Automatic Quantification Research Articles

Deep learning-based accurate diagnosis and quantitative evaluation of microvascular invasion in hepatocellular carcinoma on whole-slide histopathology images.

Microvascular invasion (MVI) is an independent prognostic factor that is associated with early recurrence and poor survival after resection of hepatocellular carcinoma (HCC). However, the traditional pathology approach is relatively subjective, time-consuming, and heterogeneous in the diagnosis of MVI. The aim of this study was to develop a deep-learning model that could significantly improve the efficiency and accuracy of MVI diagnosis. We collected H&E-stained slides from 753 patients with HCC at the First Affiliated Hospital of Zhejiang University. An external validation set with 358 patients was selected from The Cancer Genome Atlas database. The deep-learning model was trained by simulating the method used by pathologists to diagnose MVI. Model performance was evaluated with accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve. We successfully developed a MVI artificial intelligence diagnostic model (MVI-AIDM) which achieved an accuracy of 94.25% in the independent external validation set. The MVI positive detection rate of MVI-AIDM was significantly higher than the results of pathologists. Visualization results demonstrated the recognition of micro MVIs that were difficult to differentiate by the traditional pathology. Additionally, the model provided automatic quantification of the number of cancer cells and spatial information regarding MVI. We developed a deep learning diagnostic model, which performed well and improved the efficiency and accuracy of MVI diagnosis. The model provided spatial information of MVI that was essential to accurately predict HCC recurrence after surgery.

Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer

ObjectiveThis study aimed to develop and evaluate an automatic model using artificial intelligence (AI) for quantifying vascular involvement and classifying tumor resectability stage in patients with pancreatic ductal adenocarcinoma (PDAC), primarily to support radiologists in referral centers. Resectability of PDAC is determined by the degree of vascular involvement on computed tomography scans (CTs), which is associated with considerable inter-observer variability.MethodsWe developed a semisupervised machine learning segmentation model to segment the PDAC and surrounding vasculature using 613 CTs of 467 patients with pancreatic tumors and 50 control patients. After segmenting the relevant structures, our model quantifies vascular involvement by measuring the degree of the vessel wall that is in contact with the tumor using AI-segmented CTs. Based on these measurements, the model classifies the resectability stage using the Dutch Pancreatic Cancer Group criteria as either resectable, borderline resectable, or locally advanced (LA).ResultsWe evaluated the performance of the model using a test set containing 60 CTs from 60 patients, consisting of 20 resectable, 20 borderline resectable, and 20 locally advanced cases, by comparing the automated analysis obtained from the model to expert visual vascular involvement assessments. The model concurred with the radiologists on 227/300 (76%) vessels for determining vascular involvement. The model’s resectability classification agreed with the radiologists on 17/20 (85%) resectable, 16/20 (80%) for borderline resectable, and 15/20 (75%) for locally advanced cases.ConclusionsThis study demonstrates that an AI model may allow automatic quantification of vascular involvement and classification of resectability for PDAC.Relevance statementThis AI model enables automated vascular involvement quantification and resectability classification for pancreatic cancer, aiding radiologists in treatment decisions, and potentially improving patient outcomes.Key points• High inter-observer variability exists in determining vascular involvement and resectability for PDAC.• Artificial intelligence accurately quantifies vascular involvement and classifies resectability for PDAC.• Artificial intelligence can aid radiologists by automating vascular involvement and resectability assessments.Graphical

Automatic Detection of Rice Blast Fungus Spores by Deep Learning-Based Object Detection: Models, Benchmarks and Quantitative Analysis

The severity of rice blast and its impacts on rice yield are closely related to the inoculum quantity of Magnaporthe oryzae, and automatic detection of the pathogen spores in microscopic images can provide a rapid and effective way to quantify pathogen inoculum. Traditional spore detection methods mostly rely on manual feature extraction and shallow machine learning models, and are mostly designed for the indoor counting of a single spore class, which cannot handle the interference of impurity particles in the field. This study achieved automatic detection of rice blast fungus spores in the mixture with other fungal spores and rice pollens commonly encountered under field conditions by using deep learning based object detection techniques. First, 8959 microscopic images of a single spore class and 1450 microscopic images of mixed spore classes, including the rice blast fungus spores and four common impurity particles, were collected and labelled to form the benchmark dataset. Then, Faster R-CNN, Cascade R-CNN and YOLOv3 were used as the main detection frameworks, and multiple convolutional neural networks were used as the backbone networks in training of nine object detection algorithms. The results showed that the detection performance of YOLOv3_DarkNet53 is superior to the other eight algorithms, and achieved 98.0% mean average precision (intersection over union > 0.5) and an average speed of 36.4 frames per second. This study demonstrated the enormous application potential of deep object detection algorithms in automatic detection and quantification of rice blast fungus spores.

