High-resolution Imaging Research Articles

Advancing mango leaf variant identification with a robust multi-layer perceptron model

Mango, often regarded as the “king of fruits,” holds a significant position in Bangladesh’s agricultural landscape due to its popularity among the general population. However, identifying different types of mangoes, especially from mango leaves, poses a challenge for most people. While some studies have focused on mango type identification using fruit images, limited work has been done on classifying mango types based on leaf images. Early identification of mango types through leaf analysis is crucial for taking proactive steps in the cultivation process. This research introduces a novel multi-layer perceptron model called WaveVisionNet, designed to address this challenge using mango leaf datasets collected from five regions in Bangladesh. The MangoFolioBD dataset, comprising 16,646 annotated high-resolution images of mango leaves, has been curated and augmented to enhance robustness in real-world conditions. To validate the model, WaveVisionNet is evaluated on both the publicly available dataset and the MangoFolioBD dataset, achieving accuracy rates of 96.11% and 95.21%, respectively, outperforming state-of-the-art models such as Vision Transformer and transfer learning models. The model effectively combines the strengths of lightweight Convolutional Neural Networks and noise-resistant techniques, allowing for accurate analysis of mango leaf images while minimizing the impact of noise and environmental factors. The application of the WaveVisionNet model for automated mango leaf identification offers significant benefits to farmers, agricultural experts, agri-tech companies, government agencies, and consumers by enabling precise diagnosis of plant health, enhancing agricultural practices, and ultimately improving crop yields and quality.

Advancements in imaging of head and neck squamous cell carcinoma: A comprehensive review.

As a prevalent malignancy with substantial incidence and mortality worldwide, head and neck squamous cell carcinoma (HNSCC) originates from multiple locations of different tissues, which level up the difficulty and complexity of the cancer detection. The diagnosis requires highresolution imaging modalities and several approaches have been developed within recent decades to provide detailed anatomical information for HNSCC.

High-Performance Vis–NIR Photodetectors Based on Two-Dimensional Bi2Te3 Thin Film and Applications

Two-dimensional materials have excellent optoelectronic properties and have great significance in the field of photodetectors. We have prepared a thin film photodetector based on bismuth telluride (Bi2Te3) topological insulator using dual-temperature-zone vapor deposition technology. Due to the high-quality lattice structure of Bi2Te3 and the uniform and dense surface morphology of the Bi2Te3 thin film, the device exhibits excellent photoelectric response and Vis–NIR spectral range. Under 405 nm illumination, the responsivity is 5.6 mA/W, the specific detectivity is 1.22 × 107 Jones, and the response time is 262/328 ms. We designed a photodetector single-point scanning imaging system and successfully achieved high-resolution imaging at a wavelength of 532 nm. This work provides guidance for the application of two-dimensional materials, especially Bi2Te3, in the fields of photodetectors and imaging.

Performance of high-resolution diffusion-weighted magnetic resonance imaging for detecting clinically occult early breast cancers: a multi-reader study.

To compare mammography, breast ultrasound (US), high-resolution diffusion-weighted magnetic resonance imaging (DW-MRI), dynamic contrast-enhanced breast MRI (DCE-MRI), and their combinations for detecting clinically occult early breast cancers (EBCs), including ductal carcinoma in situ (DCIS). Three hundred and three consecutive women with screening imaging-detected early breast cancers (60 pure DCIS, 36 DCIS with microinvasion, and 207 invasive carcinoma less than 20mm) who underwent breast MRI at 3T including DW-MRI (b-values of 0, 800 and 1200s/mm2; in-plane resolution, 1.1 × 1.1 mm2 or 1.3 × 1.3 mm2; section thickness, 3mm) were retrospectively reviewed. Three radiologists independently reviewed each examination. Statistical analysis included Chi-square test, McNemar test for comparison of cancer detection rates, and Fleiss' Kappa for interreader agreement. Mixed-effect logistic regression analysis was employed to evaluate factors associated with cancer detection on DW-MRI. The overall cancer detection rates were 54.8% on mammography, 71.0% on breast US, 81.5% on DW-MRI, and 87.1% on DCE-MRI. On McNemar test, DW-MRI detected more cancers than mammography (adjusted p < 0.001), and its combination with mammography showed a similar cancer detection rate to DCE-MRI combined with mammography (adjusted p = 0.808). On multivariable analysis, histologic type, lesion size, ADC and CNR on DW-MRI were independent factors for cancer detection on DW-MRI. The interreader agreement for cancer detection was moderate to substantial (Fleiss' kappa: 0.52-0.65) across each modality. High-resolution DW-MRI plus mammography showed comparable cancer detection rate to DCE-MRI plus mammography for detecting clinically occult EBCs including DCIS.

