Characterizing the Contribution of Dependent Features in XAI Methods.

Explainable Artificial Intelligence (XAI) provides tools to help understanding how AI models work and reach a particular decision or outcome. It helps to increase the interpretability of models and makes them more trustworthy and transparent. In this context, many XAI methods have been proposed to make black-box and complex models more digestible from a human perspective. However, one of the main issues that XAI methods have to face especially when dealing with a high number of features is the presence of multicollinearity, which casts shadows on the robustness of the XAI outcomes, such as the ranking of informative features. Most of the current XAI methods either do not consider the collinearity or assume the features are independent which, in general, is not necessarily true. Here, we propose a simple, yet useful, proxy that modifies the outcome of any XAI feature ranking method allowing to account for the dependency among the features, and to reveal their impact on the outcome. The proposed method was applied to SHAP, as an example of XAI method which assume that the features are independent. For this purpose, several models were exploited for a well-known classification task (males versus females) using nine cardiac phenotypes extracted from cardiac magnetic resonance imaging as features. Principal component analysis and biological plausibility were employed to validate the proposed method. Our results showed that the proposed proxy could lead to a more robust list of informative features compared to the original SHAP in presence of collinearity.

Exploration of Interpretability Techniques for Deep COVID-19 Classification Using Chest X-ray Images.

The outbreak of COVID-19 has shocked the entire world with its fairly rapid spread, and has challenged different sectors. One of the most effective ways to limit its spread is the early and accurate diagnosing of infected patients. Medical imaging, such as X-ray and computed tomography (CT), combined with the potential of artificial intelligence (AI), plays an essential role in supporting medical personnel in the diagnosis process. Thus, in this article, five different deep learning models (ResNet18, ResNet34, InceptionV3, InceptionResNetV2, and DenseNet161) and their ensemble, using majority voting, have been used to classify COVID-19, pneumoniæ and healthy subjects using chest X-ray images. Multilabel classification was performed to predict multiple pathologies for each patient, if present. Firstly, the interpretability of each of the networks was thoroughly studied using local interpretability methods-occlusion, saliency, input X gradient, guided backpropagation, integrated gradients, and DeepLIFT-and using a global technique-neuron activation profiles. The mean micro F1 score of the models for COVID-19 classifications ranged from 0.66 to 0.875, and was 0.89 for the ensemble of the network models. The qualitative results showed that the ResNets were the most interpretable models. This research demonstrates the importance of using interpretability methods to compare different models before making a decision regarding the best performing model.

Bayesian DivideMix++ for Enhanced Learning with Noisy Labels.

Leveraging inexpensive and human intervention-based annotating methodologies, such as crowdsourcing and web crawling, often leads to datasets with noisy labels. Noisy labels can have a detrimental impact on the performance and generalization of deep neural networks. Robust models that are able to handle and mitigate the effect of these noisy labels are thus essential. In this work, we explore the open challenges of neural network memorization and uncertainty in creating robust learning algorithms with noisy labels. To overcome them, we propose a novel framework called "Bayesian DivideMix++" with two critical components: (i) DivideMix++, to enhance the robustness against memorization and (ii) Monte-Carlo MixMatch, which focuses on improving the effectiveness towards label uncertainty. DivideMix++ improves the pipeline by integrating the warm-up and augmentation pipeline with self-supervised pre-training and dedicated different data augmentations for loss analysis and backpropagation. Monte-Carlo MixMatch leverages uncertainty measurements to mitigate the influence of uncertain samples by reducing their weight in the data augmentation MixMatch step. We validate our proposed pipeline using four datasets encompassing various synthetic and real-world noise settings. We demonstrate the effectiveness and merits of our proposed pipeline using extensive experiments. Bayesian DivideMix++ outperforms the state-of-the-art models by considerable differences in all experiments. Our findings underscore the potential of leveraging these modifications to enhance the performance and generalization of deep neural networks in practical scenarios.

Ischemic Heart Disease and Vascular Risk Factors Are Associated With Accelerated Brain Aging.

