SCRnet: A Spatial Consistency Guided Network Using Contrastive Learning for Point Cloud Registration

Point cloud registration is used to find a rigid transformation from the source point cloud to the target point cloud. The main challenge in the point cloud registration is in finding correct correspondences in complex scenes that may contain many noise and repetitive structures. At present, many existing methods use outlier rejections to help the network obtain more accurate correspondences, but they often ignore the spatial consistency between keypoints. Therefore, to address this issue, we propose a spatial consistency guided network using contrastive learning for point cloud registration (SCRnet), in which its overall stage is symmetrical. SCRnet consists of four blocks, namely feature extraction block, confidence estimation block, contrastive learning block and registration block. Firstly, we use mini-PointNet to extract coarse local and global features. Secondly, we propose confidence estimation block, which formulate outlier rejection as confidence estimation problem of keypoint correspondences. In addition, the local spatial features are encoded into the confidence estimation block, which makes the correspondence possess local spatial consistency. Moreover, we propose contrastive learning block by constructing positive point pairs and hard negative point pairs and using Point-Pair-INfoNCE contrastive loss, which can further remove hard outliers through global spatial consistency. Finally, the proposed registration block selects a set of matching points with high spatial consistency and uses these matching sets to calculate multiple transformations, then the best transformation can be identified by initial alignment and Iterative Closest Point (ICP) algorithm. Extensive experiments are conducted on KITTI and nuScenes dataset, which demonstrate the high accuracy and strong robustness of SCRnet on point cloud registration task.

Enabling Continuous Wearable Reflectance Pulse Oximetry at the Sternum

In light of the recent Coronavirus disease (COVID-19) pandemic, peripheral oxygen saturation (SpO2) has shown to be amongst the vital signs most indicative of deterioration in persons with COVID-19. To allow for the continuous monitoring of SpO2, we attempted to demonstrate accurate SpO2 estimation using our custom chest-based wearable patch biosensor, capable of measuring electrocardiogram (ECG) and photoplethysmogram (PPG) signals with high fidelity. Through a breath-hold protocol, we collected physiological data with a wide dynamic range of SpO2 from 20 subjects. The ratio of ratios (R) used in pulse oximetry to estimate SpO2 was robustly extracted from the red and infrared PPG signals during the breath-hold segments using novel feature extraction and PPGgreen-based outlier rejection algorithms. Through subject independent training, we achieved a low root-mean-square error (RMSE) of 2.64 ± 1.14% and a Pearson correlation coefficient (PCC) of 0.89. With subject-specific calibration, we further reduced the RMSE to 2.27 ± 0.76% and increased the PCC to 0.91. In addition, we showed that calibration is more efficiently accomplished by standardizing and focusing on the duration of breath-hold rather than the resulting range in SpO2. The accurate SpO2 estimation provided by our custom biosensor and the algorithms provide research opportunities for a wide range of disease and wellness monitoring applications.

No-Reference Image Quality Assessment Of Large FLAIR MRI Datasets

<div>The study of neurodegenerative diseases have found promise through white matter lesions best visualized in FLAIR MRI; however, algorithms experience difficulty in generalizing to large multicenter datasets due to the variance of image quality and characteristics. This thesis presents a quality control tool that combines image quality assessment with outlier rejection algorithms; this tool is unique as it is specifically designed for large multicenter FLAIR MRI datasets. An image processing approach evaluates each volume by: intensity-based features, sharpness/blur-based features, signal- and contrast-to-noise ratios, noise field characteristics, motion artifact prevalence</div><div>and a total IQ score. The performance of this tool was evaluated on labelled ADNI and CCNA data reporting F1 scores of 0.82, and 0.85, respectively. Applications for this tool include potential rescan or longitudinal scanner study alongside the immediate application of outlier removal for</div><div>large FLAIR datasets.</div>

No-Reference Image Quality Assessment Of Large FLAIR MRI Datasets

<div>The study of neurodegenerative diseases have found promise through white matter lesions best visualized in FLAIR MRI; however, algorithms experience difficulty in generalizing to large multicenter datasets due to the variance of image quality and characteristics. This thesis presents a quality control tool that combines image quality assessment with outlier rejection algorithms; this tool is unique as it is specifically designed for large multicenter FLAIR MRI datasets. An image processing approach evaluates each volume by: intensity-based features, sharpness/blur-based features, signal- and contrast-to-noise ratios, noise field characteristics, motion artifact prevalence</div><div>and a total IQ score. The performance of this tool was evaluated on labelled ADNI and CCNA data reporting F1 scores of 0.82, and 0.85, respectively. Applications for this tool include potential rescan or longitudinal scanner study alongside the immediate application of outlier removal for</div><div>large FLAIR datasets.</div>

Evaluating differences in respiratory motion estimates during radiotherapy: a single planning 4DMRI versus daily 4DMRI

