Matching Regions Research Articles

Innovative integration of environmental and economic development related to water–food–energy relations

Abstract Due to severe water pollution, gradual shortage of energy resources, and increasing demand for food, the environment related to the water, food, and energy nexus has caused serious damage and pollution and has had a significant impact on economic development. In order to better promote the integration and coordinated development of the environment and economy, this article constructed an innovative technology model based on the study of the relationship between the two and analyzed the role of innovative technology in the integrated development of environment and economy. Through research, it was found that the variance contribution rate (VCR) of the third phase of innovation technology in high matching regions to the integrated development of environment and economy was 0.964, and the VCR of the sixth phase was 0.966. The VCR of the eighth period was 0.961. The VCR of the third phase of innovation technology in low matching areas to the integrated development of environment and economy was 0.791, the VCR of the sixth phase was 0.697, and the VCR of the eighth phase was 0.748. Compared to high matching regions, the VCR of innovative technologies in low matching regions to the integrated development of environment and economy is significantly lower.

Cone beam computed tomography image guidance within a magnetic resonance imaging-only planning workflow.

Magnetic Resonance Imaging (MRI)-only planning workflows offer many advantages but raises challenges regarding image guidance. The study aimed to assess the viability of MRI to Cone Beam Computed Tomography (CBCT) based image guidance for MRI-only planning treatment workflows. An MRI matching training package was developed. Ten radiation therapists, with a range of clinical image guidance experience and experience with MRI, completed the training package prior to matching assessment. The matching assessment was performed on four match regions: prostate gold seed, prostate soft tissue, rectum/anal canal and gynaecological. Each match region consisted of five patients, with three CBCTs per patient, resulting in fifteen CBCTs for each match region. The ten radiation therapists performed the CBCT image matching to CT and to MRI for all regions and recorded the match values. The median inter-observer variation for MRI-CBCT matching and CT-CBCT matching for all regions were within 2mm and 1 degree. There was no statistically significant association in the inter-observer variation in mean match values and radiation therapist image guidance experience levels. There was no statistically significant association in inter-observer variation in mean match values for MRI experience levels for prostate soft tissue and gynaecological match regions, while there was a statistically significant difference for prostate gold seed and rectum match regions. The results of this study support the concept that with focussed training, an MRI to CBCT image guidance approach can be successfully implemented in a clinical planning workflow.

Classification of medical X-ray images using supervised and unsupervised learning approaches

Most of the traditional approaches for medical image storage are least capable and scanning of relevant matching images are quite difficult. The existing approaches of content-based image retrieval (C-BIR) are less focused with medical images. The available research works with fuzzy logic approaches are very less and not efficient for medical image retrieval. Thus, there is a need of research work that can address both supervised and unsupervised learning approaches for medical image retrieval. Hence, the C-BIR technique is evolved with overcoming above stated concerns. Hence, this manuscript introduces two different C-BIR techniques using a support vector machine (SVM) and a fuzzy logic-based approach for classification. These approaches work on the classification based on feature extraction, region of Interest (ROI), corner detection, and similarity matching. The proposed approach has been analyzed for image retrieval for accuracy. The outcomes of the proposed study enhance the classification performances with retrieval than existing techniques of C-BIR.

A stable and effective calibration method for defocused cameras using synthetic speckle patterns

Well-focused and sharp target images are essential in traditional calibration, but they generally cause difficulty and inconvenience in image acquisition in practical applications. To address this problem, a stable and effective calibration method for defocused cameras is proposed in this study. Firstly, two speckle patterns are created, one of which has control points to estimate the initial value while the other, used for point pair match registration, is without control points. They are subsequently displayed on a fixed monitor and captured at each camera pose. Secondly, the initial guess for the control points is estimated using the proposed method. The retrieval of query points can then be done with high accuracy using the digital image correlation algorithm. Finally, all the calibration parameters, including lens distortion, are calculated using the plane calibration algorithm. The experiment in this study demonstrates the practicality and effectiveness of the proposed method. The accuracy and precision were quantitatively evaluated by the mean reprojection error, which was 0.057 pixels.