Aberrant white matter microstructure detected by automatic fiber quantification in pediatric myelin oligodendrocyte glycoprotein antibody-associated disease

Background and ObjectivesMyelin oligodendrocyte glycoprotein antibody-associated diseases (MOGAD) is an idiopathic inflammatory demyelinating disorder in children, for which the precise damage patterns of the white matter (WM) fibers remain unclear. Herein, we utilized diffusion tensor imaging (DTI)-based automated fiber quantification (AFQ) to identify patterns of fiber damage and to investigate the clinical significance of MOGAD-affected fiber tracts. MethodsA total of 28 children with MOGAD and 31 healthy controls were included in this study. The AFQ approach was employed to track WM fiber with 100 equidistant nodes defined along each tract for statistical analysis of DTI metrics in both the entire and nodal manner. The feature selection method was used to further screen significantly aberrant DTI metrics of the affected fiber tracts or segments for eight common machine learning (ML) to evaluate their potential in identifying MOGAD. These metrics were then correlated with clinical scales to assess their potential as imaging biomarkers. ResultsIn the entire manner, significantly reduced fractional anisotropy (FA) was shown in the left anterior thalamic radiation, arcuate fasciculus, and the posterior and anterior forceps of corpus callosum in MOGAD (all p < 0.05). In the nodal manner, significant DTI metrics alterations were widely observed across 37 segments in 10 fiber tracts (all p < 0.05), mainly characterized by decreased FA and increased radial diffusivity (RD). Among them, 14 DTI metrics in seven fiber tracts were selected as important features to establish ML models, and satisfactory discrimination of MOGAD was obtained in all models (all AUC > 0.85), with the best performance in the logistic regression model (AUC = 0.952). For those features, the FA of left cingulum cingulate and the RD of right inferior frontal-occipital fasciculus were negatively and positively correlated with the expanded disability status scale (r = -0.54, p = 0.014; r = 0.43, p = 0.03), respectively. ConclusionPediatric MOGAD exhibits extensive WM fiber tract aberration detected by AFQ. Certain fiber tracts exhibit specific patterns of DTI metrics that hold promising potential as biomarkers.

Automatic Recognition and Quantification Feeding Behaviors of Nursery Pigs Using Improved YOLOV5 and Feeding Functional Area Proposals.

A novel method is proposed based on the improved YOLOV5 and feeding functional area proposals to identify the feeding behaviors of nursery piglets in a complex light and different posture environment. The method consists of three steps: first, the corner coordinates of the feeding functional area were set up by using the shape characteristics of the trough proposals and the ratio of the corner point to the image width and height to separate the irregular feeding area; second, a transformer module model was introduced based on YOLOV5 for highly accurate head detection; and third, the feeding behavior was recognized and counted by calculating the proportion of the head in the located feeding area. The pig head dataset was constructed, including 5040 training sets with 54,670 piglet head boxes, and 1200 test sets, and 25,330 piglet head boxes. The improved model achieves a 5.8% increase in the mAP and a 4.7% increase in the F1 score compared with the YOLOV5s model. The model is also applied to analyze the feeding pattern of group-housed nursery pigs in 24 h continuous monitoring and finds that nursing pigs have different feeding rhythms for the day and night, with peak feeding periods at 7:00-9:00 and 15:00-17:00 and decreased feeding periods at 12:00-14:00 and 0:00-6:00. The model provides a solution for identifying and quantifying pig feeding behaviors and offers a data basis for adjusting the farm feeding scheme.

Detection and quantitative analysis of patient-ventilator interactions in ventilated infants by deep learning networks.

