Hyperspectral imaging and dynamic region of interest tracking approaches to quantify localized cAMP signals.

Cyclic adenosine monophosphate (cAMP) is a ubiquitous second messenger known to orchestrate a myriad of cellular functions over a wide range of timescales. In the last 20 years, a variety of single-cell sensors have been developed to measure second messenger signals including cAMP, Ca2+, and the balance of kinase and phosphatase activities. These sensors utilize changes in fluorescence emission of an individual fluorophore or Förster resonance energy transfer (FRET) to detect changes in second messenger concentration. cAMP and kinase activity reporter probes have provided powerful tools for the study of localized signals. Studies relying on these and related probes have the potential to further revolutionize our understanding of G protein-coupled receptor signaling systems. Unfortunately, investigators have not been able to take full advantage of the potential of these probes due to the limited signal-to-noise ratio of the probes and the limited ability of standard epifluorescence and confocal microscope systems to simultaneously measure the distributions of multiple signals (e.g. cAMP, Ca2+, and changes in kinase activities) in real time. In this review, we focus on recently implemented strategies to overcome these limitations: hyperspectral imaging and adaptive thresholding approaches to track dynamic regions of interest (ROI). This combination of approaches increases signal-to-noise ratio and contrast, and allows identification of localized signals throughout cells. These in turn lead to the identification and quantification of intracellular signals with higher effective resolution. Hyperspectral imaging and dynamic ROI tracking approaches offer investigators additional tools with which to visualize and quantify multiplexed intracellular signaling systems.

Increasing region of interest width reduces neonatal circumferential strain.

OBJECTIVE: There is growing interest in speckle tracking echocardiography-derived strain as a measure of left ventricular function in neonates. However, knowledge gaps remain regarding the effect of image acquisition and processing parameters on circumferential strain measurements. The aim of this study was to evaluate the effect of using different region of interest (ROI) widths on speckle tracking derived circumferential strain in healthy neonates. METHODS: Thirty healthy-term-born neonates were examined with speckle-tracking echocardiography in the short-axis view. Circumferential strain values were acquired and compared using two different ROI widths. Furthermore, strain values in the different vendor-defined wall layers were also compared. RESULTS: Increasing ROI width led to a decrease in global circumferential strain (GCS) in the midwall and epicardial layers, the respective decreases in strain being -23.4 ± .6% to -22.0 ± 1.1%, p < .0001 and 18.5 ± 1.7% to -15.6 ± 2.0%, p < .0001. Segmental analyses were consistent with these results, apart from two segments in the midwall. There was no statistically significant effect on strain for the endocardial layer. A gradient was seen where strain increased from the epicardial to endocardial layers. CONCLUSION: Increasing ROI width led to a decrease in GCS in the midwall and epicardium. There is an increase in circumferential strain when moving from the epicardial toward the endocardial layer. Clinicians wishing to implement circumferential strain into their practice should consider ROI width variation as a potential confounder in their measurements.

Performance of T2 mapping in the staging of Graves' ophthalmopathy based on different region of interest selection methods.

BACKGROUND: Discriminating the stage of Graves' ophthalmopathy (GO) is crucial for clinical decision. Application of conventional T2-weighted imaging in the staging is still limited. PURPOSE: To evaluate the performance of T2 mapping based on two different regions of interest (ROIs) for staging GO. MATERIAL AND METHODS: In total, 56 GO patients were retrospectively enrolled and divided into two groups according to the clinical activity score (CAS). T2 relaxation time (T2RT) of extraocular muscle (EOM) on T2 mapping based on two different ROIs (T2RTROI-1: ROIs were drawn separately in the four EOMs; T2RTROI-2: ROI was drawn in the most inflamed EOM) was measured and compared between active and inactive groups. RESULTS: Both T2RTROI-1 and T2RTROI-2 values in the active GO were significantly higher than those of inactive GO (P <0.001). T2RTROI-1 and T2RTROI-2 values were positively correlated with CAS (rs=0.73, 0.69; P <0.001). When the T2RTROI-1 value of 83.3 ms and T2RTROI-2 value of 106.3 ms were used as cutoff values for staging GO, respectively, the best results were obtained with areas under the curve (AUCs) of 0.822 and 0.827. There was no significant difference for AUCs between T2RTROI-1 and T2RTROI-2 (P = 0.751). Excellent and good inter-observer agreements were achieved in quantitative measurements for T2RTROI-1 and T2RTROI-2 values, respectively, with intraclass correlation coefficients of 0.954 and 0.882. CONCLUSION: The T2RT values derived from two different ROIs were useful for assessment of disease activity. Taking reproducibility and diagnostic performance into consideration, T2RTROI-1 would be an ideal image biomarker for staging GO compared to T2RTROI-2.