BACKGROUND: Ischemic heart disease (IHD) has been linked with poor brain outcomes. The brain magnetic resonance imaging-derived difference between predicted brain age and actual chronological age (brain-age delta in years, positive for accelerated brain aging) may serve as an effective means of communicating brain health to patients to promote healthier lifestyles. OBJECTIVES: The authors investigated the impact of prevalent IHD on brain aging, potential underlying mechanisms, and its relationship with dementia risk, vascular risk factors, cardiovascular structure, and function. METHODS: Brain age was estimated in subjects with prevalent IHD (n = 1,341) using a Bayesian ridge regression model with 25 structural (volumetric) brain magnetic resonance imaging features and built using UK Biobank participants with no prevalent IHD (n = 35,237). RESULTS: Prevalent IHD was linked to significantly accelerated brain aging (P < 0.001) that was not fully mediated by microvascular injury. Brain aging (positive brain-age delta) was associated with increased risk of dementia (OR: 1.13 [95% CI: 1.04-1.22]; P = 0.002), vascular risk factors (such as diabetes), and high adiposity. In the absence of IHD, brain aging was also associated with cardiovascular structural and functional changes typically observed in aging hearts. However, such alterations were not linked with risk of dementia. CONCLUSIONS: Prevalent IHD and coexisting vascular risk factors are associated with accelerated brain aging and risk of dementia. Positive brain-age delta representing accelerated brain aging may serve as an effective communication tool to show the impact of modifiable risk factors and disease supporting preventative strategies.

Telomere length is causally connected to brain MRI image derived phenotypes: A mendelian randomization study.

Recent evidence suggests that shorter telomere length (TL) is associated with neuro degenerative diseases and aging related outcomes. The causal association between TL and brain characteristics represented by image derived phenotypes (IDPs) from different magnetic resonance imaging (MRI) modalities remains unclear. Here, we use two-sample Mendelian randomization (MR) to systematically assess the causal relationships between TL and 3,935 brain IDPs. Overall, the MR results suggested that TL was causally associated with 193 IDPs with majority representing diffusion metrics in white matter tracts. 68 IDPs were negatively associated with TL indicating that longer TL causes decreasing in these IDPs, while the other 125 were associated positively (longer TL leads to increased IDPs measures). Among them, ten IDPs have been previously reported as informative biomarkers to estimate brain age. However, the effect direction between TL and IDPs did not reflect the observed direction between aging and IDPs: longer TL was associated with decreases in fractional anisotropy and increases in axial, radial and mean diffusivity. For instance, TL was positively associated with radial diffusivity in the left perihippocampal cingulum tract and with mean diffusivity in right perihippocampal cingulum tract. Our results revealed a causal role of TL on white matter integrity which makes it a valuable factor to be considered when brain age is estimated and investigated.

Estimation of biological heart age using cardiovascular magnetic resonance radiomics.

We developed a novel interpretable biological heart age estimation model using cardiovascular magnetic resonance radiomics measures of ventricular shape and myocardial character. We included 29,996 UK Biobank participants without cardiovascular disease. Images were segmented using an automated analysis pipeline. We extracted 254 radiomics features from the left ventricle, right ventricle, and myocardium of each study. We then used Bayesian ridge regression with tenfold cross-validation to develop a heart age estimation model using the radiomics features as the model input and chronological age as the model output. We examined associations of radiomics features with heart age in men and women, observing sex-differential patterns. We subtracted actual age from model estimated heart age to calculate a "heart age delta", which we considered as a measure of heart aging. We performed a phenome-wide association study of 701 exposures with heart age delta. The strongest correlates of heart aging were measures of obesity, adverse serum lipid markers, hypertension, diabetes, heart rate, income, multimorbidity, musculoskeletal health, and respiratory health. This technique provides a new method for phenotypic assessment relating to cardiovascular aging; further studies are required to assess whether it provides incremental risk information over current approaches.

Uncertainty-aware selecting for an ensemble of deep food recognition models.

