Validation of machine learning models for estimation of left ventricular ejection fraction on point-of-care ultrasound: insights on features that impact performance.

BACKGROUND: Machine learning (ML) algorithms can accurately estimate left ventricular ejection fraction (LVEF) from echocardiography, but their performance on cardiac point-of-care ultrasound (POCUS) is not well understood. OBJECTIVES: We evaluate the performance of an ML model for estimation of LVEF on cardiac POCUS compared with Level III echocardiographers' interpretation and formal echo reported LVEF. METHODS: Clinicians at a tertiary care heart failure clinic prospectively scanned 138 participants using hand-carried devices. Video data were analyzed offline by an ML model for LVEF. We compared the ML model's performance with Level III echocardiographers' interpretation and echo reported LVEF. RESULTS: There were 138 participants scanned, yielding 1257 videos. The ML model generated LVEF predictions on 341 videos. We observed a good intraclass correlation (ICC) between the ML model's predictions and the reference standards (ICC = 0.77-0.84). When comparing LVEF estimates for randomized single POCUS videos, the ICC between the ML model and Level III echocardiographers' estimates was 0.772, and it was 0.778 for videos where quantitative LVEF was feasible. When the Level III echocardiographer reviewed all POCUS videos for a participant, the ICC improved to 0.794 and 0.843 when only accounting for studies that could be segmented. The ML model's LVEF estimates also correlated well with LVEF derived from formal echocardiogram reports (ICC = 0.798). CONCLUSION: Our results suggest that clinician-driven cardiac POCUS produces ML model LVEF estimates that correlate well with expert interpretation and echo reported LVEF.

Deep Learning for Detection and Localization of B-Lines in Lung Ultrasound.

Lung ultrasound (LUS) is an important imaging modality used by emergency physicians to assess pulmonary congestion at the patient bedside. B-line artifacts in LUS videos are key findings associated with pulmonary congestion. Not only can the interpretation of LUS be challenging for novice operators, but visual quantification of B-lines remains subject to observer variability. In this work, we investigate the strengths and weaknesses of multiple deep learning approaches for automated B-line detection and localization in LUS videos. We curate and publish, BEDLUS, a new ultrasound dataset comprising 1,419 videos from 113 patients with a total of 15,755 expert-annotated B-lines. Based on this dataset, we present a benchmark of established deep learning methods applied to the task of B-line detection. To pave the way for interpretable quantification of B-lines, we propose a novel "single-point" approach to B-line localization using only the point of origin. Our results show that (a) the area under the receiver operating characteristic curve ranges from 0.864 to 0.955 for the benchmarked detection methods, (b) within this range, the best performance is achieved by models that leverage multiple successive frames as input, and (c) the proposed single-point approach for B-line localization reaches an F 1-score of 0.65, performing on par with the inter-observer agreement. The dataset and developed methods can facilitate further biomedical research on automated interpretation of lung ultrasound with the potential to expand the clinical utility.

U-LanD: Uncertainty-Driven Video Landmark Detection.

This paper presents U-LanD, a framework for automatic detection of landmarks on key frames of the video by leveraging the uncertainty of landmark prediction. We tackle a specifically challenging problem, where training labels are noisy and highly sparse. U-LanD builds upon a pivotal observation: a deep Bayesian landmark detector solely trained on key video frames, has significantly lower predictive uncertainty on those frames vs. other frames in videos. We use this observation as an unsupervised signal to automatically recognize key frames on which we detect landmarks. As a test-bed for our framework, we use ultrasound imaging videos of the heart, where sparse and noisy clinical labels are only available for a single frame in each video. Using data from 4,493 patients, we demonstrate that U-LanD can exceedingly outperform the state-of-the-art non-Bayesian counterpart by a noticeable absolute margin of 42% in R2 score, with almost no overhead imposed on the model size.

Multiple instance learning combined with label invariant synthetic data for guiding systematic prostate biopsy: a feasibility study.

PURPOSE: Ultrasound imaging is routinely used in prostate biopsy, which involves obtaining prostate tissue samples using a systematic, yet, non-targeted approach. This approach is blinded to individual patient intraprostatic pathology, and unfortunately, has a high rate of false negatives. METHODS: In this paper, we propose a deep network for improved detection of prostate cancer in systematic biopsy. We address several challenges associated with training such network: (1) Statistical labels: Since biopsy core's pathology report only represents a statistical distribution of cancer within the core, we use multiple instance learning (MIL) networks to enable learning from ultrasound image regions associated with those data; (2) Limited labels: The number of biopsy cores are limited to at most 12 per patient. As a result, the number of samples available for training a deep network is limited. We alleviate this issue by effectively combining Independent Conditional Variational Auto Encoders (ICVAE) with MIL. We train ICVAE to learn label-invariant features of RF data, which is subsequently used to generate synthetic data for improved training of the MIL network. RESULTS: Our in vivo study includes data from 339 prostate biopsy cores of 70 patients. We achieve an area under the curve, sensitivity, specificity, and balanced accuracy of 0.68, 0.77, 0.55 and 0.66, respectively. CONCLUSION: The proposed approach is generic and can be applied to several other scenarios where unlabeled data and noisy labels in training samples are present.

Cardiac point-of-care to cart-based ultrasound translation using constrained CycleGAN.

