Precise Imaging Research Articles

Spot-Based Global Registration for Subpixel Stitching of Single-Molecule Resolution Images for Tissue-Scale Spatial Transcriptomics.

Single-molecule imaging at the tissue scale has revolutionized our understanding of biology by providing unprecedented insight into the molecular expression of individual cells and their spatial organization within tissues. However, achieving precise image stitching at the single-molecule level remains a challenge, primarily due to heterogeneous background signals and dim labeling signals in single-molecule images. This paper introduces Spot-Based Global Registration (SBGR), a novel strategy that shifts the focus from raw images to identified molecular spots for high-resolution image alignment. The use of spot-based data enables straightforward and robust evaluation of the credibility of estimated translations and stitching performance. The method outperforms existing image-based stitching methods, achieving subpixel accuracy (83 ± 36 nm) with exceptional consistency. Furthermore, SBGR incorporates a mechanism to surgically remove duplicate spots in overlapping regions, maximizing information recovery from duplicate measurements. In conclusion, SBGR emerges as a robust and accurate solution for stitching single-molecule resolution images in tissue-scale spatial transcriptomics, offering versatility and potential for high-resolution spatial analysis.

Injectable Fluorescent Neural Interfaces for Cell-Specific Stimulating and Imaging.

Building on current explorations in chronic optical neural interfaces, it is essential to address the risk of photothermal damage in traditional optogenetics. By focusing on calcium fluorescence for imaging rather than stimulation, injectable fluorescent neural interfaces significantly minimize photothermal damage and improve the accuracy of neuronal imaging. Key advancements including the use of injectable microelectronics for targeted electrical stimulation and their integration with cell-specific genetically encoded calcium indicators have been discussed. These injectable electronics that allow for post-treatment retrieval offer a minimally invasive solution, enhancing both usability and reliability. Furthermore, the integration of genetically encoded fluorescent calcium indicators with injectable bioelectronics enables precise neuronal recording and imaging of individual neurons. This shift not only minimizes risks such as photothermal conversion but also boosts safety, specificity, and effectiveness of neural imaging. Embracing these advancements represents a significant leap forward in biomedical engineering and neuroscience, paving the way for advanced brain-machine interfaces.

Supermolecular Confined Silicon Phosphorescence Nanoprobes for Time-Resolved Hypoxic Imaging Analysis.

Room temperature phosphorescence (RTP) nanoprobes play crucial roles in hypoxia imaging due to their high signal-to-background ratio (SBR) in the time domain. However, synthesizing RTP probes in aqueous media with a small size and high quantum yield remains challenging for intracellular hypoxic imaging up to present. Herein, aqueous RTP nanoprobes consisting of naphthalene anhydride derivatives, cucurbit[7]uril (CB[7]), and organosilicon are reported via supermolecular confined methods. Benefiting from the noncovalent confinement of CB[7] and hydrolysis reactions of organosilicon, such small-sized RTP nanoprobes (5-10 nm) exhibit inherent tunable phosphorescence (from 400 to 680 nm) with microsecond second lifetimes (up to ∼158.7 μs) and high quantum yield (up to ∼30%). The as-prepared RTP nanoprobes illustrate excellent intracellular hypoxia responsibility in a broad range from ∼0.1 to 21% oxygen concentrations. Compared to traditional fluorescence mode, the SBR value (∼108.69) of microsecond-range time-resolved in vitro imaging is up to 2.26 times greater in severe hypoxia (<0.1% O2), offering opportunities for precision imaging analysis in a hypoxic environment.

A Multi-Element Identification System Based on Deep Learning for the Visual Field of Percutaneous Endoscopic Spine Surgery.

