Variety Of Features Research Articles

<명주보월빙> 연작에 나타난 우부형(愚婦型) 인물의 양상과 의미* -‘연군주’와 ‘연희벽’ 숙질(叔姪)을 중심으로-

This study explores the portrayal and narrative significance of the “foolish wife” (愚婦型) character type in the Myeongju Bowolbing(明珠寶月聘) series, a classic Korean novel from the late Joseon Dynasty. The series repeatedly presents this character type through the figures of Yeon Princess and Yeon Hui-byeok. In the first part, Myeongju Bowolbing, the focus is on the marriage between Ha Won-gwang and Yeon Princess, while the second part, Yunhajeong Sammun Chuirok(尹河鄭三門聚錄), examines the marriage between Ha Mong-seong and Yeon Hui-byeok. The narrative, which shows two generations of prominent male heirs marrying “foolish wives,” adds complexity and illustrates the evolution of this character type throughout the series. In the series, Yeon Princess holds the status of a “secondary wife,” while Yeon Hui-byeok occupies the role of the “primary wife,” leading to different outcomes of acceptance and exclusion. This reflects the conservative and discriminatory attitudes toward the roles of primary and secondary wives. Despite her foolishness, Yeon Princess is accepted into the family due to her love and obedience toward her husband. In contrast, Yeon Hui-byeok, lacking the qualities expected of a primary wife and consistently challenging her husband’s authority, experiences ongoing conflict and eventually dies of postpartum illness. Her death symbolizes how women who fail to meet the expectations of a primary wife and Matron of the household are excluded and erased in a patriarchal society, while also illustrating the differential expectations of primary and secondary wives in late Joseon society. Moreover, unlike other works such as Yussi Samdaerok(劉氏三代錄) and Imssi Samdaerok(林氏三代錄), which depict foolish wives from humble backgrounds, Myeongju Bowolbing portrays foolish wives from prestigious families, offering a more nuanced interpretation. The series also demonstrates narrative expansion and variation across its two parts. Through its depiction of the “foolish wife,” Myeongju Bowolbing reveals diverse character portrayals and new narrative possibilities, while also reflecting the values and consciousness of its readers from that era.

Diversity of soils on Kolguev Island with cryometamorphic horizons

Kolguev Island (Barentz Sea, the subzone of typical tundra) was poorly soil surveyed until recently. During expeditionary research 2018–2023, it was revealed that a significant proportion of the soil cover is represented by soils that have horizons with a well-manifested structure, which were diagnosed as cryometamorphic ones. In this regard, the purpose of this work is to characterize the diversity and morphological features of tundra soils with a cryometamorphic horizon identified on the island. The cryometamorphic horizons most often had the specific angular-grainy structure with sharp edges or granular structure with rounded surfaces. The most typical size of aggregates is 1–3 mm; less common – up to 4 mm or less than 1 mm. In some cases, the structure was water-resistant and the soil aggregates had a denser, drier interior. A platy-grained structure with silty-sand coatings was less common. A key feature of the cryometamorphic Kolguev soils is lacking structure in the upper 5–10 cm of the profile. Such soils are the main component of the soil cover. The gleyic subtype of cryometamorphic soils and cryometamorphic gleezems are more often found as components of the soil cover micropatterns. Cryometamorphic soils with a morphologically pronounced spodic horizon were described in one of the central parts of the island. Based on the principles of Soil Classification of Russia, the following types of soils were identified: cryometamorphic, mucky-cryometamorphic, cryometamorphic gleezems; as well as soils, that were tentatively classified as a new type – cryometamorphic podburs and a new subtype – cryometamorphic peaty gleezems. Thus, the study of Kolguev soils showed that the cryometamorphic soils are distributed much extensive than previously assumed.