PURPOSE:  The emerging market of cardiac handheld ultrasound (US) is on the rise. Despite the advantages in ease of access and the lower cost, a gap in image quality can still be observed between the echocardiography (echo) data captured by point-of-care ultrasound (POCUS) compared to conventional cart-based US, which limits the further adaptation of POCUS. In this work, we aim to present a machine learning solution based on recent advances in adversarial training to investigate the feasibility of translating POCUS echo images to the quality level of high-end cart-based US systems. METHODS:  We propose a constrained cycle-consistent generative adversarial architecture for unpaired translation of cardiac POCUS to cart-based US data. We impose a structured shape-wise regularization via a critic segmentation network to preserve the underlying shape of the heart during quality translation. The proposed deep transfer model is constrained to the anatomy of the left ventricle (LV) in apical two-chamber (AP2) echo views. RESULTS:  A total of 1089 echo studies from 841 patients are used in this study. The AP2 frames are captured by POCUS (Philips Lumify and Clarius) and cart-based (Philips iE33 and Vivid E9) US machines. The dataset of quality translation comprises a total of 441 echo studies from 395 patients. Data from both POCUS and cart-based systems of the same patient were available in 122 cases. The deep-quality transfer model is integrated into a pipeline for an automated cardiac evaluation task, namely segmentation of LV in AP2 view. By transferring the low-quality POCUS data to the cart-based US, a significant average improvement of 30% and 34 mm is obtained in the LV segmentation Dice score and Hausdorff distance metrics, respectively. CONCLUSION:  This paper presents the feasibility of a machine learning solution to transform the image quality of POCUS data to that of high-quality high-end cart-based systems. The experiments show that by leveraging the quality translation through the proposed constrained adversarial training, the accuracy of automatic segmentation with POCUS data could be improved.

Dense pooling layers in fully convolutional network for skin lesion segmentation.

One of the essential tasks in medical image analysis is segmentation and accurate detection of borders. Lesion segmentation in skin images is an essential step in the computerized detection of skin cancer. However, many of the state-of-the-art segmentation methods have deficiencies in their border detection phase. In this paper, a new class of fully convolutional network is proposed, with new dense pooling layers for segmentation of lesion regions in skin images. This network leads to highly accurate segmentation of lesions on skin lesion datasets, which outperforms state-of-the-art algorithms in the skin lesion segmentation.

Automatic biplane left ventricular ejection fraction estimation with mobile point-of-care ultrasound using multi-task learning and adversarial training.

PURPOSE: Left ventricular ejection fraction (LVEF) is one of the key metrics to assess the heart functionality, and cardiac ultrasound (echo) is a standard imaging modality for EF measurement. There is an emerging interest to exploit the point-of-care ultrasound (POCUS) usability due to low cost and ease of access. In this work, we aim to present a computationally efficient mobile application for accurate LVEF estimation. METHODS: Our proposed mobile application for LVEF estimation runs in real time on Android mobile devices that have either a wired or wireless connection to a cardiac POCUS device. We propose a pipeline for biplane ejection fraction estimation using apical two-chamber (AP2) and apical four-chamber (AP4) echo views. A computationally efficient multi-task deep fully convolutional network is proposed for simultaneous LV segmentation and landmark detection in these views, which is integrated into the LVEF estimation pipeline. An adversarial critic model is used in the training phase to impose a shape prior on the LV segmentation output. RESULTS: The system is evaluated on a dataset of 427 patients. Each patient has a pair of captured AP2 and AP4 echo studies, resulting in a total of more than 40,000 echo frames. The mobile system reaches a noticeably high average Dice score of 92% for LV segmentation, an average Euclidean distance error of 2.85 pixels for the detection of anatomical landmarks used in LVEF calculation, and a median absolute error of 6.2% for LVEF estimation compared to the expert cardiologist's annotations and measurements. CONCLUSION: The proposed system runs in real time on mobile devices. The experiments show the effectiveness of the proposed system for automatic LVEF estimation by demonstrating an adequate correlation with the cardiologist's examination.

Quantitative Characterization of the Interaction Space of the Mammalian Carbonic Anhydrase Isoforms I, II, VII, IX, XII, and XIV and their Inhibitors, Using the Proteochemometric Approach.

The critical role of carbonic anhydrases in different physiological processes has put this protein family at the center of attention, challenging major diseases like glaucoma, neurological disorders such as epilepsy and Alzheimer's disease, obesity, and cancers. Many QSAR/QSPR (quantitative structure-activity/property relationship) researches have been carried out to design potent carbonic anhydrase inhibitors (CAIs); however, using inhibitors with no selectivity for different isoforms can lead to major side-effects. Given that QSAR/QSPR methods are not capable of covering multiple targets in a unified model, we have applied the proteochemometric approach to model the interaction space that governs selective inhibition of different CA isoforms by some mono-/dihydroxybenzoic acid esters. Internal and external validation methods showed that all models were reliable in terms of both validity and predictivity, whereas Y-scrambling assessed the robustness of the models. To prove the applicability of our models, we showed how structural changes of a ligand can affect the selectivity. Our models provided interesting information that can be useful for designing inhibitors with selective behavior toward isoforms of carbonic anhydrases, aiding in their selective inhibition.

An ab initio intermolecular potential energy surface for the F(2) dimer.

Two analytical representations for the potential energy surface of the F(2) dimer were constructed on the basis of ab initio calculations up to the fourth-order of Møller-Plesset (MP) perturbation theory. The best estimate of the complete basis set limit of interaction energy was derived for analysis of basis set incompleteness errors. At the MP4/aug-cc-pVTZ level of theory, the most stable structure of the dimer was obtained at R = 6.82 au, theta(a) = 12.9 degrees , theta(b) = 76.0 degrees , and phi = 180 degrees , with a well depth of 716 microE(h). Two other minima were found for canted and X-shaped configurations with potential energies around -596 and -629 microE(h), respectively. Hexadecapole moments of monomers play an important role in the anisotropy of interaction energy that is highly R-dependent at intermediate intermolecular distances. The quality of potentials was tested by computing values of the second virial coefficient. The fitted MP4 potential has a more reasonable agreement with experimental values.