Deep learning is a machine learning technique that has revolutionized the research community due to its impressive results on various real-life problems. Recently, ensembles of Convolutional Neural Networks (CNN) have proven to achieve high robustness and accuracy in numerous computer vision challenges. As expected, the more models we add to the ensemble, the better performance we can obtain, but, in contrast, more computer resources are needed. Hence, the importance of deciding how many models to use and which models to select from a pool of trained models is huge. From the latter, a common strategy in deep learning is to select the models randomly or according to the results on the validation set. However, in this way models are chosen based on individual performance ignoring how they are expected to work together. Alternatively, to ensure a better complement between models, an exhaustive search can be used by evaluating the performance of several ensemble models based on different numbers and combinations of trained models. Nevertheless, this may result in being high computationally expensive. Considering that epistemic uncertainty analysis has recently been successfully employed to understand model learning, we aim to analyze whether an uncertainty-aware epistemic method can help us decide which groups of CNN models may work best. The method was validated on several food datasets and with different CNN architectures. In most cases, our proposal outperforms the results by a statistically significant range with respect to the baseline techniques and is much less computationally expensive compared to the brute-force search.

Brain age estimation at tract group level and its association with daily life measures, cardiac risk factors and genetic variants.

Brain age can be estimated using different Magnetic Resonance Imaging (MRI) modalities including diffusion MRI. Recent studies demonstrated that white matter (WM) tracts that share the same function might experience similar alterations. Therefore, in this work, we sought to investigate such issue focusing on five WM bundles holding that feature that is Association, Brainstem, Commissural, Limbic and Projection fibers, respectively. For each tract group, we estimated brain age for 15,335 healthy participants from United Kingdom Biobank relying on diffusion MRI data derived endophenotypes, Bayesian ridge regression modeling and 10 fold-cross validation. Furthermore, we estimated brain age for an Ensemble model that gathers all the considered WM bundles. Association analysis was subsequently performed between the estimated brain age delta as resulting from the six models, that is for each tract group as well as for the Ensemble model, and 38 daily life style measures, 14 cardiac risk factors and cardiovascular magnetic resonance imaging features and genetic variants. The Ensemble model that used all tracts from all fiber groups (FG) performed better than other models to estimate brain age. Limbic tracts based model reached the highest accuracy with a Mean Absolute Error (MAE) of 5.08, followed by the Commissural ([Formula: see text]), Association ([Formula: see text]), and Projection ([Formula: see text]) ones. The Brainstem tracts based model was the less accurate achieving a MAE of 5.86. Accordingly, our study suggests that the Limbic tracts experience less brain aging or allows for more accurate estimates compared to other tract groups. Moreover, the results suggest that Limbic tract leads to the largest number of significant associations with daily lifestyle factors than the other tract groups. Lastly, two SNPs were significantly (p value [Formula: see text]) associated with brain age delta in the Projection fibers. Those SNPs are mapped to HIST1H1A and SLC17A3 genes.

CoLe-CNN+: Context learning - Convolutional neural network for COVID-19-Ground-Glass-Opacities detection and segmentation.

BACKGROUND AND OBJECTIVE: The most common tool for population-wide COVID-19 identification is the Reverse Transcription-Polymerase Chain Reaction test that detects the presence of the virus in the throat (or sputum) in swab samples. This test has a sensitivity between 59% and 71%. However, this test does not provide precise information regarding the extension of the pulmonary infection. Moreover, it has been proven that through the reading of a computed tomography (CT) scan, a clinician can provide a more complete perspective of the severity of the disease. Therefore, we propose a comprehensive system for fully-automated COVID-19 detection and lesion segmentation from CT scans, powered by deep learning strategies to support decision-making process for the diagnosis of COVID-19. METHODS: In the workflow proposed, the input CT image initially goes through lung delineation, then COVID-19 detection and finally lesion segmentation. The chosen neural network has a U-shaped architecture using a newly introduced Multiple Convolutional Layers structure, that produces a lung segmentation mask within a novel pipeline for direct COVID-19 detection and segmentation. In addition, we propose a customized loss function that guarantees an optimal balance on average between sensitivity and precision. RESULTS: Lungs' segmentation results show a sensitivity near 99% and Dice-score of 97%. No false positives were observed in the detection network after 10 different runs with an average accuracy of 97.1%. The average accuracy for lesion segmentation was approximately 99%. Using UNet as a benchmark, we compared our results with several other techniques proposed in the literature, obtaining the largest improvement over the UNet outcomes. CONCLUSIONS: The method proposed in this paper outperformed the state-of-the-art methods for COVID-19 lesion segmentation from CT images, and improved by 38.2% the results for F1-score of UNet. The high accuracy observed in this work opens up a wide range of possible applications of our algorithm in other fields related to medical image segmentation.

