Semi-automatic Method Research Articles

Uncovering Vegetation Changes in the Urban–Rural Interface through Semi-Automatic Methods

Forest fires are considered by Portuguese civil protection as one of the most serious natural disasters due to their frequency and extent. To address the problem, the Fire Forest Defense System establishes the implementation of fuel management bands to aid firefighting. The aim of this study was to develop a model capable of identifying vegetation removal in the urban–rural interface defined by law for fuel management actions. The model uses normalised difference vegetation index (NDVI) of Sentinel-2 images time series and is based on the Welch t-test to find statistically significant differences between (i) the value of the NDVI in the pixel; (ii) the mean of the NDVI in the pixels of the same land cover type in a radius of 500 m; and (iii) their difference. The model identifies a change when the t-test points for a significant difference of the NDVI value in the ‘pixel’ as comparted to the ‘difference’ but not the ‘mean’. We use a moving window limited to 60 days before and after the analysed date to reduce the phenological variations of vegetation. The model was applied in five municipalities of Portugal and the results are promising to identify the places where the management of fuel bands was not carried out. This indicates which model could be used to assist in the verification of the annual management of the fuel bands defined in the law.

A multi–modal unsupervised fault detection system based on power signals and thermal imaging via deep AutoEncoder neural network

In this paper a multi-modal unsupervised Deep Learning based algorithm for fault detection is proposed. Such method is applied to real data from a testing procedure implemented on an industrial production line. Both thermal images and current and power measurements coming from industrial refrigerators are collected. The considered dataset is highly unbalanced with the vast majority of samples being healthy. Thermal images are processed via a Deep Convolutional neural network. The features extracted from the thermal images are thus merged to structured data of power, current and temperature. Therefore, a Deep Auto-Encoder is trained on the dataset to signal anomalies corresponding to faults in the refrigerators. Three different methods are trained and compared: (1) an automatic method in which an expert extracts relevant features from thermal images without using the image recognition module; (2) a semi-automatic method where the convolutional neural network is applied to regions of interest within the thermal images selected by an expert operator; (3) a fully automatic method in which the Deep convolutional network processes the whole thermal image without any human intervention. The three methods show comparable results with nevertheless slight differences.

Semiautomated Software to Improve Stability and Reduce Operator-Induced Variation in Vascular Ultrasound Speckle Tracking.

Ultrasound is useful in predicting arteriovenous fistula (AVF) maturation, which is essential for hemodialysis in end-stage renal disease patients. We developed ultrasound software that measures circumferential vessel wall strain (distensibility) using conventional ultrasound Digital Imaging and Communications in Medicine (DICOM) data. We evaluated user-induced variability in measurement of arterial wall distensibility and upon finding considerable variation we developed and tested 2 methods for semiautomated measurement. Ultrasound scanning of arteries of 10 subjects scheduled for AVF surgery were performed. The top and bottom of the vessel wall were tracked using the Kanade-Lucas-Tomasi (KLT) feature-tracking algorithm over the stack of images in the DICOM cine loops. The wall distensibility was calculated from the change of vessel diameter over time. Two semiautomated methods were used for comparison. The location of points selected by users for the cine loops varied significantly, with a maximum spread of up to 120 pixels (7.8 mm) for the top and up to 140 pixels (9.1 mm) for the bottom of the vessel wall. This variation in users' point selection contributed to the variation in distensibility measurements (ranging from 5.63 to 41.04%). Both semiautomated methods substantially reduced variation and were highly correlated with the median distensibility values obtained by the 10 users. Minimizing user-induced variation by standardizing point selection will increase reproducibility and reliability of distensibility measurements. Our recent semiautomated software may help expand use in clinical studies to better understand the role of vascular wall compliance in predicting the maturation of fistulas.

A New Semi-Automated Method for Service Identification

Service identification plays a key role in the design of service-oriented systems. There are non-model-based and model-based methods for extracting services from business processes. These methods suggest a set of mostly descriptive solutions that do not pay sufficient attention to service design guidelines and the conceptual relations between tasks. The challenge is to develop an algorithm to automatically identify services from business processes to simplify the analysis and reduce the gap between information technology and business needs. In this paper, we develop a semi-automated service identification method that addresses this gap. This method incorporates the Goal, Data, and Business Process Models (BPM) to identify services based on related tasks, shared data, and business requirements. It advances previous methods by simultaneously considering both semantic and structural relations between tasks which permits better and more accurate identification of services. Moreover, the proposed method considers the principles of service design such as internal cohesion of service methods, loose coupling of services, and reusability of the identified services.