Background In radiotherapy, respiratory-induced tumor motion is typically measured using a single four-dimensional computed tomography acquisition (4DCT). Irregular breathing leads to inaccurate motion estimates, potentially resulting in undertreatment of the tumor and unnecessary dose to healthy tissue. The aim of the research was to determine if a daily pre-treatment 4DMRI-strategy led to a significantly improved motion estimate compared to single planning 4DMRI (with or without outlier rejection). Methods 4DMRI data sets from 10 healthy volunteers were acquired. The first acquisition simulated a planning MRI, the respiratory motion estimate (constructed from the respiratory signal, i.e. the 1D navigator) was compared to the respiratory signal in the subsequent scans (simulating 5–29 treatment fractions). The same procedure was performed using the first acquisition of each day as an estimate for the subsequent acquisitions that day (2 per day, 4–20 per volunteer), simulating a daily MRI strategy. This was done for three outlier strategies: no outlier rejection (NoOR); excluding 5% of the respiratory signal whilst minimizing the range (Min95) and excluding the datapoints outside the mean end-inhalation and end-exhalation positions (MeanIE). Results The planning MRI median motion estimates were 27 mm for NoOR, 18 mm for Min95, and 13 mm for MeanIE. The daily MRI median motion estimates were 29 mm for NoOR, 19 mm for Min95 and 15 mm for MeanIE. The percentage of time outside the motion estimate were for the planning MRI: 2%, 10% and 32% for NoOR, Min95 and MeanIE respectively. These values were reduced with the daily MRI strategy: 0%, 6% and 17%. Applying Min95 accounted for a 30% decrease in motion estimate compared to NoOR. Conclusion A daily MRI improved the estimation of respiratory motion as compared to a single 4D (planning) MRI significantly. Combining the Min95 technique with a daily 4DMRI resulted in a decrease of inclusion time of 6% with a 30% decrease of motion. Outlier rejection alone on a planning MRI often led to underestimation of the movement and could potentially lead to an underdosage. Trial registration: protocol W15_373#16.007

Learning Two-View Correspondences and Geometry via Local Neighborhood Correlation

Seeking quality feature correspondences (also known as matches) is a foundational step in computer vision. In our work, a novel and effective network with a stable local constraint, named the Local Neighborhood Correlation Network (LNCNet), is proposed to capture abundant contextual information of each correspondence in the local region, followed by calculating the essential matrix and camera pose estimation. Firstly, the k-Nearest Neighbor (KNN) algorithm is used to divide the local neighborhood roughly. Then, we calculate the local neighborhood correlation matrix (LNC) between the selected correspondence and other correspondences in the local region, which is used to filter outliers to obtain more accurate local neighborhood information. We cluster the filtered information into feature vectors containing richer neighborhood contextual information so that they can be used to more accurately determine the probability of correspondences as inliers. Extensive experiments have demonstrated that our proposed LNCNet performs better than some state-of-the-art networks to accomplish outlier rejection and camera pose estimation tasks in complex outdoor and indoor scenes.

Patterned fabric image retrieval using relevant feedback via geometric similarity

Due to the potential value in many areas, such as e-commerce and inventory management, fabric image retrieval, which is a special case of content-based image retrieval, has recently become a research hotspot. As a major category of textile fabrics, patterned fabrics have a diverse and complex appearance, making the retrieval task more challenging. To address this situation, this paper proposes a novel approach for patterned fabric based on the non-subsampled contourlet transform (NSCT) feature descriptor and relevance feedback technique. To integrate the color information into the NSCT feature descriptor, we extract the feature of patterned fabric images in HSV color space. An outlier rejection-based parametric relevance feedback algorithm is employed to adjust the similarity matrix to improve the retrieval results. The experimental results not only show the effectiveness of the proposed approach but also demonstrate that it can significantly improve the performance of the retrieval system compared to other state-of-the-art algorithms.

Comparative performance analysis of quantum machine learning with deep learning for diabetes prediction

Background Diabetes, the fastest growing health emergency, has created several life-threatening challenges to public health globally. It is a metabolic disorder and triggers many other chronic diseases such as heart attack, diabetic nephropathy, brain strokes, etc. The prime objective of this work is to develop a prognosis tool based on the PIMA Indian Diabetes dataset that will help medical practitioners in reducing the lethality associated with diabetes. Methods Based on the features present in the dataset, two prediction models have been proposed by employing deep learning (DL) and quantum machine learning (QML) techniques. The accuracy has been used to evaluate the prediction capability of these developed models. The outlier rejection, filling missing values, and normalization have been used to uplift the discriminatory performance of these models. Also, the performance of these models has been compared against state-of-the-art models. Results The performance measures such as precision, accuracy, recall, F1 score, specificity, balanced accuracy, false detection rate, missed detection rate, and diagnostic odds ratio have been achieved as 0.90, 0.95, 0.95, 0.93, 0.95, 0.95, 0.03, 0.02, and 399.00 for DL model respectively, However for QML, these measures have been computed as 0.74, 0.86, 0.85, 0.79, 0.86, 0.86, 0.11, 0.05, and 35.89 respectively. Conclusion The proposed DL model has a high diabetes prediction accuracy as compared with the developed QML and existing state-of-the-art models. It also uplifts the performance by 1.06% compared to reported work. However, the performance of the QML model has been found as satisfactory and comparable with existing literature.