Ground Truth Reference Research Articles

Comparative Study of Traditional and Deep-Learning Denoising Approaches for Image-Based Petrophysical Characterization of Porous Media

Digital rock physics has seen significant advances owing to improvements in micro-computed tomography (MCT) imaging techniques and computing power. These advances allow for the visualization and accurate characterization of multiphase transport in porous media. Despite such advancements, image processing and particularly the task of denoising MCT images remains less explored. As such, selection of proper denoising method is a challenging optimization exercise of balancing the tradeoffs between minimizing noise and preserving original features. Despite its importance, there are no comparative studies in the geoscience domain that assess the performance of different denoising approaches, and their effect on image-based rock and fluid property estimates. Further, the application of machine learning and deep learning-based (DL) denoising models remains under-explored. In this research, we evaluate the performance of six commonly used denoising filters and compare them to five DL-based denoising protocols, namely, noise-to-clean (N2C), residual dense network (RDN), and cycle consistent generative adversarial network (CCGAN)—which require a clean reference (ground truth), as well as noise-to-noise (N2N) and noise-to-void (N2V)—which do not require a clean reference. We also propose hybrid or semi-supervised DL denoising models which only require a fraction of clean reference images. Using these models, we investigate the optimal number of high-exposure reference images that balances data acquisition cost and accurate petrophysical characterization. The performance of each denoising approach is evaluated using two sets of metrics: (1) standard denoising evaluation metrics, including peak signal-to-noise ratio (PSNR) and contrast-to-noise ratio (CNR), and (2) the resulting image-based petrophysical properties such as porosity, saturation, pore size distribution, phase connectivity, and specific surface area (SSA). Petrophysical estimates show that most traditional filters perform well when estimating bulk properties but show large errors for pore-scale properties like phase connectivity. Meanwhile, DL-based models give mixed outcomes, where supervised methods like N2C show the best performance, and an unsupervised model like N2V shows the worst performance. N2N75, which is a newly proposed semi-supervised variation of the N2N model, where 75% of the clean reference data is used for training, shows very promising outcomes for both traditional denoising performance metrics and petrophysical properties including both bulk and pore-scale measures. Lastly, N2C is found to be the most computationally efficient, while CCGAN is found to be the least, among the DL-based models considered in this study. Overall, this investigation shows that application of sophisticated supervised and semi-supervised DL-based denoising models can significantly reduce petrophysical characterization errors introduced during the denoising step. Furthermore, with the advancement of semi-supervised DL-based models, requirement of clean reference or ground truth images for training can be reduced and deployment of fast X-ray scanning can be made possible.

Using synthetic chromosome controls to evaluate the sequencing of difficult regions within the human genome

BackgroundNext-generation sequencing (NGS) can identify mutations in the human genome that cause disease and has been widely adopted in clinical diagnosis. However, the human genome contains many polymorphic, low-complexity, and repetitive regions that are difficult to sequence and analyze. Despite their difficulty, these regions include many clinically important sequences that can inform the treatment of human diseases and improve the diagnostic yield of NGS.ResultsTo evaluate the accuracy by which these difficult regions are analyzed with NGS, we built an in silico decoy chromosome, along with corresponding synthetic DNA reference controls, that encode difficult and clinically important human genome regions, including repeats, microsatellites, HLA genes, and immune receptors. These controls provide a known ground-truth reference against which to measure the performance of diverse sequencing technologies, reagents, and bioinformatic tools. Using this approach, we provide a comprehensive evaluation of short- and long-read sequencing instruments, library preparation methods, and software tools and identify the errors and systematic bias that confound our resolution of these remaining difficult regions.ConclusionsThis study provides an analytical validation of diagnosis using NGS in difficult regions of the human genome and highlights the challenges that remain to resolve these difficult regions.