Lightweight Reference-Based Video Super-Resolution Using Deformable Convolution

Super-resolution is a technique for generating a high-resolution image or video from a low-resolution counterpart by predicting natural and realistic texture information. It has various applications such as medical image analysis, surveillance, remote sensing, etc. However, traditional single-image super-resolution methods can lead to a blurry visual effect. Reference-based super-resolution methods have been proposed to recover detailed information accurately. In reference-based methods, a high-resolution image is also used as a reference in addition to the low-resolution input image. Reference-based methods aim at transferring high-resolution textures from the reference image to produce visually pleasing results. However, it requires texture alignment between low-resolution and reference images, which generally requires a lot of time and memory. This paper proposes a lightweight reference-based video super-resolution method using deformable convolution. The proposed method makes the reference-based super-resolution a technology that can be easily used even in environments with limited computational resources. To verify the effectiveness of the proposed method, we conducted experiments to compare the proposed method with baseline methods in two aspects: runtime and memory usage, in addition to accuracy. The experimental results showed that the proposed method restored a high-quality super-resolved image from a very low-resolution level in 0.0138 s using two NVIDIA RTX 2080 GPUs, much faster than the representative method.

Enhanced YOLOv8-Based Model with Context Enrichment Module for Crowd Counting in Complex Drone Imagery

Crowd counting in aerial images presents unique challenges due to varying altitudes, angles, and cluttered backgrounds. Additionally, the small size of targets, often occupying only a few pixels in high-resolution images, further complicates the problem. Current crowd counting models struggle in these complex scenarios, leading to inaccurate counts, which are crucial for crowd management. Moreover, these regression-based models only provide the total count without indicating the location or distribution of people within the environment, limiting their practical utility. While YOLOv8 has achieved significant success in detecting small targets within aerial imagery, it faces challenges when directly applied to crowd counting tasks in such contexts. To overcome these challenges, we propose an improved framework based on YOLOv8, incorporating a context enrichment module (CEM) to capture multiscale contextual information. This enhancement improves the model’s ability to detect and localize tiny targets in complex aerial images. We assess the effectiveness of the proposed framework on the challenging VisDrone-CC2021 dataset, and our experimental results demonstrate the effectiveness of this approach.

Resolution-dependent MRI-to-CT translation for orthotopic breast cancer models using deep learning.

&#xD;This study aims to investigate the feasibility of utilizing generative adversarial networks (GANs) to synthesize high-fidelity CT images from lower-resolution MR images. The goal is to reduce patient exposure to ionizing radiation while maintaining treatment accuracy and accelerating MR image acquisition. The primary focus is to determine the extent to which low-resolution MR images can be utilized to generate high-quality CT images through a systematic study of spatial resolution-dependent MRI-to-CT image conversion. &#xD;Approach. &#xD;Paired MRI-CT images were acquired from healthy control and tumor models, generated by injecting MDA-MB-231 and 4T1 tumor cells into the mammary fat pad of nude and BALB/c mice to ensure model diversification. To explore various MRI resolutions, we downscaled the highest-resolution MR image into three lower resolutions. Using a customized U-Net model, we automated region of interest masking for both MRI and CT modalities with precise alignment, achieved through three-dimensional affine paired MRI-CT registrations. Then our customized models, Nested U-Net Generative Adversarial Network (NUGAN) and Attention U-Net Generative Adversarial Network (AUGAN), were employed to translate low-resolution MR images into high-resolution CT images, followed by evaluation with separate testing datasets.&#xD;Main Results.&#xD;Our approach successfully generated high-quality CT images (0.142 mm²) from both lower-resolution (0.282 mm²) and higher-resolution (0.142 mm²) MR images, with no statistically significant differences between them, effectively doubling the speed of MR image acquisition. Our customized GANs successfully preserved anatomical details, addressing the typical loss issue seen in other MRI-CT translation techniques across all resolutions of MR image inputs.&#xD; Significance. &#xD;This study demonstrates the potential of using low-resolution MR images to generate high-quality CT images, thereby reducing radiation exposure and expediting MRI acquisition while maintaining accuracy for radiotherapy.&#xD.

