arXiv subjects

Jeremy J. Heit

Publications and source records attributed to Jeremy J. Heit.

5 recordsLinked to original sources

arXiv2024

Milli-spinner thrombectomy

Blockage of blood flow in arteries or veins by blood clots can lead to serious medical conditions. Mechanical thrombectomy (MT), minimally invasive endovascular procedures that utilize aspiration, stent retriever, or cutting mechanisms for clot removal have emerged as an effective treatment modality for ischemic stroke, myocardial infarction, pulmonary embolism, and peripheral vascular disease. However, state-of-the-art MT technologies still fail to remove clots in approximately 10% to 30% of patients, especially when treating large-size clots with high fibrin content. In addition, the working mechanism of most current MT techniques results in rupturing or cutting of clots which could lead to clot fragmentation and distal emboli. Here, we report a new MT technology based on an unprecedented mechanism, in which a milli-spinner mechanically debulks the clot by densifying its fibrin fiber network and discharging red blood cells to significantly reduce the clot volume for complete clot removal. This mechanism is achieved by the spin-induced compression and shearing of the clot. We demonstrate its effective clot-debulking performance with clot volumetric reduction of up to 90% on various sizes of clots with diverse clot compositions. Milli-spinner MT in both in-vitro pulmonary and cerebral artery flow models and in-vivo swine models demonstrate high-fidelity revascularization. The milli-spinner MT is the first reported mechanism that directly modifies the clot microstructure to facilitate clot removal, which also results in markedly improved MT efficacy compared to the existing MT mechanisms that are based on clot rupturing and cutting. This technology introduces a unique mechanical way of debulking and removing clots for future MT device development, especially for the treatment of ischemic stroke, pulmonary emboli, and peripheral thrombosis.

physics.app-ph↗

arXiv2023

USE-Evaluator: Performance Metrics for Medical Image Segmentation Models with Uncertain, Small or Empty Reference Annotations

Performance metrics for medical image segmentation models are used to measure the agreement between the reference annotation and the predicted segmentation. Usually, overlap metrics, such as the Dice, are used as a metric to evaluate the performance of these models in order for results to be comparable. However, there is a mismatch between the distributions of cases and difficulty level of segmentation tasks in public data sets compared to clinical practice. Common metrics fail to measure the impact of this mismatch, especially for clinical data sets that include low signal pathologies, a difficult segmentation task, and uncertain, small, or empty reference annotations. This limitation may result in ineffective research of machine learning practitioners in designing and optimizing models. Dimensions of evaluating clinical value include consideration of the uncertainty of reference annotations, independence from reference annotation volume size, and evaluation of classification of empty reference annotations. We study how uncertain, small, and empty reference annotations influence the value of metrics for medical image segmentation on an in-house data set regardless of the model. We examine metrics behavior on the predictions of a standard deep learning framework in order to identify metrics with clinical value. We compare to a public benchmark data set (BraTS 2019) with a high-signal pathology and certain, larger, and no empty reference annotations. We may show machine learning practitioners, how uncertain, small, or empty reference annotations require a rethinking of the evaluation and optimizing procedures. The evaluation code was released to encourage further analysis of this topic. https://github.com/SophieOstmeier/UncertainSmallEmpty.git

eess.IV↗

arXiv2023

Non-inferiority of Deep Learning Acute Ischemic Stroke Segmentation on Non-Contrast CT Compared to Expert Neuroradiologists

To determine if a convolutional neural network (CNN) deep learning model can accurately segment acute ischemic changes on non-contrast CT compared to neuroradiologists. Non-contrast CT (NCCT) examinations from 232 acute ischemic stroke patients who were enrolled in the DEFUSE 3 trial were included in this study. Three experienced neuroradiologists independently segmented hypodensity that reflected the ischemic core on each scan. The neuroradiologist with the most experience (expert A) served as the ground truth for deep learning model training. Two additional neuroradiologists (experts B and C) segmentations were used for data testing. The 232 studies were randomly split into training and test sets. The training set was further randomly divided into 5 folds with training and validation sets. A 3-dimensional CNN architecture was trained and optimized to predict the segmentations of expert A from NCCT. The performance of the model was assessed using a set of volume, overlap, and distance metrics using non-inferiority thresholds of 20%, 3ml, and 3mm. The optimized model trained on expert A was compared to test experts B and C. We used a one-sided Wilcoxon signed-rank test to test for the non-inferiority of the model-expert compared to the inter-expert agreement. The final model performance for the ischemic core segmentation task reached a performance of 0.46+-0.09 Surface Dice at Tolerance 5mm and 0.47+-0.13 Dice when trained on expert A. Compared to the two test neuroradiologists the model-expert agreement was non-inferior to the inter-expert agreement, p < 0.05. The CNN accurately delineates the hypodense ischemic core on NCCT in acute ischemic stroke patients with an accuracy comparable to neuroradiologists.

eess.IV↗

arXiv2023

Random Expert Sampling for Deep Learning Segmentation of Acute Ischemic Stroke on Non-contrast CT

Purpose: Multi-expert deep learning training methods to automatically quantify ischemic brain tissue on Non-Contrast CT Materials and Methods: The data set consisted of 260 Non-Contrast CTs from 233 patients of acute ischemic stroke patients recruited in the DEFUSE 3 trial. A benchmark U-Net was trained on the reference annotations of three experienced neuroradiologists to segment ischemic brain tissue using majority vote and random expert sampling training schemes. We used a one-sided Wilcoxon signed-rank test on a set of segmentation metrics to compare bootstrapped point estimates of the training schemes with the inter-expert agreement and ratio of variance for consistency analysis. We further compare volumes with the 24h-follow-up DWI (final infarct core) in the patient subgroup with full reperfusion and we test volumes for correlation to the clinical outcome (mRS after 30 and 90 days) with the Spearman method. Results: Random expert sampling leads to a model that shows better agreement with experts than experts agree among themselves and better agreement than the agreement between experts and a majority-vote model performance (Surface Dice at Tolerance 5mm improvement of 61% to 0.70 +- 0.03 and Dice improvement of 25% to 0.50 +- 0.04). The model-based predicted volume similarly estimated the final infarct volume and correlated better to the clinical outcome than CT perfusion. Conclusion: A model trained on random expert sampling can identify the presence and location of acute ischemic brain tissue on Non-Contrast CT similar to CT perfusion and with better consistency than experts. This may further secure the selection of patients eligible for endovascular treatment in less specialized hospitals.

cs.CV↗

arXiv2020

Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders: A Comparison Study

We show that high quality, diverse and realistic-looking diffusion-weighted magnetic resonance images can be synthesized using deep generative models. Based on professional neuroradiologists' evaluations and diverse metrics with respect to quality and diversity of the generated synthetic brain images, we present two networks, the Introspective Variational Autoencoder and the Style-Based GAN, that qualify for data augmentation in the medical field, where information is saved in a dispatched and inhomogeneous way and access to it is in many aspects restricted.

cs.CV↗