Diffusion kurtosis imaging and diffusion weighted imaging comparison in diagnosis of early hypoxic–ischemic brain edema

BackgroundHypoxic–ischemic encephalopathy (HIE) refers to cerebral hypoxic–ischemic injury caused by asphyxia during perinatal period, which is one of the important causes of neonatal death and sequelae. Early and accurate diagnosis of HIE is of great significance for the prognostic evaluation of patients. The purpose of this study is to explore the efficacy of diffusion-kurtosis imaging (DKI) and diffusion-weighted imaging (DWI) in the diagnosis of early HIE.MethodsTwenty Yorkshire newborn piglets (3–5 days) were randomly divided into control group and experimental group. DWI and DKI scanning were performed at timepoints of 3, 6, 9, 12, 16, and 24 h after hypoxic–ischemic exposure. At each timepoint, the parameter values obtained by each group scan were measured, and the lesion area of the apparent diffusion coefficient (ADC) map and mean diffusion coefficient (MDC) map were measured. (For better interpretation of this study, we replaced the description of MD with MDC). Then, we completely removed the brain for pathological examination, and observed the state of cells and mitochondria in the ADC/MDC matching area (the actual area of the lesion), and the mismatch area (the area around the lesion).ResultsIn the experimental group, the ADC and MDC values decreased with time, but the MDC decreased more significantly and the change rate was higher. Both MDC and ADC values changed rapidly from 3 to 12 h and slowly from 12 to 24 h. The MDC and ADC images showed obvious lesions at 3 h for the first time. At this time, the area of ADC lesions was larger than that of MDC. As the lesions developed, the area of ADC maps was always larger than that of the MDC maps within 24 h. By observing the microstructure of the tissues by light microscopy, we found that the ADC and MDC matching area in the experimental group showed swelling of neurons, infiltration of inflammatory cells, and local necrotic lesions. Consistent with the observation under light microscope, pathological changes were observed in the matching ADC and MDC regions under electron microscopy as well, including collapse of mitochondrial membrane, fracture of partial mitochondrial ridge, and emergence of autophagosomes. In the mismatching region, the above pathological changes were not observed in the corresponding region of the ADC map.ConclusionsDKI’s characteristic parameter MDC is better than ADC (parameter of DWI) to reflect the real area of the lesion. Therefore, DKI is superior to DWI in diagnosing early HIE.

A multi-stage fusion framework to classify breast lesions using deep learning and radiomics features computed from four-view mammograms.

Developing computer aided diagnosis (CAD) schemes of mammograms to classify between malignant and benign breast lesions has attracted a lot of research attention over the last several decades. However, unlike radiologists who make diagnostic decisions based on the fusion of image features extracted from multi-view mammograms, most CAD schemes are single-view-based schemes, which limit CAD performance and clinical utility. This study aims to develop and test a novel CAD framework that optimally fuses information extracted from ipsilateral views of bilateral mammograms using both deep transfer learning (DTL) and radiomics feature extraction methods. An image dataset containing 353 benign and 611 malignant cases is assembled. Each case contains four images: the craniocaudal (CC) and mediolateral oblique (MLO) view of the left and right breast. First, we extract four matching regions of interest (ROIs) from images that surround centers of two suspicious lesion regions seen in CC and MLO views, as well as matching ROIs in the contralateral breasts. Next, the handcrafted radiomics (HCRs) features and VGG16 model-generated automated features are extracted from each ROI resulting in eight feature vectors. Then, after reducing feature dimensionality and quantifying the bilateral and ipsilateral asymmetry of four ROIs to yield four new feature vectors, we test four fusion methods to build three support vector machine (SVM) classifiers by an optimal fusion of asymmetrical image features extracted from four view images. Using a 10-fold cross-validation method, results show that a SVM classifier trained using an optimal fusion of four view images yields the highest classification performance (AUC=0.876±0.031), which significantly outperforms SVM classifiers trained using one projection view alone, AUC=0.817±0.026 and 0.792±0.026 for the CC and MLO view of bilateral mammograms, respectively (p<0.001). The study demonstrates that the shift from single-view CAD to four-view CAD and the inclusion of both DTL and radiomics features significantly increases CAD performance in distinguishing between malignant and benign breast lesions.

