Signal-known-statistically Research Articles

Convolutional neural network-based model observer for signal known statistically task in breast tomosynthesis images.

Since human observer studies are resource-intensive, mathematical model observers are frequently used to assess task-based image quality. The most common implementation of these model observers assume that the signal information is exactly known. However, these tasks cannot thoroughly represent situations where the signal information is not exactly known in terms of size andshape. Considering the limitations of the tasks for which signal information is exactly known, we proposed a convolutional neural network (CNN)-based model observer for signal known statistically (SKS) and background known statistically (BKS) detection tasks in breast tomosynthesis images. A wide parameter search was conducted from six different acquisition angles (i.e., 10°, 20°, 30°, 40°, 50°, and 60°) within the same dose level (i.e., 2.3 mGy) under two separate acquisition schemes: (1) constant total number of projections, and (2) constant angular separation between projections. Two different types of signals: spherical (i.e., SKE tasks) and spiculated (i.e., SKS tasks) were used. The detection performance of the CNN-based model observer was compared with that of the Hotelling observer (HO) instead of the IO. Pixel-wise gradient-weighted class activation mapping (pGrad-CAM) map was extracted from each reconstructed tomosynthesis image to provide an intuitive understanding of the trained CNN-based modelobserver. The CNN-based model observer achieved a higher detection performance compared to that of the HO for all tasks. Moreover, the improvement in its detection performance was greater for SKS tasks compared to that for SKE tasks. These results demonstrated that the addition of nonlinearity improved the detection performance owing to the variation of the background and signal. Interestingly, the pGrad-CAM results effectively localized the class-specific discriminative region, further supporting the quantitative evaluation results of the CNN-based model observer. In addition, we verified that the CNN-based model observer required fewer images to achieve the detection performance of theHO. In this work, we proposed a CNN-based model observer for SKS and BKS detection tasks in breast tomosynthesis images. Throughout the study, we demonstrated that the detection performance of the proposed CNN-based model observer was superior to that of theHO.

Low-dose CT denoising via convolutional neural network with an observer loss function.

Convolutional neural network (CNN)-based denoising is an effective method for reducing complex computed tomography (CT) noise. However, the image blur induced by denoising processes is a major concern. The main source of image blur is the pixel-level loss (e.g., mean squared error [MSE] and mean absolute error [MAE]) used to train a CNN denoiser. To reduce the image blur, feature-level loss is utilized to train a CNN denoiser. A CNN denoiser trained using visual geometry group (VGG) loss can preserve the small structures, edges, and texture of the image.However, VGG loss, derived from an ImageNet-pretrained image classifier, is not optimal for training a CNN denoiser for CT images. ImageNet contains natural RGB images, so the features extracted by the ImageNet-pretrained model cannot represent the characteristics of CT images that are highly correlated with diagnosis. Furthermore, a CNN denoiser trained with VGG loss causes bias in CT number. Therefore, we propose to use a binary classification network trained using CT images as a feature extractor and newly define the feature-level loss as observerloss. As obtaining labeled CT images for training classification network is difficult, we create labels by inserting simulated lesions. We conduct two separate classification tasks, signal-known-exactly (SKE) and signal-known-statistically (SKS), and define the corresponding feature-level losses as SKE loss and SKS loss, respectively. We use SKE loss and SKS loss to train CNNdenoiser. Compared to pixel-level losses, a CNN denoiser trained using observer loss (i.e., SKE loss and SKS loss) is effective in preserving structure, edge, and texture. Observer loss also resolves the bias in CT number, which is a problem of VGG loss. Comparing observer losses using SKE and SKS tasks, SKS yields images having a more similar noise structure to referenceimages. Using observer loss for training CNN denoiser is effective to preserve structure, edge, and texture in denoised images and prevent the CT number bias. In particular, when using SKS loss, denoised images having a similar noise structure to reference images are generated.