The study of patient-ventilator interactions (PVI) in mechanically ventilated neonates is limited by the lack of unified PVI definitions and tools to perform large scale analyses. An observational study was conducted in 23 babies randomly selected from 170 neonates who were ventilated with SIPPV-VG, SIMV-VG or PSV-VG mode for at least 12 h. 500 breaths were randomly selected and manually annotated from each recording to train convolutional neural network (CNN) models for PVI classification. The average asynchrony index (AI) over all recordings was 52.5%. The most frequently occurring PVIs included expiratory work (median: 28.4%, interquartile range: 23.2-40.2%), late cycling (7.6%, 2.8-10.2%), failed triggering (4.6%, 1.2-6.2%) and late triggering (4.4%, 2.8-7.4%). Approximately 25% of breaths with a PVI had two or more PVIs occurring simultaneously. Binary CNN classifiers were developed for PVIs affecting ≥1% of all breaths (n = 7) and they achieved F1 scores of >0.9 on the test set except for early triggering where it was 0.809. PVIs occur frequently in neonates undergoing conventional mechanical ventilation with a significant proportion of breaths containing multiple PVIs. We have developed computational models for seven different PVIs to facilitate automated detection and further evaluation of their clinical significance in neonates. The study of patient-ventilator interactions (PVI) in mechanically ventilated neonates is limited by the lack of unified PVI definitions and tools to perform large scale analyses. By adapting a recent taxonomy of PVI definitions in adults, we have manually annotated neonatal ventilator waveforms to determine prevalence and co-occurrence of neonatal PVIs. We have also developed binary deep learning classifiers for common PVIs to facilitate their automatic detection and quantification.

Geometric remodeling of tricuspid valve in pulmonary hypertension and its correlation with pulmonary hypertension severity: a prospectively case-control study using four-dimensional automatic tricuspid valve quantification technology.

Evaluation of the tricuspid valve (TV) is crucial for clinical decision making and post-treatment follow-up in pulmonary hypertension (PH) patients. However, little is known about 4-dimensional (4D) TV geometric remodeling in patients with PH. The aim of this study was to examine the 4D geometry of the TV in PH and its correlation with PH severity. A total of 74 PH patients with mean pulmonary arterial pressure >25 mmHg and 15 age- and gender-matched healthy individuals were consecutively included from September 2017 to December 2018 in National Center for Cardiovascular Diseases, Fuwai Hospital. All participants underwent 2-dimensional (2D) and 4D transthoracic echocardiography and PH patients underwent right heart catheterization (RHC) within 48 hours of echocardiography. TV geometry was analyzed using a dedicated 4D echocardiography from the right ventricular-focused apical view. Compared with controls, PH patients had significantly larger 4D tricuspid annular (TA) and TV tenting sizes except in the 2-chamber diameter. In high-quality image cases, maximal tenting height (MTH), coaptation point height, tenting volume and 4-chamber diameter had good or moderate correlation with PH severity graded according to RHC mean pulmonary artery pressure (r=0.705, r=0.644, r=0.602, r=0.472, respectively; P<0.001 for all). In multivariable linear regression analysis, PH severity was independently associated with coaptation point height (F=18.070, P<0.001 with an R2=0.647) and MTH (F=25.576, P<0.001 with an R2=0.378). Among all 4D TV parameters, MTH had the highest area under the receiver operating characteristic (ROC) curve (AUC) in high-quality image cases [AUC =0.857, 95% confidence interval (CI): 0.743-0.972; P<0.001], comparable to echocardiographic systolic pulmonary arterial pressure (AUC =0.847, 95% CI: 0.733-0.961; P<0.001). In PH, TV geometric remodeling occurs mainly in TA septal-lateral dimension and TV tenting height. Worsening PH is an independent determinant of TV coaptation point height and MTH, not TA size. MTH shows a great diagnostic potential to detect severe PH.