Ubiquitous conservative interaction patterns between post-spliced introns and their mRNAs revealed by genome-wide interspecies comparison.

Introns, as important vectors of biological functions, can influence many stages of mRNA metabolism. However, in recent research, post-spliced introns are rarely considered. In this study, the optimal matched regions between introns and their mRNAs in nine model organism genomes were investigated with improved Smith-Waterman local alignment software. Our results showed that the distributions of mRNA optimal matched frequencies were highly consistent or universal. There are optimal matched frequency peaks in the UTR regions, which are obvious, especially in the 3'-UTR. The matched frequencies are relatively low in the CDS regions of the mRNA. The distributions of the optimal matched frequencies around the functional sites are also remarkably changed. The centers of the GC content distributions for different sequences are different. The matched rate distributions are highly consistent and are located mainly between 60% and 80%. The most probable value of the optimal matched segments is about 20bp for lower eukaryotes and 30bp for higher eukaryotes. These results show that there are abundant functional units in the introns, and these functional units are correlated structurally with all kinds of sequences of mRNA. The interaction between the post-spliced introns and their corresponding mRNAs may play a key role in gene expression.

Intrinsically Disordered Kiwellin Protein-Like Effectors Target Plant Chloroplasts and are Extensively Present in Rust Fungi.

The effector proteins produced by plant pathogens are one of the essential components of host-pathogen interaction. Despite being important, most of the effector proteins remain unexplored due to the diversity in their primary sequence generated by the high selection pressure of the host immune system. However to maintain the primary function in the infection process, these effectors may tend to maintain their native protein fold to perform the corresponding biological function. In the present study, unannotated candidate secretory effector proteins of sixteen major plant fungal pathogens were analyzed to find the conserved known protein folds using homology, ab initio, and AlphaFold/Rosetta Foldprotein dimensional (3D) structure approaches. Several unannotated candidate effector proteins were found to match various known conserved protein families potentially involved in host defense manipulation in different plant pathogens. Surprisingly a large number of plant Kiwellin proteins fold like secretory proteins (> 100) were found in studied rust fungal pathogens. Many of them were predicted as potential effector proteins. Furthermore, template independent modelling usingAlphaFold/Rosetta Fold analysis and structural comparison of these candidates also predicted them to match with plant Kiwellin proteins. We also found plant Kiwellin matching proteinsoutside rusts including several non-pathogenic fungi suggesting the broad function of these proteins. One of the highest confidently modeled Kiwellin matching candidates effectors, Pstr_13960 (97.8%), from the Indian P. striiformis race Yr9 was characterized using overexpression, localization, and deletion studies in Nicotiana benthamiana. The Pstr_13960 suppressed the BAX-induced cell death and localized in the chloroplast. Furthermore, the expression of the Kiwellin matching region (Pst_13960_kiwi) alone suppressed the BAX-induced cell death in N. benthamiana despite the change of location to the cytoplasm and nucleus, suggesting the novel function of the Kiwellin corefold in rust fungi. Molecular docking showed that Pstr_13960 can interact with plant Chorismate mutases (CMs) using three loops conserved in plant and rust Kiwellins. Further analysis of Pstr_13960 showed to contain Intrinsically disordered regions (IDRs) in place of the N-terminal β1/β2 region found in plant Kiwellins suggesting the evolution of rust Kiwellins-like effectors (KLEs). Overall, this study reports the presence of a Kiwellin protein-like fold containing a novel effector protein family in rust fungi depicting a classical example of the evolution of effectors at the structure level as Kiwellin effectors show very low significant similarity to plant Kiwellin at the sequence level.