Dual-decoding branch contrastive augmentation for image manipulation localization

With the rapid development of image editing techniques, forensic analysis to detect malicious image manipulation has become an important research topic. The current image manipulation detection and localization methods can accommodate diverse forms of tampering. However, their approach to handling various tampering detection types is limited to a uniform regression pathway. This approach fails to recognize the unique characteristics of copy-move tampering, which is significantly different from other tampering types. Employing a generic detection methodology indiscriminately poses the risk of confusing the training regression trajectory of the deep learning models. To mitigate this challenge, this paper introduces a novel framework featuring a dual-decoding branch structure specifically designed to augment features pertinent to copy-move tampering types. Moreover, it facilitates the detection of tampered regions, irrespective of the tampering type, within the main branch. To achieve this goal, we first introduce a contrastive augmentation module in the encoder, which maximizes the feature space distance between the manipulation regions and pristine regions. Next, we design a parallel attention module to extract more diverse multiscale features. Moreover, we introduce a constrained shifted-window dual attention module to extract tampering noise features. In the decoder, we design a dual-decoding branch to capture both the homologous and tampering features, and we employ contrastive learning to minimize the feature space distance of the homologous regions for copy-move manipulation detection. Finally, we design a category normalization loss function to balance the model’s attention across each category. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art performance on various benchmark datasets.

Growth and Convergence in Portugal

Contrary to other EU countries, Portugal has become relatively poorer for almost a quarter of century. Growth decomposition exercises show that this is due to a reduction in capital accumulation and a sharp fall in total factor productivity. There are areas in which the country can act to reduce the fall, by capitalizing on national comparative advantages and the diverse but complementary features of its two largest metropolitan regions, Lisbon and Porto. However, this requires policy changes.

Clinical imaging diagnosis of pulmonary cryptococcosis with different therapeutic responses

We aimed to differentiate and evaluate the clinical imaging features of pulmonary cryptococcosis with different therapeutic responses. The clinical imaging data of 70 patients with PC (complete response PC 37 cases and incomplete response PC 33 cases) were collected and compared to determine the independent risk factors for different therapeutic responses, and their diagnostic performances were verified by receiver operating characteristic curve analysis. Compared with complete response PC, incomplete response PC was more common with immunosuppression (10.8% vs. 45.5%, P = 0.001), intermediate progress (8.1% vs. 39.4%, P = 0.002), bilateral distribution (21.6% vs. 78.8%, P < 0.001), consolidation-interstitial pattern (10.8% vs. 42.4%, P = 0.003), pleural effusion (0 vs. 27.3%, P = 0.002) and mediastinal lymphadenopathy (0 vs. 24.2%, P = 0.005). Multivariate logistic regression showed that immunosuppression, intermediate progress, and bilateral distribution were independent risk factors, with low to moderate areas under curves (AUC, 0.656–0.786). Their combined performance was good with an AUC of 0.888. The diverse clinical imaging features can reflect the therapeutic response of PC. Immunosuppression, intermediate progress, and bilateral distribution were independent risk factors. Their combination can significantly improve diagnostic effects.

Human limits in machine learning: prediction of potato yield and disease using soil microbiome data

BackgroundThe preservation of soil health is a critical challenge in the 21st century due to its significant impact on agriculture, human health, and biodiversity. We provide one of the first comprehensive investigations into the predictive potential of machine learning models for understanding the connections between soil and biological phenotypes. We investigate an integrative framework performing accurate machine learning-based prediction of plant performance from biological, chemical, and physical properties of the soil via two models: random forest and Bayesian neural network.ResultsPrediction improves when we add environmental features, such as soil properties and microbial density, along with microbiome data. Different preprocessing strategies show that human decisions significantly impact predictive performance. We show that the naive total sum scaling normalization that is commonly used in microbiome research is one of the optimal strategies to maximize predictive power. Also, we find that accurately defined labels are more important than normalization, taxonomic level, or model characteristics. ML performance is limited when humans can’t classify samples accurately. Lastly, we provide domain scientists via a full model selection decision tree to identify the human choices that optimize model prediction power.ConclusionsOur study highlights the importance of incorporating diverse environmental features and careful data preprocessing in enhancing the predictive power of machine learning models for soil and biological phenotype connections. This approach can significantly contribute to advancing agricultural practices and soil health management.