Exploring the impact of excluding intrahepatic segmental vessels on liver stiffness measurement and advanced fibrosis diagnosis using magnetic resonance elastography.

BACKGROUND: The impact of excluding intrahepatic segmental vessels from regions of interest (ROIs) on liver stiffness measurement (LSM) via magnetic resonance elastography (MRE) remains uncertain. PURPOSE: To determine the effect of excluding intrahepatic segmental vessels from ROIs on LSM obtained from MRE. MATERIAL AND METHODS: This retrospective analysis included 95 participants who underwent successful two-dimensional gradient recalled-echo MRE before hepatic tumor resection (n = 49) or living liver donation (n = 46). The conventional LSM was determined by manually drawing ROIs on the elastogram within the 95% confidence region, staying 1 cm within the liver capsule and excluding large hilar vessels, the gallbladder, hepatic lesions, and artifacts. In addition, the modified LSM was determined by excluding intrahepatic segmental vessels. LSMs obtained by the two methods were compared with paired sample signed-rank test. Diagnostic performance for advanced fibrosis was calculated and compared using McNemar's test and Delong's test. The stage of hepatic fibrosis was assessed using surgical specimens by the METAVIR system. RESULTS: The modified LSM was larger than the conventional LSM (2.4 kPa vs. 2.2 kPa in reader 1; 2.7 kPa vs. 2.4 kPa in reader 2; P < 0.001). The modified LSM showed superior sensitivity (0.841 vs. 0.659 in reader 1; 0.864 vs. 0.705 in reader 2; P < 0.05) and area under the curve (0.901 vs. 0.820 in reader 1; 0.912 vs. 0.843 in reader 2; P < 0.05) for detecting advanced fibrosis (≥F3) than conventional LSM. CONCLUSION: The exclusion of intrahepatic segmental vessels from ROIs in MRE affected the LSM and enhanced diagnostic performance for advanced fibrosis.

Automated Region of Interest-Based Data Augmentation for Fallen Person Detection in Off-Road Autonomous Agricultural Vehicles.

Due to the global population increase and the recovery of agricultural demand after the COVID-19 pandemic, the importance of agricultural automation and autonomous agricultural vehicles is growing. Fallen person detection is critical to preventing fatal accidents during autonomous agricultural vehicle operations. However, there is a challenge due to the relatively limited dataset for fallen persons in off-road environments compared to on-road pedestrian datasets. To enhance the generalization performance of fallen person detection off-road using object detection technology, data augmentation is necessary. This paper proposes a data augmentation technique called Automated Region of Interest Copy-Paste (ARCP) to address the issue of data scarcity. The technique involves copying real fallen person objects obtained from public source datasets and then pasting the objects onto a background off-road dataset. Segmentation annotations for these objects are generated using YOLOv8x-seg and Grounded-Segment-Anything, respectively. The proposed algorithm is then applied to automatically produce augmented data based on the generated segmentation annotations. The technique encompasses segmentation annotation generation, Intersection over Union-based segment setting, and Region of Interest configuration. When the ARCP technique is applied, significant improvements in detection accuracy are observed for two state-of-the-art object detectors: anchor-based YOLOv7x and anchor-free YOLOv8x, showing an increase of 17.8% (from 77.8% to 95.6%) and 12.4% (from 83.8% to 96.2%), respectively. This suggests high applicability for addressing the challenges of limited datasets in off-road environments and is expected to have a significant impact on the advancement of object detection technology in the agricultural industry.