Changes in the incidence of transfusion reactions in hematological patients over the past 30 years.

Patients with hematological diseases are polytransfused and often immunocompromised, therefore susceptible to transfusion reactions (TR). This study aims to document the incidence of TRs in adult hematological patients and assess the effect of changes in the production of blood components and transfusion practice on their occurrence. Retrospective observational analysis of TRs reported from 1993 to 2019 was performed. For the analysis of the effect of changes on the incidence of TRs, the evaluated time was divided into two periods: the 1st period before the introduction of changes in production, when leukoreduced blood components were used only selectively, and the 2nd period, when semi-automated method of production and universal leukoreduction was introduced. The decrease in the incidence of TRs was observed for both red blood cell (RBC) and platelet concentrate (PC) transfusions in the 2nd period. Since platelet additive solution has been used, a further decrease in the incidence was reported. The decrease in incidence was also observed for delayed hemolytic/serological transfusion reactions and for transfusion-transmitted bacterial infections. Four cases of incorrect blood transfusions were uniquely related to the hematological patients, caused by antigen loss and transfusion ordering after ABO-incompatible hematopoietic stem cell transplantation. Our results provided evidence that the introduction of tools offered by modern transfusion medicine: universal leukodepletion, plasma replacement with additive solutions, sensitive laboratory techniques, prophylactic antigen matching policy, informatization, and automatization, decreased the incidence of TRs and improved transfusion safety.

Semi-Automatic Method to Evaluate Ecological Value of Urban Settlements with the Biotope Area Factor Index: Sources and Logical Framework

As the number of people living in cities continues to increase and as their needs continue rapidly to evolve, planners and scholars have been encouraged to define what constitutes high levels of quality of life in urban settlements. The relationship of an area’s inhabitants with natural and green resources increases urban environmental value, which is one of the most relevant aspects in the determination of the quality of life in built-up contexts. Moreover, it is fundamental to find quantitative parameters that can monitor the development of planning processes, working together with natural systems. The authors present a comparative method that can be used to analyze and evaluate the ecological value of urban settlements, using a semi-automatic process that is based on calculating the biotope area factor (BAF) using different open-access databases (a cartographic dataset, aerial imagery, and Sentinel-2 images). Two different Italian case studies that are set in the Milan metropolitan area are presented. In this paper, the authors describe the two settlements using the city-planning parameters of physical structure and morphology; they show the ecological differences and similarities throughout the various remote sensing sources and data. Finally, the authors indicate how the research can be developed, highlighting the weaknesses, the potentiality, the replicability process, and the urban planning implications of the methodology.

A novel semiautomated method for background activity and biological tumour volume definition to improve standardisation of 18F-FET PET imaging in glioblastoma

BackgroundMulticentre clinical trials evaluating the role of 18F-Fluoroethyl-l-tyrosine (18F-FET) PET as a diagnostic biomarker in glioma management have highlighted a need for standardised methods of data analysis. 18F-FET uptake normalised against background in the contralateral brain is a standard imaging technique to delineate the biological tumour volume (BTV). Quantitative analysis of 18F-FET PET images requires a consistent and robust background activity. Currently, defining background activity involves the manual selection of an arbitrary region of interest, a process that is subject to large variability. This study aims to eliminate methodological errors in background activity definition through the introduction of a semiautomated method for region of interest selection. A new method for background activity definition, involving the semiautomated generation of mirror-image (MI) reference regions, was compared with the current state-of-the-art method, involving manually drawing crescent-shape (gCS) reference regions. The MI and gCS methods were tested by measuring values of background activity and resulting BTV of 18F-FET PET scans of ten patients with recurrent glioblastoma multiforme generated from inputs provided by seven readers. To assess intra-reader variability, each scan was evaluated six times by each reader. Intra- and inter-reader variability in background activity and BTV definition was assessed by means of coefficient of variation.ResultsCompared to the gCS method, the MI method showed significantly lower intra- and inter-reader variability both in background activity and in BTV definition.ConclusionsThe proposed semiautomated MI method minimises intra- and inter-reader variability, providing a valuable approach for standardisation of 18F-FET PET quantitative parameters.Trial registration ANZCTR, ACTRN12618001346268. Registered 9 August 2018, https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=374253

