Type Mapping Research Articles

Biotope Map Creation Method and Utilization Plan for Eco-Friendly Urban Development

A biotope map provides ecological and spatial information that reflects the natural and ecological features and values of a city. In South Korea, efforts have been made to create a map that includes grades based on evaluating the ecological value of a specific surface space. However, plans for applications have not been established, except for development restrictions or regulations for biotopes with high ecological value ratings. The aim of this study was to promote environmentally friendly and sustainable urban management through ecological land use management for all biotope types that are influenced by anthropogenic land use. Strategies for maintenance, protection, recovery, improvement, creation, and reduction based on ecological restoration principles were set as management goals. To achieve these management goals, evaluation items and indicators were suggested for minor-classification types and applied to Dongducheon City. Management strategies were suggested for target sites based on grades and thematic maps of biotope types to be utilized, such as urban ecological axes, river naturality restoration, and wetland and forest preservation. These findings support sustainable and environmentally friendly urban development by providing fundamental data for ecological and environmental management, including the preservation and restoration of natural environments and the creation of urban ecological networks.

Automated Sentinel-1 sea ice type mapping and in-situ validation during the CIRFA-22 cruise

Abstract We present a fully-automated workflow to map sea ice types from Sentinel-1 data and transfer the results in near real-time to the research vessel Kronprins Haakon (KPH) in order to support tactical navigation and decision-making during a research cruise conducted towards Belgica Bank in April and May 2022. We used overlapping SAR and optical imagery to train a pixel-wise classifier for the required season and region, and implemented a processing chain with the Norwegian Ice Service at MET Norway that automatically classifies all Sentinel-1 images covering the area of interest. During the cruise, classification results were available on KPH within hours after image acquisition, which is significantly faster than manually produced ice charts. We evaluate the results both quantitatively, based on manually selected validation regions, and qualitatively in comparison to in-situ observations and photographs. Our findings show that open water, level ice, and deformed ice are classified with high accuracy, while young ice remains challenging due to its variable small-scale surface roughness. This work presents one of the first attempts to transfer automated ice type classification results into the field in near real-time and contributes to bridging the gap between research and operations in automated sea ice mapping.

Global aerosol-type classification using a new hybrid algorithm and Aerosol Robotic Network data

Abstract. The properties of aerosols are highly uncertain owing to the complex changes in their composition in different regions. The radiative properties of different aerosol types differ considerably and are vital for studying aerosol regional and/or global climate effects. Traditional aerosol-type identification algorithms, generally based on cluster or empirical analysis methods, are often inaccurate and time-consuming. In response, our study aimed to develop a new aerosol-type classification model using an innovative hybrid algorithm to improve the precision and efficiency of aerosol-type identification. This novel algorithm incorporates an optical database, constructed using the Mie scattering model, and employs a random forest algorithm to classify different aerosol types based on the optical data from the database. The complex refractive index was used as a baseline to assess the performance of our hybrid algorithm against the traditional Gaussian kernel density clustering method for aerosol-type identification. The hybrid algorithm demonstrated impressive consistency rates of 90 %, 85 %, 84 %, 84 %, and 100 % for dust, mixed-coarse (mixed, course-mode aerosol), mixed-fine (mixed, fine-mode aerosol), urban/industrial, and biomass burning aerosols, respectively. Moreover, it achieved remarkable precision, with evaluation metric indexes for micro-precision, micro-recall, micro-F1-score, and accuracy of 95 %, 89 %, 91 %, and 89 %, respectively. Lastly, a global map of aerosol types was generated using the new hybrid algorithm to characterize aerosol types across the five continents. This study, utilizing a novel approach for the classification of aerosol, will help improve the accuracy of aerosol inversion and determine the sources of aerosol pollution.

