Dataset Information

Use of a convolutional neural network to identify infarct core using computed tomography perfusion parameters.

ABSTRACT:

Purpose

Computed tomography perfusion (CTP) is used to diagnose ischemic strokes through contralateral hemisphere comparisons of various perfusion parameters. Various perfusion parameter thresholds have been utilized to segment infarct tissue due to differences in CTP software and patient baseline hemodynamics. This study utilized a convolutional neural network (CNN) to eliminate the need for non-universal parameter thresholds to segment infarct tissue.

Methods

CTP data from 63 ischemic stroke patients was retrospectively collected and perfusion parameter maps were generated using Vitrea CTP software. Infarct ground truth labels were segmented from diffusion-weighted imaging (DWI) and CTP and DWI volumes were registered. A U-net based CNN was trained and tested five separate times using each CTP parameter (cerebral blood flow (CBF), cerebral blood volume (CBV), time-to-peak (TTP), mean-transit-time (MTT), delay time). 8,352 infarct slices were utilized with a 60:30:10 training:testing:validation split and Monte Carlo cross-validation was conducted using 20 iterations. Infarct volumes were reconstructed following segmentation from each CTP slice. Infarct spatial and volumetric agreement was compared between each CTP parameter and DWI.

Results

Spatial agreement metrics (Dice coefficient, positive predictive value) for each CTP parameter in predicting infarct volumes are: CBF=(0.67, 0.76), CBV=(0.44, 0.62), TTP=(0.60, 0.67), MTT=(0.58, 0.62), delay time=(0.57, 0.60). 95% confidence intervals for volume differences with DWI infarct are: CBF=14.3±11.5 mL, CBV=29.6±21.2 mL, TTP=7.7±15.2 mL, MTT=-10.7±18.6 mL, delay time=-5.7±23.6 mL.

Conclusions

CBF is the most accurate CTP parameter in segmenting infarct tissue. Segmentation of infarct using a CNN has the potential to eliminate non-universal CTP contralateral hemisphere comparison thresholds.

SUBMITTER: Rava RA

PROVIDER: S-EPMC7946163 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Use of a convolutional neural network to identify infarct core using computed tomography perfusion parameters.

Rava Ryan A RA Podgorsak Alexander R AR Waqas Muhammad M Snyder Kenneth V KV Levy Elad I EI Davies Jason M JM Siddiqui Adnan H AH Ionita Ciprian N CN

Proceedings of SPIE--the International Society for Optical Engineering 20210215

<h4>Purpose</h4>Computed tomography perfusion (CTP) is used to diagnose ischemic strokes through contralateral hemisphere comparisons of various perfusion parameters. Various perfusion parameter thresholds have been utilized to segment infarct tissue due to differences in CTP software and patient baseline hemodynamics. This study utilized a convolutional neural network (CNN) to eliminate the need for non-universal parameter thresholds to segment infarct tissue.<h4>Methods</h4>CTP data from 63 is ...[more]

PMID: 33707811

Similar Datasets

Project description:Background and purposeThe ISLES challenge (Ischemic Stroke Lesion Segmentation) enables globally diverse teams to compete to develop advanced tools for stroke lesion analysis with machine learning. Detection of irreversibly damaged tissue on computed tomography perfusion (CTP) is often necessary to determine eligibility for late-time-window thrombectomy. Therefore, the aim of ISLES-2018 was to segment infarcted tissue on CTP based on diffusion-weighted imaging as a reference standard.MethodsThe data, from 4 centers, consisted of 103 cases of acute anterior circulation large artery occlusion stroke who underwent diffusion-weighted imaging rapidly after CTP. Diffusion-weighted imaging lesion segmentation was performed manually and acted as a reference standard. The data were separated into 63 cases for training and 40 for testing, upon which quality metrics (dice score coefficient, Hausdorff distance, absolute lesion volume difference, etc) were computed to rank methods based on their overall performance.ResultsTwenty-four different teams participated in the challenge. Median time to CTP was 185 minutes (interquartile range, 180-238), the time between CTP and magnetic resonance imaging was 36 minutes (interquartile range, 25-79), and the median infarct lesion size was 15.2 mL (interquartile range, 5.7-45). The best performance for Dice score coefficient and absolute volume difference were 0.51 and 10.1 mL, respectively, from different teams. Based on the ranking criteria, the top team's algorithm demonstrated for average Dice score coefficient and average absolute volume difference 0.51 and 10.2 mL, respectively, outperforming the conventional threshold-based method (dice score coefficient, 0.3; volume difference, 15.3). Diverse algorithms were used, almost all based on deep learning, with top-ranked approaches making use of the raw perfusion data as well as methods to synthetically generate complementary information to boost prediction performance.ConclusionsMachine learning methods may predict infarcted tissue from CTP with improved accuracy compared with threshold-based methods used in clinical routine. This dataset will remain public and can be used to test improvement in algorithms over time.