Advanced photodetector for hybrid PET-MRI systems

Background Currently, a wide variety of silicon photomultipliers (SiPMs) are available, each designed for specific applications in fields such as science, medicine, and industry. Advances in production technology have led to the development of more sensitive and efficient photodiodes, which are critical for applications requiring precision, such as medical imaging. Methods A research group has been working on designing a highly sensitive photodiode to enhance the capabilities of next-generation PET-MRI scanners. This involves integrating micropixel avalanche photodiodes (MAPDs) to improve image resolution. The chosen design features deep-immersion MAPDs with a pixel size of 12 microns and a density of 1000 pixels per square millimeter, allowing for high-detail photon detection. The 4x4 mm2 active area is optimized to balance sensitivity and size for high-resolution medical imaging. To produce these photodiodes, the group has outlined a production plan involving 20-inch silicon wafers grown using multiple techniques to enhance material properties. The Malaysian Institute of Microelectronic Systems (MIMOS), renowned for its expertise in optical microelectronics, was selected as the production center. With MIMOS' state-of-the-art facilities, the project aims to meet stringent medical diagnostics standards. Results The experimental results demonstrated that the MAPD-3NM photodiode achieved an amplification factor 1.8 times greater than the MAPD-3NK under optimal conditions. Its overvoltage range increased by 100%, reaching 4 V, enhancing photon detection and amplification. The MAPD-3NM also showed a significant reduction in dark current, about 3.5 times lower than the MAPD-3NK, improving performance in low-light environments. Additionally, the MAPD-3NM had a capacitance of 200 pF compared to 176 pF for the MAPD-3NK, contributing to its superior performance. These improvements make the MAPD-3NM more efficient and sensitive for scientific and medical applications. Conclusions This project represents a major advancement in photodetector technology for medical diagnostics, aiming to develop more accurate and efficient PET-MRI scanners that enhance patient outcomes with improved imaging capabilities.

Deep learning for 3D vascular segmentation in hierarchical phase contrast tomography: a case study on kidney

Automated blood vessel segmentation is critical for biomedical image analysis, as vessel morphology changes are associated with numerous pathologies. Still, precise segmentation is difficult due to the complexity of vascular structures, anatomical variations across patients, the scarcity of annotated public datasets, and the quality of images. Our goal is to provide a foundation on the topic and identify a robust baseline model for application to vascular segmentation using a new imaging modality, Hierarchical Phase-Contrast Tomography (HiP-CT). We begin with an extensive review of current machine-learning approaches for vascular segmentation across various organs. Our work introduces a meticulously curated training dataset, verified by double annotators, consisting of vascular data from three kidneys imaged using HiP-CT as part of the Human Organ Atlas Project. HiP-CT pioneered at the European Synchrotron Radiation Facility in 2020, revolutionizes 3D organ imaging by offering a resolution of around 20 μm/voxel and enabling highly detailed localised zooms up to 1–2 μm/voxel without physical sectioning. We leverage the nnU-Net framework to evaluate model performance on this high-resolution dataset, using both known and novel samples, and implementing metrics tailored for vascular structures. Our comprehensive review and empirical analysis on HiP-CT data sets a new standard for evaluating machine learning models in high-resolution organ imaging. Our three experiments yielded Dice similarity coefficient (DSC) scores of 0.9523, 0.9410, and 0.8585, respectively. Nevertheless, DSC primarily assesses voxel-to-voxel concordance, overlooking several crucial characteristics of the vessels and should not be the sole metric for deciding the performance of vascular segmentation. Our results show that while segmentations yielded reasonably high scores-such as centerline DSC ranging from 0.82 to 0.88, certain errors persisted. Specifically, large vessels that collapsed due to the lack of hydrostatic pressure (HiP-CT is an ex vivo technique) were segmented poorly. Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed. Such errors, particularly in significant vessels, obstruct the understanding of the structures by interrupting vascular tree connectivity. Our study establishes the benchmark across various evaluation metrics, for vascular segmentation of HiP-CT imaging data, an imaging technology that has the potential to substantively shift our understanding of human vascular networks.