Estimation of Reference Voltages for Time-Difference Electrical Impedance Tomography

Electrical impedance tomography (EIT), as a merging technology, has been widely used in the industrial and clinical fields. However, the causes of the uncertainty of measuring reference voltages, which are affected by medium temperature, measurement errors, and reference conductivity distribution that varies with the patient’s posture, have brought obstacles to applying EIT in industry and medicine. In the paper, two methods: the Multiple Measurements (MM) method and the deep learning method, convolutional neural network (CNN) are proposed to establish the nonlinear mapping between measurement voltages and reference voltages. The novelty of the article is firstly adopting the deep learning method to estimate the reference voltages from measurement voltages for the time-difference EIT. Both static experiments—water tank experiments and dynamic experiments—two-phase flow experiments were carried out. Compared with the two existing estimation methods: best homogeneous (BH) approximation and measurement-scale feature (MSF), and the proposed MM method, the deep learning method shows excellent results in quantitative analysis of the relative errors of reference voltages and ground truth. In addition, the CNN method also displays a better performance in qualitative analysis in terms of the reconstructed tomographic images. The study shows the potential to real-time estimate the reference voltages for time-difference EIT in the industrial and medical fields.

An Efficient Machine Learning Enabled Non-Destructive Technique for Remote Monitoring of Sugarcane Crop Health

Crop health can be predicted based on various biochemical variables of crops, which include chlorophyll, phenol, carbohydrate, lipid, protein, hydrogen peroxide, and proline as these variables play a critical role in maintaining the intricate phytochemistry of crop plants. In-situ monitoring of the above-mentioned variables is very cumbersome and laborious, so it is atrociously needed to identify some alternatives to monitor these variables in crop plants. Assessing these variables using satellite data may be a good choice provided it has a high spatial and temporal resolution. Sentinel-2 satellite sensor contains VNIR/SWIR spectral region, two red-edge bands, and also has good spatial as well as temporal resolution so it may be the finest option. Precise information of the field is required for the development of a retrieval algorithm for which the drone data is used, as it is highly accurate ground truth reference data. In previous studies, the researchers have primarily focused on the monitoring of biophysical and morphological parameters of crop plants like leaf area index, plant height, and stomatal conductance using these spectral features. Because monitoring biochemical variables of crop plants using satellite derivatives is still a difficult undertaking for academics, just a few studies have been published. As a result, in this study, an attempt is made to establish a methodology for monitoring sugarcane crop biochemical characteristics utilising satellite-derived variables. Satellite derivatives, i.e., vegetation indices are extracted using Sentinel-2 data while biochemical variables of the crop (as mentioned above) are analyzed using leaf samples in the laboratory using optimized protocols. Subsequently, a Machine learning-based Gaussian process regression model is developed for all the biochemical variables using the different combinations of vegetation indices. The developed model showed promising results with R² greater than 0.7 and NRMSE less than 0.2 thus holding good potential for effective monitoring the crop health condition remotely.

Bivariate Based Susceptibility Mapping for Gully Erosion in Wanjoga River Catchment Upper Tana Basin, Kenya

Gullies occur in semi-arid regions characterized by rainfall variability and seasonality, increased overland flow, affecting ecological fragility of an area. In most gully prone areas, extent of land affected by gullies is increasing. Thus, predicting susceptibility to gully erosion in semi-arid environment is an important step towards effectively rehabilitating and prevention against gully erosion. Proneness to gully occurrence was assessed against; Land cover/land use, slope, soil characteristics, rainfall variability and elevation, and modelled using geographical information system (GIS)-based bivariate statistical approach. Objectives of the study were; a) to assess influence of geomorphological factors on gully erosion, b) analyze and develop gully erosion susceptibility map, c) verify gully susceptibility images using error matrix of class labels in classified map against ground truth reference data. Total of 66 gullied areas (width and depth ≥ ranging 0.5), were mapped using 15m resolution Landsat images for 2018 and field surveys to estimate susceptibility to gully erosion by Global Mapper software in GIS. The images were verified using 120 pixels of known 15 gully presence or absence to produce an error matrix based on comparison of actual outcomes to predicted outcomes. Influence of conditioning factors to gully erosion showed a significant positive relationship between gully susceptibility and gully conditioning factors with consistency value; CR =0.097; value< 0.1, indicating, individual conditioning factors had an importance in influencing gully erosion. Slope (43%) and soil lithotype (25%), most influenced gully susceptibility, while land cover/land use (12%) and rainfall (12%) had least impact. Verification results showed satisfactory agreement between susceptibility map and field data on gullied areas at approximately 76.2%, an error of positive value of 4% and a negative value of 7%. Thus, production of susceptibility map by bivariate statistical method represents a useful tool for ending long and short-term gully emergencies by planning conservation of semi-arid regions.