Behavioural and neurophysiological signatures in the retrieval of individual memories of recent and remote real-life routine episodic events.

Autobiographical memory (AM) has been largely investigated as the ability to recollect specific events that belong to an individual's past. However, how we retrieve real-life routine episodes and how the retrieval of these episodes changes with the passage of time remain unclear. Here, we asked participants to use a wearable camera that automatically captured pictures to record instances during a week of their routine life and implemented a deep neural network-based algorithm to identify picture sequences that represented episodic events. We then asked each participant to return to the lab to retrieve AMs for single episodes cued by the selected pictures 1 week, 2 weeks and 6-14 months after encoding while scalp electroencephalographic (EEG) activity was recorded. We found that participants were more accurate in recognizing pictured scenes depicting their own past than pictured scenes encoded in the lab, and that memory recollection of personally experienced events rapidly decreased with the passing of time. We also found that the retrieval of real-life picture cues elicited a strong and positive 'ERP old/new effect' over frontal regions and that the magnitude of this ERP effect was similar throughout memory tests over time. However, we observed that recognition memory induced a frontal theta power decrease and that this effect was mostly seen when memories were tested after 1 and 2 weeks but not after 6-14 months from encoding. Altogether, we discuss the implications for neuroscientific accounts of episodic retrieval and the potential benefits of developing individual-based AM exploration strategies at the clinical level.

Data preparation for artificial intelligence in medical imaging: A comprehensive guide to open-access platforms and tools.

The vast amount of data produced by today's medical imaging systems has led medical professionals to turn to novel technologies in order to efficiently handle their data and exploit the rich information present in them. In this context, artificial intelligence (AI) is emerging as one of the most prominent solutions, promising to revolutionise every day clinical practice and medical research. The pillar supporting the development of reliable and robust AI algorithms is the appropriate preparation of the medical images to be used by the AI-driven solutions. Here, we provide a comprehensive guide for the necessary steps to prepare medical images prior to developing or applying AI algorithms. The main steps involved in a typical medical image preparation pipeline include: (i) image acquisition at clinical sites, (ii) image de-identification to remove personal information and protect patient privacy, (iii) data curation to control for image and associated information quality, (iv) image storage, and (v) image annotation. There exists a plethora of open access tools to perform each of the aforementioned tasks and are hereby reviewed. Furthermore, we detail medical image repositories covering different organs and diseases. Such repositories are constantly increasing and enriched with the advent of big data. Lastly, we offer directions for future work in this rapidly evolving field.

CoLe-CNN: Context-learning convolutional neural network with adaptive loss function for lung nodule segmentation.

BACKGROUND AND OBJECTIVE: An accurate segmentation of lung nodules in computed tomography images is a crucial step for the physical characterization of the tumour. Being often completely manually accomplished, nodule segmentation turns to be a tedious and time-consuming procedure and this represents a high obstacle in clinical practice. In this paper, we propose a novel Convolutional Neural Network for nodule segmentation that combines a light and efficient architecture with innovative loss function and segmentation strategy. METHODS: In contrast to most of the standard end-to-end architectures for nodule segmentation, our network learns the context of the nodules by producing two masks representing all the background and secondary-important elements in the Computed Tomography scan. The nodule is detected by subtracting the context from the original scan image. Additionally, we introduce an asymmetric loss function that automatically compensates for potential errors in the nodule annotations. We trained and tested our Neural Network on the public LIDC-IDRI database, compared it with the state of the art and run a pseudo-Turing test between four radiologists and the network. RESULTS: The results proved that the behaviour of the algorithm is very near to the human performance and its segmentation masks are almost indistinguishable from the ones made by the radiologists. Our method clearly outperforms the state of the art on CT nodule segmentation in terms of F1 score and IoU of 3.3% and 4.7%, respectively. CONCLUSIONS: The main structure of the network ensures all the properties of the UNet architecture, while the Multi Convolutional Layers give a more accurate pattern recognition. The newly adopted solutions also increase the details on the border of the nodule, even under the noisiest conditions. This method can be applied now for single CT slice nodule segmentation and it represents a starting point for the future development of a fully automatic 3D segmentation software.