A convolutional neural network-based anthropomorphic model observer for signal-known-statistically and background-known-statistically detection tasks

The purpose of this study is implementation of an anthropomorphic model observer using a convolutional neural network (CNN) for signal-known-statistically (SKS) and background-known-statistically (BKS) detection tasks. We conduct SKS/BKS detection tasks on simulated cone beam computed tomography (CBCT) images with eight types of signal and randomly varied breast anatomical backgrounds. To predict human observer performance, we use conventional anthropomorphic model observers (i.e. the non-prewhitening observer with an eye-filter, the dense difference-of-Gaussian channelized Hotelling observer (CHO), and the Gabor CHO) and implement CNN-based model observer. We propose an effective data labeling strategy for CNN training reflecting the inefficiency of human observer decision-making on detection and investigate various CNN architectures (from single-layer to four-layer). We compare the abilities of CNN-based and conventional model observers to predict human observer performance for different background noise structures. The three-layer CNN trained with labeled data generated by our proposed labeling strategy predicts human observer performance better than conventional model observers for different noise structures in CBCT images. This network also shows good correlation with human observer performance for general tasks when training and testing images have different noise structures.

Approximating the Ideal Observer and Hotelling Observer for Binary Signal Detection Tasks by Use of Supervised Learning Methods.

It is widely accepted that the optimization of medical imaging system performance should be guided by task-based measures of image quality (IQ). Task-based measures of IQ quantify the ability of an observer to perform a specific task, such as detection or estimation of a signal (e.g., a tumor). For binary signal detection tasks, the Bayesian Ideal Observer (IO) sets an upper limit of observer performance and has been advocated for use in optimizing medical imaging systems and data-acquisition designs. Except in special cases, the determination of the IO test statistic is analytically intractable. Markov-chain Monte Carlo (MCMC) techniques can be employed to approximate the IO detection performance, but their reported applications have been limited to relatively simple object models. In cases where the IO test statistic is difficult to compute, the Hotelling Observer (HO) can be employed. To compute the HO test statistic, potentially large covariance matrices must be accurately estimated and subsequently inverted, which can present computational challenges. This paper investigates the supervised learning-based methodologies for approximating the IO and HO test statistics. Convolutional neural networks (CNNs) and single-layer neural networks (SLNNs) are employed to approximate the IO and HO test statistics, respectively. The numerical simulations were conducted for both signal-known-exactly (SKE) and signal-known-statistically (SKS) signal detection tasks. The considered background models include the lumpy object model and the clustered lumpy object model. The measurement noise models considered are Gaussian, Laplacian, and mixed Poisson-Gaussian. The performances of the supervised learning methods are assessed via receiver operating characteristic (ROC) analysis, and the results are compared to those produced by the use of traditional numerical methods or analytical calculations when feasible. The potential advantages of the proposed supervised learning approaches for approximating the IO and HO test statistics are discussed.

Channelized model observer for the detection and estimation of signals with unknown amplitude, orientation, and size

As a task-based approach for medical image quality assessment, model observers (MOs) have been proposed as surrogates for human observers. While most MOs treat only signal-known-exactly tasks, there are few studies on signal-known-statistically (SKS) MOs, which are clinically more relevant. In this paper, we present a new SKS MO named channelized joint detection and estimation observer (CJO), capable of detecting and estimating signals with unknown amplitude, orientation, and size. We evaluate its estimation and detection performance using both synthesized (correlated Gaussian) backgrounds and real clinical (magnetic resonance) backgrounds. The results suggest that the CJO has good performance in the SKS detection-estimation task.

Mass detection on mammograms: influence of signal shape uncertainty on human and model observers

We studied the influence of signal variability on human and model observers for detection tasks with realistic simulated masses superimposed on real patient mammographic backgrounds and synthesized mammographic backgrounds (clustered lumpy backgrounds, CLB). Results under the signal-known-exactly (SKE) paradigm were compared with signal-known-statistically (SKS) tasks for which the observers did not have prior knowledge of the shape or size of the signal. Human observers' performance did not vary significantly when benign masses were superimposed on real images or on CLB. Uncertainty and variability in signal shape did not degrade human performance significantly compared with the SKE task, while variability in signal size did. Implementation of appropriate internal noise components allowed the fit of model observers to human performance.