Search

Background Angiography-derived physiological assessment of coronary lesions has emerged as an alternative to wire based assessment aiming at less-invasiveness and shorter procedural time as well as cost effectiveness in physiology-guided decision making. However, current available image-derived physiology software have limitations including the requirement of multiple projections and are time consuming.Methods/Design The ReVEAL iFR (Radiographic imaging Validation and EvALuation for Angio-iFR) trial is a multicenter, multicontinental, validation study which aims to validate the diagnostic accuracy of the Angio-iFR medical software device (Philips, San Diego, US) in patients undergoing angiography for Chronic Coronary Syndrome (CCS). The Angio-iFR will enable operators to predict both the iFR and FFR value within a few seconds from a single projection of cine angiography by using a lumped parameter fluid dynamics model. Approximately 440 patients with at least one de-novo 40% to 90% stenosis by visual angiographic assessment will be enrolled in the study. The primary endpoint is the sensitivity and specificity of the iFR and FFR for a given lesion compared to the corresponding invasive measures. The enrollment started in August 2019, and was completed in March 2021.Summary The Angio-iFR system has the potential of simplifying physiological evaluation of coronary stenosis compared with available systems, providing estimates of both FFR and iFR. The ReVEAL iFR study will investigate the predictive performance of the novel Angio-iFR software in CCS patients. Ultimately, based on its unique characteristics, the Angio-iFR system may contribute to improve adoption of functional coronary assessment and the workflow in the catheter laboratory.

Algorithms for automated analysis of intravascular ultrasound (IVUS) images can be disturbed by guidewires, which are often encountered when treating bifurcations in percutaneous coronary interventions. Detecting guidewires in advance can therefore help avoiding potential errors. This task is not trivial, since guidewires appear rather small compared to other relevant objects in IVUS images. We employed CNNs with additional multi-task learning as well as different guidewire-specific regularizations to enable and improve guidewire detection. In this context, we developed a network block which generates heatmaps that highlight guidewires without the need of localization annotations. The guidewire detection results reach values of 0.931 in terms of the F1-score and 0.996 in terms of area under curve (AUC). Comparing thresholded guidewire heatmaps with ground truth segmentation masks leads to a Dice score of 23.1 % and an average Hausdorff distance of 1.45 mm. Guidewire detection has proven to be a task that CNNs can handle quite well. Employing multi-task learning and guidewire-specific regularizations further improve detection results and enable generation of heatmaps that indicate the position of guidewires without actual labels.

Objective The aim is to evaluate whether smart worklist prioritization by artificial intelligence (AI) can optimize the radiology workflow and reduce report turnaround times (RTATs) for critical findings in chest radiographs (CXRs). Furthermore, we investigate a method to counteract the effect of false negative predictions by AI—resulting in an extremely and dangerously long RTAT, as CXRs are sorted to the end of the worklist. Methods We developed a simulation framework that models the current workflow at a university hospital by incorporating hospital-specific CXR generation rates and reporting rates and pathology distribution. Using this, we simulated the standard worklist processing “first-in, first-out” (FIFO) and compared it with a worklist prioritization based on urgency. Examination prioritization was performed by the AI, classifying eight different pathological findings ranked in descending order of urgency: pneumothorax, pleural effusion, infiltrate, congestion, atelectasis, cardiomegaly, mass, and foreign object. Furthermore, we introduced an upper limit for the maximum waiting time, after which the highest urgency is assigned to the examination. Results The average RTAT for all critical findings was significantly reduced in all prioritization simulations compared to the FIFO simulation (e.g., pneumothorax: 35.6 min vs. 80.1 min; p p p Conclusion Our simulations demonstrate that smart worklist prioritization by AI can reduce the average RTAT for critical findings in CXRs while maintaining a small maximum RTAT as FIFO. Key Points • Development of a realistic clinical workflow simulator based on empirical data from a hospital allowed precise assessment of smart worklist prioritization using artificial intelligence. • Employing a smart worklist prioritization without a threshold for maximum waiting time runs the risk of false negative predictions of the artificial intelligence greatly increasing the report turnaround time. • Use of a state-of-the-art convolution neural network can reduce the average report turnaround time almost to the upper limit of a perfect classification algorithm (e.g., pneumothorax: 35.6 min vs. 30.4 min).

It is now recognized that a number of excipients previously considered to be "inert" have the capacity to alter drug oral bioavailability through a range of in vivo effects. The various mechanisms through which an excipient can affect in vivo gastrointestinal physiology and drug absorption characteristics were explored in "A Critical Overview of The Biological Effects of Excipients (Part I): Impact on Gastrointestinal Absorption." The next critical issue that needs to be discussed is how these biological effects are evaluated. Therefore, in Part 2 of this critical overview, the in vitro, in vivo, and in silico methods for evaluating excipient effects are considered. Examples are provided to illustrate how such studies employing these various procedures have been used to promote formulation understanding and optimization. Finally, a discussion of how the Center for Drug Evaluation and Research applies these tools to support biowaivers is provided.