Image-Compression Techniques: Classical and "Region-of-Interest-Based" Approaches Presented in Recent Papers.

Image compression is a vital component for domains in which the computational resources are usually scarce such as automotive or telemedicine fields. Also, when discussing real-time systems, the large amount of data that must flow through the system can represent a bottleneck. Therefore, the storage of images, alongside the compression, transmission, and decompression procedures, becomes vital. In recent years, many compression techniques that only preserve the quality of the region of interest of an image have been developed, the other parts being either discarded or compressed with major quality loss. This paper proposes a study of relevant papers from the last decade which are focused on the selection of a region of interest of an image and on the compression techniques that can be applied to that area. To better highlight the novelty of the hybrid methods, classical state-of-the-art approaches are also analyzed. The current work will provide an overview of classical and hybrid compression methods alongside a categorization based on compression ratio and other quality factors such as mean-square error and peak signal-to-noise ratio, structural similarity index measure, and so on. This overview can help researchers to develop a better idea of what compression algorithms are used in certain domains and to find out if the presented performance parameters are of interest for the intended purpose.

Outcome measures for electric field modeling in tES and TMS: A systematic review and large-scale modeling study.

BACKGROUND: Electric field (E-field) modeling is a potent tool to estimate the amount of transcranial magnetic and electrical stimulation (TMS and tES, respectively) that reaches the cortex and to address the variable behavioral effects observed in the field. However, outcome measures used to quantify E-fields vary considerably and a thorough comparison is missing. OBJECTIVES: This two-part study aimed to examine the different outcome measures used to report on tES and TMS induced E-fields, including volume- and surface-level gray matter, region of interest (ROI), whole brain, geometrical, structural, and percentile-based approaches. The study aimed to guide future research in informed selection of appropriate outcome measures. METHODS: Three electronic databases were searched for tES and/or TMS studies quantifying E-fields. The identified outcome measures were compared across volume- and surface-level E-field data in ten tES and TMS modalities targeting two common targets in 100 healthy individuals. RESULTS: In the systematic review, we extracted 308 outcome measures from 202 studies that adopted either a gray matter volume-level (n = 197) or surface-level (n = 111) approach. Volume-level results focused on E-field magnitude, while surface-level data encompassed E-field magnitude (n = 64) and normal/tangential E-field components (n = 47). E-fields were extracted in ROIs, such as brain structures and shapes (spheres, hexahedra and cylinders), or the whole brain. Percentiles or mean values were mostly used to quantify E-fields. Our modeling study, which involved 1,000 E-field models and > 1,000,000 extracted E-field values, revealed that different outcome measures yielded distinct E-field values, analyzed different brain regions, and did not always exhibit strong correlations in the same within-subject E-field model. CONCLUSIONS: Outcome measure selection significantly impacts the locations and intensities of extracted E-field data in both tES and TMS E-field models. The suitability of different outcome measures depends on the target region, TMS/tES modality, individual anatomy, the analyzed E-field component and the research question. To enhance the quality, rigor, and reproducibility in the E-field modeling domain, we suggest standard reporting practices across studies and provide four recommendations.

Neoadjuvant chemotherapy induces an elevation of tumour apparent diffusion coefficient values in patients with ovarian cancer.