Towards fully automatic quantification of REM sleep without atonia according to the Sleep Innsbruck Barcelona (SINBAR) scoring method

Towards fully automatic quantification of REM sleep without atonia according to the Sleep Innsbruck Barcelona (SINBAR) scoring method

Automatic Outer Contour Detection and Quantification of Vehicles Using Monocular Vision

Oversized vehicles have the potential to collide with walls or ceilings when passing through tunnels and bridges, posing a serious threat to the health of transportation infrastructure and public safety. Hence, it is crucial to accurately and immediately detect vehicle dimensions, including length, width, and height, to avoid such accidents. Using computer vision and view geometry, this study presents a framework for automatically detecting and quantifying the outer contours of vehicles through monocular vision. First, traffic scene images are captured which are then used to create a transformation matrix of the ground surface. Second, a modified Mask region-based convolutional neural network (Mask R-CNN) is constructed to detect and segment the vehicle instances from the video frames. Finally, a view geometry-based algorithm was developed to detect the outer contours of passing vehicles and quantify their dimensions. In the field test, the accuracy of the vehicle segmentation and the identified vehicle dimensions was validated. In addition, the proposed method’s superiority was confirmed by comparing it with two other existing approaches. The comparison results show that the proposed method has better accuracy and is more convenient to use since it does not require a premeasured reference. In addition, the developed method can accurately identify not only the dimensions of vehicles parallel to the road but also vehicles that are changing lanes or making a U-turn.

A Gibbs Posterior Framework for Fair Clustering.

The rise of machine learning-driven decision-making has sparked a growing emphasis on algorithmic fairness. Within the realm of clustering, the notion of balance is utilized as a criterion for attaining fairness, which characterizes a clustering mechanism as fair when the resulting clusters maintain a consistent proportion of observations representing individuals from distinct groups delineated by protected attributes. Building on this idea, the literature has rapidly incorporated a myriad of extensions, devising fair versions of the existing frequentist clustering algorithms, e.g., k-means, k-medioids, etc., that aim at minimizing specific loss functions. These approaches lack uncertainty quantification associated with the optimal clustering configuration and only provide clustering boundaries without quantifying the probabilities associated with each observation belonging to the different clusters. In this article, we intend to offer a novel probabilistic formulation of the fair clustering problem that facilitates valid uncertainty quantification even under mild model misspecifications, without incurring substantial computational overhead. Mixture model-based fair clustering frameworks facilitate automatic uncertainty quantification, but tend to showcase brittleness under model misspecification and involve significant computational challenges. To circumnavigate such issues, we propose a generalized Bayesian fair clustering framework that inherently enjoys decision-theoretic interpretation. Moreover, we devise efficient computational algorithms that crucially leverage techniques from the existing literature on optimal transport and clustering based on loss functions. The gain from the proposed technology is showcased via numerical experiments and real data examples.

White matter microstructure alterations in type 2 diabetes mellitus and its correlation with cerebral small vessel disease and cognitive performance

Microstructural abnormalities of white matter fiber tracts are considered as one of the etiology of diabetes-induced neurological disorders. We explored the cerebral white matter microstructure alteration accurately, and to analyze its correlation between cerebral small vessel disease (CSVD) burden and cognitive performance in type 2 diabetes mellitus (T2DM). The clinical-laboratory data, cognitive scores [including mini-mental state examination (MMSE), Montreal cognitive assessment (MoCA), California verbal learning test (CVLT), and symbol digit modalities test (SDMT)], CSVD burden scores of the T2DM group (n = 34) and healthy control (HC) group (n = 21) were collected prospectively. Automatic fiber quantification (AFQ) was applied to generate bundle profiles along primary white matter fiber tracts. Diffusion tensor images (DTI) metrics and 100 nodes of white matter fiber tracts between groups were compared. Multiple regression analysis was used to analyze the relationship between DTI metrics and cognitive scores and CSVD burden scores. For fiber-wise and node-wise, DTI metrics in some commissural and association fibers were increased in T2DM. Some white matter fiber tracts DTI metrics were independent predictors of cognitive scores and CSVD burden scores. White matter fiber tracts damage in patients with T2DM may be characterized in specific location, especially commissural and association fibers. Aberrational specific white matter fiber tracts are associated with visuospatial function and CSVD burden.