Liverwort (Marchantiophyta) and Hornwort (Anthocerotophyta) Flora of Yenice District (Çanakkale): New Floristic Findings from the Northern Part of Mount Ida (Kaz Dağı)

The Yenice district of Çanakkale stands out due to its diverse land features, being part of the Kaz Dağı (Mount Ida), its expansive coniferous and deciduous forests, and its potential for high biological diversity and endemism. It also provides highly suitable habitats for liverworts. However, the absence of legally protected areas highlights the need for a detailed assessment of the region's biodiversity. Liverworts are key components of floristic biological richness. Nevertheless, studies on the liverwort flora in both Çanakkale province and Yenice district are quite limited. Based on these considerations, this study aimed to investigate the liverwort flora of the Yenice district. During the study, a total of 295 liverwort specimens were collected from 74 different sites representative of the district’s various regions. The collected specimens were identified using appropriate methods and preserved as herbarium material. As a result of the study, 29 liverwort species from 17 families and 1 hornwort species were identified from the area. Of the identified species, 7 taxa are new records for the B6 grid square according to Henderson’s grid system (1961), and 13 taxa are new records for Çanakkale province.

Beyond business: Exploring the social engagement of entrepreneurs in Phnom Penh, Cambodia

The current article aims to shed light on the social engagement practices of businesses in Phnom Penh, Cambodia, and to inform readers about those practices. In particular, the article examines how entrepreneurs engage in social activities, establish communication with their contemporaries, and advocate for entrepreneurship. The data was collected from a representative sample of business owners while employing a quantitative research design to determine how much business owners participate in social activities. The ongoing research has yielded preliminary findings and conclusions. The findings reveal that entrepreneurs have high social engagement through active participation in mentoring programs, knowledge-sharing activities, and networking events. They demonstrated their participation in these activities. The findings shed light on the significance of social capital and the growth of communities within the framework of Phnom Penh's environment for entrepreneurial endeavours. The implications of this study for policy, practice, theory, and future research, emphasizing the need to foster a culture that encourages social activity among entrepreneurs and fosters a supportive environment, were discussed. The study adds to the expanding body of literature on entrepreneurship by highlighting the diverse features of entrepreneurial pursuits and the importance of social engagement that extends beyond corporate objectives. Future studies should be conducted with a bigger sample size and scope.

Multi-Target Tracking with Multiple Unmanned Aerial Vehicles Based on Information Fusion

In high-altitude scenarios, targets tend to occupy a small number of pixels within the UAV’s field of view, resulting in substantial errors when identity recognition is attempted based solely on appearance features during multi-UAV joint tracking. Existing methodologies typically propose projecting multi-view data onto a single plane and leveraging distance information for identity association; however, their accuracy remains low as they are contingent on one-dimensional target information. To address this limitation, this paper introduces the UAVST-HM (UAV Swarm Tracking in High-altitude scenarios for Multiple targets) model, specifically designed to handle the characteristics of targets in the field of view of multiple UAVs at high altitudes. Initially, we develop techniques for extracting targets’ appearance, geometric, and distribution features. Subsequently, adaptive weights, calculated based on the mean of the respective features, are devised to amalgamate these diverse features, thereby constructing a cost matrix for cross-view target identity matching. This matrix is processed through the Hungarian algorithm, and multi-view target identity association is ultimately achieved via threshold filtering. On the MDMT dataset, our method enhances the MDA indicator, which assesses cross-view target identity matching, by 1.78 percentage points compared to the current state of the art. This significant enhancement substantially improves the overall efficacy of multi-UAV joint visual tracking from a high-altitude perspective.