OBJECTIVES: Multiparametric magnetic resonance imaging (mMRI) is the modality of choice in the imaging of ovarian cancer (OC). We aimed to investigate the feasibility of different types of regions of interest (ROIs) in the measurement of apparent diffusion coefficient (ADC) values of diffusion-weighted imaging in OC patients treated with neoadjuvant chemotherapy (NACT). METHODS: We retrospectively enrolled 23 consecutive patients with advanced OC who had undergone NACT and mMRI. Seventeen of them had been imaged before and after NACT. Two observers independently measured the ADC values in both ovaries and in the metastatic mass by drawing on a single slice of (1) freehand large ROIs (L-ROIs) covering the solid parts of the whole tumour and (2) three small round ROIs (S-ROIs). The side of the primary ovarian tumour was defined. We evaluated the interobserver reproducibility and statistical significance of the change in tumoural pre- and post-NACT ADC values. Each patient's disease was defined as platinum-sensitive, semi-sensitive, or resistant. The patients were deemed either responders or non-responders. RESULTS: The interobserver reproducibility of the L-ROI and S-ROI measurements ranged from good to excellent (ICC range: 0.71-0.99). The mean ADC values were significantly higher after NACT in the primary tumour (L-ROI p < 0.001, S-ROIs p < 0.01), and the increase after NACT was associated with sensitivity to platinum-based chemotherapy. The changes in the ADC values of the omental mass were associated with a response to NACT. CONCLUSION: The mean ADC values of the primary tumour increased significantly after NACT in the OC patients, and the amount of increase in omental mass was associated with the response to platinum-based NACT. Our study indicates that quantitative analysis of ADC values with a single slice and a whole tumour ROI placement is a reproducible method that has a potential role in the evaluation of NACT response in patients with OC. TRIAL REGISTRATION: Retrospectively registered (institutional permission code: 5302501; date of the permission: 31.7.2020).

Neural suppression in odor recognition memory.

Little is known about the neural basis of lower- and higher-order olfactory functions such as odor memory, compared with other sensory systems. The aim of this study was to explore neural networks and correlates associated with 3 functions: passive smelling (PS), odor encoding (OE), and in particular odor recognition memory (ORM). Twenty-six healthy participants were examined using functional magnetic resonance imaging conducted across 3 sessions, one for each function. Independent component analysis revealed a difference between sessions where a distinct ORM component incorporating hippocampus and posterior cingulate showed delayed triggering dissociated from odor stimulation and recognition. By contrasting Hit for ORM (target odors correctly recognized as old) and a combination of PS and detected odors from OE, we found significantly lower activations in amygdala, piriform cortex, insula, thalamus, and the inferior parietal lobule. Region of interest analysis including anterior insula, posterior cingulate gyrus, dentate gyrus, left middle frontal gyrus, amygdala, and piriform cortex demonstrated that Hit were associated with lower activations compared with other memory responses. In summary, our findings suggest that successful recognition of familiar odors (odor familiarity) is associated with neural suppression in the abovementioned regions of interest. Additionally, network including the hippocampus and posterior cingulate is engaged in a postrecognition process. This process may be related to incidental encoding of less familiar and more novel odors (odor novelty) and should be subject for future research.

Microstructural Alterations in Projection and Association Fibers in Neonatal Hypoxia-Ischemia.