High-resolution imaging of the evolving bipolar outflows in symbiotic novae: The case of the RS Ophiuchi 2021 nova outburst

High-resolution imaging of the evolving bipolar outflows in symbiotic novae: The case of the RS Ophiuchi 2021 nova outburst

Visual and Radar Data Fusion: Complementary or Alternative Sensors in Intelligent Driving Systems

This article explores the role and advantages and disadvantages of visual and radar data fusion in intelligent driving systems. With the rapid development of intelligent driving technology, the comprehensive perception of the environment by car perception systems has become crucial, usually requiring the combination of low, medium, and high-precision sensors. Visual sensors perform excellently in acquiring high-resolution images and recognizing detailed information, while radar sensors have higher stability and penetration in harsh weather conditions. Due to the limitations of a single sensor in complex driving environments, data fusion has become a key strategy for improving the performance of perception systems. By comparing different perception schemes and application scenarios, this article analyzes the actual effects and potential advantages of visual and radar data fusion, revealing its important role in intelligent driving technology. Fusion technology can compensate for the shortcomings of various sensors, and improve the accuracy and reliability of environmental perception, but still faces challenges in data synchronization, algorithm selection, and real-time performance. This article aims to provide valuable insights for the development of future intelligent driving technology.

The Latest Development of Synthetic Aperture Radar: An Overview

Abstract. Synthetic Aperture Radar (SAR) technology enables high-resolution imaging regardless of weather conditions, offering immense potential for target detection and recognition. This paper reviews the latest advancements in SAR technology, highlighting key developments and applications. The limitations of traditional SAR imaging techniques, particularly the trade-off between resolution and swath width, have been addressed by High Resolution Wide Swath (HRWS) SAR, enabling simultaneous acquisition of high-resolution and wide-swath data. Multi-polarimetric SAR provides richer scattering information for improved target recognition accuracy, while deep learning algorithms enhance image quality and recognition performance. Emerging technologies like 3D-ISAR and holographic imaging offer novel approaches to target recognition and tracking. We discuss the development history, performance advantages, and limitations of these technologies, providing a comprehensive overview of their practical applications. We identify current challenges and future trends in SAR target imaging and recognition, including computational efficiency, adversarial attack defense, data acquisition and processing, and feature extraction and classification. Potential research directions, such as integrated multi-mode SAR systems, multi-source data fusion, and adversarial attack defense strategies, are outlined to fully harness the potential of SAR technology in target imaging and recognition.

AI-based Validation of Deforestation Using High-Resolution Satellite Imagery in the Brazilian Amazon

Abstract. Forests play an important role in the Earth systems for carbon sequestration and climate change mitigation, yet they have been increasingly disturbed by deforestation and forest degradation at an unprecedented pace. The Brazilian Amazon, for instance, experienced a 140% rise in deforestation from 2012 to 2020, with a record loss of 13,200 km2 between August 2020 and July 2021. Alarmingly, 87% of 2019 deforestation alerts occurred on private properties, with 61% in legally restricted areas. Existing deforestation monitoring systems, such as PRODES and the Global Forest Change dataset, use about 30m resolution satellite imagery, which is insufficient for operational validation at fine scales. The Deforestation Alert System by Imazon leverages high-resolution PlanetScope data (3-4m) but faces challenges due to fewer spectral bands and variations in reflectance values across different satellite sensors and dates. As a result, current validation is based mainly on manual inspection which is highly time-consuming. To address the challenges and automate the validation process, this work develops a system based on deep learning – known for its ability to capture complex texture patterns in high-resolution images – to inspect and confirm new deforestation sites. Specifically, the system takes inputs from potential deforestation sites suggested by coarse-resolution products and uses a pair of PlanetScope images before and after the change at each site to determine new deforestation (excluding existing deforestation). Our results demonstrate that the new system achieves robust and high-quality accuracy under various test conditions.

Widespread 3′UTR capped RNAs derive from G-rich regions in proximity to AGO2 binding sites

The 3′ untranslated region (3′UTR) plays a crucial role in determining mRNA stability, localisation, translation and degradation. Cap analysis of gene expression (CAGE), a method for the detection of capped 5′ ends of mRNAs, additionally reveals a large number of apparently 5′ capped RNAs derived from locations within the body of the transcript, including 3′UTRs. Here, we provide direct evidence that these 3′UTR-derived RNAs are indeed capped and widespread in mammalian cells. By using a combination of AGO2 enhanced individual nucleotide resolution UV crosslinking and immunoprecipitation (eiCLIP) and CAGE following siRNA treatment, we find that these 3′UTR-derived RNAs likely originate from AGO2-binding sites, and most often occur at locations with G-rich motifs bound by the RNA-binding protein UPF1. High-resolution imaging and long-read sequencing analysis validate several 3′UTR-derived RNAs, showcase their variable abundance and show that they may not co-localise with the parental mRNAs. Taken together, we provide new insights into the origin and prevalence of 3′UTR-derived RNAs, show the utility of CAGE-seq for their genome-wide detection and provide a rich dataset for exploring new biology of a poorly understood new class of RNAs.Graphical Schematic representation of the proposed model where 3′UTR-derived RNAs originate from G-rich regions enriched in AGO2 and UPF1 binding sites.