Assessment of left atrial function in patients with metabolic syndrome by four-dimensional automatic left atrial quantification

ObjectiveThis study aimed at assessing the changes of left atrial (LA) volume and strain function in metabolic syndrome (MS) patients using four-dimensional automatic left atrial quantification (4D-LAQ) and exploring independent correlative factors for LA function. MethodsA total of 110 MS patients and 70 normal controls were selected and assigned into the MS group and the control group, respectively. Echocardiogram parameters were routinely examined and the thickness of epicardial adipose tissue (EAT) were measured with a parasternal long axis of left ventricle(LV). The LA volume and strain parameters were determined using 4D-LAQ. The independent correlation factors for LA strain parameters in MS patients were investigated through linear regression analysis. ResultsCompared with the control group, LA volume parameters were increased in the MS group, LA strain parameters and LA emptying fraction (LAEF) were decreased (all P < 0.05). EAT thickness is associated with LA reservoir longitudinal strain (LASr), conduit longitudinal strain (LAScd), reservoir circumferential strain (LASr-c), and conduit circumferential strain (LAScd-c) (all P < 0.05). LA contraction longitudinal (LASct) and circumferential strain (LASct-c) were not statistically significant. Regression analysis results show that systolic blood pressure (SBP) and triglyceride (TG) are independent correlative factors. Intra-observer and inter-observer repeatability test showed that the LA parameters examined by 4D-LAQ had good agreement. Conclusions4D-LAQ is capable of effectively assessing the LA function in MS patients and providing a useful reference for clinical diagnosis. SBP and TG serve as the independent correlative factors for LA function.

Feasibility of Adapting Various Tumor-to-normal Bone Ratio Images on an Automatic Quantification Package for Phantom-based Image Quality Assessment in Bone SPECT

We investigated the impact of the tumor-to-normal bone ratio (TNR) on the concordance rate between a detectability score classified by software (DSsoft) using an automatic quantification package for bone SPECT (Hone Graph) and a detectability score classified by visual assessment (DSvisual), and considered the feasibility of applying this software to various TNR images. 99mTc solution was filled into a SIM2 bone phantom to achieve TNRs of 4, 6, and 8, performed by dynamic SPECT acquisitions performed for 12 minutes; reconstructions were performed using ordered subset expectation maximization at timepoints ranging from 4 to 12 minutes. This yielded a total of 384 lesions (96 SPECT images). We investigated the weighted kappa (κw) coefficient between DSsoft and DSvisual at various TNRs and evaluated the change in analysis accuracy before and after applying newly created analysis parameters. DSs were defined on a 4-point scale (4: excellent, 3: adequate, 2: average, 1: poor), and visual evaluations were conducted by three board-certified nuclear medicine technologists. The κw coefficients between DSsoft and DSvisual were 0.75, 0.97, and 0.93 for TNRs 4, 6, and 8, respectively, with each κw coefficient being significant (p<0.01). In the TNR 4 image group, κw coefficients significantly increased with the implementation of new parameters proposed in this study. We concluded that the software's automatic analysis would be closer to a visual assessment within the TNR range of 4-8 and that applying new parameters derived from this study to images with TNR 4 further improves the software's automatic analysis accuracy of DSsoft. We suggest that software will be a useful tool for optimizing bone SPECT imaging techniques.

Multi-task localization of the hemidiaphragms and lung segmentation in portable chest X-ray images of COVID-19 patients.

The COVID-19 can cause long-term symptoms in the patients after they overcome the disease. Given that this disease mainly damages the respiratory system, these symptoms are often related with breathing problems that can be caused by an affected diaphragm. The diaphragmatic function can be assessed with imaging modalities like computerized tomography or chest X-ray. However, this process must be performed by expert clinicians with manual visual inspection. Moreover, during the pandemic, the clinicians were asked to prioritize the use of portable devices, preventing the risk of cross-contamination. Nevertheless, the captures of these devices are of a lower quality. The automatic quantification of the diaphragmatic function can determine the damage of COVID-19 on each patient and assess their evolution during the recovery period, a task that could also be complemented with the lung segmentation. We propose a novel multi-task fully automatic methodology to simultaneously localize the position of the hemidiaphragms and to segment the lung boundaries with a convolutional architecture using portable chest X-ray images of COVID-19 patients. For that aim, the hemidiaphragms' landmarks are located adapting the paradigm of heatmap regression. The methodology is exhaustively validated with four analyses, achieving an 82.31% 2.78% of accuracy when localizing the hemidiaphragms' landmarks and a Dice score of 0.9688 0.0012 in lung segmentation. The results demonstrate that the model is able to perform both tasks simultaneously, being a helpful tool for clinicians despite the lower quality of the portable chest X-ray images.