Aboveground Biomass Inversion Based on Object-Oriented Classification and Pearson–mRMR–Machine Learning Model

Cities play a crucial role in the carbon cycle. Measuring urban aboveground biomass (AGB) is essential for evaluating carbon sequestration. Satellite remote sensing enables large-scale AGB inversion. However, the apparent differences between forest and grassland biomass pose a significant challenge to the accurate estimation of urban AGB using satellite-based data. To address this limitation, this study proposed a novel AGB estimation method using the eastern part of the Zhahe mining area in Huaibei City as the study area, which integrates land cover classification, feature selection, and machine learning modelling to generate high quality biomass maps of different vegetation types in an urban area with complex feature distribution. Utilizing the GEE platform and Sentinel-2 image, we developed an object-oriented machine learning classification algorithm, combining SNIC and GLCM to extract vegetation information. Optimal feature variables for forest and crop-grass AGB inversion were selected using the Pearson–mRMR algorithm. Finally, we constructed nine machine learning models for AGB inversion and selected the model with the highest accuracy to generate the AGB map of the study area. The results of the study are as follows: (1) Compared with the pixel-based classification method, the object-oriented classification method can extract the boundaries of different vegetation types more accurately. (2) Forest AGB is strongly correlated with vegetation indices and physiological parameters, while agri-grass AGB is primarily associated with vegetation indices and vegetation physiological parameters. (3) For forest AGB modelling, the RF-R model outperforms other machine learning models with an R2 of 0.77. For agri-grass AGB modelling, the XGBoost-R model is more accurate, with an R2 of 0.86. (4) The mean forest AGB in the study area was 4.60 kg/m2, while the mean agri-grass AGB was 0.71 kg/m2. High AGB values were predominantly observed in forested areas, which were mainly distributed along roads, waterways, and mountain ranges. Overall, this study contributes to a better understanding of the health of local urban ecosystems and provides valuable insights for ecosystem protection and the sustainable use of natural resources.

A Scoping Review of GIS Mapping of Type 1 Diabetes in Children: Identifying Current Gaps and Future Research Directions Using PRISMA-ScR.

Type 1 Diabetes poses a significant public health threat, especially in low-and-middle countries, where resources are limited. The use of geographical information systems in diabetes research has shown the potential to reveal several epidemiological risk factors. This scoping review aimed to identify the scope and extent of the current literature and explore its limitations on the geographical mapping of children with type 1 diabetes. A scoping review was conducted using five electronic databases and included studies published between the years 2000 and 2023. The search terms included: "Type 1 Diabetes Mellitus", "GIS mapping", "Juvenile Onset Diabetes Mellitus", "Spatial Epidemiology", "Spatial Clustering", "Spatial analysis", and "Geographic information system". Relevant full-text articles that met the inclusion criteria were selected for review. The search identified 17 studies that met the criteria for inclusion in the review. More than half the studies were conducted before 2015 (n=11; 61%). All studies were conducted in High-Income Countries. More than 10 articles studied environmental factors, 3 of them focused on the environment, 6 of them included sociodemographic factors, and 1 study incorporated nutrition (as a variable) in environmental factors. 2 studies focused on the accessibility of health services by pediatric patients. Studies on type 1 diabetes highlight the complex relationship between incidence and risk, suggesting comprehensive prevention and treatment. Geographical mapping has potential in low- and middle-income nations, but further research is needed to develop innovative strategies. The importance of geomappping in understanding the risk factors for Type 1 Diabetes is highlighted in this scoping review, which also suggests a possible direction for focused interventions, particularly in settings with low resources.

Hyperspectral crop image classification via ensemble of classification model with optimal training

Agriculture is a significant source of income, and categorizing the crop has turned into vital factor that aids more in the crop production sector. Traditionally, crop development stage determination is done manually by eye inspection. However, producing high-quality crop type maps using modern approaches remains difficult. In this paper, the hyperspectral crop image classification model is proposed that includes four stages, they are (a) preprocessing, (b) segmentation, (c) feature extraction and (d) classification. In the preprocessing step, the hyperspectral image is provided as input, where the filtering process will carried out using median filtering. The filtered image is then used as the segmentation’s input. The image is segmented in the segmentation step using the enhanced entropy-based fuzzy c-means technique. Subsequently, spectral spatial features and vegetation index-based features are derived from segmented images. The final step is the classification, where the ensemble of classification model will be used that includes models like Convolutional Neural Networks (CNN), Deep Maxout (DMO), Recurrent Neural Networks (RNN), and Bidirectional Gated Recurrent Unit (Bi-GRU), respectively. The proposed Self Improved Tasmanian devil Optimization (SI-TDO) approach has optimally adjusted the Bi-GRU model’s training weights to enhance ensemble classification performance. Finally, the effectiveness of the proposed SI-TDO method compared to the traditional algorithm is examined for several metrics. The SI-TDO obtained the greatest accuracy of 94.68% in training rate 80, while other existing models have the lowest ratings.