EDDINet: Enhancing drug–drug interaction prediction via information flow and consensus constrained multi-graph contrastive learning

Predicting drug–drug interactions (DDIs) is crucial for understanding and preventing adverse drug reactions (ADRs). However, most existing methods inadequately explore the interactive information between drugs in a self-supervised manner, limiting our comprehension of drug–drug associations. This paper introduces EDDINet: Enhancing Drug-Drug Interaction Prediction via Information Flow and Consensus-Constrained Multi-Graph Contrastive Learning for precise DDI prediction. We first present a cross-modal information-flow mechanism to integrate diverse drug features, enriching the structural insights conveyed by the drug feature vector. Next, we employ contrastive learning to filter various biological networks, enhancing the model’s robustness. Additionally, we propose a consensus regularization framework that collaboratively trains multi-view models, producing high-quality drug representations. To unify drug representations derived from different biological information, we utilize an attention mechanism for DDI prediction. Extensive experiments demonstrate that EDDINet surpasses state-of-the-art unsupervised models and outperforms some supervised baseline models in DDI prediction tasks. Our approach shows significant advantages and holds promising potential for advancing DDI research and improving drug safety assessments. Our codes are available at: https://github.com/95LY/EDDINet_code.

Automated Generation of Lung Cytological Images from Image Findings Using Text-to-Image Technology

Cytology, a type of pathological examination, involves sampling cells from the human body and observing the morphology of the nucleus, cytoplasm, and cell arrangement. In developing classification AI technologies to support cytology, it is essential to collect and utilize a diverse range of images without bias. However, this is often challenging in practice because of the epidemiologic bias of cancer types and cellular characteristics. The main aim of this study was to develop a method to generate cytological diagnostic images from image findings using text-to-image technology in order to generate diverse images. In the proposed method, we collected Papanicolaou-stained specimens derived from the lung cells of 135 lung cancer patients, from which we extracted 472 patch images. Descriptions of the corresponding findings for these patch images were compiled to create a data set. This dataset was then utilized to finetune the Stable Diffusion (SD) v1 and v2 models. The cell images generated by this method closely resemble real images, and both cytotechnologists and cytopathologists provided positive subjective evaluations. Furthermore, SDv2 demonstrated shapes and contours of nuclei and cytoplasm that were more similar to real images compared to SDv1, showing superior performance in quantitative evaluation metrics. When the generated images were utilized in the classification tasks for cytological images, there was an improvement in classification performance. These results indicate that the proposed method may be effective for generating high-quality cytological images, which enables the image classification model to learn diverse features, thereby improving classification performance.

Investigating the Surface Damage to Fuzhou’s Ancient Houses (Gu-Cuo) Using a Non-Destructive Testing Method Constructed via Machine Learning

As an important part of traditional Chinese architecture, Fuzhou’s ancient houses have unique cultural and historical value. However, over time, environmental factors such as efflorescence and plant growth have caused surface damage to their gray brick walls, leading to a decline in the quality of the buildings’ structure and even posing a threat to the buildings’ safety. Traditional damage detection methods mainly rely on manual labor, which is inefficient and consumes a lot of human resources. In addition, traditional non-destructive detection methods, such as infrared imaging and laser scanning, often face difficulty in accurately identifying specific types of damage, such as efflorescence and plant growth, on the surface of gray bricks and are easily hampered by diverse surface features. This study uses the YOLOv8 machine learning model for the automated detection of two common types of damage to the gray brick walls of Fuzhou’s ancient houses: efflorescence and plant growth. We establish an efficient gray brick surface damage detection model through dataset collection and annotation, experimental parameter optimization, model evaluation, and analysis. The research results reveal the following. (1) Reasonable hyperparameter settings and model-assisted annotation significantly improve the detection accuracy and stability. (2) The model’s average precision (AP) is improved from 0.30 to 0.90, demonstrating good robustness in detecting complex backgrounds and high-resolution real-life images. The F1 value of the model’s gray brick detection efficiency is improved (classification model performance index) from 0.22 to 0.77. (3) The model’s ability to recognize the damage details of gray bricks under high-resolution conditions is significantly enhanced, demonstrating its ability to cope with complex environments. (4) The simplified data enhancement strategy effectively reduces the feature extraction interference and enhances the model’s adaptability in different environments.