BACKGROUND: Diffusion MRI (dMRI) is known to be sensitive to hypoxic-ischemic encephalopathy (HIE). However, existing dMRI studies used simple diffusion tensor metrics and focused only on a few selected cerebral regions, which cannot provide a comprehensive picture of microstructural injury. PURPOSE: To systematically characterize the microstructural alterations in mild, moderate, and severe HIE neonates compared to healthy neonates with advanced dMRI using region of interest (ROI), tract, and fixel-based analyses. STUDY TYPE: Prospective. POPULATION: A total of 42 neonates (24 males and 18 females). FIELD STRENGTH/SEQUENCE: 3-T, diffusion-weighted echo-planar imaging. ASSESSMENT: Fractional anisotropy (FA), mean diffusivity (MD), radial diffusivity (RD), axial diffusivity (AD), fiber density (FD), fiber cross-section (FC), and fiber density and cross-section (FDC) were calculated in 40 ROIs and 6 tracts. Fixel-based analysis was performed to assess group differences in individual fiber components within a voxel (fixel). STATISTICAL TESTS: One-way analysis of covariance (ANCOVA) to compare dMRI metrics among severe/moderate/mild HIE and control groups and general linear model for fixel-wise group differences (age, sex, and body weight as covariates). Adjusted P value < 0.05 was considered statistically significant. RESULTS: For severe HIE, ROI-based analysis revealed widespread regions, including the deep nuclei and white matter with reduced FA, while in moderate injury, only FC was decreased around the posterior watershed zones. Tract-based analysis demonstrated significantly reduced FA, FD, and FC in the right inferior fronto-occipital fasciculus (IFOF), right inferior longitudinal fasciculus (ILF), and splenium of corpus callosum (SCC) in moderate HIE, and in right IFOF and left anterior thalamic radiation (ATR) in mild HIE. Correspondingly, we found altered fixels in the right middle-posterior IFOF and ILF, and in the central-to-right part of SCC in moderate HIE. DATA CONCLUSION: For severe HIE, extensive microstructural injury was identified. For moderate-mild HIE, association fiber injury in posterior watershed area with a rightward lateralization was found. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 3.

Correlation of Apparent Diffusion Coefficient With Proliferation and Apoptotic Indexes in a Murine Model of Fibrosarcoma: Comparison of Four Methods for MRI Region of Interest Positioning.

BACKGROUND: Diffusion-weighted imaging (DWI) has demonstrated great potential in predicting the expression of tumor cell proliferation and apoptosis indexes. PURPOSE: To evaluate the impact of four region of interest (ROI) methods on interobserver variability and apparent diffusion coefficient (ADC) values and to examine the correlation of ADC values with Ki-67, Bcl-2, and P53 labeling indexes (LIs) in a murine model of fibrosarcoma. STUDY TYPE: Prospective, animal model. ANIMAL MODEL: A total of 22 female BALB/c mice bearing intramuscular fibrosarcoma xenografts. FIELD STRENGTH/SEQUENCE: A 3.0 T/T1-weighted fast spin-echo (FSE), T2-weighted fast relaxation fast spin-echo, and DWI PROPELLER FSE sequences. ASSESSMENT: Four radiologists measured ADC values using four ROI methods (oval, freehand, small-sample, and whole-volume). Immunohistochemical assessment of Ki-67, Bcl-2, and P53 LIs was performed. STATISTICAL TESTS: Interclass correlation coefficient (ICC), one-way analysis of variance followed by LSD-t post hoc analysis, and Pearson correlation test were performed. The statistical threshold was defined as a P-value of <0.05. RESULTS: All ROI methods for ADC measurements showed excellent interobserver agreement (ICC range, 0.832-0.986). The ADC values demonstrated significant differences among the four ROI methods. The ADC values for oval, freehand, small-sample, and whole-volume ROI methods showed a moderately negative correlation with Ki-67 (r = -0.623; r = -0.629; r = -0.642, and r = -0.431) and Bcl-2 (r = -0.590; r = -0.597; r = -0.659, and r = -0.425) LIs, but no correlation with P53 LI (r = 0.364, P = 0.104; r = 0.350, P = 0.120; r = 0.379, P = 0.091; r = 0.390, P = 0.080). DATA CONCLUSION: The ADC value can be used to evaluate cell proliferation and apoptosis indexes in a murine model of fibrosarcoma, employing the small-sample ROI as a reliable method. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 3.

Reliability of T2-weighted signal intensity-based quantitative measurements and visual grading of lumbar disc degeneration on MRI.