Hierarchical Approach to Classify Food Scenes in Egocentric Photo-Streams.

Recent studies have shown that the environment where people eat can affect their nutritional behavior [1]. In this paper, we provide automatic tools for personalized analysis of a person's health habits by the examination of daily recorded egocentric photo-streams. Specifically, we propose a new automatic approach for the classification of food-related environments, that is able to classify up to 15 such scenes. In this way, people can monitor the context around their food intake in order to get an objective insight into their daily eating routine. We propose a model that classifies food-related scenes organized in a semantic hierarchy. Additionally, we present and make available a new egocentric dataset composed of more than 33 000 images recorded by a wearable camera, over which our proposed model has been tested. Our approach obtains an accuracy and F-score of 56% and 65%, respectively, clearly outperforming the baseline methods.

Acceptability of a lifelogging wearable camera in older adults with mild cognitive impairment: a mixed-method study.

BACKGROUND: The main objective of this research was to evaluate the acceptance of technology based on a wearable lifelogging camera in a sample of older adults diagnosed with mild cognitive impairment (MCI). METHODS: A mixed-method design was used, consisting of a self-report questionnaire, numerous images taken by users, and a series of focus group discussions. The patients were involved in an individualized training programme. RESULTS: Nine MCI patients and their caregiver relatives were included. They showed good acceptance of the camera and downloaded an appropriate number of images on a daily basis. Perceived severity and ease of use were the main factors associated with the intention to use the device. CONCLUSIONS: Older adults with MCI can become competent users of lifelogging wearable cameras with a good level of acceptance. Privacy concerns are outweighed by the potential benefits for memory. Limitations, strengths and implications for future research are discussed.

Potential Use of Mobile Phone Applications for Self-Monitoring and Increasing Daily Fruit and Vegetable Consumption: A Systematized Review.

A wide range of chronic diseases could be prevented through healthy lifestyle choices, such as consuming five portions of fruits and vegetables daily, although the majority of the adult population does not meet this recommendation. The use of mobile phone applications for health purposes has greatly increased; these applications guide users in real time through various phases of behavioural change. This review aimed to assess the potential of self-monitoring mobile phone health (mHealth) applications to increase fruit and vegetable intake. PubMed and Web of Science were used to conduct this systematized review, and the inclusion criteria were: randomized controlled trials evaluating mobile phone applications focused on increasing fruit and/or vegetable intake as a primary or secondary outcome performed from 2008 to 2018. Eight studies were included in the final assessment. The interventions described in six of these studies were effective in increasing fruit and/or vegetable intake. Targeting stratified populations and using long-lasting interventions were identified as key aspects that could influence the effectiveness of these interventions. In conclusion, evidence shows the effectiveness of mHealth application interventions to increase fruit and vegetable consumption. Further research is needed to design effective interventions and to determine their efficacy over the long term.

Assessment of intracoronary stent location and extension in intravascular ultrasound sequences.