Intelligent technologies and their transformative role in modern agriculture: A comparative approach

The escalating global demand for food, propelled by a burgeoning population and the unpredictable shifts in climatic conditions, presents a challenge that traditional plant breeding alone struggles to address. In response to this pressing need, the infusion of intelligent technologies emerges as a pivotal solution, poised not only to boost production but also to meet the burgeoning demand. This transformative approach encompasses a spectrum of cutting-edge tools, including Remote Sensing and GIS, Aeroponics, Drone Technology, Biotechnology, Artificial Intelligence, Machine Learning, and, ultimately, Robotics. The synergistic integration of these technologies will enhance agricultural monitoring by facilitating precise crop surveillance, early detection and mitigation of diseases and pests, optimization of water resources, accurate mapping of land use and crop types, comprehensive environmental monitoring, real-time weather and climate tracking, efficient nutrient management, precise irrigation and spraying practices, reliable yield prediction, advanced demand forecasting, genetic analysis, and informed decision-making processes. The amalgamation of intelligent technologies with modern plant breeding methodologies signifies a significant advancement towards achieving more efficient and sustainable agricultural practices. This convergence not only addresses the immediate need for increased food production but also sets the stage for a resilient and future-ready agricultural landscape. In this era of integration, we witness the harmonious coexistence of tradition and innovation, paving the way for a more abundant and secure agricultural future.

Contrasting constraints on the temporal and spatial extents of normal faults from the Hilltop and Lewis mining districts, northern Shoshone Range, Nevada, USA

Mapping of rock types, structural geology, and hydrothermal alteration, supported by geochronology and thermochronology, sheds light on the original spatial relationships of hydrothermal systems to intrusions in the northern Shoshone Range in north-central Nevada. Rocks in the Hilltop district are tilted ~35–40°E, as indicated by orientations of flattened pumice fiamme and bedding in sedimentary rocks along a single set of presently low-angle normal faults that initiated at 60–70°W dips. New U-Pb zircon geochronology from two sets of dikes in the Lewis district could suggest late Eocene–early Oligocene extension, but definitive crosscutting relations are lacking to demonstrably support this potential earlier period of normal faulting. Reinterpretation of previously reported apatite fission-track cooling ages with a new palinspastic restoration in the Lewis mining district concurs with middle Miocene extension as documented to the south at the Caetano caldera; however, the depth of burial of the Lewis district—and thus the significance of the apatite fission-track cooling ages—is uncertain. The comparable orientations and tilting history, supported by fault scaling relations, suggest that the temporally coincident extension in the Caetano caldera to the south represents the along-strike continuation of the same system of normal faults as in the Hilltop and Lewis districts, with changes in observed offset, percent extension, and fault spacing attributed to the gradual tipping out of the fault system northward.

Development of Activity Data for Greenhouse Gas Inventory in Settlements in South Korea

In South Korea, Agriculture, Forestry, and Other Land Use (AFOLU) collates greenhouse gas (GHG) inventories. However, the settlement category lacks a clear definition of land use and activity data. This study proposed a method for examining the settlement spatial extent and constructing activity data to estimate GHG emissions and absorption as a pilot calculation, as well as to provide data for land use classification. Utilizing cadastral maps (CDMs), settlement spatial extents were determined, with settlements occupying approximately 11% of the total land area in 2019, or 9% excluding overlaps. Activity data for settlements were established through a sampling method and analysis of aerial orthoimages from 2000 and 2019. After removing overlaps with digital forest type maps and smart farm maps, settlement activity data covered approximately 18.47% based on CDMs, or 12.66% excluding overlaps. In 2019, CO2 emissions and absorptions were estimated at 622.16 ktCO2yr−1 based on CDMs and 242.16 ktCO2yr−1, excluding overlaps. To enhance GHG inventory calculation consistency and compliance with TACCC principles, clear spatial extents for settlements must be established. This entails constructing activity data and assessing GHG inventories accordingly. GHG inventory statistics should also inform future nationally determined contributions.

