Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPatchFCN for Intracranial Hemorrhage Detection
84
0
0.0
(
0
)
Added by
Weicheng Kuo
Publication date
2018
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This paper studies the problem of detecting and segmenting acute intracranial hemorrhage on head computed tomography (CT) scans. We propose to solve both tasks as a semantic segmentation problem using a patch-based fully convolutional network (PatchFCN). This formulation allows us to accurately localize hemorrhages while bypassing the complexity of object detection. Our system demonstrates competitive performance with a human expert and the state-of-the-art on classification tasks (0.976, 0.966 AUC of ROC on retrospective and prospective test sets) and on segmentation tasks (0.785 pixel AP, 0.766 Dice score), while using much less data and a simpler system. In addition, we conduct a series of controlled experiments to understand why PatchFCN outperforms standard FCN. Our studies show that PatchFCN finds a good trade-off between batch diversity and the amount of context during training. These findings may also apply to other medical segmentation tasks.
rate research
Read More
Deep learning for clinical applications is subject to stringent performance requirements, which raises a need for large labeled datasets. However, the enormous cost of labeling medical data makes this challenging. In this paper, we build a cost-sensitive active learning system for the problem of intracranial hemorrhage detection and segmentation on head computed tomography (CT). We show that our ensemble method compares favorably with the state-of-the-art, while running faster and using less memory. Moreover, our experiments are done using a substantially larger dataset than earlier papers on this topic. Since the labeling time could vary tremendously across examples, we model the labeling time and optimize the return on investment. We validate this idea by core-set selection on our large labeled dataset and by growing it with data from the wild.
Computed tomography (CT) is the imaging modality used in the diagnosis of neurological emergencies, including acute stroke and traumatic brain injury. Advances in deep learning have led to models that can detect and segment hemorrhage on head CT. PatchFCN, one such supervised fully convolutional network (FCN), recently demonstrated expert-level detection of intracranial hemorrhage on in-sample data. However, its potential for similar accuracy outside the training domain is hindered by its need for pixel-labeled data from outside institutions. Also recently, a semi-supervised technique, Noisy Student (NS) learning, demonstrated state-of-the-art performance on ImageNet by moving from a fully-supervised to a semi-supervised learning paradigm. We combine the PatchFCN and Noisy Student approaches, extending semi-supervised learning to an intracranial hemorrhage segmentation task. Surprisingly, the NS model performance surpasses that of a fully-supervised oracle model trained with image-level labels on the same data. It also performs comparably to another recently reported supervised model trained on a labeled dataset 600x larger than that used to train the NS model. To our knowledge, we are the first to demonstrate the effectiveness of semi-supervised learning on a head CT detection and segmentation task.
Background: Deep learning techniques have achieved high accuracy in image classification tasks, and there is interest in applicability to neuroimaging critical findings. This study evaluates the efficacy of 2D deep convolutional neural networks (DCNNs) for detecting basal ganglia (BG) hemorrhage on noncontrast head CT. Materials and Methods: 170 unique de-identified HIPAA-compliant noncontrast head CTs were obtained, those with and without BG hemorrhage. 110 cases were held-out for test, and 60 were split into training (45) and validation (15), consisting of 20 right, 20 left, and 20 no BG hemorrhage. Data augmentation was performed to increase size and variation of the training dataset by 48-fold. Two DCNNs were used to classify the images-AlexNet and GoogLeNet-using untrained networks and those pre-trained on ImageNet. Area under the curves (AUC) for the receiver-operator characteristic (ROC) curves were calculated, using the DeLong method for statistical comparison of ROCs. Results: The best performing model was the pre-trained augmented GoogLeNet, which had an AUC of 1.00 in classification of hemorrhage. Preprocessing augmentation increased accuracy for all networks (p<0.001), and pretrained networks outperformed untrained ones (p<0.001) for the unaugmented models. The best performing GoogLeNet model (AUC 1.00) outperformed the best performing AlexNet model (AUC 0.95)(p=0.01). Conclusion: For this dataset, the best performing DCNN identified BG hemorrhage on noncontrast head CT with an AUC of 1.00. Pretrained networks and data augmentation increased classifier accuracy. Future prospective research would be important to determine if the accuracy can be maintained on a larger cohort of patients and for very small hemorrhages.
In this work, we present a neuromorphic system that combines for the first time a neural recording headstage with a signal-to-spike conversion circuit and a multi-core spiking neural network (SNN) architecture on the same die for recording, processing, and detecting High Frequency Oscillations (HFO), which are biomarkers for the epileptogenic zone. The device was fabricated using a standard 0.18$mu$m CMOS technology node and has a total area of 99mm$^{2}$. We demonstrate its application to HFO detection in the iEEG recorded from 9 patients with temporal lobe epilepsy who subsequently underwent epilepsy surgery. The total average power consumption of the chip during the detection task was 614.3$mu$W. We show how the neuromorphic system can reliably detect HFOs: the system predicts postsurgical seizure outcome with state-of-the-art accuracy, specificity and sensitivity (78%, 100%, and 33% respectively). This is the first feasibility study towards identifying relevant features in intracranial human data in real-time, on-chip, using event-based processors and spiking neural networks. By providing neuromorphic intelligence to neural recording circuits the approach proposed will pave the way for the development of systems that can detect HFO areas directly in the operation room and improve the seizure outcome of epilepsy surgery.
Enodvascular coils treat intracranial aneurysms (IAs) by causing them to occlude by thrombosis. Ideally, coiled IAs eventually occlude in the long-term. However, 20.8% are found incompletely occluded at treatment follow-up. Computer simulations of coiling and its effect on aneurysmal flow could help clinicians predict treatment outcomes a priori, but it requires accurate modeling of coils and their deployment procedure. In addition to being accurate, coiling simulations must be efficient to be used as a bedside tool. To date, several virtual coiling techniques have been developed, but they lack either accuracy or efficiency. For example, finite-element-based virtual coiling methods model the mechanics of coiling and are highly accurate, at the expense of high computational cost (and thus low efficiency). Geometric-rule-based coiling techniques ignore the mechanics and therefore are computationally efficient, but may produce unrealistic coil deployments. In order to develop a virtual coiling method that combines accuracy and efficiency, we propose a novel virtual coiling algorithm that models coil deployment with nonlinear mechanics and nonlinear contact. Our approach is potentially more accurate than existing simple techniques because we model coil mechanics. It is also potentially faster than finite-element techniques because it models the most time-consuming part of these algorithms-namely contact resolution-with a novel formulation that resolves contact faster with exponential functions. Moreover, we model the coils pre-shape as well as coil packaging into the catheter, both of which are important to model but are lacking from most existing techniques.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