BACKGROUND: Decrease in signal intensity (SI) of the nucleus pulposus (NP) on T2-weighted (T2W) images, a sign of disc degeneration (DD), is usually graded based on an observer's image interpretation. No gold standard for quantitative assessment of NP SI exists to date. PURPOSE: To compare different quantitative methods and visual gradings of lumbar DD and to evaluate the ability of the quantitative methods to differentiate DD grades. MATERIAL AND METHODS: The mean SI of 95 lumbar discs was measured from sagittal T2W images using three regions of interest (ROI): the whole disc, ellipsoid ROI on the NP, and targeted ROI on the most homogenous, brightest area of the NP. SI values were adjusted with cerebrospinal fluid (CSF) SI and compared with vertebral bone SI-adjusted values. DD was evaluated with Pfirrmann grading and visual grading of NP SI. Intra- and inter-observer agreements and relationships between measurements and visual gradings were assessed. RESULTS: Repeatability of all measurements was excellent. All measurements had a strong correlation with Pfirrmann grading and visual NP SI grading, and the CSF SI-adjusted values had a stronger correlation than the vertebral bone SI-adjusted values. The SI values obtained with the targeted ROI had the most significant differences between visual DD grades. CONCLUSION: Quantitative measurement of the NP SI provides a reliable method for evaluating lumbar DD. Targeted selection of the NP structures included in the measurement offers the best differentiation of DD grades. A reliable quantitative method for DD evaluation is needed for the development of machine-learning-based DD classification.

Influence of the area of the aqueduct and region of interest on quantification of stroke volume in healthy volunteers using phase-contrast cine magnetic resonance imaging.

BACKGROUND: Phase-contrast cine magnetic resonance imaging (PC-MRI) has been used to measure cerebrospinal fluid (CSF) flow dynamics, but the influence of the area of the aqueduct and region of interest (ROI) on quantification of stroke volume (SV) has not been assessed. PURPOSE: To assess the influence of the area of the ROI in quantifying the aqueductal SV measured with PC-MRI within the cerebral aqueduct. MATERIAL AND METHODS: Nine healthy volunteers (mean age = 29.6 years) were enrolled in the study, and brain MRI examinations were performed on a 3.0-T system. Quantitative analysis of the aqueductal CSF flow was performed using manual ROI placement. ROIs were separately drawn for each of the 12 phases of the cardiac cycle, and changes in aqueduct size during the cardiac cycle were determined. The SV was calculated using 12 different aqueductal ROIs and compared with the SV calculated using a fixed ROI size. RESULTS: There was variation in the size of the aqueduct during the cardiac cycle. In addition, the measured SV increased with a greater area of the ROI. A significant difference in the calculated SVs with the 12 variable ROIs was observed compared with that using a fixed ROI throughout the cardiac cycle. CONCLUSION: To establish reliable reference values for the SV in future studies, a variable ROI should be considered.

Assessment of MRI image distortion based on 6 consecutive years of annual QAs and measurements on 14 MRI scanners used for radiation therapy.

PURPOSE: To determine the magnitude of MRI image distortion based on 6 consecutive years of annual quality assurances/measurements on 14 MRI scanners used for radiation therapy and to provide evidence for the inclusion of additional margin for treatment planning. METHODS AND MATERIALS: We used commercial MRI image phantoms to quantitatively study the MRI image distortion over period of 6 years for up to 14 1.5 and 3 T MRI scanners that could potentially be used to provide MRI images for treatment planning. With the phantom images collected from 2016 to 2022, we investigated the MRI image distortion, the dependence of distortion on the distance from the imaging isocenter, and the possible causes of large distortion discovered. RESULTS: MRI image distortion increases with the distance from the imaging isocenter. For a region of interest (ROI) with a radius of 100 mm centered at the isocenter, the mean magnitude of distortion for all MRI scanners is 0.44 ± 0.18 mm $0.44 \pm 0.18\;{\rm{mm}}$ , and the maximum distortion varies from 0.52 to 1.31 mm $0.52\;{\rm{to}}\;1.31\;{\rm{mm}}$ depending on MRI scanners. For an ROI with a radius of 200 mm centered at the isocenter, the mean magnitude of distortion increases to 0.84 ± 0.45 mm $0.84 \pm 0.45\;{\rm{mm}}$ , and the range of the maximum distortion increases to 1.92 - 5.03 mm $1.92 - 5.03\;{\rm{mm}}$ depending on MRI scanners. The distortion could reach 2 mm at 150 mm from the isocenter. CONCLUSION: An additional margin to accommodate image distortion should be considered for treatment planning. Imaging with proper patient alignment to the isocenter is vital to reducing image distortion. We recommend performing image distortion checks annually and after major upgrade on MRI scanners.