Efficiency of +IDonBlender Photogrammetric Tool in Facial Prosthetics Rehabilitation – An Evaluation Study

Several open-source 3D modeling software tools have recently been featured to reconstruct a 3D image-based model using Structure from Motion (SfM) algorithms such as +IDonBlender. It is, therefore, necessary to evaluate the accuracy of the models extracted from this tool to prove effectiveness for different applications. This paper aims to evaluate the +IDonBlender methodology tool in rehabilitating facial deformations. +IDonBlender is an add-on tool programmed within Blender software and designed for medical applications. In this research, two individuals from different genders have volunteered to contribute to this study, one with severe facial deformation and the other is healthy with no defects. To assess the robustness of the derived digital model from the +IDonBlender methodology, Agisoft Metashape was used to process the data and create a reference model for comparison purposes. Various scenarios were followed for evaluation: (i) scaling the model based on reference ground truth points, (ii) scaling the model based on known real distance between two reference points, and (iii) cloud-to-mesh (C2M) analysis was applied to individual scenarios to assess the accuracy of the +IDonBlender model through cloud compare analysis. Next, the density analysis of the model was also used to investigate the model resolution for further post-processing and prototyping. The results show that the variation between the tested and the reference models in terms of coordinates and distance measurements was (0.470 mm) and (0.471mm), respectively. Despite the fact that the +IDonBlender model resolution was lower than the Metashape model, the overall results delivered acceptable geometric error values. Therefore, following visual and statistical point clouds data analysis, one can claim the robustness of the +IDonBlender 3D modeling tool for maxillofacial rehabilitation, surgical planning and other clinical applications.

BioCPPNet: automatic bioacoustic source separation with deep neural networks

We introduce the Bioacoustic Cocktail Party Problem Network (BioCPPNet), a lightweight, modular, and robust U-Net-based machine learning architecture optimized for bioacoustic source separation across diverse biological taxa. Employing learnable or handcrafted encoders, BioCPPNet operates directly on the raw acoustic mixture waveform containing overlapping vocalizations and separates the input waveform into estimates corresponding to the sources in the mixture. Predictions are compared to the reference ground truth waveforms by searching over the space of (output, target) source order permutations, and we train using an objective function motivated by perceptual audio quality. We apply BioCPPNet to several species with unique vocal behavior, including macaques, bottlenose dolphins, and Egyptian fruit bats, and we evaluate reconstruction quality of separated waveforms using the scale-invariant signal-to-distortion ratio (SI-SDR) and downstream identity classification accuracy. We consider mixtures with two or three concurrent conspecific vocalizers, and we examine separation performance in open and closed speaker scenarios. To our knowledge, this paper redefines the state-of-the-art in end-to-end single-channel bioacoustic source separation in a permutation-invariant regime across a heterogeneous set of non-human species. This study serves as a major step toward the deployment of bioacoustic source separation systems for processing substantial volumes of previously unusable data containing overlapping bioacoustic signals.

A method for T1 and T2 relaxation times validation and harmonization as a support to MRI mapping

We present a proof-of-concept study focusing on a method for the intra- and inter-center validation and harmonization of data obtained from MRI T1 and T2 maps. The method is based on a set of MnCl2 samples that provide in-scan ground-truth reference values regardless of the details of the MRI protocol. The relaxation times of MnCl2 aqueous solutions were first measured by means of an NMR laboratory relaxometer, as a function of concentration and temperature. The obtained T1 and T2 values, once renormalized at the scanner temperature, were used as reference values for the MRI mapping measurements of the MnCl2 relaxation times. By using different clinical MRI scanners and sequences, we found a good agreement for standard and turbo sequences (limits of agreement: 5% for IR, SE, IR-TSE; 10% for TSE), while an under-estimation and an over-estimation were found respectively for MOLLI and T2-prep TrueFISP, as already reported in the literature. The linearity of the relaxation rates with the concentration predicted by the Solomon-Bloembergen-Morgan theory was observed for every dataset at all temperatures, except for T2-prep TrueFISP maps results. Some preliminary results of an in vivo experiment are also presented.