Lumbar disc herniation is a common degenerative lumbar disease with an increasing incidence. Percutaneous endoscopic lumbar discectomy can treat lumbar disc herniation safely and effectively with a minimally invasive procedure. However, the learning curve of this technology is steep, which means that initial learners are often not sufficiently proficient in endoscopic operations, which can easily lead to iatrogenic damage. At present, the application of computer deep learning technology to clinical diagnosis, treatment, and surgical navigation has achieved satisfactory results. The objective of our team is to develop a multi-element identification system for the visual field of endoscopic spine surgery using deep learning algorithms and to evaluate the feasibility of this system. We established an image database by collecting surgical videos of 48 patients diagnosed with lumbar disc herniation, which was labeled by two spinal surgeons. We selected 6000 images of the visual field of percutaneous endoscopic spine surgery (including various tissue structures and surgical instruments), divided into the training data, validation data, and test data according to 2:1:2. We developed convolutional neural network models based on instance segmentation-Solov2, CondInst, Mask R-CNN and Yolact, and set the four network model backbone as ResNet101 and ResNet50 respectively. Mean average precision (mAP) and frames per second (FPS) were used to measure the performance of each model for classification, localization and recognition in real time, and AP (average) is used to evaluate how easily an element is detected by neural networks based on computer deep learning. Comprehensively comparing mAP and FSP of each model for bounding box test and segmentation task for the test set of images, we found that Solov2 (ResNet101) (mAP = 73.5%, FPS = 28.9), Mask R-CNN (ResNet101) (mAP = 72.8%, FPS = 28.5) models are the most stable, with higher precision and faster image processing speed. Combining the average precision of the elements in the bounding box test and segmentation tasks in each network, the AP(average) was highest for tool 3 (bbox-0.85, segm-0.89) and lowest for tool 5 (bbox-0.63, segm-0.72) in the instrumentation, whereas in the anatomical tissue elements, the fibrosus annulus (bbox-0.68, segm-0.69) and ligamentum flavum (bbox-0.65, segm-0.62) had higher AP(average),while extra-dural fat (bbox-0.42, segm-0.44) was lowest. Our team has developed a multi-element identification system for the visual field of percutaneous endoscopic spine surgery adapted to the interlaminar and foraminal approaches, which can identify and track anatomical tissue (nerve, ligamentum flavum, nucleus pulposus, etc.) and surgical instruments (endoscopic forceps, an high-speed diamond burr, etc.), which can be used in the future as a virtual educational tool or applied to the intraoperative real-time assistance system for spinal endoscopic operation.

Application of Image Segmentation Algorithms in Computer Vision

In the field of computer vision (CV), image segmentation technology, as a fundamental part, has a crucial impact on the accuracy of subsequent image processing tasks. Image segmentation is not only a crucial transitional step from image processing to image analysis, but also a hot and difficult research topic in the field of CV. Although significant progress has been made in the research of image segmentation algorithms, existing segmentation algorithms may still face challenges in certain specific scenarios due to the complexity and diversity of images, making it difficult to achieve ideal segmentation results. In recent years, the rapid development of deep learning (DL) technology has brought new breakthroughs to the field of image segmentation. DL models, especially Convolutional Neural Networks (CNNs), can capture semantic information of images more accurately by automatically learning feature representations in images, thereby achieving more precise image segmentation. This article delves into the research and application of image segmentation algorithms in CV, with a focus on the application of DL in the field of image segmentation. With the continuous development of advanced technologies such as DL, it is believed that image segmentation technology will play a greater role in more fields in the future.

Computed tomography multi-planar and 3D image assessment protocol for detailed analysis of inner ear malformations in patients undergoing cochlear implantation counseling.

&lt;b&gt;&lt;br&gt;Introduction:&lt;/b&gt; Congenital inner ear malformations resulting from embryogenesis may be visualized in radiological scans. Many attempts have been made to describe and classify the defects of the inner ear based on anatomical and radiological findings.&lt;/br&gt; &lt;b&gt;&lt;br&gt;Aim:&lt;/b&gt; The aim was to propose and discuss computed tomography multi-planar and 3D image assessment protocols for detailed analysis of inner ear malformations in patients undergoing cochlear implantation counseling.&lt;/br&gt; &lt;b&gt;&lt;br&gt;Material and methods:&lt;/b&gt; A retrospective analysis of 22 malformed inner ears. CT scans were analyzed using the Multi-Planar Reconstruction (MPR) option and 3D reconstruction.&lt;/br&gt; &lt;b&gt;&lt;br&gt;Results:&lt;/b&gt; The protocol of image interpretation was developed to allow reproducibility for evaluating each set of images. The following malformations were identified: common cavity, cochlear hypoplasia type II, III, and IV, incomplete partition type II and III, and various combinations of vestibule labyrinth malformations. All anomalies have been presented and highlighted in figures with appropriate descriptions for easier identification. Figures of normal inner ears were also included for comparison. 3D reconstructions for each malformation were presented, adding clinical value to the detailed analysis.&lt;/br&gt; &lt;b&gt;&lt;br&gt;Conclusions:&lt;/b&gt; Properly analyzing CT scans in cochlear implantation counseling is a necessary and beneficial tool for appropriate candidate selection and preparation for surgery. As proposed in this study, the unified scans evaluation scheme simplifies the identification of malformations and reduces the risk of omitting particular anomalies. Multi-planar assessment of scans provides most of the necessary details. The 3D reconstruction technique is valuable in addition to diagnostics influencing the decision-making process. It can minimize the risk of misdiagnosis. Disclosure of the inner ear defect and its precise imaging provides detailed anatomical knowledge of each ear, enabling the selection of the appropriate cochlear implant electrode and the optimal surgical technique.&lt;/br&gt.

