Classic RNA sequencing dissociates cells from their native tissue architecture, discarding spatial information that critically shapes transcriptional programs in development, homeostasis, and cancer. However, current ST platforms often produce incomplete and noisy profiles due to technical limitations and tissue variability. These limitations obscure biologically meaningful spatial patterns and hinder downstream interpretation. Here, we introduce STORM (spatial transcriptomics optimization by resolution via matrix factorization), a machine learning framework that improves the fidelity of spatial transcriptomics data under severe sparsity. STORM formulates spatial transcriptomics recovery as a low-rank tensor decomposition problem and integrates multimodal biological priors through a principled regularization strategy. Specifically, the model jointly captures spatial continuity, tissue morphology derived from whole-slide histology images, and gene-gene interaction structure informed by protein-protein interaction networks. This method enables accurate reconstruction at unobserved locations while preserving biologically meaningful spatial structure. Across diverse lung tissue profiles, including both healthy and malignant samples, STORM consistently outperforms existing state-of-the-art methods in recovering spatial gene-expression patterns and remains robust even when a majority of spatial measurements are missing. By explicitly embedding biological structure into the reconstruction process, STORM provides a reliable foundation for high-resolution spatial transcriptomic analysis in settings where experimental data are sparse or incomplete. Availability: The source code developed in this study is publicly available at https://github.com/denizgurarslan/STORM.

Abstract The Arnold’s Cat Map (ACM) is one of the chaotic transformations, which is utilized by numerous scrambling and encryption algorithms in Information Security. Traditionally, the ACM is used in image scrambling whereby repeated application of the ACM matrix, any image can be scrambled. The transformation obtained by the ACM matrix is periodic; therefore, the original image can be reconstructed using the scrambled image whenever the elements of the matrix, hence the key, is known. The transformation matrices in all the chaotic maps employing ACM has limitations on the choice of the free parameters which generally require the area-preserving property of the matrix used in transformation, that is, the determinant of the transformation matrix to be $$\pm 1.$$ ± 1 . This reduces the number of possible set of keys which leads to discovering the ACM matrix in encryption algorithms using the brute-force method. Additionally, the period obtained is small which also causes the faster discovery of the original image by repeated application of the matrix. These two parameters are important in a brute-force attack to find out the original image from a scrambled one. The objective of the present study is to increase the key space of the ACM matrix, hence increase the security of the scrambling process and make a brute-force attack more difficult. It is proved mathematically that area-preserving property of the traditional matrix is not required for the matrix to be used in scrambling process. Removing the restriction enlarges the maximum possible key space and, in many cases, increases the period as well. Additionally, it is supplied experimentally that, in scrambling images, the new ACM matrix is equivalent or better compared to the traditional one with longer periods. Consequently, the encryption techniques with ACM become more robust compared to the traditional ones. The new ACM matrix is compatible with all algorithms that utilized the original matrix. In this novel contribution, we proved that the traditional enforcement of the determinant of the ACM matrix to be one is redundant and can be removed.

In the last decade, numerous supervised deep learning approaches have been proposed for visual-inertial odometry (VIO) and depth map estimation, which require large amounts of labelled data. To overcome the data limitation, self-supervised learning has emerged as a promising alternative that exploits constraints such as geometric and photometric consistency in the scene. In this study, we present a novel self-supervised deep learning-based VIO and depth map recovery approach (SelfVIO) using adversarial training and self-adaptive visual-inertial sensor fusion. SelfVIO learns the joint estimation of 6 degrees-of-freedom (6-DoF) ego-motion and a depth map of the scene from unlabelled monocular RGB image sequences and inertial measurement unit (IMU) readings. The proposed approach is able to perform VIO without requiring IMU intrinsic parameters and/or extrinsic calibration between IMU and the camera. We provide comprehensive quantitative and qualitative evaluations of the proposed framework and compare its performance with state-of-the-art VIO, VO, and visual simultaneous localization and mapping (VSLAM) approaches on the KITTI, EuRoC and Cityscapes datasets. Detailed comparisons prove that SelfVIO outperforms state-of-the-art VIO approaches in terms of pose estimation and depth recovery, making it a promising approach among existing methods in the literature.

