Dataset Information

Accuracy, uncertainty, and adaptability of automatic myocardial ASL segmentation using deep CNN.

ABSTRACT:

Purpose

To apply deep convolution neural network to the segmentation task in myocardial arterial spin labeled perfusion imaging and to develop methods that measure uncertainty and that adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff.

Methods

The Monte Carlo dropout U-Net was trained on data from 22 subjects and tested on data from 6 heart transplant recipients. Manual segmentation and regional myocardial blood flow were available for comparison. We consider 2 global uncertainty measures, named "Dice uncertainty" and "Monte Carlo dropout uncertainty," which were calculated with and without the use of manual segmentation, respectively. Tversky loss function with a hyperparameter β was used to adapt the model to a specific false-positive versus false-negative tradeoff.

Results

The Monte Carlo dropout U-Net achieved a Dice coefficient of 0.91 ± 0.04 on the test set. Myocardial blood flow measured using automatic segmentations was highly correlated to that measured using the manual segmentation (R² = 0.96). Dice uncertainty and Monte Carlo dropout uncertainty were in good agreement (R² = 0.64). As β increased, the false-positive rate systematically decreased and false-negative rate systematically increased.

Conclusion

We demonstrate the feasibility of deep convolution neural network for automatic segmentation of myocardial arterial spin labeling, with good accuracy. We also introduce 2 simple methods for assessing model uncertainty. Finally, we demonstrate the ability to adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff. These findings are directly relevant to automatic segmentation in quantitative cardiac MRI and are broadly applicable to automatic segmentation problems in diagnostic imaging.

SUBMITTER: Do HP

PROVIDER: S-EPMC6989045 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeManually tracing regions of interest (ROIs) within the liver is the de facto standard method for measuring liver attenuation on computed tomography (CT) in diagnosing nonalcoholic fatty liver disease (NAFLD). However, manual tracing is resource intensive. To address these limitations and to expand the availability of a quantitative CT measure of hepatic steatosis, we propose the automatic liver attenuation ROI-based measurement (ALARM) method for automated liver attenuation estimation.MethodsThe ALARM method consists of two major stages: (a) deep convolutional neural network (DCNN)-based liver segmentation and (b) automated ROI extraction. First, liver segmentation was achieved using our previously developed SS-Net. Then, a single central ROI (center-ROI) and three circles ROI (periphery-ROI) were computed based on liver segmentation and morphological operations. The ALARM method is available as an open source Docker container (https://github.com/MASILab/ALARM).ResultsTwo hundred and forty-six subjects with 738 abdomen CT scans from the African American-Diabetes Heart Study (AA-DHS) were used for external validation (testing), independent from the training and validation cohort (100 clinically acquired CT abdominal scans). From the correlation analyses, the proposed ALARM method achieved Pearson correlations = 0.94 with manual estimation on liver attenuation estimations. When evaluating the ALARM method for detection of nonalcoholic fatty liver disease (NAFLD) using the traditional cut point of < 40 HU, the center-ROI achieved substantial agreements (Kappa = 0.79) with manual estimation, while the periphery-ROI method achieved "excellent" agreement (Kappa = 0.88) with manual estimation. The automated ALARM method had reduced variability compared to manual measurements as indicated by a smaller standard deviation.ConclusionsWe propose a fully automated liver attenuation estimation method termed ALARM by combining DCNN and morphological operations, which achieved "excellent" agreement with manual estimation for fatty liver detection. The entire pipeline is implemented as a Docker container which enables users to achieve liver attenuation estimation in five minutes per CT exam.

Project description:Purpose: More and more automatic segmentation tools are being introduced in routine clinical practice. However, physicians need to spend a considerable amount of time in examining the generated contours slice by slice. This greatly reduces the benefit of the tool's automaticity. In order to overcome this shortcoming, we developed an automatic quality assurance (QA) method for automatic segmentation using convolutional neural networks (CNNs). Materials and Methods: The study cohort comprised 680 patients with early-stage breast cancer who received whole breast radiation. The overall architecture of the automatic QA method for deep learning-based segmentation included the following two main parts: a segmentation CNN model and a QA network that was established based on ResNet-101. The inputs were from computed tomography, segmentation probability maps, and uncertainty maps. Two kinds of Dice similarity coefficient (DSC) outputs were tested. One predicted the DSC quality level of each slice ([0.95, 1] for "good," [0.8, 0.95] for "medium," and [0, 0.8] for "bad" quality), and the other predicted the DSC value of each slice directly. The performances of the method to predict the quality levels were evaluated with quantitative metrics: balanced accuracy, F score, and the area under the receiving operator characteristic curve (AUC). The mean absolute error (MAE) was used to evaluate the DSC value outputs. Results: The proposed methods involved two types of output, both of which achieved promising accuracy in terms of predicting the quality level. For the good, medium, and bad quality level prediction, the balanced accuracy was 0.97, 0.94, and 0.89, respectively; the F score was 0.98, 0.91, and 0.81, respectively; and the AUC was 0.96, 0.93, and 0.88, respectively. For the DSC value prediction, the MAE was 0.06 ± 0.19. The prediction time was approximately 2 s per patient. Conclusions: Our method could predict the segmentation quality automatically. It can provide useful information for physicians regarding further verification and revision of automatic contours. The integration of our method into current automatic segmentation pipelines can improve the efficiency of radiotherapy contouring.