An Open-Source Deep Learning Network for Reconstruction of High-Resolution OCT Angiograms of Retinal Intermediate and Deep Capillary Plexuses.

PurposeWe propose a deep learning–based image reconstruction algorithm to produce high-resolution optical coherence tomographic angiograms (OCTA) of the intermediate capillary plexus (ICP) and deep capillary plexus (DCP).MethodsIn this study, 6-mm × 6-mm macular scans with a 400 × 400 A-line sampling density and 3-mm × 3-mm scans with a 304 × 304 A-line sampling density were acquired on one or both eyes of 180 participants (including 230 eyes with diabetic retinopathy and 44 healthy controls) using a 70-kHz commercial OCT system (RTVue-XR; Optovue, Inc., Fremont, California, USA). Projection-resolved OCTA algorithm removed projection artifacts in voxel. ICP and DCP angiograms were generated by maximum projection of the OCTA signal within the respective plexus. We proposed a deep learning–based method, which receives inputs from registered 3-mm × 3-mm ICP and DCP angiograms with proper sampling density as the ground truth reference to reconstruct 6-mm × 6-mm high-resolution ICP and DCP en face OCTA. We applied the same network on 3-mm × 3-mm angiograms to enhance these images further. We evaluated the reconstructed 3-mm × 3-mm and 6-mm × 6-mm angiograms based on vascular connectivity, Weber contrast, false flow signal (flow signal erroneously generated from background), and the noise intensity in the foveal avascular zone.ResultsCompared to the originals, the Deep Capillary Angiogram Reconstruction Network (DCARnet)–enhanced 6-mm × 6-mm angiograms had significantly reduced noise intensity (ICP, 7.38 ± 25.22, P < 0.001; DCP, 11.20 ± 22.52, P < 0.001), improved vascular connectivity (ICP, 0.95 ± 0.01, P < 0.001; DCP, 0.96 ± 0.01, P < 0.001), and enhanced Weber contrast (ICP, 4.25 ± 0.10, P < 0.001; DCP, 3.84 ± 0.84, P < 0.001), without generating false flow signal when noise intensity lower than 650. The DCARnet-enhanced 3-mm × 3-mm angiograms also reduced noise, improved connectivity, and enhanced Weber contrast in 3-mm × 3-mm ICP and DCP angiograms from 101 eyes. In addition, DCARnet preserved the appearance of the dilated vessels in the reconstructed angiograms in diabetic eyes.ConclusionsDCARnet can enhance 3-mm × 3-mm and 6-mm × 6-mm ICP and DCP angiogram image quality without introducing artifacts.Translational RelevanceThe enhanced 6-mm × 6-mm angiograms may be easier for clinicians to interpret qualitatively.

Human-Level Comparable Control Volumes Mapping With an Unsupervised-Learning Model for CT-Guided Radiotherapy

To develop an unsupervised deep learning model with auto-mapped control volume (CV) from daily patient positioning CT (dCT) to planning computed tomography (pCT) for highly accurate patient positioning.An unsupervised learning framework is proposed to automatically generate the couch shifts (translations and rotations) for mapping CVs from dCT to pCT. Inputs to the network are the dCT, the pCT, and the CVs' locations within the pCT. The outputs are the transformational parameters of the dCT for head-and-neck cancer (HNC) patient positioning. We train the network to maximize image similarity between the CV in the pCT and dCT using normalized cross-correlation. We used a total of 158 HNC patients with 554 CT scans for network evaluation. Each patient underwent several CT scans at different time points. For the test cases, couch shifts are obtained by averaging translational and rotational parameters derived with different CVs. These means are then compared to ground-truth reference shifts obtained by the alignment of bony landmarks identified by an experienced radiation oncologist.Systematic/random positioning errors between the model prediction and the reference are smaller than 0.47/1.13 mm and 0.17/0.29° in translations and rotations, respectively. Pearson's correlation coefficient between model predictions and reference values exceeded 0.98. In comparison to standard registrations, the proposed method increased the proportion of cases registered within clinically accepted tolerance from 66.67% to 90.91%.A novel unsupervised learning technique was established to map CVs from pCT to dCT for HNC patient positioning. Our results show that fast and highly accurate HNC patient positioning is achievable by leveraging state-of-the-art deep learning strategies.