SiamLight: lightweight networks for object tracking via attention mechanisms and pixel-level cross-correlation

Despite Siamese-based trackers have achieved great success in recent years, researchers have focused more on the accuracy of trackers than their complexity, which leads to their inapplicability in some scenarios, and the real-time speed can be greatly limited. In this work, we propose a lightweight network method called SiamLight for object tracking. MobileNet-V3 is selected as the backbone network. The PG-corr module is added as the feature fusion module, a strategy that decomposes the template feature into spatial and channel kernels, reducing the matching regions and suppressing the effect of similar interference. In addition, we also add the CSM module, which carries out attention to the channel and spatial simultaneously. CSM module not only reduces the number of parameters but also ensures that it can be integrated into existing network architectures as a plug-and-play module. Finally, multiple separable convolution blocks are added to the classification and regression branches to meet our lightweight parameters and Flops requirements. The experiments on LaSOT, VOT2018, VOT2019, OTB100, and UAV123 benchmarks show that the method has fewer Flops and parameters than state-of-the-art trackers.

Open-source navigation system for tracking dissociated parts with multi-registration.

During reconstructive surgery, knee and hip replacements, and orthognathic surgery, small misalignments in the pose of prosthesis and bones can lead to severe complications. Hence, the translational and angular accuracies are critical. However, traditional image-based surgical navigation lacks orientation data between structures, and imageless systems are unsuitable for cases of deformed anatomy. We introduce an open-source navigation system using a multiple registration approach that can track instruments, implants, and bones to precisely guide the surgeon in emulating a preoperative plan. We derived the analytical error of our method and designed a set of phantom experiments to measure its precision and accuracy. Additionally, we trained two classification models to predict the system reliability from fiducial points and surface matching registration data. Finally, to demonstrate the procedure feasibility, we conducted a complete workflow for a real clinical case of a patient with fibrous dysplasia and anatomical misalignment of the right femur using plastic bones. The system is able to track the dissociated fragments of the clinical case and average alignment errors in the anatomical phantoms of [Formula: see text] mm and [Formula: see text]. While the fiducial-points registration showed satisfactory results given enough points and covered volume, we acknowledge that the surface refinement step is mandatory when attempting surface matching registrations. We believe that our device could bring significant advantages for the personalized treatment of complex surgical cases and that its multi-registration attribute is convenient for intraoperative registration loosening cases.

UMRFormer-net: a three-dimensional U-shaped pancreas segmentation method based on a double-layer bridged transformer network.

Methods based on the combination of transformer and convolutional neural networks (CNNs) have achieved impressive results in the field of medical image segmentation. However, most of the recently proposed combination segmentation approaches simply treat transformers as auxiliary modules which help to extract long-range information and encode global context into convolutional representations, and there is a lack of investigation on how to optimally combine self-attention with convolution. We designed a novel transformer block (MRFormer) that combines a multi-head self-attention layer and a residual depthwise convolutional block as the basic unit to deeply integrate both long-range and local spatial information. The MRFormer block was embedded between the encoder and decoder in U-Net at the last two layers. This framework (UMRFormer-Net) was applied to the segmentation of three-dimensional (3D) pancreas, and its ability to effectively capture the characteristic contextual information of the pancreas and surrounding tissues was investigated. Experimental results show that the proposed UMRFormer-Net achieved accuracy in pancreas segmentation that was comparable or superior to that of existing state-of-the-art 3D methods in both the Clinical Proteomic Tumor Analysis Consortium Pancreatic Ductal Adenocarcinoma (CPTAC-PDA) dataset and the public Medical Segmentation Decathlon dataset (self-division). UMRFormer-Net statistically significantly outperformed existing transformer-related methods and state-of-the-art 3D methods (P<0.05, P<0.01, or P<0.001), with a higher Dice coefficient (85.54% and 77.36%, respectively) or a lower 95% Hausdorff distance (4.05 and 8.34 mm, respectively). UMRFormer-Net can obtain more matched and accurate segmentation boundary and region information in pancreas segmentation, thus improving the accuracy of pancreas segmentation. The code is available at https://github.com/supersunshinefk/UMRFormer-Net.

MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term for continual self-supervision, which has been proved to be effective on difficult matching regions. However, this method also amplify the inevitable mismatch in unsupervised setting, blocking the learning process towards optimal solution. To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement. Concretely, taking estimation of off-the-shelf unsupervised approach as pseudo labels, our insight locates at defining a confidence selection mechanism to extract relative good matches, and then add diverse data augmentation for distilling adequate and reliable knowledge from teacher to student. Thanks to the decouple nature of our method, we can choose a stronger student architecture for sufficient learning. Finally, better student prediction is adopted to transfer knowledge back to the efficient teacher without additional costs in real deployment. Rather than formulating it as a supervised task, we find that introducing an extra unsupervised term for multi-target learning achieves best final results. Extensive experiments show that our approach, termed MDFlow, achieves state-of-the-art real-time accuracy and generalization ability on challenging benchmarks. Code is available at https://github.com/ltkong218/MDFlow.

Fault detection for discrete-time fuzzy systems with measurement errors using interval observers

This paper presents an interval observer-based fault detection (FD) strategy for discrete-time T–S fuzzy systems with measurement errors. The system and measurement outputs are selected as the premise variables of plant and observer respectively. The bounds of mismatch items caused by the measurement errors are established by covering matched region, mismatched left adjacent region and right adjacent region. Piecewise Lyapunov function, taking full account of possible transitions, is employed to drive observer design condition. FD is turned into optimization problem with disturbance attenuation, fault sensitivity and nonnegativity constraints. The decision is implemented by judging whether zero is excluded from the residual interval. Finally, simulation is explored to verify the scheme.

A robust detection and localization technique for copy-move forgery in digital images

Image forensic analysis becomes a major role in the field of digital image security due to tampering and forgery. The image forgery violates the authenticity and ownership of digital images. Copy-move forgery considers a significant kind of image forensic analysis algorithm. In this kind, the forger copies a part of an original image and then pastes it into the selected position from the same image. The purpose of forgery is to hide or highlight a specific region of the original image. To detect copy-move forgery, there are two traditional techniques: block-based and keypoint-based. The main drawback of the keypoint-based technique is the insufficient features for the small and flat regions, which causes undetected forgery. In contrast, the block-based technique has intensive processing. Therefore, this paper proposes a robust scheme that overcomes the drawbacks of the above techniques and maintains their advantages. This scheme adopts three connected stages, the first detects the initial duplicated regions using the SURF-HOG detector and descriptor. Subsequently, the second stage localizes the primary matched regions by SLIC segmentation and then selects the suspicious neighbor regions to be combined with primary regions to obtain the active regions. In the third stage, the block-based technique adopts overlapping Zernike moments to extract sufficient key points from the produced active regions. In the final stage, the duplicated regions are classified into authentic or forged regions. The proposed scheme provides not only forgery detection but also localization and recognition for the duplicated regions. The experimental results show that the proposed scheme is fast and has high accuracy for forgery detection and localization, at least 93.75, and 7.25 in terms of True Positive and False Positive Rates. Moreover, the scheme has high robustness under various conditions and attacks such as geometric transformation attacks and compound photometric attacks. The proposed scheme can be used in sensitive applications such as cybercrime detection and adopted as evidence in the courts.

Classification of Gravity Matching Areas Using PSO-BP Neural Networks based on PCA and Satellite Altimetry Data over the Western Pacific

For inertial navigation systems (INS), as one of the major methods for underwater navigation, errors diverge over time. With the development of geophysical navigation technology, gravity navigation has become an effective method of navigation. Significant changes in the gravity characteristic of the matching region ensure that gravity matching navigation works effectively. In this paper, we combine artificial intelligence algorithms and statistical metrics to classify gravity-matching navigation regions. Firstly, this paper analyzes and extracts gravity anomaly data from a matching region in different ways. Then, a particle swarm optimization (PSO) algorithm is used to optimize the network weights of a back propagation (BP) NN. Finally, based on principal component analysis (PCA) theory and PSO-BP NN, this paper proposes the PPBA method to classify the matching area. Moreover, the Terrain Contour Matching (TERCOM) matching algorithm and gravity anomaly data from the Western Pacific are used to verify the classification performance of the PPBA method. The experiments prove that the PPBA method has a high classification accuracy, and the classification results are consistent with the matching navigation experimental results. This work can provide a reference for designing navigation regions and navigation routes for submarines.