Hyaluronic acid functionalized iron–platinum nanoparticles for photothermal therapy and photoacoustic imaging

This study represents an innovative approach to construct multi-functional nanoplatforms for cancer diagnosis and therapy by combining hyaluronic acid (HA) with iron-platinum nanoparticles (FePt NPs). These HA-coated FePt NPs, referred to as FePt@HA NPs, demonstrated remarkable biocompatibility, high absorption, and excellent light-to-heat conversion properties in the near-infrared (NIR) region, making them ideal candidates for photothermal therapy (PTT). In vitro studies revealed their effective cancer cell eradication under NIR laser irradiation, while in vivo experiments on mice showcased their superior heating capabilities. Moreover, FePt@HA NPs exhibited a distinct and strong photoacoustic (PA) signal, facilitating enhanced and precise intra-tumoral PA imaging. Our results highlight the potential of FePt@HA NPs as promising photothermal agents for future PTT applications. They offer high selectivity, precision, and minimal side effects in cancer treatment, along with their valuable PA imaging application for tumor localization and characterization.

Design of an Iterative Method for Enhanced Retinal Image Analysis Using Stacked Deep Learning Operations

The necessity for advanced diagnostic techniques in ophthalmology has become increasingly evident, particularly for conditions such as glaucoma and diabetic retinopathy, which necessitate precise retinal image analysis. Current methodologies, while effective to a degree, fall short in terms of accuracy, efficiency, and adaptability, especially in semantic segmentation and disease classification tasks. These limitations underscore the need for more sophisticated and reliable approaches to retinal image analysis. In response, this work introduces a comprehensive framework leveraging Fully Convolutional Neural Networks (FCNNs) for optic disc segmentation and Cup-to-Disc Ratio (CDR) estimation. The selection of FCNNs is predicated on their demonstrated proficiency in semantic segmentation, ability to discern spatial dependencies, and capacity to learn intricate structures within fundus images without relying on manually engineered features. This approach aims to surpass existing segmentation accuracy benchmarks, targeting over 95% Intersection over Union (IoU) while reducing the mean absolute error in CDR estimation to below 10%. To address the challenges of data variability and quality, the framework incorporates Contrast Limited Adaptive Histogram Equalization (CLAHE) for synthetic data generation, enhancing local contrast while preserving image integrity levels. This method is expected to improve contrast in augmented images by 30%, simultaneously enhancing image quality metrics. Furthermore, the introduction of an overlapping sliding window technique with adaptive patch sizes ensures meticulous coverage and analysis of fundus images, significantly elevating lesion detection sensitivity and reducing false positives. Lastly, the framework employs an innovative multi-disease classification strategy utilizing ensemble learning and stacking of CNN architectures. This synergistic approach amalgamates multiple base models to diminish overfitting risks and enhance generalization capabilities, aiming for a classification accuracy surpassing 95% in binary assessments and 85% for specific retinal diseases. The proposed model not only addresses the current gaps in retinal image analysis but also sets a new standard for precision, reliability, and efficiency in diagnosing and managing ocular diseases, marking a significant step forward in the application of artificial intelligence in ophthalmology.