Deep Encodings vs. Linguistic Features in Lexical Complexity Prediction

AbstractIn this work, we present a novel approach to lexical complexity prediction (LCP) that combines diverse linguistic features with encodings from deep neural networks. We explore the integration of 23 handcrafted linguistic features with embeddings from two well-known language models: BERT and XLM-RoBERTa. Our method concatenates these features before inputting them into various machine learning algorithms, including SVM, Random Forest, and fine-tuned transformer models. We evaluate our approach using two datasets: CompLex for English (a high-resource language) and CLexIS2 for Spanish (a relatively low-resource language in ), allowing us to study performance issues from a cross-lingual perspective. Our experiments involve different combinations of linguistic features with encodings from pretrained deep learning models, testing both token-based and sequence-related encodings. The results demonstrate the effectiveness of our hybrid approach. For the English CompLex corpus, our best model achieved a mean absolute error (MAE) of 0.0683, representing a 29.2% improvement over using linguistic features alone (MAE 0.0965). On the Spanish CLexIS2 corpus, we achieved an MAE of 0.1323, a 19.4. These findings show that handcrafted linguistic features play a fundamental role in achieving higher performance, particularly when combined with deep learning approaches. Our work suggests that hybrid approaches should be considered over full end-to-end solutions for LCP tasks, especially in multilingual contexts.

A new multivariate blood glucose prediction method with hybrid feature clustering and online transfer learning.

Accurate blood glucose (BG) prediction is greatly benefit for the treatment of diabetes. Generally, clinical physicians are required to comprehensively analyze various factors, such as patient's body temperature, meal, sleep, insulin injection, continuous glucose monitoring (CGM), and other information, to evaluate the fluctuation trend of blood glucose. To address this problem, this paper proposes a multivariate blood glucose prediction method based on mixed feature clustering. It clusters time series data with diverse or mixed features related to blood glucose, effectively leveraging correlations and distribution characteristics. By combining incremental clustering of multivariate time series with transfer learning, this method achieves online prediction of blood glucose levels. The experimental results indicate that the proposed method can decrease the prediction error RMSE by 4.2% (PH=30min) and 5.9% (PH=60min). Compared with other prediction methods, the training time of the multivariate prediction method is reduced by 5.2% (PH=30min) and 4.7% (PH=60min). It was also validated and compared with other methods in a real dataset. The proposed method in this study has lower prediction error and better prediction performance in the prediction horizon(PH) of PH=30, 45, 60, 75, and 90min, respectively. Compared with the traditional unitary and multivariate time series prediction method, the approach proposed in this paper significantly improves the accuracy and robustness of blood glucose prediction. According to the evaluation results on the data set from OhioT1DM and the Sixth People's Hospital of Shanghai, the proposed method has better generalization performance and clinical acceptability.

A TISZA-TÓ VÁLTOZATOS TERMÉSZETI ADOTTSÁGAINAK TURISZTIKAI KIHASZNÁLÁSA

Lake Tisza is a lowland reservoir with an area of 127 km2 in the middle of the Carpathian Basin established in the 1970s. Among its original functions, in addition to flood control, it was expected to irrigate a larger agricultural area and increase water freight transport. Today, buffering of extreme water conditions, nature conservation and recreation have become the main profiles. The diverse hydroecological features and mosaic landscape structure of the lake allow for versatile nature conservation and utilization in tourism. This differentiated use is in line with the worldwide trend of favouring locations with multiple leisure activities in close proximity to each other. Lake Tisza offers fishing, swimming, sailing, canoeing, nature observation boating and cycling opportunities, but due to its status as a Ramsar bird conservation site, it is also a valuable destination for ornithologists. In the course of our research, we examined the current spatial pattern of these activities and the possible arrangement of expedient further development.