Although wireless capsule endoscopy is the preferred modality for diagnosis and assessment of small bowel diseases, the poor camera resolution is a substantial limitation for both subjective and automated diagnostics. Enhanced-resolution endoscopy has shown to improve adenoma detection rate for conventional endoscopy and is likely to do the same for capsule endoscopy. In this work, we propose and quantitatively validate a novel framework to learn a mapping from low-to-high-resolution endoscopic images. We combine conditional adversarial networks with a spatial attention block to improve the resolution by up to factors of 8× , 10× , 12× , respectively. Quantitative and qualitative studies demonstrate the superiority of EndoL2H over state-of-the-art deep super-resolution methods Deep Back-Projection Networks (DBPN), Deep Residual Channel Attention Networks (RCAN) and Super Resolution Generative Adversarial Network (SRGAN). Mean Opinion Score (MOS) tests were performed by 30 gastroenterologists qualitatively assess and confirm the clinical relevance of the approach. EndoL2H is generally applicable to any endoscopic capsule system and has the potential to improve diagnosis and better harness computational approaches for polyp detection and characterization. Our code and trained models are available at https://github.com/CapsuleEndoscope/EndoL2H.

In this study, we propose a deep learning based vehicle make and model recognition method for weakly illuminated near-infrared camera images (NIR). Unlike earlier approaches that consider color images obtained in well-lit environments, this study proposes an approach for images captured at night-time. In the proposed approach, vehicle localization is carried out using single shot multi-box detector (SSD)model. Next, we utilize a convolutional neural network (CNN)based vehicle model classifier on the detected vehicle region. Data sets of different shade, light, reflection and other lighting effects have been created to be used in the training and testing stages of the proposed methods. Vehicle make and model classification model was tested using 3327 real-world night-time NIR images collected on a roadway. In order to observe the performance of the proposed vehicle make-model recognition method on enhanced images, three popular low-light image enhancement methods are also applied to our test dataset. Proposed model achieved 86% accuracy rate in model recognition and 95% accuracy rate in make recognition tasks.

A reliable, real time, multi-sensor fusion functionality is crucial for localization of actively controlled capsule endoscopy robots, which are an emerging, minimally invasive diagnostic and therapeutic technology for the gastrointestinal (GI) tract. In this study, we propose a novel multi-sensor fusion approach based on a particle filter that incorporates an online estimation of sensor reliability and a non-linear kinematic model learned by a recurrent neural network. Our method sequentially estimates the true robot pose from noisy pose observations delivered by multiple sensors. We experimentally test the method using 5 degree-of-freedom (5-DoF) absolute pose measurement by a magnetic localization system and a 6-DoF relative pose measurement by visual odometry. In addition, the proposed method is capable of detecting and handling sensor failures by ignoring corrupted data, providing the robustness expected of a medical device. Detailed analyses and evaluations are presented using ex vivo experiments on a porcine stomach model, proving that our system achieves high translational and rotational accuracies for different types of endoscopic capsule robot trajectories.

In the last decade, researchers and medical device companies have made major advances towards transforming passive capsule endoscopes into active medical robots. One of the major challenges is to endow capsule robots with accurate perception of the environment inside the human body, which will provide necessary information and enable improved medical procedures. We extend the success of deep learning approaches from various research fields to the problem of sensor fusion for endoscopic capsule robots in the case of asynchronous and asymmetric sensor data without any need of calibration between sensors. The results performed on real pig stomach datasets show that our method achieves high precision for both translational and rotational movements and contains various advantages over traditional sensor fusion techniques.