Research on Efficient Feature Generation and Spatial Aggregation for Remote Sensing Semantic Segmentation

Semantic segmentation algorithms leveraging deep convolutional neural networks often encounter challenges due to their extensive parameters, high computational complexity, and slow execution. To address these issues, we introduce a semantic segmentation network model emphasizing the rapid generation of redundant features and multi-level spatial aggregation. This model applies cost-efficient linear transformations instead of standard convolution operations during feature map generation, effectively managing memory usage and reducing computational complexity. To enhance the feature maps’ representation ability post-linear transformation, a specifically designed dual-attention mechanism is implemented, enhancing the model’s capacity for semantic understanding of both local and global image information. Moreover, the model integrates sparse self-attention with multi-scale contextual strategies, effectively combining features across different scales and spatial extents. This approach optimizes computational efficiency and retains crucial information, enabling precise and quick image segmentation. To assess the model’s segmentation performance, we conducted experiments in Changge City, Henan Province, using datasets such as LoveDA, PASCAL VOC, LandCoverNet, and DroneDeploy. These experiments demonstrated the model’s outstanding performance on public remote sensing datasets, significantly reducing the parameter count and computational complexity while maintaining high accuracy in segmentation tasks. This advancement offers substantial technical benefits for applications in agriculture and forestry, including land cover classification and crop health monitoring, thereby underscoring the model’s potential to support these critical sectors effectively.

Unsupervised Multi-parametric MRI Registration Using Neural Optimal Transport.

Precise deformable image registration of multi-parametric MRI sequences is necessary for radiologists in order to identify abnormalities and diagnose diseases, such as prostate cancer and lymphoma. Despite recent advances in unsupervised learning-based registration, volumetric medical image registration that requires considering the variety of data distributions is still challenging. To address the problem of multi-parametric MRI sequence data registration, we propose an unsupervised domain-transported registration method, called OTMorph by employing neural optimal transport that learns an optimal transport plan to map different data distributions. We have designed a novel framework composed of a transport module and a registration module: the former transports data distribution from the moving source domain to the fixed target domain, and the latter takes the transported data and provides the deformed moving volume that is aligned with the fixed volume. Through end-to-end learning, our proposed method can effectively learn deformable registration for the volumes in different distributions. Experimental results with abdominal multi-parametric MRI sequence data show that our method has superior performance over around 67-85% in deforming the MRI volumes compared to the existing learning-based methods. Our method is generic in nature and can be used to register inter-/intra-modality images by mapping the different data distributions in network training.

Lifelike PixelPrint phantoms for assessing clinical image quality and dose reduction capabilities of a deep learning CT reconstruction algorithm.

Deep learning CT reconstruction (DLR) has become increasingly popular as a method for improving image quality and reducing radiation exposure. Due to their nonlinear nature, these algorithms result in resolution and noise performance which are object-dependent. Therefore, traditional CT phantoms, which lack realistic tissue morphology, have become inadequate for assessing clinical imaging performance. We propose to utilize 3D-printed PixelPrint phantoms, which exhibit lifelike attenuation profiles, textures, and structures, as a better tool for evaluating DLR performance. In this study, we evaluate a DLR algorithm (Precise Image (PI), Philips Healthcare) using a custom PixelPrint lung phantom and perform head-to-head comparisons between DLR, iterative reconstruction, and filtered back projection (FBP) with scans acquired at a broad range of radiation exposures (CTDIvol: 0.5, 1, 2, 4, 6, 9, 12, 15, 19, and 20 mGy). We compared the performance of each resultant image using noise, peak signal to noise ratio (PSNR), structural similarity index (SSIM), feature-based similarity index (FSIM), information theoretic-based statistic similarity measure (ISSM) and universal image quality index (UIQ). Iterative reconstruction at 9 mGy matches the image quality of FBP at 12 mGy (diagnostic reference level) for all metrics, demonstrating a dose reduction capability of 25%. Meanwhile, DLR matches the image quality of diagnostic reference level FBP images at doses between 4 - 9 mGy, demonstrating dose reduction capabilities between 25% and 67%. This study shows that DLR allows for reduced radiation dose compared to both FBP and iterative reconstruction without compromising image quality. Furthermore, PixelPrint phantoms offer more realistic testing conditions compared to traditional phantoms in the evaluation of novel CT technologies. This, in turn, promotes the translation of new technologies, such as DLR, into clinical practice.

Assessment of Mental Foramen Characteristics in Syrian Population Using Cone Beam Computed Tomography: A Pilot Study.