Tropical Cyclone Rainfall Structure and Its Long-Term Trend over the Western North Pacific

Abstract The tropical cyclone (TC) rainfall structure over the western North Pacific is categorized into four typical types. Clusters I and IV are featured by the southward-shifted and northward-shifted rainfall centers, respectively. Meanwhile, clusters II and III are characterized by the weak and strong maximum rainfall rates near the TC center, respectively. Apart from rainfall, clusters I–IV show diverse features in locations, intensities, and lifetime stages. Both clusters I and III appear over the low-latitude regions. However, TCs in cluster III have the strongest intensity and are in the mature stage of their lifetime, while TCs in cluster I are relatively weaker and in earlier stages. On the contrary, cluster IV has the highest mean latitude positions and strong intensity, mainly in their later lifetime period. Cluster II shows the weakest TC intensity and mainly locates in the subtropics. Diverse TC locations lead to different effects of large-scale circulation on TC rainfall patterns in clusters I–IV. For clusters I and III, abundant moisture provided by the southwest monsoon causes heavy rainfall. In contrast, cluster IV is mainly affected by midlatitude westerly troughs, which is responsible for the northward-shifted rainfall center. Cluster II shows the weakest TC intensity, resulting in a small rainfall rate. Further analysis shows that the changes in the relative frequency contributed 36% of the decreasing trend of basin-mean inner-core rainfall during 1998–2019, and the shift of rainfall pattern from cluster III to cluster I due to the enhanced monsoon plays a central role.

The Origin and Geography of Brown Forest Soils

Brown soils, Brown forest soils, Burozems or Cambisols have been studied for more than 100 years, and to this day, their nature, origin and process organization remain controversial. In addition, issues of their geography are quite controversial, especially in such a large country as Russia. A brief review of the literature on the morphological diversity features of the genesis and origin of brown soils in the various geographical locations of Eurasia is given. It was shown that the genesis of brown soils is not as closely related to the type of forest vegetation as previously thought, although, at the same time, the vast majority of brown soils are forest soils. Depending on the geographic situation and local climatic and geogenic conditions, Brown forest soils have related subtypes among adjacent soil types in different natural zones. Thus, in the polar zone, they are close to Entic Podzols, in the subtropics to Cinamonic soil, and in the forest-steppe, they replace zonal Retisols in positions with a relatively less contrasting and even climate. Being to a certain extent intrazonal soils, brown soils are combined with other more intrazonal soils—Rendzinas—and form the so-called Burozem-Rendzinas on uplands, composed of carbonate rocks in various natural zones. The article is illustrated with original photographs of Brown forest soils from various natural zones, taken by the author during numerous expeditions. It has been established that Burozems combine the characteristics of intrazonal soil, which is inherent in all natural zones, and have elements of zonal soils, as well as adjacent intrazonal soils in invariant combinations of soil-forming factors. From this, two conclusions can follow about their further classification fate: a more thorough justification for an independent soil type or a classification of structural metamorphism and in situ transformation of minerals among various existing zonal soil types.

SPOTIFY APPLICATION AS A MEDIUM TO IMPROVE THE STUDENTS’ LISTENING ABILITY

The advent of digital technology has revolutionized various sectors, including education, by providing automated and sophisticated systems to enhance learning experiences. This study explores the effectiveness of the Spotify application as a medium to improve students' listening abilities in English. Recognizing the significance of listening as one of the four essential language skills, this research addresses the challenge students face in mastering listening due to limited vocabulary and noisy classroom environments. Utilizing a pre-experimental design with a quantitative approach, this study involved pre-test and post-test assessments of two groups: a control class and an experimental class using the Spotify application. The research instrument consisted of written tests, including fill-in and multiple-choice formats, designed to measure students' listening performance. Data collection focused on comparing pre-test and post-test scores to evaluate improvements. The findings revealed a significant enhancement in students' listening abilities after using the Spotify application, with mean scores increasing from 42.89 to 82.42, reflecting a 39.52% improvement. The t-test value further supported these results (5.72 &gt; 2.026). The study concludes that Spotify, with its diverse features such as music discovery, personalized playlists, lyrics integration, and offline access, serves as an effective tool to engage students and improve their listening skills. This method not only addresses the difficulties students face in listening but also motivates them through an enjoyable and interactive learning process.