Project description:PURPOSE:Scatter is a major factor degrading the image quality of cone beam computed tomography (CBCT). Conventional scatter correction strategies require handcrafted analytical models with ad hoc assumptions, which often leads to less accurate scatter removal. This study aims to develop an effective scatter correction method using a residual convolutional neural network (CNN). METHODS:A U-net based 25-layer CNN was constructed for CBCT scatter correction. The establishment of the model consists of three steps: model training, validation, and testing. For model training, a total of 1800 pairs of x-ray projection and the corresponding scatter-only distribution in nonanthropomorphic phantoms taken in full-fan scan were generated using Monte Carlo simulation of a CBCT scanner installed with a proton therapy system. An end-to-end CNN training was implemented with two major loss functions for 100 epochs with a mini-batch size of 10. Image rotations and flips were randomly applied to augment the training datasets during training. For validation, 200 projections of a digital head phantom were collected. The proposed CNN-based method was compared to a conventional projection-domain scatter correction method named fast adaptive scatter kernel superposition (fASKS) method using 360 projections of an anthropomorphic head phantom. Two different loss functions were applied for the same CNN to evaluate the impact of loss functions on the final results. Furthermore, the CNN model trained with full-fan projections was fine-tuned for scatter correction in half-fan scan by using transfer learning with additional 360 half-fan projection pairs of nonanthropomorphic phantoms. The tuned-CNN model for half-fan scan was compared with the fASKS method as well as the CNN-based method without the fine-tuning using additional lung phantom projections. RESULTS:The CNN-based method provides projections with significantly reduced scatter and CBCT images with more accurate Hounsfield Units (HUs) than that of the fASKS-based method. Root mean squared error of the CNN-corrected projections was improved to 0.0862 compared to 0.278 for uncorrected projections or 0.117 for the fASKS-corrected projections. The CNN-corrected reconstruction provided better HU quantification, especially in regions near the air or bone interfaces. All four image quality measures, which include mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM), indicated that the CNN-corrected images were significantly better than that of the fASKS-corrected images. Moreover, the proposed transfer learning technique made it possible for the CNN model trained with full-fan projections to be applicable to remove scatters in half-fan projections after fine-tuning with only a small number of additional half-fan training datasets. SSIM value of the tuned-CNN-corrected images was 0.9993 compared to 0.9984 for the non-tuned-CNN-corrected images or 0.9990 for the fASKS-corrected images. Finally, the CNN-based method is computationally efficient - the correction time for the 360 projections only took less than 5 s in the reported experiments on a PC (4.20 GHz Intel Core-i7 CPU) with a single NVIDIA GTX 1070 GPU. CONCLUSIONS:The proposed deep learning-based method provides an effective tool for CBCT scatter correction and holds significant value for quantitative imaging and image-guided radiation therapy.

Project description:IntroductionComputed tomography perfusion (CTP) imaging has become an important tool in evaluating acute recanalization treatment candidates. Large clinical trials have successfully used RAPID automated imaging analysis software for quantifying ischemic core and penumbra, yet other commercially available software vendors are also on the market. We evaluated the possible difference in ischemic core and perfusion lesion volumes and the agreement rate of target mismatch between OLEA, MIStar, and Syngo.Via versus RAPID software in acute recanalization treatment candidates.Patients and methodsAll consecutive stroke-code patients with baseline CTP RAPID imaging at Helsinki University Hospital during 8/2018-9/2021 were included. Ischemic core was defined as cerebral blood flow <30% than the contralateral hemisphere and within the area of delay time (DT) >3s with MIStar. Perfusion lesion volume was defined as DT > 3 s (MIStar) and Tmax > 6 s with all other software. A perfusion mismatch ratio of ⩾1.8, a perfusion lesion volume of ⩾15 mL, and ischemic core <70 mL was defined as target mismatch. The mean pairwise differences of the core and perfusion lesion volumes between software were calculated using the Bland-Altman method and the agreement of target mismatch between software using the Pearson correlation.ResultsA total of 1606 patients had RAPID perfusion maps, 1222 of which had MIStar, 596 patients had OLEA, and 349 patients had Syngo.Via perfusion maps available. Each software was compared with simultaneously analyzed RAPID software. MIStar showed the smallest core difference compared with RAPID (-2 mL, confidence interval (CI) from -26 to 22), followed by OLEA (2 mL, CI from -33 to 38). Perfusion lesion volume differed least with MIStar (4 mL, CI from -62 to 71) in comparison with RAPID, followed by Syngo.Via (6 mL, CI from -94 to 106). MIStar had the best agreement rate with target mismatch of RAPID followed by OLEA and Syngo.Via.Discussion and conclusionComparison of RAPID with three other automated imaging analysis software showed variance in ischemic core and perfusion lesion volumes and in target mismatch.

Dataset Information

Use of a convolutional neural network to identify infarct core using computed tomography perfusion parameters.

Purpose

Methods

Results

Conclusions

Publications

Use of a convolutional neural network to identify infarct core using computed tomography perfusion parameters.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets