Show newer

Interpretable Embeddings for Segmentation-Free Single-Cell Analysis in Multiplex Imaging arxiv.org/abs/2411.03341 .IV .CV

A networked small-gain theorem based on discrete-time diagonal stability arxiv.org/abs/2411.03380 .SY .OC .SY

BOston Neonatal Brain Injury Data for Hypoxic Ischemic Encephalopathy (BONBID-HIE): II. 2-year Neurocognitive Outcome and NICU Outcome arxiv.org/abs/2411.03456 .IV .CV

TopoTxR: A topology-guided deep convolutional network for breast parenchyma learning on DCE-MRIs arxiv.org/abs/2411.03464 .IV .CV

Digital Twin for Autonomous Surface Vessels: Enabler for Safe Maritime Navigation arxiv.org/abs/2411.03465 .SY .RO .SY

Enhancing Weakly Supervised Semantic Segmentation for Fibrosis via Controllable Image Generation arxiv.org/abs/2411.03551 .IV .AI .CV

Upper Mid-Band Channel Measurements and Characterization at 6.75 GHz FR1(C) and 16.95 GHz FR3 in an Indoor Factory Scenario arxiv.org/abs/2411.03565 .SP

Privacy Preserving Mechanisms for Coordinating Airspace Usage in Advanced Air Mobility arxiv.org/abs/2411.03582 .SY .SY

Beam Tracking for Full-Duplex User Terminals in Low Earth Orbit Satellite Communication Systems arxiv.org/abs/2411.03606 .SP

Multi-bit Distributed Detection of Sparse Stochastic Signals over Error-Prone Reporting Channels arxiv.org/abs/2411.03612 .SP

Revisiting the Fraunhofer and Fresnel Boundaries for Phased Array Antennas arxiv.org/abs/2411.02417 .SP .IT .IT

Revisiting the Fraunhofer and Fresnel Boundaries for Phased Array Antennas

This paper presents the characterization of near-field propagation regions for phased array antennas, with a particular focus on the propagation boundaries defined by Fraunhofer and Fresnel distances. These distances, which serve as critical boundaries for understanding signal propagation behavior, have been extensively studied and characterized in the literature for single-element antennas. However, the direct application of these results to phased arrays, a common practice in the field, is argued to be invalid and non-exact. This work calls for a deeper understanding of near-field propagation to accurately characterize such boundaries around phased array antennas. More specifically, for a single-element antenna, the Fraunhofer distance is $d^{\mathrm{F}}=2D^2 \sin^2(θ)/λ$ where $D$ represents the largest dimension of the antenna, $λ$ is the wavelength and $θ$ denotes the observation angle. We show that for phased arrays, $d^{\mathrm{F}}$ experiences a fourfold increase (i.e., $d^{\mathrm{F}}=8D^2 \sin^2(θ)/λ$) provided that $|θ-\fracπ{2}|>θ^F$ (which holds for most practical scenarios), where $θ^F$ is a small angle whose value depends on the number of array elements, and for the case $|θ-\fracπ{2}|\leqθ^F$, we have $d^{\mathrm{F}}\in[2D^2/λ,8D^2\cos^2(θ^F)/λ]$, where the precise value is obtained according to some square polynomial function $\widetilde{F}(θ)$. Besides, we also prove that the Fresnel distance for phased array antennas is given by $d^{\mathrm{N}}=1.75 \sqrt{{D^3}/λ}$ which is $\sqrt{8}$ times greater than the corresponding distance for a conventional single-element antenna with the same dimension.

arXiv.org

A Study on Characterization of Near-Field Sub-Regions For Phased-Array Antennas arxiv.org/abs/2411.02425 .SP .IT .IT

A Study on Characterization of Near-Field Sub-Regions For Phased-Array Antennas

We characterize three near-field sub-regions for phased array antennas by elaborating on the boundaries {\it Fraunhofer}, {\it radial-focal}, and {\it non-radiating} distances. The {\it Fraunhofer distance} which is the boundary between near and far field has been well studied in the literature on the principal axis (PA) of single-element center-fed antennas, where PA denotes the axis perpendicular to the antenna surface passing from the antenna center. The results are also valid for phased arrays if the PA coincides with the boresight, which is not commonly the case in practice. In this work, we completely characterize the Fraunhofer distance by considering various angles between the PA and the boresight. For the {\it radial-focal distance}, below which beamfocusing is feasible in the radial domain, a formal characterization of the corresponding region based on the general model of near-field channels (GNC) is missing in the literature. We investigate this and elaborate that the maximum-ratio-transmission (MRT) beamforming based on the simple uniform spherical wave (USW) channel model results in a radial gap between the achieved and the desired focal points. While the gap vanishes when the array size $N$ becomes sufficiently large, we propose a practical algorithm to remove this gap in the non-asymptotic case when $N$ is not very large. Finally, the {\it non-radiating} distance, below which the reactive power dominates active power, has been studied in the literature for single-element antennas. We analytically explore this for phased arrays and show how different excitation phases of the antenna array impact it. We also clarify some misconceptions about the non-radiating and Fresnel distances prevailing in the literature.