Multi-feature vision transformer for automatic defect detection and quantification in composites using thermography

This paper proposes a novel multi-feature vision transformer model for automatic defect detection and quantification in composites using thermography. Firstly, a sampling strategy for infrared data is proposed to address the issues of data class overlap and imbalance. Secondly, multiple feature fusion is employed to aggregate various important infrared features that exhibit strong correlations with defects. Furthermore, a multi-feature vision transformer (VIT) model that leverages self-attention mechanisms to capture global context and long-range dependencies in the composite images is developed. Experiments are performed to verify the effectiveness of the proposed method. The results show that the proposed method has excellent performance in terms of both accuracy and generalization capability.

An open-source machine-learning approach for obtaining high-quality quantitative wood anatomy data from E. grandis and P. radiata xylem

Quantitative wood anatomy is a subfield in dendrochronology that requires effective open-source image analysis tools. In this research, the bioimage analysis software QuPath (v0.4.4) is introduced as a candidate for accurately quantifying the cellular properties of the xylem in an automated manner. Additionally, the potential of QuPath to detect the transition of early- to latewood tracheids over the growing season was evaluated to assess a potential application in dendroecological studies. Various algorithms in QuPath were optimized to quantify different xylem cell types in Eucalyptus grandis and the transition of early- to latewood tracheids in Pinus radiata. These algorithms were coded into cell detection scripts for automatic quantification of stem microsections and compared to a manually curated method to assess the accuracy of the cell detections. The automatic cell detection approach, using QuPath, has been validated to be reproducible with an acceptable error when assessing fibers, vessels, early- and latewood tracheids. However, further optimization for parenchyma is still required. This proposed method developed in QuPath provides a scalable and accurate approach for quantifying anatomical features in stem microsections. With minor amendments to the detection and classification algorithms, this strategy is likely to be viable in other plant species.

A transformer-based deep learning method for automatic pixel-level crack detection and feature quantification

Purpose Crack detection of pavement is a critical task in the periodic survey. Efficient, effective and consistent tracking of the road conditions by identifying and locating crack contributes to establishing an appropriate road maintenance and repair strategy from the promptly informed managers but still remaining a significant challenge. This research seeks to propose practical solutions for targeting the automatic crack detection from images with efficient productivity and cost-effectiveness, thereby improving the pavement performance.Design/methodology/approach This research applies a novel deep learning method named TransUnet for crack detection, which is structured based on Transformer, combined with convolutional neural networks as encoder by leveraging a global self-attention mechanism to better extract features for enhancing automatic identification. Afterward, the detected cracks are used to quantify morphological features from five indicators, such as length, mean width, maximum width, area and ratio. Those analyses can provide valuable information for engineers to assess the pavement condition with efficient productivity.Findings In the training process, the TransUnet is fed by a crack dataset generated by the data augmentation with a resolution of 224 × 224 pixels. Subsequently, a test set containing 80 new images is used for crack detection task based on the best selected TransUnet with a learning rate of 0.01 and a batch size of 1, achieving an accuracy of 0.8927, a precision of 0.8813, a recall of 0.8904, an F1-measure and dice of 0.8813, and a Mean Intersection over Union of 0.8082, respectively. Comparisons with several state-of-the-art methods indicate that the developed approach in this research outperforms with greater efficiency and higher reliability.Originality/value The developed approach combines TransUnet with an integrated quantification algorithm for crack detection and quantification, performing excellently in terms of comparisons and evaluation metrics, which can provide solutions with potentially serving as the basis for an automated, cost-effective pavement condition assessment scheme.