Novel architecture with selected feature vector for effective classification of mitotic and non-mitotic cells in breast cancer histology images

The paper focuses on the detection of mitosis in breast cancer. Detection methods in vogue rely heavily on visual inspection and assessment of histology images by trained pathologists, so the validation of results is a time-consuming process. Even accuracy wise, there remains room for improvement. This calls for high accuracy automated systems to replace manual assessments. Mitotic count is important because it provides us information about the aggressiveness of the tumour cells i.e. how rapidly it is spreading in the human body. To address this research gap, the current study is devoted to construct a novel framework utilizing neural network-based concepts along with reduced feature vectors and multiple machine learning techniques to classify the mitotic and non-mitotic cells. The dominant features in the detection of mitosis are texture features, therefore the texture of cells is used to derive the efficient reduced feature vectors which plays a significant role in identifying cancerous cells. During the feature engineering process, the features that distinguish a cancer cell from the normal cells were identified. Using these features as the base features, extraction with multiple techniques like GLCM, LBP and LTP along with classification algorithms like SVM, Naive Bayes and Random Forest were applied to the source dataset of the images, whose ground truth reference was available. Inspiring from Neural Networks, the proposed architecture allocates different weights to different features which increases the productivity of the model. The proposed framework is a new and intelligent version of ensemble learning which makes ensemble learning a more powerful tool for accurate and high-throughput results. The proposed method outperforms techniques already reported in the literature for the detection of mitotic cells in MITOS-12, AMIDA 13, MITOS-14 and TUPAC16.

Evaluation of Subseasonal-to-Seasonal (S2S) precipitation forecast from the North American Multi-Model ensemble phase II (NMME-2) over the contiguous U.S.

The second phase of the North America Multi-Model Ensemble (NMME-2) provides globally available Subseasonal-to-Seasonal (S2S) precipitation forecasts with a daily resolution. The S2S precipitation forecasts are getting increasing attention for their potentials in providing hydrometeorological forcing information for water resources planning at an extended range. However, the forecast skills of many existing S2S forecast products will significantly decrease when the lead time increases, hindering their applicability for watershed-scale hydrologic modeling. Therefore, forecast validation and large-scale evaluation are of great importance for water resources planning and hydrological applications. In this study, we comprehensively evaluate the S2S precipitation forecasts from the NMME-2 dataset over the contiguous United States (CONUS) and during the study period from 1982 to 2011. Three aspects of precipitation forecast capabilities are compared and analyzed: bias, skill scores, and the ability to predict extreme precipitation events. The Parameter-elevation Regressions on Independent Slopes Model (PRISM) is used as ground truth reference. Differs from other regional forecast validation study, we further examined and analyzed the dependences of NMME-2 precipitation forecast skills according to different seasonality, geographical locations, and lead times. Results show that the forecast biases are not sensitive to lead times but are seasonally dependent of all NMME-2 models. Overestimations are found in the Western U.S. in cooler seasons while underestimations are observed in the central regions of the U.S. in warmer seasons. The forecast skill of all individual NMME-2 models generally decreases as increases of lead times. The simple model averaging (SMA) of five NMME-2 models demonstrates a higher forecast skill than any individual NMME-2 models. Spatially, the highest forecast skill scores are observed at coastal areas in the Western U.S. with an one-week lead time. As compared to the historical resampled forecasts, NMME-2 also shows better performance in predicting extreme precipitation events above 99% percentiles and below 1% percentiles with higher probability of detections and lower false alarm ratios. The obtained results suggest the great potentials of NMME-2 precipitation forecasts in assisting ensemble hydrologic forecasts at the S2S scale over the CONUS.

Comparison of different deep learning architectures for synthetic CT generation from MR images.