arXiv.org

Chronic Obstructive Pulmonary Disease Prediction Using Deep Convolutional Network arxiv.org/abs/2411.02449 .IV .CV

Chronic Obstructive Pulmonary Disease Prediction Using Deep Convolutional Network

AI and deep learning are two recent innovations that have made a big difference in helping to solve problems in the clinical space. Using clinical imaging and sound examination, they also work on improving their vision so that they can spot diseases early and correctly. Because there aren't enough trained HR, clinical professionals are asking for help with innovation because it helps them adapt to more patients. Aside from serious health problems like cancer and diabetes, the effects of respiratory infections are also slowly getting worse and becoming dangerous for society. Respiratory diseases need to be found early and treated quickly, so listening to the sounds of the lungs is proving to be a very helpful tool along with chest X-rays. The presented research hopes to use deep learning ideas based on Convolutional Brain Organization to help clinical specialists by giving a detailed and thorough analysis of clinical respiratory sound data for Ongoing Obstructive Pneumonic identification. We used MFCC, Mel-Spectrogram, Chroma, Chroma (Steady Q), and Chroma CENS from the Librosa AI library in the tests we ran. The new system could also figure out how serious the infection was, whether it was mild, moderate, or severe. The test results agree with the outcome of the deep learning approach that was proposed. The accuracy of the framework arrangement has been raised to a score of 96% on the ICBHI. Also, in the led tests, we used K-Crisp Cross-Approval with ten parts to make the presentation of the new deep learning approach easier to understand. With a 96 percent accuracy rate, the suggested network is better than the rest. If you don't use cross-validation, the model is 90% accurate.

arXiv.org

Weakly supervised deep learning model with size constraint for prostate cancer detection in multiparametric MRI and generalization to unseen domains arxiv.org/abs/2411.02466 .IV .AI .LG

Weakly supervised deep learning model with size constraint for prostate cancer detection in multiparametric MRI and generalization to unseen domains

Fully supervised deep models have shown promising performance for many medical segmentation tasks. Still, the deployment of these tools in clinics is limited by the very timeconsuming collection of manually expert-annotated data. Moreover, most of the state-ofthe-art models have been trained and validated on moderately homogeneous datasets. It is known that deep learning methods are often greatly degraded by domain or label shifts and are yet to be built in such a way as to be robust to unseen data or label distributions. In the clinical setting, this problematic is particularly relevant as the deployment institutions may have different scanners or acquisition protocols than those from which the data has been collected to train the model. In this work, we propose to address these two challenges on the detection of clinically significant prostate cancer (csPCa) from bi-parametric MRI. We evaluate the method proposed by (Kervadec et al., 2018), which introduces a size constaint loss to produce fine semantic cancer lesions segmentations from weak circle scribbles annotations. Performance of the model is based on two public (PI-CAI and Prostate158) and one private databases. First, we show that the model achieves on-par performance with strong fully supervised baseline models, both on in-distribution validation data and unseen test images. Second, we observe a performance decrease for both fully supervised and weakly supervised models when tested on unseen data domains. This confirms the crucial need for efficient domain adaptation methods if deep learning models are aimed to be deployed in a clinical environment. Finally, we show that ensemble predictions from multiple trainings increase generalization performance.

arXiv.org

Multi-modal Spatial Clustering for Spatial Transcriptomics Utilizing High-resolution Histology Images arxiv.org/abs/2411.02534 .IV .CV

Multi-modal Spatial Clustering for Spatial Transcriptomics Utilizing High-resolution Histology Images

Understanding the intricate cellular environment within biological tissues is crucial for uncovering insights into complex biological functions. While single-cell RNA sequencing has significantly enhanced our understanding of cellular states, it lacks the spatial context necessary to fully comprehend the cellular environment. Spatial transcriptomics (ST) addresses this limitation by enabling transcriptome-wide gene expression profiling while preserving spatial context. One of the principal challenges in ST data analysis is spatial clustering, which reveals spatial domains based on the spots within a tissue. Modern ST sequencing procedures typically include a high-resolution histology image, which has been shown in previous studies to be closely connected to gene expression profiles. However, current spatial clustering methods often fail to fully integrate high-resolution histology image features with gene expression data, limiting their ability to capture critical spatial and cellular interactions. In this study, we propose the spatial transcriptomics multi-modal clustering (stMMC) model, a novel contrastive learning-based deep learning approach that integrates gene expression data with histology image features through a multi-modal parallel graph autoencoder. We tested stMMC against four state-of-the-art baseline models: Leiden, GraphST, SpaGCN, and stLearn on two public ST datasets with 13 sample slices in total. The experiments demonstrated that stMMC outperforms all the baseline models in terms of ARI and NMI. An ablation study further validated the contributions of contrastive learning and the incorporation of histology image features.