An improved face attributes editing method based on DDIM

The main advantage of DDIM is that it guarantees the quality of the generated images while increasing the efficiency of the generation by modifying the sampling strategy in the diffusion process. DiffusionRig, which addresses the problem of maintaining identity consistency by learning the person-specific facial prior in a tiny personalized dataset, is a successful representation of the DDIM strategy. Based on DiffusionRig, in this article, we propose an improved face attributes editing method based on DDIM to improve naturalness and accuracy of editing results in complex face attribute editing tasks and the generalization ability. Our method combines DDIM and DECA together and use two-stage training strategy. To reduce DiffusionRig’s limitations in handling face attribute editing tasks that require nonlinear understanding and fine-tuning, our method also introduces a channel attention mechanism and a depth-separable convolution technique in the training model. In the first stage we trained our model on the open FFHQ dataset, which consists of 30,000 high-resolution face image. In the second stage, the model was refined by using a tiny personalized dataset. Face attribute editing experiments,comparative experiment with DiffusionRig, and a series of ablation experiments have been performed. Then, the validity of our improved method is verified by qualitative and quantitative analysis.

Generative 3D Reconstruction of Martian Surfaces using Monocular Images

Abstract. High-resolution digital terrain models (DEM) are crucial for Mars scientific exploration and engineering demands, such as mission route planning, landing site selection, and topography research. However, DEMs generated based on photogrammetry or photometry suffer from limited stereo coverage and complex generative processes. Therefore, we propose a GAN-based monocular 3D reconstruction method, which utilizes high-resolution monocular orbital images to achieve pixel-level Martian terrain reconstruction. We preprocess the image data and then invert the elevation using the trained generative model. Finally, we recover the absolute scale through post-processing. In this work, we use HiRISE orthorectified images and DEMs with a resolution of 2 m and 0.25 m to validate the effectiveness of our method. We evaluated our method in four areas with different landforms and found that the predicted DEM and HiRISE DEM have height consistency with the root mean square error of about 2 m. This indicates that the proposed GAN-based method has certain effectiveness and generalization and great potential in high-resolution monocular Martian DEM reconstruction.

Late olfactory bulb involvement in COVID19.

Transient or persistent hypo-anosmia is common in SARS‑CoV‑2 infection but olfactory pathway late-term morphometric changes are still under investigation. We evaluated late olfactory bulb (OB) imaging changes and their correlates with the olfactory function in otherwise neurologically asymptomatic COVID-19 patients. Eighty-three subjects (mean-age 43±14 years; 54 females; time-interval infection/MRI: 129±68 days) affected by asymptomatic to mild COVID19 in 2020 and 25 healthy controls (mean-age 40±13 years; 9 females) underwent 3T-MRI and olfactory function evaluation through anamnestic questionnaire and Sniffin' Sticks. Exclusion criteria were intensive care treatment or neurological involvement other than olfaction. Maximal OB area was measured blindly on high-resolution coronal T2w images by two observers. Patients were subdivided into: i) persistently hypo/anosmic, ii) recovered normosmic and iii) never complaining smell dysfunction with proven normal olfactory function. No significant differences were observed among patients' subgroups (p=0.76). Intra-observer and inter-observer reliability were high.(r=0.96 and 0.86). Former COVID19 patients had decreased mean maximal OB area than controls (6.52±1.11mm2 vs 7.26±1.17mm2, p=0.008) even when considering persistently hypo-anosmic (6.46±0.90, p=0.006) or normosmic patients at MRI (6.57±1.25, p=0.04). SARS-CoV-2 infection is associated with mid/late-term morphological changes on the olfactory bulbs, regardless of presence or persistence of olfactory dysfunction. The long-term consequences on olfactory aging need to be further investigated including possible links with neurodegenerative disorders.