Background Knowledge of the mental foramen (MF) characteristics is crucial for avoiding iatrogenic injuries during dental implant placement, root canal treatment, orthognathic surgery, and other dental and surgical interventions. Cone beam computed tomography (CBCT) offers a valuable tool for evaluating the MF characteristics with its precise anatomical details. The current study investigates the horizontal and vertical position variations in addition to the exit angle of MF within the Syrian adult population. Materials and methods The sample included CBCT scans of 42 subjects with an equal number of males and females (21 males, 21 females), with no underlying pathology in the investigated region, mean age was 24.7 years (SD: 7.2 years). CBCT scans were retrospectively analyzed in terms of the vertical, horizontal, and exit angle direction of MF. The chi-square test was conducted to investigate statistical differences in terms of MF horizontal and vertical positions. A T-test was conducted to investigate statistical differences in terms of exit angle direction. Comparisons were conducted between males and females groups, and between the left and right sides in the total sample group. Results The most frequent horizontal position was position 3 (MF between the first and second premolars) on the right side (n=20, 47.61%), and on the left side (n=21, 50%). The most frequent vertical position was position 3 (MF below the apices of the premolars) on the right side (n=29, 69.04%), and on the left side (n=27, 64.28%).The exit angle of the MF was in a backward direction, with a mean value of 118.42° (SD: 6.45 degrees), and 115.97° (SD: 7.29 degrees) on the right and left side, respectively. Statistically significant differences were found in terms of the right vertical position between males and females (P value < 0.05). Conclusion Variations in MF characteristics exist in the Syrian population. Statistically significant differences were found in the right vertical position of MF. The current study findings necessitate precise preoperative three-dimensional imaging for dental interventions among this population. By establishing normative values for the Syrian population, the results can contribute to improved surgical planning and patient care, and can be used for comparative studies for more understanding of the human anatomical variations.

Machine learning and new insights for breast cancer diagnosis.

Breast cancer (BC) is the most prominent form of cancer among females all over the world. The current methods of BC detection include X-ray mammography, ultrasound, computed tomography, magnetic resonance imaging, positron emission tomography and breast thermographic techniques. More recently, machine learning (ML) tools have been increasingly employed in diagnostic medicine for its high efficiency in detection and intervention. The subsequent imaging features and mathematical analyses can then be used to generate ML models, which stratify, differentiate and detect benign and malignant breast lesions. Given its marked advantages, radiomics is a frequently used tool in recent research and clinics. Artificial neural networks and deep learning (DL) are novel forms of ML that evaluate data using computer simulation of the human brain. DL directly processes unstructured information, such as images, sounds and language, and performs precise clinical image stratification, medical record analyses and tumour diagnosis. Herein, this review thoroughly summarizes prior investigations on the application of medical images for the detection and intervention of BC using radiomics, namely DL and ML. The aim was to provide guidance to scientists regarding the use of artificial intelligence and ML in research and the clinic.

A smart mRNA-initiated DNAzyme nanogenerator for precise imaging and gene therapy in vivo

Despite the significant potential of gene therapy mediated by deoxyribozyme (DNAzyme) in various diseases, the success of clinical cancer treatment remains challenging due to its low selectivity and efficiency. In this study, a novel DNAzyme nanogenerator (NG) triggered by mRNA was developed for in vivo tumour-enhanced imaging and precise gene therapy. After entering target cells, the NG could initiate a DNAzyme catalytic reaction in response to tumour-associated mRNA targets within the cells. The DNAzyme catalytic reaction continuously cleaved the DNA substrate sandwiched by labeled dyes, resulting in significantly amplified fluorescence release and continuous generation of another effective DNAzyme, silencing VEGF-related genes. The detection limit of NG for TK1 mRNA reached 3.62 pM. Additionally, NG could selectively image at tumour sites and specifically generate DNAzyme in tumor cells. NG accurately identified tumors in vivo and significantly inhibited tumour growth with negligible toxicity, thus expanding the toolbox for on-demand gene delivery and precise therapy.

A deep semantic network-based image segmentation of soybean rust pathogens.