Fully automated quantification of LV regional wall motion from echocardiograms to detect myocardial infarction

Abstract Funding Acknowledgements Type of funding sources: Private company. Main funding source(s): Ultromics Ltd Background Myocardial wall motion analysis from echocardiography allows precise assessment of cardiac contractile function. Strain, which assesses myocardial deformation, has been shown to enable earlier detection of myocardial disease [1]. Current analysis software packages [2] use semi-automated methods to compute strain, which frequently require manual endocardial delineation and iterative contour adjustment based on tracking results, respectively, causing significant variability. Purpose We present a fully automated pipeline for tracking left ventricular (LV) wall motion to quantify global and segmental longitudinal strain from 2D echocardiograms, and go on to validate the pipeline with an openly available myocardial infarction (MI) dataset. Methods We applied our existing deep learning-based automated contouring method [3] to delineate the endocardial border in the A4C, A2C and A3C views and combined this with spline-based elastic image registration to track LV motion through time. We sampled points from a region of interest initiated from the endocardial border at the end-diastolic (ED) frame, and tracked subsequent motion by recomputing updated positions of all sample points based on each frame‘s displacement field, enabling us to both track the myocardium throughout the cardiac cycle and calculate longitudinal strain relative to the ED frame. The automated endocardial contour was used to regularise the process. The pipeline was independently tested on the HMC-QU dataset [4] which was downloaded from Kaggle and consists of a single cardiac cycle from the A4C view from 160 patients who were diagnosed with an acute MI and underwent echocardiography either prior to percutaneous coronary intervention or within 24 hours of undergoing the procedure; the dataset includes the labels of ED and end-systolic (ES) frames, as well as the presence of an MI in 6 segments excluding the apical cap (Fig 1a), as determined by the consensus of cardiologists from HMC Hospital in Qatar. The Wilcoxon signed-rank test was used to compare peak strain between the MI and non-MI segments; ROC curves were computed to compare the performance of the automatically derived peak longitudinal strain against the MI labels. Results Fig 1b shows ROC curves of peak segmental longitudinal strain for detecting MI, with the best performance in the mid-anterolateral segment (AUC 0.84), and a lower performance for basal segments than mid and apical segments, consistent with known variation in clinical practice [5]. Fig 2 shows that peak longitudinal strain computed from our pipeline was statistically significantly more positive in segments with an MI. Conclusions We present a fully automated pipeline for calculating segmental strain across a cardiac cycle to identify infarcted segments without any observer variability. Clinical application of this method has the potential to identify and monitor regional myocardial function and benefit patient management. Abstract Figure. Fig1. ROC of peak longitudinal strains Abstract Figure. Fig2.Boxplot of peak longitudinal strain

Microplastic detection and identification by Nile red staining: Towards a semi-automated, cost- and time-effective technique

Microplastic pollution is an issue of concern due to the accumulation rates in the marine environment combined with the limited knowledge about their abundance, distribution and associated environmental impacts. However, surveying and monitoring microplastics in the environment can be time consuming and costly. The development of cost- and time-effective methods is imperative to overcome some of the current critical bottlenecks in microplastic detection and identification, and to advance microplastics research. Here, an innovative approach for microplastic analysis is presented that combines the advantages of high-throughput screening with those of automation. The proposed approach used Red Green Blue (RGB) data extracted from photos of Nile red-fluorescently stained microplastics (50–1200 μm) to train and validate a ‘Plastic Detection Model’ (PDM) and a ‘Polymer Identification Model’ (PIM). These two supervised machine learning models predicted with high accuracy the plastic or natural origin of particles (95.8%), and the polymer types of the microplastics (88.1%). The applicability of the PDM and the PIM was demonstrated by successfully using the models to detect (92.7%) and identify (80%) plastic particles in spiked environmental samples that underwent laboratorial processing. The classification models represent a semi-automated, high-throughput and reproducible method to characterize microplastics in a straightforward, cost- and time-effective yet reliable way.

Combining Diffusion-Weighted Imaging and T2-Weighted Imaging to Delineate Tumorous Tissue in Peritoneal Carcinomatosis: A Comparative Study with 18F-Fluoro-Deoxyglucose Positron Emission Tomography with Computed Tomography (FDG PET/CT).