Value of the retina in the diagnosis of Alzheimer's disease

AbstractVision, which is a process that requires the involvement of a large number of neurons, is often impaired during Alzheimer's disease (AD). Over the past few decades, research has shown that several visual functions and structures are compromised during AD and can also be used to differentiate affected individuals from those who show normal aging. Retina is a projection from the central nervous system and shares many features with the brain. Classically, the damage in AD was thought to be restricted mainly to the brain. However, in the last years it has been demonstrated in retinas of AD human postmortem specimens, the presence of Aβ plaques and pTau deposition, being more abundant in the superior region of the retina matching with greater neuronal degeneration. Also, it has been suggested that Aβ plaques in the retina may anticipate those in the brain. In addition, recently it has also been possible to observe in vivo Aβ plaques in human retinas, with imaging techniques and ingesting curcumin as a marker of Aβ deposits. Recently, using in vivo hyperspectral imaging techniques in the retina, it has been reported that Aβ load in the brain can be predicted. These findings provide histopathological evidence that the visual system may be altered much earlier in the AD disease process than previously thought, and thus support the use of visual biomarkers in the early detection of the disease. Current in vivo imaging techniques such as OCT are allowing ophthalmologists to detect and quantify data consistent with the histopathological findings described in the retinas of AD patients. In early AD, OCT has demonstrated a thickening of the macular region and a subsequent thinning of the peripapillary area of the retina in more advanced stages of the disease. New analytic methods have shown in AD patients that thinned regions are interspersed with thickened ones in all retinal layers, except inner nuclear and outer segments. This causes roughness to appear on retinal layer thickness maps, finding that Fractal Dimension (FD) of retinal layers is greater in the AD patients, being roughness of retinal layers, assessed by the FD of their thickness maps, a possible early retinal biomarker of AD.In the other hand, recent data suggest the vascular involvement of the retina in AD patients. Vascular changes in the retina are thought to share similar pathogenic mechanisms with cerebral vasculature. OCT and OCT angiography (OCTA) has demonstrated a thinning of the choroidal thickness in early AD and decrease of the foveal avascular zone in patients with moderate AD.All these observations support the value of the retina as a biomarker of AD that will allow us, with the development of new research, to discover new retinal biomarkers that will help us to improve the diagnosis and follow‐up of this growing pathology.

The epidemiology, healthcare and societal burden of basal cell carcinoma in Wales 2000-2018: a retrospective nationwide analysis.

Basal cell carcinoma (BCC) represents the most commonly occurring cancer worldwide within the white population. Reports predict 298 308 cases of BCC in the UK by 2025, at a cost of £265-366 million to the National Health Service (NHS). Despite the morbidity, societal and healthcare pressures brought about by BCC, routinely collected healthcare data and global registration remain limited. To calculate the incidence of BCC in Wales between 2000 and 2018 and to establish the related healthcare utilization and estimated cost of care. The Secure Anonymised Information Linkage (SAIL) databank is one of the largest and most robust health and social care data repositories in the UK. Cancer registry data were linked to routinely collected healthcare databases between 2000 and 2018. Pathological data from Swansea Bay University Health Board (SBUHB) were used for internal validation. A total of 61 404 histologically proven BCCs were identified within the SAIL Databank during the study period. The European age-standardized incidence for BCC in 2018 was 224.6 per 100 000 person-years. Based on validated regional data, a 45% greater incidence was noted within SBUHB pathology vs. matched regions within SAIL between 2016 and 2018. A negative association between deprivation and incidence was noted with a higher incidence in the least socially deprived and rural dwellers. Approximately 2% travelled 25-50 miles for dermatological services compared with 37% for plastic surgery. Estimated NHS costs of surgically managed lesions for 2002-2019 equated to £119.2-164.4 million. Robust epidemiological data that are internationally comparable and representative are scarce for nonmelanoma skin cancer. The rising global incidence coupled with struggling healthcare systems in the post-COVID-19 recovery period serve to intensify the societal and healthcare impact. This study is the first to demonstrate the incidence of BCC in Wales and is one of a small number in the UK using internally validated large cohort datasets. Furthermore, our findings demonstrate one of the highest published incidences within the UK and Europe.