Cover Caption

AbstractIn the fascinating realm of insect neuroscience, researchers are achieving remarkable breakthroughs by delving into the complexities of the insect brain, which, despite its minuscule size, showcases an astonishing level of complexity. Utilizing the advanced methodology of single‐cell RNA‐sequencing, scientists are now able to dissect the brain's intricate cellular architecture at an unprecedented resolution. This sophisticated technique reveals the distinct roles individual cells play in governing behaviors such as learning, memory, and social interactions. Through meticulous mapping of various cell types and their interconnections, these pioneering studies not only deepen our comprehension of insect behavior but also propel the field of neuroscience into new frontiers (see pages 314–327). Image provided by Hao Zheng.

Determination of the Groundwater Potential Zones in Babylon Using Remote Sensing & GIS Techniques

Freshwater found underground in the tiny spaces (pores) of soil and rocks is known as groundwater. Groundwater is a valuable resource that considerably contributes to the yearly supplies. To preserve water quality and oversee groundwater systems, evaluation of the potential zone of groundwater recharge is crucial. Using remote sensing and Geographic Information System (GIS) tools, groundwater potential zones are identified. This study proposes to use satellite imagery and the software program (ArcGIS) to find a groundwater potential zone in Babylon City, Iraq. A groundwater map has been created using various data, namely slope, drainage density, lineament density, land use/land cover, geology type, soil type, and rainfall map. All these data are collected using a weighted overlay tool. Five categories were created based on the groundwater results: very poor, poor, moderate, good, and exceptional. The 'good' class covers about 32% of the study area. The current study shows that excellent groundwater class exists in Al-Hindiyah Dam, Al-Muhaweel, Al-Midhatiyah, Al-Kifil, and Al-Mashrua’a. The excellent groundwater class in Al-Shommali covers approximately 198.0054 km2. Certain areas like Al-Musaib Center, Al-Hilla Center, Al-Hashimiyah, and Abi Garaq don't have much groundwater. The moderate and excellent classes cover around 19% of the study area. The main conclusion is that Remote Sensing and GIS have gained recognition as a practical approach to mapping groundwater potential zones due to their ability to integrate diverse spatial data.

Evaluation of Land Suitability of The Post-Mine Area for Settlement in The Kuranji Region of Padang City

The increase in population in Padang City is related to the many needs that must be met by the community such as housing or settlement needs. The availability of land that meets the criteria to be used as a settlement location guarantees a decent life for each community. This research aims to evaluate the land suitability of post-mining areas for settlements in the Kuranji area of Padang City. Data collection is done by analyzing the parameters used in determining the ideal settlement area, namely, slope level map, soil type map, erosion hazard, soil texture, flood hazard, and soil carrying capacity. The data that has been obtained is analyzed using the scoring or weighting method to determine the level of land suitability. Based on the calculations and analysis carried out on the evaluation of land suitability for settlements in the Gunung Sarik area, it can be concluded that the post-mining area in the Gunung Sarik area is suitable for settlements with a land suitability level value of 57 which with a land suitability level value of 58.7 - 37.4 is appropriate with details of 6 physical parameters that are met, namely, the level of slope 15.76%; Alluvial soil type, erosion hazard 348.83 tons/day/year, never flooded, fine soil texture (Clay), and has good soil bearing capacity (165 kg/cm 2 ).

Investigation of the solvability of boundary value problems for the nonlocal Poisson equation with periodic conditions in circular domains

In this paper, boundary value problems with transformed arguments are studied in the unit ball. The transformation of the arguments is specified using the involution type mapping. These mappings participate both in the equation and in the boundary conditions. The equation under consideration is a nonlocal analog of the Poisson equation. Boundary conditions are specified as a relationship between the value of the desired function in the upper hemisphere and the value of the lower hemisphere. These conditions generalize the known periodic conditions for spherical regions. When studying boundary value problems, the properties of involutive mappings are used. The problems under consideration are solved by reducing them to analogues of boundary value problems with periodic conditions for the classical Poisson equation. Using well-known statements for periodic problems for the problems under consideration, theorems on the existence and uniqueness of solutions are proved. Exact conditions for the solvability of the problems under study are found. Spectral questions related to periodic problems are also studied. Eigenfunctions and eigenvalues of these problems are found.