BackgroundThe high rate of malignancy of peritoneal carcinomatosis makes its accurate detection vital in treatment planning. The combination of anatomical and functional information, provided by T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI), respectively, could potentially aid in the segmentation of tumors. The aim of this study was to compare the functional tumor volume estimated by a T2WI- and DWI-derived apparent diffusion coefficient (ADC) map, with metabolic tumor volume measured by 18F-fluoro-deoxyglucose positron emission tomography with computed tomography (FDG PET/CT).Material/MethodsIn 108 lesions from 108 patients with peritoneal carcinomatosis, gross tumor volume (GTV) was manually delineated on DWI. Within each region of interest, k-means clustering was used to exclude non-tumorous tissue from tumorous tissue. The high-cellularity tumor volume estimated from ADC (HCTVADC) and combined high-cellularity tumor volume (HCTVC), which was estimated by combining anatomical information from T2WI and functional information from ADC, were generated. Taking metabolic tumor volume (MTV) in PET/CT as a reference, GTV, HCTVADC, and HCTVC were compared with MTV.ResultsGTV (P=0.017) and HCTVADC (P=0.048) differed significantly from MTV. However, the HCTVC measured by combining DWI and T2WI showed high concordance (ICC=0.99) with the MTV measured by FDG PET/CT in differentiating tumorous tissues with high cellularity from non-tumorous tissues.ConclusionsIn conclusion, our results suggested the potential value of this semiautomatic method serving as an alternative to PET/CT in radiotherapy tumor contouring.

Semi-automatic wafer map pattern classification with convolutional neural networks

In semiconductor manufacturing, the defect patterns of wafer maps provide crucial information to identify the root causes of wafer defects. Recently, convolutional neural networks (CNNs) have been actively applied to automatic wafer map pattern classification. As a requirement for real-world application, a CNN must be as accurate as a process engineer. Existing studies have attempted to improve the training phase of a CNN to make it more accurate. However, they often fail to achieve the near-perfect accuracy requirement in practice. To sidestep the difficulty, we focus on improving the inference phase of an imperfect CNN with the aid of a process engineer. In this paper, we propose a semi-automatic wafer map pattern classification method that selectively utilizes the CNN for classifying new wafer maps. Given a query wafer map, we decide whether to use the CNN by quantifying its predictive uncertainty on the wafer map. If the predictive uncertainty is sufficiently low, the wafer map is classified using the CNN. Otherwise, the wafer map is subject to manual classification by a process engineer. In the experiments using the WM-811k dataset, the proposed method attains an accuracy of over 99% with a CNN coverage of 93%.

Performance evaluation of segmentation methods for assessing the lens of the frog Thoropa miliaris from synchrotron-based phase-contrast micro-CT images.

In the context of synchrotron microtomography using propagation-based phase-contrast imaging (XSPCT), we evaluated the performance of semiautomatic and automatic image segmentation of soft biological structures by means of Dice Similarity Coefficient (DSC) and volume quantification. We took advantage of the phase-contrast effects of XSPCT to provide enhanced object boundaries and improved visualization of the lenses of the frog Thoropa miliaris. Then, we applied semiautomatic segmentation methods 1 and 2 (Interpolation and Watershed, respectively) and method 3, an automatic segmentation algorithm using the U-Net architecture, to the reconstructed images. DSC and volume quantification of the lenses were used to quantify the performance of image segmentation methods. Comparing the lenses segmented by the three methods, the most pronounced difference in volume quantification was between methods 1 and 3: a reduction of 4.24%. Method 1, 2 and 3 obtained the global average DSC of 97.02%, 95.41% and 89.29%, respectively. Although it obtained the lowest DSC, method 3 performed the segmentation in a matter of seconds, while the semiautomatic methods had the average time to segment the lenses around 1h and 30min. Our results suggest that the performance of U-Net was impaired due to the irregularities of the ROI edges mainly in its lower and upper regions, but it still showed high accuracy (DSC=89.29%) with significantly reduced segmentation time compared to the semiautomatic methods. Besides, with the present work we have established a baseline for future assessments of Deep Neural Networks applied to XSPCT volumes.

Hyper-fusion network for semi-automatic segmentation of skin lesions.