Among the different available methods for synthetic CT generation from MR images for the task of MR-guided radiation planning, the deep learning algorithms have and do outperform their conventional counterparts. In this study, we investigated the performance of some most popular deep learning architectures including eCNN, U-Net, GAN, V-Net, and Res-Net for the task of sCT generation. As a baseline, an atlas-based method is implemented to which the results of the deep learning-based model are compared. A dataset consisting of 20 co-registered MR-CT pairs of the male pelvis is applied to assess the different sCT production methods' performance. The mean error (ME), mean absolute error (MAE), Pearson correlation coefficient (PCC), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR) metrics were computed between the estimated sCT and the ground truth (reference) CT images. The visual inspection revealed that the sCTs produced by eCNN, V-Net, and ResNet, unlike the other methods, were less noisy and greatly resemble the ground truth CT image. In the whole pelvis region, the eCNN yielded the lowest MAE (26.03±8.85 HU) and ME (0.82±7.06 HU), and the highest PCC metrics were yielded by the eCNN (0.93±0.05) and ResNet (0.91±0.02) methods. The ResNet model had the highest PSNR of 29.38±1.75 among all models. In terms of the Dice similarity coefficient, the eCNN method revealed superior performance in major tissue identification (air, bone, and soft tissue). All in all, the eCNN and ResNet deep learning methods revealed acceptable performance with clinically tolerable quantification errors.

Machine Learning-Enabled Determination of Diffuseness of Brain Arteriovenous Malformations from Magnetic Resonance Angiography.

The diffuseness of brain arteriovenous malformations (bAVMs) is a significant factor in surgical outcome evaluation and hemorrhagic risk prediction. However, there are still predicaments in identifying diffuseness, such as the judging variety resulting from different experience and difficulties in quantification. The purpose of this study was to develop a machine learning (ML) model to automatically identify the diffuseness of bAVM niduses using three-dimensional (3D) time-of-flight magnetic resonance angiography (TOF-MRA) images. A total of 635 patients with bAVMs who underwent TOF-MRA imaging were enrolled. Three experienced neuroradiologists delineated the bAVM lesions and identified the diffuseness on TOF-MRA images, which were considered the ground-truth reference. The U-Net-based segmentation model was trained to segment lesion areas. Eight mainstream ML models were trained through the radiomic features of segmented lesions to identify diffuseness, based on which an integrated model was built and yielded the best performance. In the test set, the Dice score, F2 score, precision, and recall for the segmentation model were 0.80 [0.72-0.84], 0.80 [0.71-0.86], 0.84 [0.77-0.93], and 0.82 [0.69-0.89], respectively. For the diffuseness identification model, the ensemble-based model was applied with an area under the Receiver-operating characteristic curves (AUC) of 0.93 (95% CI 0.87-0.99) in the training set. The AUC, accuracy, precision, recall, and F1 score for the diffuseness identification model were 0.95, 0.90, 0.81, 0.84, and 0.83, respectively, in the test set. The ML models showed good performance in automatically detecting bAVM lesions and identifying diffuseness. The method may help to judge the diffuseness of bAVMs objectively, quantificationally, and efficiently.

DETECTION OF PRIMARY OCCLUSAL CARIES USING STATIONARY INTRAORAL TOMOSYNTHESIS: A PILOT STUDY

<h3>BACKGROUND</h3> The implementation of preventive strategies has aided in the noticeable decline of caries prevalence in developed countries. With the reduction of caries prevalence, there is a higher demand for more sensitive and accurate caries detection modalities. In this study we explore the utility of stationary intraoral tomosynthesis (sIOT) in occlusal caries detection. <h3>OBJECTIVE(S)</h3> In this ex vivo diagnostic accuracy study we aim to evaluate the accuracy and assess the sensitivity, specificity, and area under the ROC curve of s-IOT in detecting primary occlusal caries and to compare the results with digital intraoral bitewings, cone beam computed tomography (CBCT), and the histologic standard reference. <h3>STUDY DESIGN</h3> Sixty de-identified extracted human teeth were selected. The teeth selected included unrestored premolar or molar teeth with fully formed roots. The occlusal surfaces exhibited a status that ranged from sound to carious lesions extending into the inner third of the dentin. Teeth with developmental defects such as hypoplasia or fluorosis were excluded from the study. The teeth were coded and randomly mounted using polyvinyl siloxane (PVS) in dental dentoforms and imaged with the 3 imaging modalities (s-IOT, IO bitewings, and CBCT). A reader study was conducted in which 3 calibrated observers were presented with the 3 imaging modalities. A wash-out period of at least 2 weeks was allowed between sessions, with 1 modality displayed per session. The readers were asked to assess their confidence in caries presence using a 5-point Likert scale and to assess caries depth. After imaging, the teeth were sectioned and histologic examination was completed to establish the ground truth reference. <h3>RESULTS</h3> Accuracy, sensitivity, specificity, and area under the ROC curve of the 3 radiographic modalities will be compared with the histologic standard reference. Results are pending final statistical analysis.

