question answering and retrieval tasks, driving forward the integration of intelligent devices into our daily lives.

CGFTNet:Content-Guided Frequency Domain Transform Network for Face Super-Resolution

Recent advancements in face super resolution (FSR) have been propelled by deep learning techniques using convolutional neural networks (CNN). However, existing methods still struggle with effectively capturing global facial structure information, leading to reduced fidelity in reconstructed images, and often require additional manual data annotation. To overcome these challenges, we introduce a content-guided frequency domain transform network (CGFTNet) for face super-resolution tasks. The network features a channel attention-linked encoder-decoder architecture with two key components: the Frequency Domain and Reparameterized Focus Convolution Feature Enhancement module (FDRFEM) and the Content-Guided Channel Attention Fusion (CGCAF) module. FDRFEM enhances feature representation through transformation domain techniques and reparameterized focus convolution (RefConv), capturing detailed facial features and improving image quality. CGCAF dynamically adjusts feature fusion based on image content, enhancing detail restoration. Extensive evaluations across multiple datasets demonstrate that the proposed CGFTNet consistently outperforms other state-of-the-art methods.

Visualizing Volumetric and Segmentation Data using Mol* Volumes & Segmentations 2.0.

Ever-increasing availability of experimental volumetric data (e.g., in.ccp4,.mrc,.map,.rec,.zarr,.ome.tif formats) and advances in segmentation software (e.g., Amira, Segger, IMOD) and formats (e.g.,.am,.seg,.mod, etc.) have led to a demand for efficient web-based visualization tools. Despite this, current solutions remain scarce, hindering data interpretation and dissemination. Previously, we introduced Mol* Volumes & Segmentations (Mol* VS), a web application for the visualization of volumetric, segmentation, and annotation data (e.g., semantically relevant information on biological entities corresponding to individual segmentations such as Gene Ontology terms or PDB IDs). However, this lacked important features such as the ability to edit annotations (e.g., assigning user-defined descriptions of a segment) and seamlessly share visualizations. Additionally, setting up Mol* VS required a substantial programming background. This article presents an updated version, Mol* VS 2.0, that addresses these limitations. As part of Mol* VS 2.0, we introduce the Annotation Editor, a user-friendly graphical interface for editing annotations, and the Volumes & Segmentations Toolkit (VSToolkit) for generating shareable files with visualization data. The outlined protocols illustrate the utilization of Mol* VS 2.0 for visualization of volumetric and segmentation data across various scales, showcasing the progress in the field of molecular complex visualization. © 2024 The Author(s). Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: VSToolkit-setting up and visualizing a user-constructed Mol* VS 2.0 database entry Basic Protocol 2: VSToolkit-visualizing multiple time frames and volume channels Support Protocol 1: Example: Adding database entry idr-13457537 Alternate Protocol 1: Local-server-and-viewer-visualizing multiple time frames and volume channels Support Protocol 2: Addition of database entry custom-tubhiswt Basic Protocol 3: VSToolkit-visualizing a specific channel and time frame Basic Protocol 4: VSToolkit-visualizing geometric segmentation Basic Protocol 5: VSToolkit-visualizing lattice segmentations Alternate Protocol 2: "Local-server-and-viewer"-visualizing lattice segmentations Basic Protocol 6: "Local-server-and-viewer"-visualizing multiple volume channels Support Protocol 3: Deploying a server API Support Protocol 4: Hosting Mol* viewer with VS extension 2.0 Support Protocol 5: Example: Addition of database entry empiar-11756 Support Protocol 6: Example: Addition of database entry emd-1273 Support Protocol 7: Editing annotations Support Protocol 8: Addition of database entry idr-5025553.

Quantification of Empty Lacunae in Tissue Sections of Osteonecrosis of the Femoral Head Using YOLOv8 Artificial Intelligence Model

ABSTRACTHistomorphometry is an important technique in the evaluation of non‐traumatic osteonecrosis of the femoral head (ONFH). Quantification of empty lacunae and pyknotic cells on histological images is the most reliable measure of ONFH pathology, yet it is time and manpower consuming. This study focused on the application of artificial intelligence (AI) technology to tissue image evaluation. The aim of this study is to establish an automated cell counting platform using YOLOv8 as an object detection model on ONFH tissue images and to evaluate and validate its accuracy. From 30 ONFH model rabbits, 270 tissue images were prepared; based on evaluations by three researchers, ground truth labels were created to classify each cell in the image into two classes (osteocytes and empty lacunae) or three classes (osteocytes, pyknotic cells, and empty lacunae). Two and three classes were then annotated on each image. Transfer learning based on annotated data (80% for training and 20% for validation) was performed using YOLOv8n and YOLOv8x with different parameters. To evaluate the detection accuracy of the training model, the mean average precision (mAP (50)) and precision‐recall curve were identified. In addition, the reliability of cell counting by YOLOv8 relative to manual cell counting was evaluated by linear regression analysis using five histological images unused in previous experiments. The mAP (50) for the detection of empty lacunae was 0.868 for the YOLOv8n and 0.883 for the YOLOv8x. The mAP (50) for the three classes was 0.735 for the YOLOv8n model and 0.750 for the YOLOv8x model. The quantification of empty lacunae by automated cell counting obtained in the learning was highly correlated with the manual counting data. The development of an AI‐applied automated cell counting platform will significantly reduce the time and effort of manual cell counting in histological analysis.