Segmentation of skin lesions is an important step for imaging-based clinical decision support systems. Automatic skin lesion segmentation methods based on fully convolutional networks (FCNs) are regarded as the state-of-the-art for accuracy. When there are, however, insufficient training data to cover all the variations in skin lesions, where lesions from different patients may have major differences in size/shape/texture, these methods failed to segment the lesions that have image characteristics, which are less common in the training datasets. FCN-based semi-automatic segmentation methods, which fuse user-inputs with high-level semantic image features derived from FCNs offer an ideal complement to overcome limitations of automatic segmentation methods. These semi-automatic methods rely on the automated state-of-the-art FCNs coupled with user-inputs for refinements, and therefore being able to tackle challenging skin lesions. However, there are a limited number of FCN-based semi-automatic segmentation methods and all these methods focused on 'early-fusion', where the first few convolutional layers are used to fuse image features and user-inputs and then derive fused image features for segmentation. For early-fusion based methods, because the user-input information can be lost after the first few convolutional layers, consequently, the user-input information will have limited guidance and constraint in segmenting the challenging skin lesions with inhomogeneous textures and fuzzy boundaries. Hence, in this work, we introduce a hyper-fusion network (HFN) to fuse the extracted user-inputs and image features over multiple stages. We separately extract complementary features which then allows for an iterative use of user-inputs along all the fusion stages to refine the segmentation. We evaluated our HFN on three well-established public benchmark datasets - ISBI Skin Lesion Challenge 2017, 2016 and PH2 - and our results show that the HFN is more accurate and generalizable than the state-of-the-art methods, in particular with challenging skin lesions.

Making Semi-Automatic Segmentation Method to be Automatic Using Deep Learning for Biventricular Segmentation

Ventricular Segmentation or Delineation of Cardiac Magnetic Resonance Imaging (CMRI) is significant in obtaining the cardiac contractile function, which in turn is taken as input for diagnosing Cardio Vascular Diseases (CVD). Many automatic and semi-automatic methods were evolved to meet the constraints of diagnosing CVDs. Among these, semi-automatic methods require user intervention for delineation of ventricles, which consumes time and leads to intra and inter-observability, as with manual delineation. Thus, the automatic method is suggested by most of the researchers to address the above-stated problem. We proposed Saliency-based Active contour U-Net (SACU-Net) for automatic bi-ventricular segmentation which is found to surpass the existing highest developed methods regarding closeness to the gold standard. Three schemes are used by our proposed algorithm, namely 1. Saliency Detection Scheme for Region of Interest (ROI) Localization to concentrate only on Object of Interest, 2. Drop-out embedded U-net for Initial Contour evolution that performs initial segmentation and 3. Local-Global-based Regional active Contour (LGRAC) to fine-tune and avoid leaking, merging of ventricles during Delineation. We used three datasets namely Automatic Cardiac Diagnosing Challenge (ACDC) of MICCAI 2017, Right Ventricular Segmentation Challenge (RVSC) of MICCAI 2012, and Sunny Brook (SB) of MICCAI 2009 dataset to test the adaptability nature of our algorithm over different scanner resolutions and protocols. 100 and 50 CMRI Images of ACDC were used for training and testing respectively which obtained average Dice Coefficient (DC) metric of 0.963, 0.934, and 0.948 for Left Ventricular Cavity (LVC), Left Ventricular Myocardium (LVM), and Right Ventricular Cavity (RVC) respectively. 32 and 16 CMRI Images of RVSC are used for preparing and experimenting respectively, which obtained an average DC metric of 0.95 for RVC.30 and 15 CMRI Images of SB are used for preparing and experimenting respectively, which obtained average DC metric of 0.96 and 0.97 for LVC and LVM, respectively. Hausdorff Distance (HD) Metrics are also calculated to learn the distance of proposed delineated ventricles to reach the gold standard. The above resultant metrics show the robustness of our proposed SACU-Net in the segmentation of ventricles of CMRI than previous methods.