Automatic Counterfeit Currency Detection Using a Novel Snapshot Hyperspectral Imaging Algorithm.

In this study, a snapshot-based hyperspectral imaging (HSI) algorithm that converts RGB images to HSI images is designed using the Raspberry Pi environment. A Windows-based Python application is also developed to control the Raspberry Pi camera and processor. The mean gray values (MGVs) of two distinct regions of interest (ROIs) are selected from three samples of 100 NTD Taiwanese currency notes and compared with three samples of counterfeit 100 NTD notes. Results suggest that the currency notes can be easily differentiated on the basis of MGV values within shorter wavelengths, between 400 nm and 500 nm. However, the MGV values are similar in longer wavelengths. Moreover, if an ROI has a security feature, then the classification method is considerably more efficient. The key features of the module include portability, lower cost, a lack of moving parts, and no processing of images required.

Fast and Accurate ROI Extraction for Non-Contact Dorsal Hand Vein Detection in Complex Backgrounds Based on Improved U-Net.

In response to the difficulty of traditional image processing methods to quickly and accurately extract regions of interest from non-contact dorsal hand vein images in complex backgrounds, this study proposes a model based on an improved U-Net for dorsal hand keypoint detection. The residual module was added to the downsampling path of the U-Net network to solve the model degradation problem and improve the feature information extraction ability of the network; the Jensen-Shannon (JS) divergence loss function was used to supervise the final feature map distribution so that the output feature map tended to Gaussian distribution and improved the feature map multi-peak problem; and Soft-argmax is used to calculate the keypoint coordinates of the final feature map to realize end-to-end training. The experimental results showed that the accuracy of the improved U-Net network model reached 98.6%, which was 1% better than the original U-Net network model; the improved U-Net network model file was only 1.16 M, which achieved a higher accuracy than the original U-Net network model with significantly reduced model parameters. Therefore, the improved U-Net model in this study can realize dorsal hand keypoint detection (for region of interest extraction) for non-contact dorsal hand vein images and is suitable for practical deployment in low-resource platforms such as edge-embedded systems.

Performance Analysis of Six Semi-Automated Tumour Delineation Methods on [18F] Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (FDG PET/CT) in Patients with Head and Neck Cancer.

Background. Head and neck cancer (HNC) is the seventh most common neoplastic disorder at the global level. Contouring HNC lesions on [18F] Fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) scans plays a fundamental role for diagnosis, risk assessment, radiotherapy planning and post-treatment evaluation. However, manual contouring is a lengthy and tedious procedure which requires significant effort from the clinician. Methods. We evaluated the performance of six hand-crafted, training-free methods (four threshold-based, two algorithm-based) for the semi-automated delineation of HNC lesions on FDG PET/CT. This study was carried out on a single-centre population of n=103 subjects, and the standard of reference was manual segmentation generated by nuclear medicine specialists. Figures of merit were the Sørensen-Dice coefficient (DSC) and relative volume difference (RVD). Results. Median DSC ranged between 0.595 and 0.792, median RVD between -22.0% and 87.4%. Click and draw and Nestle's methods achieved the best segmentation accuracy (median DSC, respectively, 0.792 ± 0.178 and 0.762 ± 0.107; median RVD, respectively, -21.6% ± 1270.8% and -32.7% ± 40.0%) and outperformed the other methods by a significant margin. Nestle's method also resulted in a lower dispersion of the data, hence showing stronger inter-patient stability. The accuracy of the two best methods was in agreement with the most recent state-of-the art results. Conclusions. Semi-automated PET delineation methods show potential to assist clinicians in the segmentation of HNC lesions on FDG PET/CT images, although manual refinement may sometimes be needed to obtain clinically acceptable ROIs.