PURPOSE: An intraluminal coronary stent is a metal scaffold deployed in a stenotic artery during percutaneous coronary intervention (PCI). In order to have an effective deployment, a stent should be optimally placed with regard to anatomical structures such as bifurcations and stenoses. Intravascular ultrasound (IVUS) is a catheter-based imaging technique generally used for PCI guiding and assessing the correct placement of the stent. A novel approach that automatically detects the boundaries and the position of the stent along the IVUS pullback is presented. Such a technique aims at optimizing the stent deployment. METHODS: The method requires the identification of the stable frames of the sequence and the reliable detection of stent struts. Using these data, a measure of likelihood for a frame to contain a stent is computed. Then, a robust binary representation of the presence of the stent in the pullback is obtained applying an iterative and multiscale quantization of the signal to symbols using the Symbolic Aggregate approXimation algorithm. RESULTS: The technique was extensively validated on a set of 103 IVUS of sequences of in vivo coronary arteries containing metallic and bioabsorbable stents acquired through an international multicentric collaboration across five clinical centers. The method was able to detect the stent position with an overall F-measure of 86.4%, a Jaccard index score of 75% and a mean distance of 2.5 mm from manually annotated stent boundaries, and in bioabsorbable stents with an overall F-measure of 88.6%, a Jaccard score of 77.7 and a mean distance of 1.5 mm from manually annotated stent boundaries. Additionally, a map indicating the distance between the lumen and the stent along the pullback is created in order to show the angular sectors of the sequence in which the malapposition is present. CONCLUSIONS: Results obtained comparing the automatic results vs the manual annotation of two observers shows that the method approaches the interobserver variability. Similar performances are obtained on both metallic and bioabsorbable stents, showing the flexibility and robustness of the method.

Calcium detection, its quantification, and grayscale morphology-based risk stratification using machine learning in multimodality big data coronary and carotid scans: A review.

PURPOSE OF REVIEW: Atherosclerosis is the leading cause of cardiovascular disease (CVD) and stroke. Typically, atherosclerotic calcium is found during the mature stage of the atherosclerosis disease. It is therefore often a challenge to identify and quantify the calcium. This is due to the presence of multiple components of plaque buildup in the arterial walls. The American College of Cardiology/American Heart Association guidelines point to the importance of calcium in the coronary and carotid arteries and further recommend its quantification for the prevention of heart disease. It is therefore essential to stratify the CVD risk of the patient into low- and high-risk bins. RECENT FINDING: Calcium formation in the artery walls is multifocal in nature with sizes at the micrometer level. Thus, its detection requires high-resolution imaging. Clinical experience has shown that even though optical coherence tomography offers better resolution, intravascular ultrasound still remains an important imaging modality for coronary wall imaging. For a computer-based analysis system to be complete, it must be scientifically and clinically validated. This study presents a state-of-the-art review (condensation of 152 publications after examining 200 articles) covering the methods for calcium detection and its quantification for coronary and carotid arteries, the pros and cons of these methods, and the risk stratification strategies. The review also presents different kinds of statistical models and gold standard solutions for the evaluation of software systems useful for calcium detection and quantification. Finally, the review concludes with a possible vision for designing the next-generation system for better clinical outcomes.

Wall-based measurement features provides an improved IVUS coronary artery risk assessment when fused with plaque texture-based features during machine learning paradigm.

BACKGROUND: Planning of percutaneous interventional procedures involves a pre-screening and risk stratification of the coronary artery disease. Current screening tools use stand-alone plaque texture-based features and therefore lack the ability to stratify the risk. METHOD: This IRB approved study presents a novel strategy for coronary artery disease risk stratification using an amalgamation of IVUS plaque texture-based and wall-based measurement features. Due to common genetic plaque makeup, carotid plaque burden was chosen as a gold standard for risk labels during training-phase of machine learning (ML) paradigm. Cross-validation protocol was adopted to compute the accuracy of the ML framework. A set of 59 plaque texture-based features was padded with six wall-based measurement features to show the improvement in stratification accuracy. The ML system was executed using principle component analysis-based framework for dimensionality reduction and uses support vector machine classifier for training and testing-phases. RESULTS: The ML system produced a stratification accuracy of 91.28%, demonstrating an improvement of 5.69% when wall-based measurement features were combined with plaque texture-based features. The fused system showed an improvement in mean sensitivity, specificity, positive predictive value, and area under the curve by: 6.39%, 4.59%, 3.31% and 5.48%, respectively when compared to the stand-alone system. While meeting the stability criteria of 5%, the ML system also showed a high average feature retaining power and mean reliability of 89.32% and 98.24%, respectively. CONCLUSIONS: The ML system showed an improvement in risk stratification accuracy when the wall-based measurement features were fused with the plaque texture-based features.

Relationship between Automated Coronary Calcium Volumes and a Set of Manual Coronary Lumen Volume, Vessel Volume and Atheroma Volume in Japanese Diabetic Cohort.