PURPOSE: Implanting stents to re-open stenotic lesions during percutaneous coronary interventions is considered a standard treatment for acute or chronic coronary syndrome. Intravascular ultrasound (IVUS) can be used to guide and assess the technical success of these interventions. Automatically segmenting stent struts in IVUS sequences improves workflow efficiency but is non-trivial due to a challenging image appearance entailing manifold ambiguities with other structures. Manual, ungated IVUS pullbacks constitute a challenge in this context. We propose a fully data-driven strategy to first longitudinally detect and subsequently segment stent struts in IVUS frames. APPROACH: A cascaded deep learning approach is presented. It first trains an encoder model to classify frames as “stent,” “no stent,” or “no use.” A segmentation model then delineates stent struts on a pixel level only in frames with a stent label. The first stage of the cascade acts as a gateway to reduce the risk for false positives in the second stage, the segmentation, which is trained on a smaller and difficult-to-annotate dataset. Training of the classification and segmentation model was based on 49,888 and 1826 frames of 74 sequences from 35 patients, respectively. RESULTS: The longitudinal classification yielded Dice scores of 92.96%, 82.35%, and 94.03% for the classes stent, no stent, and no use, respectively. The segmentation achieved a Dice score of 65.1% on the stent ground truth (intra-observer performance: 75.5%) and 43.5% on all frames (including frames without stent, with guidewires, calcium, or without clinical use). The latter improved to 49.5% when gating the frames by the classification decision and further increased to 57.4% with a heuristic on the plausible stent strut area. CONCLUSIONS: A data-driven strategy for segmenting stents in ungated, manual pullbacks was presented—the most common and practical scenario in the time-critical clinical workflow. We demonstrated a mitigated risk for ambiguities and false positive predictions.

Many active pharmaceutical ingredients (APIs) in the pharmaceutical pipeline require bioavailability enhancing formulations due to very low aqueous solubility. Although spray dried dispersions (SDDs) have demonstrated broad utility in enhancing the bioavailability of such APIs by trapping them in a high-energy amorphous form, many new chemical entities (NCEs) are poorly soluble not just in water, but in preferred organic spray drying solvents, e.g., methanol (MeOH) and acetone. Spraying poorly solvent soluble APIs from dilute solutions leads to low process throughput and small particles that challenge downstream processing. For APIs with basic pKa values, spray solvent solubility can be dramatically increased by using an acid to ionize the API. Specifically, we show that acetic acid can increase API solubility in MeOH:H2O by 10-fold for a weakly basic drug, gefitinib (GEF, pKa 7.2), by ionizing GEF to form the transient acetate salt. The acetic acid is removed during drying, resulting in a SDD of the original GEF free base having performance similar to SDDs sprayed from solvents without acetic acid. The increase in solvent solubility enables large scale manufacturing for these challenging APIs by significantly increasing the throughput and reducing the amount of solvent required.

The recent publication “Association between Urinary Metabolites and the Exposure of Intensive Care Newborns to Plasticizers of Medical Devices Used for Their Care Management” by L. Bernard et al. (2021) [...]

Knowing the shape of vascular calcifications is crucial for appropriate planning and conductance of percutaneous coronary interventions. The clinical workflow can therefore benefit from automatic segmentation of calcified plaques in intravascular ultrasound (IVUS) images. To solve segmentation problems with convolutional neural networks (CNNs), large datasets are usually required. However, datasets are often rather small in the medical domain. Hence, developing and investigating methods for increasing CNN performance on small datasets can help on the way towards clinically relevant results. We compared two state-of-the-art CNN architectures for segmentation, U-Net and DeepLabV3, and investigated how incorporating auxiliary image data with vessel wall and lumen annotations improves the calcium segmentation performance by using these either for pretraining or multi-task training. DeepLabV3 outperforms U-Net with up to 6.3 % by means of the Dice coefficient and 36.5 % by means of the average Hausdorff distance. Using auxiliary data improves the segmentation performance in both cases, whereas the multi-task approach outperforms the pre-training approach. The improvements of the multi-task approach in contrast to not using auxiliary data at all is 5.7 % for the Dice coefficient and 42.9 % for the average Hausdorff distance. Automatic segmentation of calcified plaques in IVUS images is a demanding task due to their relatively small size compared to the image dimensions and due to visual ambiguities with other image structures. We showed that this problem can generally be tackled by CNNs. Furthermore, we were able to improve the performance by a multi-task learning approach with auxiliary segmentation data.