Species Abundance Modelling of Arctic-Boreal Zone Ducks Informed by Satellite Remote Sensing

The Arctic-Boreal zone (ABZ) covers over 26 million km2 and is home to numerous duck species; however, understanding the spatiotemporal distribution of their populations across this vast landscape is challenging, in part due to extent and data scarcity. Species abundance models for ducks in the ABZ commonly use static (time invariant) habitat covariates to inform predictions, such as wetland type and extent maps. For the first time in this region, we developed species abundance models using high-resolution, time-varying wetland inundation data produced using satellite remote sensing methods. This data captured metrics of surface water extent and inundated vegetation in the Peace Athabasca Delta, Canada, which is within the NASA Arctic Boreal Vulnerability Experiment core domain. We used generalized additive mixed models to demonstrate the improved predictive value of this novel data set over time-invariant data. Our findings highlight both the potential complementarity and efficacy of dynamic wetland inundation information for improving estimation of duck abundance and distribution at high latitudes. Further, these data can be an asset to spatial targeting of biodiversity conservation efforts and developing model-based metrics of their success under rapidly changing climatic conditions.

Crop Type Mapping and Winter Wheat Yield Prediction Utilizing Sentinel-2: A Case Study from Upper Thracian Lowland, Bulgaria

The aim of this study is to predict and map winter wheat yield in the Parvomay municipality, situated in the Upper Thracian Lowland of Bulgaria, utilizing satellite data from Sentinel-2. The main crops grown in the research area are winter wheat, rapeseed, sunflower, and maize. To distinguish winter wheat fields accurately, we evaluated classification methods such as Support Vector Machines (SVM) and Random Forest (RF). These methods were applied to satellite multispectral data acquired by the Sentinel-2 satellites during the growing season of 2020–2021. In accordance with their development cycles, temporal image composites were developed to identify suitable moments when each crop is most accurately distinguished from others. Ground truth data obtained from the integrated administration and control system (IACS) were used for training the classifiers and assessing the accuracy of the final maps. Winter wheat fields were masked using the crop mask created from the best-performing classification algorithm. Yields were predicted with regression models calibrated with in situ data collected in the Parvomay study area. Both SVM and RF algorithms performed well in classifying winter wheat fields, with SVM slightly outperforming RF. The produced crop maps enable the application of crop-specific yield models on a regional scale. The best predictor of yield was the green NDVI index (GNDVI) from the April monthly composite image.

Combining Deep Learning and Street View Imagery to Map Smallholder Crop Types

Accurate crop type maps are an essential source of information for monitoring yield progress at scale, projecting global crop production, and planning effective policies. To date, however, crop type maps remain challenging to create in low- and middle-income countries due to a lack of ground truth labels for training machine learning models. Field surveys are the gold standard in terms of accuracy but require an often-prohibitively large amount of time, money, and statistical capacity. In recent years, street-level imagery, such as Google Street View, KartaView, and Mapillary, has become available around the world. Such imagery contains rich information about crop types grown at particular locations and times. In this work, we develop an automated system to generate crop type ground references using deep learning and Google Street View imagery. The method efficiently curates a set of street-view images containing crop fields, trains a model to predict crop types using either weakly-labeled images from disparate out-of-domain sources or zero-shot labeled street view images with GPT-4V, and combines the predicted labels with remote sensing time series to create a wall-to-wall crop type map. We show that, in Thailand, the resulting country-wide map of rice, cassava, maize, and sugarcane achieves an accuracy of 93%. We publicly release the first-ever crop type map for all of Thailand 2022 at 10m-resolution with no gaps. To our knowledge, this is the first time a 10m-resolution, multi-crop map has been created for any smallholder country. As the availability of roadside imagery expands, our pipeline provides a way to map crop types at scale around the globe, especially in underserved smallholder regions.