A Deep Learning Approach for Arabic Manuscripts Classification.

For centuries, libraries worldwide have preserved ancient manuscripts due to their immense historical and cultural value. However, over time, both natural and human-made factors have led to the degradation of many ancient Arabic manuscripts, causing the loss of significant information, such as authorship, titles, or subjects, rendering them as unknown manuscripts. Although catalog cards attached to these manuscripts might contain some of the missing details, these cards have degraded significantly in quality over the decades within libraries. This paper presents a framework for identifying these unknown ancient Arabic manuscripts by processing the catalog cards associated with them. Given the challenges posed by the degradation of these cards, simple optical character recognition (OCR) is often insufficient. The proposed framework uses deep learning architecture to identify unknown manuscripts within a collection of ancient Arabic documents. This involves locating, extracting, and classifying the text from these catalog cards, along with implementing processes for region-of-interest identification, rotation correction, feature extraction, and classification. The results demonstrate the effectiveness of the proposed method, achieving an accuracy rate of 92.5%, compared to 83.5% with classical image classification and 81.5% with OCR alone.

Limited Sampling Spatial Interpolation Evaluation for 3D Radio Environment Mapping.

The increasing densification and diversification of modern and upcoming wireless networks have become an important motivation for the development of agile spectrum sharing. Radio environment maps (REMs) are a basic tool for spectrum utilisation characterisation and adaptive resource allocation, but they need to be estimated through accurate interpolation methods. This work evaluated the performance of two established algorithms for spatial three-dimensional (3D) data collected in two real-world scenarios: indoors, through a mechanical measuring system, and outdoors, through an unmanned aerial vehicle (UAV) for measurement collection. The investigation was undertaken for the complete dataset on two-dimensional (2D) planes of different altitudes and for a subset of limited samples (representing the regions of interest or RoIs), which were combined together to describe the spatial 3D environment. A minimum error of -9.5 dB was achieved for a sampling ratio of 21%. The methods' performance and the input data were analysed through the resulting Kriging error standard deviation (STD) and the STD of the distances between the measurement and the estimated points. Based on the results, several challenges for the interpolation performance and the analysis of the spatial RoIs are described. They facilitate the future development of 3D spectrum occupancy characterisation in indoor and UAV-based scenarios.

A Deep Recurrent Learning-Based Region-Focused Feature Detection for Enhanced Target Detection in Multi-Object Media.

Target detection in high-contrast, multi-object images and movies is challenging. This difficulty results from different areas and objects/people having varying pixel distributions, contrast, and intensity properties. This work introduces a new region-focused feature detection (RFD) method to tackle this problem and improve target detection accuracy. The RFD method divides the input image into several smaller ones so that as much of the image as possible is processed. Each of these zones has its own contrast and intensity attributes computed. Deep recurrent learning is then used to iteratively extract these features using a similarity measure from training inputs corresponding to various regions. The target can be located by combining features from many locations that overlap. The recognized target is compared to the inputs used during training, with the help of contrast and intensity attributes, to increase accuracy. The feature distribution across regions is also used for repeated training of the learning paradigm. This method efficiently lowers false rates during region selection and pattern matching with numerous extraction instances. Therefore, the suggested method provides greater accuracy by singling out distinct regions and filtering out misleading rate-generating features. The accuracy, similarity index, false rate, extraction ratio, processing time, and others are used to assess the effectiveness of the proposed approach. The proposed RFD improves the similarity index by 10.69%, extraction ratio by 9.04%, and precision by 13.27%. The false rate and processing time are reduced by 7.78% and 9.19%, respectively.