Reference in-vitro dataset for inertial-sensor-to-bone alignment applied to the tibiofemoral joint

Skin-attached inertial sensors are increasingly used for kinematic analysis. However, their ability to measure outside-lab can only be exploited after correctly aligning the sensor axes with the underlying anatomical axes. Emerging model-based inertial-sensor-to-bone alignment methods relate inertial measurements with a model of the joint to overcome calibration movements and sensor placement assumptions. It is unclear how good such alignment methods can identify the anatomical axes. Any misalignment results in kinematic cross-talk errors, which makes model validation and the interpretation of the resulting kinematics measurements challenging. This study provides an anatomically correct ground-truth reference dataset from dynamic motions on a cadaver. In contrast with existing references, this enables a true model evaluation that overcomes influences from soft-tissue artifacts, orientation and manual palpation errors. This dataset comprises extensive dynamic movements that are recorded with multimodal measurements including trajectories of optical and virtual (via computed tomography) anatomical markers, reference kinematics, inertial measurements, transformation matrices and visualization tools. The dataset can be used either as a ground-truth reference or to advance research in inertial-sensor-to-bone-alignment.

A Pseudo-Value Approach to Analyze the Semantic Similarity of the Speech of Children With and Without Autism Spectrum Disorder.

Conversational impairments are well known among people with autism spectrum disorder (ASD), but their measurement requires time-consuming manual annotation of language samples. Natural language processing (NLP) has shown promise in identifying semantic difficulties when compared to clinician-annotated reference transcripts. Our goal was to develop a novel measure of lexico-semantic similarity – based on recent work in natural language processing (NLP) and recent applications of pseudo-value analysis – which could be applied to transcripts of children’s conversational language, without recourse to some ground-truth reference document. We hypothesized that: (a) semantic coherence, as measured by this method, would discriminate between children with and without ASD and (b) more variability would be found in the group with ASD. We used data from 70 4- to 8-year-old males with ASD (N = 38) or typically developing (TD; N = 32) enrolled in a language study. Participants were administered a battery of standardized diagnostic tests, including the Autism Diagnostic Observation Schedule (ADOS). ADOS was recorded and transcribed, and we analyzed children’s language output during the conversation/interview ADOS tasks. Transcripts were converted to vectors via a word2vec model trained on the Google News Corpus. Pairwise similarity across all subjects and a sample grand mean were calculated. Using a leave-one-out algorithm, a pseudo-value, detailed below, representing each subject’s contribution to the grand mean was generated. Means of pseudo-values were compared between the two groups. Analyses were co-varied for nonverbal IQ, mean length of utterance, and number of distinct word roots (NDR). Statistically significant differences were observed in means of pseudo-values between TD and ASD groups (p = 0.007). TD subjects had higher pseudo-value scores suggesting that similarity scores of TD subjects were more similar to the overall group mean. Variance of pseudo-values was greater in the ASD group. Nonverbal IQ, mean length of utterance, or NDR did not account for between group differences. The findings suggest that our pseudo-value-based method can be effectively used to identify specific semantic difficulties that characterize children with ASD without requiring a reference transcript.