Extracting Typical Samples Based on Image Environmental Factors to Obtain an Accurate and High-Resolution Soil Type Map

Soil surveying and mapping provide important support for environmental science research on soil and other resources. Due to the rapid change in land use and the long update cycle of soil maps, historical conventional soil maps (CSMs) may be outdated and have low accuracy. Therefore, there is an urgent need for accurate and up-to-date soil maps. Soil has a high correlation with its corresponding environmental factors in space, and typical samples contain an appropriate soil–environment relationship of soil types. Understanding how to extract typical samples according to environmental factors and determine the implied soil–environment relationship is the key to updating soil maps. In this study, a hierarchical typical sample extraction method based on land use type and environmental factors was designed. According to the corresponding relationship between the soil type and the land use type (ST-LU), the outdate soil map patches caused by changes in land use were excluded, follow by typical samples being extracted according to the peak intervals of the soil–environmental factor histograms. Additionally, feature selection was performed through variance analysis and mutual information, and four machine learning models were used to predict soil types. In addition, the influence of environmental factors on soil prediction was discussed, in terms of variable importance analysis. Using an overall common validation set, the results show that the prediction accuracy using typical samples for learning in the modeling set is above 0.8, while the prediction accuracy when using random samples is only about 0.4. Compared with the original soil map, the accuracy and resolution of the predicted soil maps based on typical samples are greatly improved. In general, typical samples can effectively explore the actual soil–environment knowledge implied in the soil type map. By extracting typical samples from historical soil type map and combining them with high-resolution remote sensing data, we can generate new soil type maps with high accuracy and short update cycle. This can provide some references for typical sampling design and soil type prediction.

Abstract 4900: Spatial Atlas of Human Anatomy (SAHA): A subcellular, multiscale spatial odyssey of immune and gastrointestinal tissues and tumors

Abstract The Spatial Atlas of Human Anatomy (SAHA) is a foundational effort to map 250 million cells and transcriptomes and proteomes of 30 non-diseased organs from healthy adults at two spatial scales: whole transcriptome of histological features (50 µm to 2 mm), and 1,000-plex RNA and 64-plex protein panels at spatial subcellular resolution (50 nm across 1 cm2). The project aims to establish and validate best practices in experimental design, sample processing, data analysis, and data standards for high-content spatial analysis across multiple human organs at whole transcriptome and proteome levels. The profiled samples will capture variability across genders and ancestries. All results, including raw and processed data, will be made available to the scientific community through the SAHA data portal and AtoMxTM Spatial Informatics Platform. Here we present the part of Phase I data collected specifically around immune (bone marrow and lymph node) and gastrointestinal tissues (ileum, appendix, colon, and liver), and compare these data to colon and liver cancer samples. On serial sections, we perform spatial whole transcriptome data (with GeoMx® Digital Spatial Profiler) and 1,000-plex RNA profiles and 64-plex protein profiles collected by the CosMx™ Spatial Molecular Imager (SMI) matched to the exact shape of functional histological organ features from H&E and immunofluorescence stainings. Our data, which spans ~1.5 million cells collected across ~1,100 fields of view, enables the highest-ever subcellular resolution maps of cell types, lineage states, metabolic capacity, cellular neighborhoods, subcellular movements of organelles, and spatially resolved (and novel) ligand-receptor interactions across normal and cancer tissues. Through comparing these data to several cancer samples collected across multiple spatial platforms, we show how spatial organ atlasing at multiple scales can uncover unique insights into organ development, health, and cancer. We also show how the SAHA data can serve as a benchmark reference for spatial precision medicine. Citation Format: Jiwoon Park, Roberto Gregorio, Erika Hissong, Sanjay Patel, Brian Robinson, Fabio Socciarelli, Evenlyn Metzger, Yan Liang, Jason Reeves, Joseph Beechem, Olivier Elemento, Alicia Alonso, Shauna Houlihan, Robert Schwartz, Christopher E. Mason. Spatial Atlas of Human Anatomy (SAHA): A subcellular, multiscale spatial odyssey of immune and gastrointestinal tissues and tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4900.

Abstract 899: Development of a deep learning model for cell type mapping in colorectal cancer using H&E images leveraging image-based spatial transcriptomics data