INTRODUCTION: A high degree of correlation exists between Coronary Artery Diseases (CAD) and calcification of the vessel wall. For Percutaneous Coronary Interventional (PCI) planning, it is essential to have an exact understanding of the extent to which calcium volume is correlated to the lumen, vessel, and atheroma volume regions in the coronary artery, which is unclear in recent studies. AIM: Four automated Coronary Calcium Volume (aCCV) measurement methods {threshold, Fuzzy c-Means (FCM), K-means, and Hidden Markov Random Field (HMRF)} and its correlation with three manual (experts) coronary parameters namely: Coronary Vessel Volume (mCVV), Coronary Lumen Volume (mCLV), and Coronary Atheroma Volume (mCAV), was determined in a Japanese diabetic cohort. MATERIALS AND METHODS: Intravascular Ultrasound (IVUS) image dataset from 19 patients (around 40,090 frames) was collected using 40 MHz IVUS catheter (Atlantis® SR Pro, Boston Scientific®, pullback speed of 0.5 mm/sec). The methodology consisted of automatically computing the calcium volume in the entire IVUS coronary videos using FCM, K-means, and HMRF based pixel classification and comparing it against the previously published threshold-based method. The Coefficient of Correlation (CC) was then established between the four aCCV and three manually (experts) coronary parameters: mCVV, mCLV, and mCAV computed using iMAP software Boston Scientific®. Statistical tests (Two-tailed paired Student t-test, Wilcoxon signed rank test, Mann-Whitney test, Chi-square test, and Kolmogorov-Smirnov KS-test) were performed to demonstrate consistency, reliability, and accuracy of the proposed work. RESULTS: Correlation coefficient of: (a) automated threshold-based volume; (b) automated FCM based volume; (c) automated K-means based volume; and (d) automated HMRF based volume and corresponding three manually (expert's) coronary parameters (mCLV, mCVV, mCAV) were: (0.51, 0.40, 0.48), (0.52, 0.38, 0.49), (0.56, 0.45, 0.52), and (0.57, 0.42, 0.56), respectively. The CC between age and haemoglobin was 0.50. CONCLUSION: Automated coronary volume measurement using HMRF method is more accurate compared to threshold, FCM, and K-means-based method, since it is more strongly correlated with three expert's readings.

Well-balanced system for coronary calcium detection and volume measurement in a low resolution intravascular ultrasound videos.

BACKGROUND: Accurate and fast quantitative assessment of calcium volume is required during the planning of percutaneous coronary interventions procedures. Low resolution in intravascular ultrasound (IVUS) coronary videos poses a threat to calcium detection causing over-estimation in volume measurement. We introduce a correction block that counter-balances the bias introduced during the calcium detection process. METHOD: Nineteen patients image dataset (around 40,090 frames), IRB approved, were collected using 40MHz IVUS catheter (Atlantis® SR Pro, Boston Scientific®, pullback speed of 0.5mm/sec). A new set of 20 generalized and well-balanced systems each consisting of three stages: (i) calcium detection, (ii) calibration and (iii) measurement, while ensuring accuracy of four soft classifiers (Threshold, FCM, K-means and HMRF) and workflow speed using five multiresolution techniques (bilinear, bicubic, wavelet, Lanczos, Gaussian Pyramid) were designed. Results of the three calcium detection methods were benchmarked against the Threshold-based method. RESULTS: All 20 well-balanced systems with calibration block show superior performance. Using calibration block, FCM versus Threshold-based method shows the highest cross-correlation 0.99 (P<0.0001), Jaccard index 0.984±0.013 (P<0.0001), and Dice similarity 0.992±0.007 (P<0.0001). The corresponding area under the curve for four calcium detection techniques is: 1.0, 1.0, 0.97 and 0.93, respectively. The mean overall performance improvement is 38.54% and when adapting calibration block. The mean workflow speed improvement is 62.14% when adapting multiresolution paradigm. Three clinical tests shows consistency, reliability, and stability of our well-balanced system. CONCLUSIONS: A well-balanced system with a combination of Threshold embedded with Lanczos multiresolution was optimal and can be useable in clinical settings.