Study on the Evolutionary Characteristics of Post-Fire Forest Recovery Using Unmanned Aerial Vehicle Imagery and Deep Learning: A Case Study of Jinyun Mountain in Chongqing, China

Forest fires pose a significant threat to forest ecosystems, with severe impacts on both the environment and human society. Understanding the post-fire recovery processes of forests is crucial for developing strategies for species diversity conservation and ecological restoration and preventing further damage. The present study proposes applying the EAswin-Mask2former model based on semantic segmentation in deep learning using visible light band data to better monitor the evolution of burn areas in forests after fires. This model is an improvement of the classical semantic segmentation model Mask2former and can better adapt to the complex environment of burned forest areas. This model employs Swin-Transformer as the backbone for feature extraction, which is particularly advantageous for processing high-resolution images. It also includes the Contextual Transformer (CoT) Block to better capture contextual information capture and incorporates the Efficient Multi-Scale Attention (EMA) Block into the Efficiently Adaptive (EA) Block to enhance the model’s ability to learn key features and long-range dependencies. The experimental results demonstrate that the EAswin-Mask2former model can achieve a mean Intersection-over-Union (mIoU) of 76.35% in segmenting complex forest burn areas across different seasons, representing improvements of 3.26 and 0.58 percentage points, respectively, over the Mask2former models using ResNet and Swin-Transformer backbones, respectively. Moreover, this method surpasses the performance of the DeepLabV3+ and Segformer models by 4.04 and 1.75 percentage points, respectively. Ultimately, the proposed model offers excellent segmentation performance for both forest and burn areas and can effectively track the evolution of burned forests when combined with unmanned aerial vehicle (UAV) remote sensing images.

The MeerKAT view on Galactic supernova remnants

The integrated radio spectrum of supernova remnants (SNRs) and the spatial variation of the spectral indices across these extended sources are powerful tools for studying the shocks and particle acceleration processes occurring in different SNR regions. Characterization of these processes requires sensitive flux density measurements and high-resolution images, which are not always available due to observing difficulties. We want to show the potentiality of the high-resolution SARAO MeerKAT legacy Galactic Plane Survey (SMGPS) images regarding the morphological and spectral characterization of 29 known galactic SNRs. We used the SMGPS data at $1.284$ GHz coupled with data from the GaLactic and Extragalactic All-sky Murchison Widefield Array (GLEAM) survey ($0.072-0.231$ GHz) to characterize the integrated spectrum of each source and search for spatial spectral variation through analysis of sensitive spectral index maps. We were able to redefine the exact morphology of four SNRs (G024.7-00.6, G051.4+00.7, G348.7+0.3, and G351.9+00.1), distinguishing them from unrelated sources or identifying new emission regions associated with them and never observed before. In many other cases, we identified in the SMGPS images several overlaid with the remnants, and we were able to estimate their spectral contribution through inspection of the spatial variation of the spectral indices across the remnants. The integrated spectral indices show a more uniform distribution with respect to what is obtained by considering the values reported in the literature. We show that new sensitive and high-resolution data are crucial to firmly constraining both the integrated and spatially resolved spectrum of SNRs, especially for the less studied objects of the southern hemisphere. The comparison of our SMGPS-GLEAM spectral index maps with IR, molecular, and gamma -ray images allowed us to investigate the nature of the peculiar remnant regions.

Mesoscopic axially swept oblique plane microscope for the imaging of freely moving organisms with near-isotropic resolution

Rapid three-dimensional imaging over extended fields of view (FOVs) is crucial to the study of organism-wide systems and biological processes in vivo. Selective-plane illumination microscopy (SPIM) is a powerful method for high spatio-temporal resolution in toto imaging of such biological specimens. However, typical SPIM implementations preclude conventional sample mounting and have anisotropic imaging performance, in particular when designed for large FOVs over 1 mm diameter. Here, we introduce axial sweeping of the illumination into a non-orthogonal dual-objective oblique plane microscope (OPM) design, thereby enabling the observation of freely moving animals over millimeter-sized FOVs, at close to isotropic, sub-cellular resolution. We apply our mesoscopic axially swept OPM (MASOPM) to image the behavioral dynamics of the sea anemone Nematostella vectensis over 1 × 0.7 × 0.4 mm at 1.7 × 2.6 × 3.7 µm resolution and 0.5 Hz volume rate.