Reliable and real-time 3D reconstruction and localization functionality is a crucial prerequisite for the navigation of actively controlled capsule endoscopic robots as an emerging, minimally invasive diagnostic and therapeutic technology for use in the gastrointestinal (GI) tract. In this study, we propose a fully dense, non-rigidly deformable, strictly real-time, intraoperative map fusion approach for actively controlled endoscopic capsule robot applications which combines magnetic and vision-based localization, with non-rigid deformations based frame-to-model map fusion. The performance of the proposed method is evaluated using four different ex-vivo porcine stomach models. Across different trajectories of varying speed and complexity, and four different endoscopic cameras, the root mean square surface reconstruction errors vary from 1.58 to 2.17 cm.

In the last decade, many medical companies and research groups have tried to convert passive capsule endoscopes as an emerging and minimally invasive diagnostic technology into actively steerable endoscopic capsule robots which will provide more intuitive disease detection, targeted drug delivery and biopsy-like operations in the gastrointestinal(GI) tract. In this study, we introduce a fully unsupervised, realtime odometry and depth learner for monocular endoscopic capsule robots. We establish the supervision by warping view sequences and assigning the re-projection minimization to the loss function, which we adopt in multi-view pose estimation and single-view depth estimation network. Detailed quantitative and qualitative analyses of the proposed framework performed on non-rigidly deformable ex-vivo porcine stomach datasets proves the effectiveness of the method in terms of motion estimation and depth recovery.

Ingestible wireless capsule endoscopy is an emerging minimally invasive diagnostic technology for inspection of the GI tract and diagnosis of a wide range of diseases and pathologies. Medical device companies and many research groups have recently made substantial progresses in converting passive capsule endoscopes to active capsule robots, enabling more accurate, precise, and intuitive detection of the location and size of the diseased areas. Since a reliable real time pose estimation functionality is crucial for actively controlled endoscopic capsule robots, in this study, we propose a monocular visual odometry (VO) method for endoscopic capsule robot operations. Our method lies on the application of the deep recurrent convolutional neural networks (RCNNs) for the visual odometry task, where convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used for the feature extraction and inference of dynamics across the frames, respectively. Detailed analyses and evaluations made on a real pig stomach dataset proves that our system achieves high translational and rotational accuracies for different types of endoscopic capsule robot trajectories.

Despite significant progress achieved in the last decade to convert passive capsule endoscopes to actively controllable robots, robotic capsule endoscopy still has some challenges. In particular, a fully dense three-dimensional (3D) map reconstruction of the explored organ remains an unsolved problem. Such a dense map would help doctors detect the locations and sizes of the diseased areas more reliably, resulting in more accurate diagnoses. In this study, we propose a comprehensive medical 3D reconstruction method for endoscopic capsule robots, which is built in a modular fashion including preprocessing, keyframe selection, sparse-then-dense alignment-based pose estimation, bundle fusion, and shading-based 3D reconstruction. A detailed quantitative analysis is performed using a non-rigid esophagus gastroduodenoscopy simulator, four different endoscopic cameras, a magnetically activated soft capsule robot, a sub-millimeter precise optical motion tracker, and a fine-scale 3D optical scanner, whereas qualitative ex-vivo experiments are performed on a porcine pig stomach. To the best of our knowledge, this study is the first complete endoscopic 3D map reconstruction approach containing all of the necessary functionalities for a therapeutically relevant 3D map reconstruction.

Untethered robots miniaturized to the length scale of millimeter and below attract growing attention for the prospect of transforming many aspects of health care and bioengineering. As the robot size goes down to the order of a single cell, previously inaccessible body sites would become available for high-resolution in situ and in vivo manipulations. This unprecedented direct access would enable an extensive range of minimally invasive medical operations. Here, we provide a comprehensive review of the current advances in biomedical untethered mobile milli/microrobots. We put a special emphasis on the potential impacts of biomedical microrobots in the near future. Finally, we discuss the existing challenges and emerging concepts associated with designing such a miniaturized robot for operation inside a biological environment for biomedical applications.