Kajian Perbandingan Akurasi DTM Pengolahan Data Foto Udara Menggunakan Metode Otomatis Dan Semi-Otomatis Filtering

Advances in UAV technology produce various superior products that can be utilized for the development and analysis of natural dynamics. One of them is DTM which is a visual representation of the shape of the ground surface that is displayed in 3 dimensions. DTM is obtained from the results of DSM filtering, where all features above the ground are digitally removed using a certain method. To produce a good DTM, a good quality DSM is needed, therefore a Horizontal and Vertical accuracy analysis was carried out based on ASPRS 2015. In this study, two software with different data processing methods were used, namely automatic filtering and semi-automatic filtering from DSM to DTM. To determine the quality of DTM, spot-height data is used as a comparison which is considered to be the actual form in the field. From the series of data processing processes, DTM results were obtained which were then tested for accuracy utilizing statistical validation tests using the calculation of RMSEZ values and non-statistical validation tests (Visual) using the transverse profile method. The test results show that the DTM produced by the PCI Geomatica software with the semi-automatic filtering method has more accurate and precise quality than the DTM from the SAGA GIS software with the automatic filtering method with an elevation value of 1,249 m and RMSEz 3,542 m to the spot-height. Then the visualization of the DTM transverse profile produced by the PCI Geomatica software semi-automatic filtering method to the spot height also does not appear to experience a significant difference where the elevation at Point 1 is 0.5 m and Point 2 is 0.5 m.

On the role of REM sleep microstructure in suppressing interictal spikes in Electrical Status Epilepticus during Sleep

ObjectiveNon-Rapid Eye Movement (NREM) sleep promotes the spread and propagation of Interictal Epileptiform Discharges (IEDs), while IEDs are suppressed during REM. Recently, it has been shown that the inhibitory effect on epileptic activity is mostly exerted by the phasic REM (PREM) microstate. This study aims at assessing if this holds true even in the extreme condition of IEDs activation during sleep represented by Electrical Status Epilepticus during Sleep (ESES). Methodseight patients affected by ESES, who underwent long-term EEG were included. REM was subdivided into phasic and tonic microstates along with the sleep scoring. IEDs count was carried out using a semi-automatic method and a Spike Index (SI) was calculated. ResultsThe SI was significantly higher in NREM sleep than in REM. Within REM, the SI was significantly lower in PREM than in tonic REM (TREM). The SI was reduced by 84% in TREM with respect to NREM and by 97% in PREM with respect to NREM. Moreover, the SI was reduced by 87% in PREM with respect to TREM. ConclusionsPREM has a greater suppressive effect on epileptic activity even in the extreme IEDs activation during sleep typical of ESES. SignificanceUnderstanding the protective effect of PREM sleep on epileptic activity might be relevant for future therapeutic approaches.

Gap analysis of exceptional species—Using a global list of exceptional plants to expand strategic ex situ conservation action beyond conventional seed banking

With two in five plant species facing extinction, plant diversity loss demands action that integrates ex situ with in situ conservation approaches. While conservation in seed banks has been widely adopted, this technology cannot be applied to exceptional species, which require alternative approaches. We propose a new conceptual framework, resulting in the creation of a global working Exceptional Status List. Using a semi-automated method to evaluate over 23,000 seed plants, 775 were identified as exceptional, <3% of those predicted to be exceptional. These were further characterized by one or more of four exceptionality factors (EF): Species with desiccation intolerant seeds (EF2, 50%), short-lived seeds (EF3, 36.6%), unavailable seeds (EF1, 12.6%), or deeply dormant seeds (EF4, 3.4%). One quarter of the identified exceptional species are threatened, and the four families with the most exceptional species were Dipterocarpaceae, Arecaceae, Rutaceae, and Fabaceae. Only 20% of plant genera have had even one species assessed for exceptionality. Although 688 exceptional species are in ex situ collections, most were represented by only 1–4 ex situ sites, primarily living plant collections, with very few in cryobanks. This project illustrates the significant gaps in our knowledge of exceptionality and the need for additional input from researchers and practitioners. The Exceptional Status List is provided as a conservation toolkit, to highlight gaps in knowledge and serve as the basis for further input and research, providing the basis for prioritizing goals and developing strategies for action to address the conservation challenges of exceptional plants.