Deep features for image copy move forgery detection

In this modern era, there has been a increase in the copying and moving of illegalities, distributing them, and then tempered images. These days even the most secured data sometimes go under devastating forgery. Copy forgery is seen to be the easiest copying method without leaving any obvious traces of manipulating an image’s content.Like working on the pixels of an image by geometrical and illumination techniques which are either cut or copied or copied to some other place of the identical image. In this paper, we propose copy paste forgery detection of an image by extracting and grouping SIFT key points for analyzation. The first step is to find suspicious clusters of key points and patches to roughly estimate the dimensionality of SIFT. Secondly, it finds pixel level, scale, and color by comparingsimilar neighborhoods of matching duplicated regions. The results prove to be giving good performance scores, computational timing, and complexity

Relapse Rates and Disease-Specific Mortality Following Procedures for Fertility Preservation at Time of Breast Cancer Diagnosis

Breast cancer (BC) is the most common indication for fertility preservation (FP) in women of reproductive age. Procedures for FP often include hormonal stimulation, but current data are scarce regarding whether using hormonal stimulation for FP is associated with any deterioration in BC prognosis. To investigate the risk of disease-specific mortality and relapse in women who underwent FP with or without hormonal stimulation compared with women who did not at time of BC diagnosis. This Swedish nationwide prospective cohort study was conducted to assess the safety of hormonal and nonhormonal FP procedures indicated by BC in Sweden from January 1, 1994, through June 30, 2017. Women were identified from any of the regional FP programs located at Swedish university hospitals. A total of 425 women were found to have undergone FP, and 850 population comparators who had not undergone FP were sampled from regional BC registers and matched on age, calendar period of diagnosis, and region. Relapse-free survival was assessed in a subcohort of 241 women who underwent FP and 482 women who had not, with complete data. Nationwide demographic and health care registers provided data on outcome, disease- and treatment-related variables, and socioeconomic characteristics. Data analyses were performed between November 2021 and March 2022 and completed in June 2022. Relapse and disease-specific mortality after a diagnosis of BC. The final study population included 1275 women (mean [SD] age, 32.9 [3.8] years) at the time of BC diagnosis. After stratification by the matching variables age, calendar period, and region, and adjustment for country of birth, education, parity at diagnosis, tumor size, number of lymph node metastases, and estrogen receptor status, disease-specific mortality was similar in women who underwent hormonal FP (adjusted hazard ratio [aHR], 0.59; 95% CI, 0.32-1.09), women who underwent nonhormonal FP (aHR, 0.51; 95% CI, 0.20-1.29), and women who were not exposed to FP (reference). In a subcohort with detailed data on relapse, adjusted rate of disease-specific mortality and relapse were also similar among the groups who underwent hormonal FP (aHR, 0.81; 95% CI, 0.49-1.37), underwent nonhormonal FP (aHR, 0.75; 95% CI, 0.35-1.62), and were not exposed to FP (reference). In this cohort study, FP with or without hormonal stimulation was not associated with any increased risk of relapse or disease-specific mortality in women with BC. Results of this study provide much needed additional evidence on the safety of FP procedures in women with BC and may influence current health care practice to the benefit of young women with BC who wish to preserve their fertility.

Multi-Type Object Tracking Based on Residual Neural Network Model

In this paper, a tracking algorithm based on the residual neural network model and machine learning is proposed. Compared with the widely used VGG network, the residual neural network has deeper characteristic layers and special additional layer structure, which break the symmetry of the network and reduce the degradation of the neural network. The additional layer and convolution layer are used for feature fusion to represent the target. The multi-features of the object can be captured by using the developed algorithm, so that the accuracy of tracking can be improved in some complex scenarios. In addition, we defined a new measure to calculate the similarity of different image regions and find the optimal matched region. The search area is delimited according to the continuity of the target motion, which improves the real-time performance of tracking. The experimental results illustrate that the proposed algorithm achieved a higher accuracy while taking into account the real time performance, especially in dealing with some complex scenarios such as deformation, rotation changes and background clutters, in comparison with the Multi-Domain Network (MDNet) algorithm based on a convolutional neural network.