Asian soybean rust is a highly aggressive leaf-based disease triggered by the obligate biotrophic fungus Phakopsora pachyrhizi which can cause up to 80% yield loss in soybean. The precise image segmentation of fungus can characterize fungal phenotype transitions during growth and help to discover new medicines and agricultural biocides using large-scale phenotypic screens. The improved Mask R-CNN method is proposed to accomplish the segmentation of densely distributed, overlapping and intersecting microimages. First, Res2net is utilized to layer the residual connections in a single residual block to replace the backbone of the original Mask R-CNN, which is then combined with FPG to enhance the feature extraction capability of the network model. Secondly, the loss function is optimized and the CIoU loss function is adopted as the loss function for boundary box regression prediction, which accelerates the convergence speed of the model and meets the accurate classification of high-density spore images. The experimental results show that the mAP for detection and segmentation, accuracy of the improved algorithm is improved by 6.4%, 12.3% and 2.2% respectively over the original Mask R-CNN algorithm. This method is more suitable for the segmentation of fungi images and provide an effective tool for large-scale phenotypic screens of plant fungal pathogens.

All-sky Guide Star Catalog for CSST

The China Space Station Telescope (CSST) is a two-meter space telescope with multiple back-end instruments. The Fine Guidance Sensor (FGS) is an essential subsystem of the CSST Precision Image Stability System to ensure the required absolute pointing accuracy and line-of-sight stabilization. In this study, we construct the Main Guide Star Catalog for FGS. To accomplish this, we utilize the information about the FGS and object information from the Gaia Data Release 3. We provide an FGS instrument magnitude and exclude variables, binaries, and high proper motion stars from the catalog to ensure uniform FGS guidance capabilities. Subsequently, we generate a HEALPix index, which provides a hierarchical tessellation of the celestial sphere, and employ the Voronoi algorithm to achieve a homogeneous distribution of stars across the catalog. This distribution ensures adequate coverage and sampling of the sky. The performance of the CSST guide star catalog was assessed by simulating the field of view of the FGS according to the CSST mock survey strategy catalog. The analysis of the results indicates that this catalog provides adequate coverage and accuracy. The catalog's performance meets the FGS requirements, ensuring the functioning of the FGS and its guidance capabilities.

Supermicrosurgical lymphovenous anastomosis.

Lymphedema impairs patients' function and quality of life. Currently, supermicrosurgical lymphovenous anastomosis (LVA) is regarded as a significant and effective treatment for lymphedema. This article aims to review recent literature on this procedure, serving as a reference for future research and surgical advancements. Evolving since the last century, LVA has emerged as a pivotal domain within modern microsurgery. It plays a crucial role in treating lymphatic disorders. Recent literature discusses clinical imaging, surgical techniques, postoperative care, and efficacy. Combining advanced tools, precise imaging, and surgical skills, LVA provides a safer and more effective treatment option for lymphedema patients, significantly enhancing their quality of life. This procedure also presents new challenges and opportunities in the realm of microsurgery.

Rationally Designed Benzobisthiadiazole-Based Covalent Organic Framework for High-Performance NIR-II Fluorescence Imaging-Guided Photodynamic Therapy.

Although being applied as photosensitizers for photodynamic therapy, covalent organic frameworks (COFs) fail the precise fluorescence imaging in vivo and phototherapy in deep-tissue, due to short excitation/emission wavelengths. Herein, this work proposes the first example of NIR-II emissive and benzobisthiadiazole-based COF-980. Comparing to its ligands, the structure of COF-980 can more efficiently reducing the energy gap (ΔES1-T1) between the excited state and the triplet state to enhance photodynamic therapy efficiency. Importantly, COF-980 demonstrates high photostability, good anti-diffusion property, superior reactive oxygen species (ROS) generation efficiency, promising imaging ability, and ROS production in deep tissue (≈8mm). Surprisingly, COF-980 combined with laser irradiation could trigger larger amount of intracellular ROS to high efficiently induce cancer cell death. Notably, COF-980 NPs precisely enable PDT guided by NIR-II fluorescence imaging that effectively inhibit the 4T1 tumor growth with negligible adverse effects. This study provides a universal approach to developing long-wavelength emissive COFs and exploits its applications for biomedicine.