A high-throughput semi-automated bone segmentation workflow for murine hindpaw micro-CT datasets

IntroductionMicro-computed tomography (μCT) is a valuable imaging modality for longitudinal quantification of bone volumes to identify disease or treatment effects for a broad range of conditions that affect bone health. Complex structures, such as the hindpaw with up to 31 distinct bones in mice, have considerable analytic potential, but quantification is often limited to a single bone volume metric due to the intensive effort of manual segmentation. Herein, we introduce a high-throughput, user-friendly, and semi-automated method for segmentation of murine hindpaw μCT datasets. MethodsIn vivo μCT was performed on male (n = 4; 2–8-months) and female (n = 4; 2–5-months) C57BL/6 mice longitudinally each month. Additional 9.5-month-old male C57BL/6 hindpaws (n = 6 hindpaws) were imaged by ex vivo μCT to investigate the effects of resolution and integration time on analysis outcomes. The DICOMs were exported to Amira software for the watershed-based segmentation, and watershed markers were generated automatically at approximately 80% accuracy before user correction. The semi-automated segmentation method utilizes the original data, binary mask, and bone-specific markers that expand to the full volume of the bone using watershed algorithms. ResultsCompared to the conventional manual segmentation using Scanco software, the semi-automated approach produced similar raw bone volumes. The semi-automated segmentation also demonstrated a significant reduction in segmentation time for both experienced and novice users compared to standard manual segmentation. ICCs between experienced and novice users were >0.9 (excellent reliability) for all but 4 bones. DiscussionThe described semi-automated segmentation approach provides remarkable reliability and throughput advantages. Adoption of the semi-automated segmentation approach will provide standardization and reliability of bone volume measures across experienced and novice users and between institutions. The application of this model provides a considerable strategic advantage to accelerate various research opportunities in pre-clinical bone and joint analysis towards clinical translation.

A Lightweight Dangerous Liquid Detection Method Based on Depthwise Separable Convolution for X-Ray Security Inspection.

For personal safety and crime prevention, some research studies based on deep learning have achieved success in the object detection of X-ray security inspection. However, the research on dangerous liquid detection is still scarce, and most research studies are focused on the detection of some prohibited and common items. In this paper, a lightweight dangerous liquid detection method based on the Depthwise Separable convolution for X-ray security inspection is proposed. Firstly, a dataset of seven common dangerous liquids with multiple postures in two detection environments is established. Secondly, we propose a novel detection framework using the dual-energy X-ray data instead of pseudocolor images as the objects to be detected, which improves the detection accuracy and realizes the parallel operation of detection and imaging. Thirdly, in order to ensure the detection accuracy and reduce the computational consumption and the number of parameters, based on the Depthwise Separable convolution and the Squeeze-and-Excitation block, a lightweight object location network and a lightweight dangerous liquid classification network are designed as the backbone networks of our method to achieve the location and classification of the dangerous liquids, respectively. Finally, a semiautomatic labeling method is proposed to improve the efficiency of data labeling. Compared with the existing methods, the experimental results demonstrate that our method has better performance and wider applicability.

Semi-automated quantification of hair cells in the mature mouse utricle

The mouse utricle model system is the best-characterized ex vivo preparation for studies of mature mammalian hair cells (HCs). Despite the many advantages of this model system, efficient and reliable quantification of HCs from cultured utricles has been a persistent challenge with this model system. Utricular HCs are commonly quantified by counting immunolabeled HCs in regions of interest (ROIs) placed over an image of the utricle. Our data indicate that the accuracy of HC counts obtained using this method can be impacted by variability in HC density across different regions of the utricle. In addition, the commonly used HC marker myosin 7a results in a diffuse cytoplasmic stain that is not conducive to automated quantification and must be quantified manually, a labor-intensive task. Furthermore, myosin 7a immunoreactivity is retained in dead HCs, resulting in inaccurate quantification of live HCs using this marker. Here we have developed a method for semi-automated quantification of surviving HCs that combines immunoreactivity for the HC-specific transcription factor Pou4f3 with labeling of activated caspase 3/7 (AC3/7) to detect apoptotic HCs. The discrete nuclear Pou4f3 signal allowed us to utilize the binary or threshold function within ImageJ to automate HC quantification. To further streamline this process, we created an ImageJ macro that automates the process from raw image loading to a final quantified image that can be immediately evaluated for accuracy. Within this quantified image, the user can manually correct the quantification via an image overlay indicating the counted HC nuclei. Pou4f3-positive HCs that also express AC3/7 are subtracted to yield accurate counts of surviving HCs. Overall, we present a semi-automated method that is faster than manual HC quantification and identifies surviving HCs with high accuracy.