arXiv.org

Advanced XR-Based 6-DOF Catheter Tracking System for Immersive Cardiac Intervention Training arxiv.org/abs/2411.02611 .IV .AI .GR .HC .RO

Advanced XR-Based 6-DOF Catheter Tracking System for Immersive Cardiac Intervention Training

Extended Reality (XR) technologies are gaining traction as effective tools for medical training and procedural guidance, particularly in complex cardiac interventions. This paper presents a novel system for real-time 3D tracking and visualization of intracardiac echocardiography (ICE) catheters, with precise measurement of the roll angle. A custom 3D-printed setup, featuring orthogonal cameras, captures biplane video of the catheter, while a specialized computer vision algorithm reconstructs its 3D trajectory, localizing the tip with sub-millimeter accuracy and tracking the roll angle in real-time. The system's data is integrated into an interactive Unity-based environment, rendered through the Meta Quest 3 XR headset, combining a dynamically tracked catheter with a patient-specific 3D heart model. This immersive environment allows the testing of the importance of 3D depth perception, in comparison to 2D projections, as a form of visualization in XR. Our experimental study, conducted using the ICE catheter with six participants, suggests that 3D visualization is not necessarily beneficial over 2D views offered by the XR system; although all cardiologists saw its utility for pre-operative training, planning, and intra-operative guidance. The proposed system qualitatively shows great promise in transforming catheter-based interventions, particularly ICE procedures, by improving visualization, interactivity, and skill development.

arXiv.org

Divergent Domains, Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Grading arxiv.org/abs/2411.02614 .IV .CV

Divergent Domains, Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Grading

Diabetic Retinopathy (DR) constitutes 5% of global blindness cases. While numerous deep learning approaches have sought to enhance traditional DR grading methods, they often falter when confronted with new out-of-distribution data thereby impeding their widespread application. In this study, we introduce a novel deep learning method for achieving domain generalization (DG) in DR grading and make the following contributions. First, we propose a new way of generating image-to-image diagnostically relevant fundus augmentations conditioned on the grade of the original fundus image. These augmentations are tailored to emulate the types of shifts in DR datasets thus increase the model's robustness. Second, we address the limitations of the standard classification loss in DG for DR fundus datasets by proposing a new DG-specific loss, domain alignment loss; which ensures that the feature vectors from all domains corresponding to the same class converge onto the same manifold for better domain generalization. Third, we tackle the coupled problem of data imbalance across DR domains and classes by proposing to employ Focal loss which seamlessly integrates with our new alignment loss. Fourth, due to inevitable observer variability in DR diagnosis that induces label noise, we propose leveraging self-supervised pretraining. This approach ensures that our DG model remains robust against early susceptibility to label noise, even when only a limited dataset of non-DR fundus images is available for pretraining. Our method demonstrates significant improvements over the strong Empirical Risk Minimization baseline and other recently proposed state-of-the-art DG methods for DR grading. Code is available at https://github.com/sharonchokuwa/dg-adr.

arXiv.org

Active Prompt Tuning Enables Gpt-40 To Do Efficient Classification Of Microscopy Images arxiv.org/abs/2411.02639 .IV .AI .CV

Active Prompt Tuning Enables Gpt-40 To Do Efficient Classification Of Microscopy Images

Traditional deep learning-based methods for classifying cellular features in microscopy images require time- and labor-intensive processes for training models. Among the current limitations are major time commitments from domain experts for accurate ground truth preparation; and the need for a large amount of input image data. We previously proposed a solution that overcomes these challenges using OpenAI's GPT-4(V) model on a pilot dataset (Iba-1 immuno-stained tissue sections from 11 mouse brains). Results on the pilot dataset were equivalent in accuracy and with a substantial improvement in throughput efficiency compared to the baseline using a traditional Convolutional Neural Net (CNN)-based approach. The present study builds upon this framework using a second unique and substantially larger dataset of microscopy images. Our current approach uses a newer and faster model, GPT-4o, along with improved prompts. It was evaluated on a microscopy image dataset captured at low (10x) magnification from cresyl-violet-stained sections through the cerebellum of a total of 18 mouse brains (9 Lurcher mice, 9 wild-type controls). We used our approach to classify these images either as a control group or Lurcher mutant. Using 6 mice in the prompt set the results were correct classification for 11 out of the 12 mice (92%) with 96% higher efficiency, reduced image requirements, and lower demands on time and effort of domain experts compared to the baseline method (snapshot ensemble of CNN models). These results confirm that our approach is effective across multiple datasets from different brain regions and magnifications, with minimal overhead.

arXiv.org
Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.