Abstract 5504: Integrating ultrahigh-plex spatial phenotyping: From discovery to clinical applications

Abstract Background The journey from discovering predictive spatial biomarkers (known as spatial signatures) for immunotherapy responses to their clinical application necessitates a cohesive approach bridging ultrahigh-plex discovery experiments with high-throughput translational studies. This study focuses on integrating Akoya Biosciences spatial multiplexed imaging technologies with advanced data analysis techniques for comprehensive spatial phenotyping across the discovery-to-clinical continuum. Methods Human formalin-fixed, paraffin-embedded (FFPE) cancer tissues were profiled using ultrahigh-plex PhenoCode™ Discovery panels to examine cell lineage, immune activation, and checkpoint markers via the PhenoCycler®-Fusion spatial biology platform. The subsequent use of PhenoCode™ Signature panels targeted specific biomarkers of immune profile, immune contexture, tumor-infiltrating lymphocytes (TIL), macrophage polarization, and T cell status via the PhenoImager® HT platform. Open-source whole slide image analysis software QuPath was employed for precise image analysis, including ROI segmentation, cell detection, classification, exploration of spatial interactions, and identification of distinct spatial signatures. Results Our analysis revealed distinct spatial relationships within various tumor types, quantifying immune cell distributions and their interactions. The ultrahigh-plex data correlated with high-throughput signature panel analyses, thus paving a new simplified way for targeted identification and development of predictive spatial signatures for immunotherapy outcomes. Conclusions The combined use of ultrahigh-plex discovery panels, high-throughput signature panels, and deep-learning image analysis provides a comprehensive understanding of cellular interactions in the tumor microenvironment. This integrated approach, utilizing Akoya's end-to-end workflows, accelerates the identification of predictive spatial biomarker signatures across various human tissue samples. Citation Format: Aditya Pratapa, Ning Ma, Niyati Jhaveri. Integrating ultrahigh-plex spatial phenotyping: From discovery to clinical applications [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 5504.

Abstract 3529: Leveraging deep learning for fully automated analysis of pre-clinical mouse positron emission tomography

Abstract Turning early-cancer diagnosis into actionable treatment often relies on highly accurate and sensitive imaging techniques to guide surgical intervention or to monitor therapeutic efficacy. Earli is developing a highly sensitive, orthogonal approach that uses genetic constructs to usurp dysregulated cancer pathways to force the tumor to produce a PET reporter gene, enabling the use of radiotracers amenable to positron emission tomography/computed tomography (PET/CT) to guide precision imaging. However, analysis of PET/CT images using standard manual and semi-automated methods is challenging resulting in reduced experimental throughput and user variability, highlighting the need for a fully automated PET/CT analysis pipeline using Deep Learning (DL). To increase pre-clinical throughput and reduce inter-user variability, we developed an automated DL processing pipeline in Python to perform three major tasks: separation of multi-mouse bed data for PET uptake quantification by mouse, segmentation of tumors and background organs, and quantification of PET signal for PK/PD analysis. Preclinical PET/CT data was acquired using a 4 animal, multi-mouse bed and separated into individual mice by co-registering the reconstructed CT image against a multi-mouse bed reference mask using a rigid 3D Euler transformation algorithm and cropping at fixed indices. Following mouse separation, a 3D nnUNet architecture is used to perform semantic segmentation of regions of interest (ROI) on CT for bi-hemispheric subcutaneous tumors, lungs, liver, kidneys, spleen, and the bladder. nnUNet was trained on PET/CT of 311 mice consisting of a mixture of naïve and tumor-bearing animals subcutaneously implanted with H1299 cells using a five-fold cross-validation strategy with 1000 epochs per fold. Model performance was evaluated by comparing the network prediction to the reference manually annotated masks using the Dice coefficient. PET uptake is reported as percent injected dose per milliliter (%ID/mL) or standardized uptake value (SUV). Segmentation performance results for the hold-out set identified mean Dice scores greater than 0.80 for all ROIs, reflecting the similarity between model predictions and human annotations. The automated pipeline reduced the analysis time from 5.5-6 hours per mouse when using traditional manual/semi-automatic approaches to approximately 15 minutes. In summary, we developed a fully automated DL-based PET/CT quantification pipeline for pre-clinical mouse studies that provides accurate ROI segmentation and PET uptake quantification, significantly increasing experimental throughput and reducing inter-user variability. Further improvements to model inference include loss functions weighted for poor performing ROIs and addition of lung nodule segmentation for eventual translation to humans as an accompaniment to Earli’s theranostic programs. Citation Format: Hung-Yu Henry Lee, Mohammed Goryawala, Tim Sproul, Maggie Louie, David Suhy. Leveraging deep learning for fully automated analysis of pre-clinical mouse positron emission tomography [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 3529.