An Enhanced Feature Learning CNN Using Auto-encoder for Partially Occluded Target Recognition in SAR Imagery

Deep learning algorithms have found extensive utility in Automatic Target Recognition (ATR) using Synthetic Aperture Radar (SAR). Despite this, conventional deep learning-based ATR models often lack in their performance when subjected to Extended Operating Conditions (EOCs). Significant variations in depression, noise interference, limited training data, and partial occlusion are primary factors in EOCs. In this paper, we proposed a deep neural network-based technique to recognize SAR targets for Standard Operating Conditions (SOC) and Extended Operating Conditions (EOC). The proposed approach comprises an encoder and decoder network. The encoder network integrates multiple dilated convolutions to address noise-induced recognition challenges for extracting multi-scale features. Furthermore, a feature refinement module is integrated within the multi-scale channels to enhance the extraction of discriminative and resilient features. Feature refinement selectively emphasizes informative features while suppressing irrelevant ones. Additionally, a salient attention block and a spatial feature learning module are introduced for feature selection. Selected features are then utilized in the top-level network layer of the encoder network to preserve spatial relationships among diverse features. This spatial feature learning module aids in recognition performance, particularly when training data is scarce. The decoder network consists of stacked transposed convolution layers, facilitating the encoder network's acquisition of discriminative image features. Experimental evaluations were conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset to validate the efficacy of the proposed methodology.

TMIC-60. BRATS-PATH: ASSESSING HETEROGENEOUS HISTOPATHOLOGIC REGIONS IN GLIOBLASTOMA

Abstract Glioblastoma, the most common malignant primary adult brain tumor, poses significant diagnostic and treatment challenges due to its heterogeneous molecular and micro-environmental profiles. To this end, we organize the BraTS-Path challenge to provide a public benchmarking environment and a comprehensive dataset to develop and validate AI models for identifying distinct histopathologic glioblastoma sub-regions in H&amp;E-stained digitized tissue sections. We identified 188 multi-institutional diagnostic slides of glioblastoma (IDH-wt, Gr.4) cases, from the TCGA-GBM and TCGA-LGG data collections, following their reclassification according to the 2021 WHO classification criteria. Sub-regions were selected according to distinctive morphology of histopathologic features and included aggressive tumor biology and areas consistent with potential treatment effect. Selected sub-region annotations included cellular tumor, geographic necrosis, cortical infiltration, pseudopalisading necrosis, microvascular proliferation, white matter penetration, regions dense with macrophages, leptomeningeal infiltration, and presence of lymphocytes. We obtained 107,340 patches of size 512x512 from the 9 sub-regions. A global network of board-certified expert neuropathologists defined and followed a systematic annotation protocol based on clinical definitions and only delineated sub-regions with high confidence, thus ensuring high-quality standardized data. Each tissue section was assigned to an annotator-approver pair, with the annotator delineating sub-regions and the approver ensuring the consistency of the annotations. By crowdsourcing annotations, the BraTS-Path challenge harnesses the collective expertise of clinical neuropathologists and fosters a collaborative environment to advance the neuro-oncology field. The anticipated developed algorithms are expected to integrate state-of-the-art computational methods, achieving high accuracy in identifying diverse histopathologic features and advancing clinical decision-making processes. The BraTS-Path challenge aims to bridge the gap between research and clinical practice by promoting the development of AI-driven tools for precise tumor characterization. This collaborative effort can significantly enhance our understanding of glioblastoma, improve diagnostic accuracy, and inform treatment strategies, thereby contributing to better patient outcomes.