Abstract Purpose The tumor microenvironment (TME) is crucial in colorectal cancer as it influences disease progression, treatment response, and patient outcomes, providing valuable insights for personalized therapies and prognostic assessments. Here, we have developed a deep learning model by integrating hematoxylin and eosin (H&E) stained images of colorectal cancer and image-based spatial transcriptomics (Xenium) to infer spatial mapping of cell types in TME only using H&E images. Methods A total of 30 H&E images of colorectal cancer obtained by tissue microarray were registered with image-based spatial transcriptomics data (Xenium). Utilizing a Variational Autoencoder (VAE) based model and leveraging reference single-cell data enables the acquisition of cell types for individual cells in image-based spatial transcriptomics. A convolutional neural network (CNN) model was developed using H&E image as inputs to predict cell types in H&E-stained tissue image patches of colorectal cancer collected from various patients. The model also estimated the cell types from H&E-stained whole slide tissue image of colorectal cancer of The Cancer Genome Atlas (TCGA-COAD). Results The accuracy of the model's predictions for cell types using H&E image patches was notably high and exhibited a significant concordance with the results obtained through the validation. The Intersection over Union (IoU) metric for image segmentation indicated a value of 0.66 for epithelial cells and 0.44 for TNK cells. The output of deep learning model for epithelial cells and T/NK cells from TCGA-COAD tissue images showed a correlation with human-labeled regions of cancer epithelium and immune cells. Conclusions Leveraging image-based spatial transcriptomics, we developed a deep learning model capable of discerning various cell types within the tumor microenvironment solely from H&E images. This clinically translatable approach is valuable for investigating tumor microenvironment to develop biomarkers associated with various cancer therapeutics particularly immuno-oncology drugs. This approach can yield objective deep learning-based models without human labels for characterizing the tumor microenvironment in single-cell resolution, particularly regarding spatial immune distribution. Citation Format: Seungho Cook, Dongjoo Lee, Myunghyun Lim, Jae Eun Lee, Daeseung Lee, Hyung-Jun Im, Jung-Soo Pyo, Kwon Joong Na, Hongyoon Choi. Development of a deep learning model for cell type mapping in colorectal cancer using H&E images leveraging image-based spatial transcriptomics data [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 899.

Abstract 7424: iStarTLS: Advanced detection and phenotyping of tertiary lymphoid structures

Abstract Tertiary lymphoid structures (TLSs) are clusters of immune cells formed in non-lymphoid tissues. They are often found at sites of chronic inflammation, notably within the invasive margins and the core of various solid tumors. TLSs are pivotal in mediating anti-tumor immunity. However, our understanding of TLSs in large/complex tissue contexts remains incomplete due to the lack of computational tools to effectively detect and phenotype TLSs. Recent advances in spatially resolved transcriptomics (SRT) present a broader spectrum of analytical possibilities for investigating the spatial phenotypic heterogeneity of TLSs and their interaction with stromal and cancer cells. Here, we present iStarTLS (Inferring Super-resolution Tissue ARchitecture for TLSs), a computational toolkit designed to process SRT data for TLS detection and phenotyping and showcase its performance on breast, bladder, and lung cancer samples. By effectively integrating spatial gene expression data with state-of-the-art machine learning techniques, we can substantially enhance our capabilities in TLS detection and comprehensive phenotyping. iStarTLS starts by enhancing the spatial resolution of spot-level gene expression data to near-single-cell resolution by leveraging high-resolution information provided by paired histology images. To detect TLSs and infer their cellular composition, we developed a TLS signature. Based on the high-resolution gene expression measurements and a curated reference panel of cell type-specific markers, we score cell type-specific gene signatures to obtain a cell type probability map across the whole tissue section. This map gives rise to a segmentation of key cell type components of TLSs, enabling the spatial mapping and colocalization of different cell types. Moreover, such an approach would allow us to infer the phenotypic states of cells within the TLSs, assess their cellular compositions, and discern their cellular organization in large, spatially heterogeneous tissues at a near-single-cell resolution. Notably, in conjunction with nuclei segmentation of high-resolution histology images, iStarTLS precisely maps high endothelial venules (HEVs), a key structure within TLSs often overlooked by previous studies. iStarTLS paves the way for uncovering novel mechanisms of immune-tumor interactions and designing personalized therapies targeting specific cellular components or states within TLSs. Citation Format: Kyung Serk Cho, Jiahui Jiang, Daiwei Zhang, Yunhe Liu, Jianfeng Chen, Rossana L. Segura, Xinmiao Yan, Guangsheng Pei, Luisa M. Soto, Yanshuo Chu, Ansam F. Sinjab, Cassian Yee, Scott Kopetz, Anirban Maitra, Andrew Futreal, Alexander Lazar, Amir A. Jazaeri, Humam Kadara, Jianjun Gao, Mingyao Li, Linghua Wang. iStarTLS: Advanced detection and phenotyping of tertiary lymphoid structures [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7424.