Automated pixel-level crack detection and quantification using deep convolutional neural networks for structural condition assessment

Crack detection is a crucial task in assessing the condition of concrete structures. Herein, a novel deep learning method based on convolutional neural networks, referred to as R-FPANet, is proposed for crack detection. The R-FPANet performs automatic segmentation and quantification of crack morphology at the pixel level. In this methodology, the modularization concept based on the following three modules is adopted: ResNet-50 is chosen as the backbone to extract features from images, the Feature Pyramid Network with Dense Block is integrated to promote the fusion of both shallow and deep features as well as enhance feature reuse, and self-attention mechanisms such as Channel Attention Module and Position Attention Module are introduced to strengthen the dependency between features. Based on the crack segmentation results, a suitably established framework is developed for quantitative analysis of the major geometric parameters, including crack area, crack length, crack mean width and crack max-width at the pixel level. To verify the effectiveness of the proposed method, a large-scale concrete crack image dataset was produced and carefully labeled at the pixel level and then utilized to train the model. Finally, our experiments reveal that the proposed approach achieves an Intersection over Union of 83.07%, further indicating that the segmentation performance of the proposed method is better than the state-of-the-art models and also confirming that the crack quantification results are close to reality. Overall, the proposed method performs well, contributing to crack detection and quantification with great potential for practical use.

Automatic Quantification of Enlarged Perivascular Space in Patients With Traumatic Brain Injury Using Super-Resolution of T2-Weighted Images.

The perivascular space (PVS) is important to brain waste clearance and brain metabolic homeostasis. Enlarged PVS (ePVS) becomes visible on magnetic resonance imaging (MRI) and is best appreciated on T2-weighted (T2w) images. However, quantification of ePVS is challenging because standard-of-care T1-weighted (T1w) and T2w images are often obtained via two-dimensional (2D) acquisition, whereas accurate quantification of ePVS normally requires high-resolution volumetric three-dimensional (3D) T1w and T2w images. The purpose of this study was to investigate the use of a deep-learning-based super-resolution (SR) technique to improve ePVS quantification from 2D T2w images for application in patients with traumatic brain injury (TBI). We prospectively recruited 26 volunteers (age: 31 ± 12 years, 12 male/14 female) where both 2D T2w and 3D T2w images were acquired along with 3D T1w images to validate the ePVS quantification using SR T2w images. We then applied the SR method to retrospectively acquired 2D T2w images in 41 patients with chronic TBI (age: 41 ± 16 years, 32 male/9 female). ePVS volumes were automatically quantified within the whole-brain white matter and major brain lobes (temporal, parietal, frontal, occipital) in all subjects. Pittsburgh Sleep Quality Index (PSQI) scores were obtained on all patients with TBI. Compared with the silver standard (3D T2w), in the validation study, the SR T2w provided similar whole-brain white matter ePVS volume (r = 0.98, p < 0.0001), and similar age-related ePVS burden increase (r = 0.80, p < 0.0001). In the patient study, patients with TBI with poor sleep showed a higher age-related ePVS burden increase than those with good sleep. Sleep status is a significant interaction factor in the whole brain (p = 0.047) and the frontal lobe (p = 0.027). We demonstrate that images produced by SR of 2D T2w images can be automatically analyzed to produce results comparable to those obtained by 3D T2 volumes. Reliable age-related ePVS burden across the whole-brain white matter was observed in all subjects. Poor sleep, affecting the glymphatic function, may contribute to the accelerated increase of ePVS burden following TBI.

A hybrid Machine Learning unmixing method for automatic analysis of [formula omitted]-spectra with spectral variability

Automatic identification and quantification of γ-emitting radionuclides, taking into account spectral deformations due to γ-interactions in radioactive source surroundings, is a challenging task in the nuclear field. In that context, this paper presents a Machine Learning approach based on autoencoder that can learn a model for the spectral signatures of γ-emitters with variability. Training and test datasets were obtained by means of simulated γ-spectra computed with the Geant4 simulation code according to increasing material thicknesses (steel, lead). A novel hybrid unmixing algorithm combining a pretrained autoencoder is studied for joint estimation of spectral signatures and counting in the case of mixtures of four radionuclides (57Co, 60Co, 133Ba, 137Cs). The investigations were carried out to account for spectral deformations due to attenuation, Compton scattering and fluorescence at high and low statistics. This study demonstrates the validity of this novel hybrid approach combining Machine Learning and Maximum Likelihood for the automatic full-spectrum analysis of γ-spectra.