Development of UAV-Based PM2.5 Monitoring System

This paper proposes a UAV-based PM2.5 air quality and temperature-humidity monitoring system. The system includes an air quality detector comprising four Arduino sensor modules. Specifically, it includes a dust (DSM501A) sensor and a temperature and humidity (DHT11) sensor. The NEO-6M GPS module and DS3231 real-time module are also included for input visualization. A DIY SD card logging shield and memory module is also available for data recording purposes. The Arduino-based board houses multiple sensors and all are programmable using the Arduino integrated development environment (IDE) coding tool. Measurements conducted in a vertical flight path show promise where comparisons with ground truth references data showed good similarity. Overall, the results point to the idea that a light-weight and portable system can be used for accurate and reliable remote sensing data collection (in this case, PM2.5 concentration data and environmental data).

Deep Learning-Based Carotid Plaque Segmentation from B-Mode Ultrasound Images

Carotid ultrasound measurement of total plaque area (TPA) provides a method for quantifying carotid plaque burden and monitoring changes in carotid atherosclerosis in response to medical treatment. Plaque boundary segmentation is required to generate the TPA measurement; however, training of observers and manual delineation are time consuming. Thus, our objective was to develop an automated plaque segmentation method to generate TPA from longitudinal carotid ultrasound images. In this study, a deep learning-based method, modified U-Net, was used to train the segmentation model and generate TPA measurement. A total of 510 plaques from 144 patients were used in our study, where the Monte Carlo cross-validation was used by randomly splitting the data set into 2/3 and 1/3 for training and testing. Two observers were trained to manually delineate the 510 plaques separately, which were used as the ground-truth references. Two U-Net models (M1 and M2) were trained using the two different ground-truth data sets from the two observers to evaluate the accuracy, variability and sensitivity on the ground-truth data sets used for training our method. The results of the algorithm segmentations of the two models yielded strong agreement with the two manual segmentations with the Pearson correlation coefficient r = 0.989 (p < 0.0001) and r = 0.987 (p < 0.0001). Comparison of the U-Net and manual segmentations resulted in mean TPA differences of 0.05 ± 7.13 mm2 (95% confidence interval: 14.02–13.02 mm2) and 0.8 ± 8.7 mm2 (17.85–16.25 mm2) for the two models, which are small compared with the TPA range in our data set from 4.7 to 312.8 mm2. Furthermore, the mean time to segment a plaque was only 8.3 ± 3.1 ms. The presented deep learning-based method described has sufficient accuracy with a short computation time and exhibits high agreement between the algorithm and manual TPA measurements, suggesting that the method could be used to measure TPA and to monitor the progression and regression of carotid atherosclerosis.

Dosimetric impact of using a commercial metal artifact reduction tool in carbon ion therapy in patients with hip prostheses

The study investigated the dosimetric impact of an iterative metal artifact reduction (iMAR) tool on carbon ion therapy for pelvic cancer patients with hip prostheses. An anthropomorphic pelvic phantom with unilateral and bilateral hip prostheses was used to simulate pelvic cancer patients with metal implants. The raw data obtained from phantom CT scanning were reconstructed with a regular filtered back projection (FBP) algorithm and then corrected with iMAR. The phantom without hip prosthesis was also scanned and used as a reference ground truth (GT). The CT images of three prostate and four sarcoma patients with unilateral hip prosthesis were also reconstructed by FBP and iMAR algorithm and compared. iMAR algorithm reduced the metal artifacts and the maximum WEPL deviation in phantom images from −19.1 to −0.4 mm. However, the CT numbers cannot be retrieved using iMAR for periprosthetic bone materials, eventually leading to a WEPL deviation of −3.6 mm. The use of iMAR improved large discrepancies in DVHs of PTVs and the gamma index between FBP and GT images but increased the difference in the bladder DVH for bilateral hip prostheses due to newly introduced artifacts. In the patient study, the discrepancies of dose distribution were small on iMAR images when compared with FBP images for most cases, except for two sarcoma cases where gamma analysis failed and dose coverage in 98% of the PTV maximally reduced due to large volume of dark metal artifacts. iMAR reduced the metal artifacts and improved dose distribution accuracy in carbon ion radiotherapy for pelvic cancer. However, the residual and newly introduced artifacts, especially with bilateral hip prostheses, may potentially increase WEPL inaccuracy and dose uncertainty. The use of iMAR has the potential to improve carbon ion treatment planning of pelvic cancer but should be used with caution.