Proceedings ArticleDOI
A task-informed model training method for deep neural network-based image denoising
Kaiyan Li,Hua Li,Mark A. Anastasio +2 more
- Vol. 12035, pp 1203510-1203510
Reads0
Chats0
TLDR
The presented results indicate that the task-informed training method can improve observer performance while providing control over the trade off between traditional and task-based measures of image quality.Abstract:
A variety of deep neural network (DNN)-based image denoising methods have been proposed for use with medical images. These methods are typically trained by minimizing loss functions that quantify a distance between the denoised image and the defined target image (e.g., a noise-free or low noise image). They have demonstrated high performance in terms of traditional image quality metrics such as root mean square error (RMSE), structural similarity index metric (SSIM), or peak signal-to-noise ratio (PSNR). However, it has been reported that these denoising methods may not improve the objective measures of image quality (IQ). In this work, a task-informed model training method that preserves task-specific information is established and systematically evaluated with clinical realistic simulated low-dose X-ray computed tomography (CT) images. Specifically, binary signal detection tasks under signal-known-statistically (SKS) with background-known-statistically (BKS) conditions are considered. The low-dose CT denoising networks are first pretrained by use of a mean-square-error (MSE) loss function. A fully connected layer with a sigmoid activation function is subsequently appended to the denoising network, which can be interpreted as a single layer neural network-based numerical observer (SLNN-NO). A hybrid loss function consisting of a binary cross-entropy loss function and mean square loss function is employed to jointly fine-tune the denoising network and train the SLNN-NO. The performance of the SLNN-NO on denoised data is quantified to evaluate the impact of the task-informed training procedure on the denoising network. The presented results indicate that the task-informed training method can improve observer performance while providing control over the trade off between traditional and task-based measures of image quality.read more
Citations
More filters
Journal ArticleDOI
Joint localization and classification of breast tumors on ultrasound images using a novel auxiliary attention-based framework
Zong Fan,Ping Gong,Shanshan Tang,Christine U. Lee,Xiaohui Zhang,Pengfei Song,Shigao Chen,Hua Li +7 more
TL;DR: A novel joint localization and classification model based on the attention mechanism and disentangled semi-supervised learning strategy is proposed for automatic breast lesion detection and localization in computer-aided diagnosis.
Journal ArticleDOI
A novel adversarial learning strategy for medical image classification
Zong Fan,Xiaohui Zhang,Jacob Gasienica,Jennifer Potts,Su Ruan,Wade L. Thorstad,H. Gay,Xiaowei Wang,Hua Li +8 more
TL;DR: This modularized framework demonstrates its ability to adapt the feature extraction networks and auxiliary networks to various applications, thus holding the potential to be applied to other clinical applications in the future.
Journal ArticleDOI
Utilization of an attentive map to preserve anatomical features for training convolutional neural network based low dose CT denoiser.
TL;DR: In this paper , an attentive map derived from a lesion classifier is created to represent the extent to which each pixel influences the decision by the lesions classifier, which is used as a weight to emphasize important parts of the image.
Proceedings ArticleDOI
Estimating task-based performance bounds for image reconstruction methods by use of learned-ideal observers
TL;DR: In this article , the performance of the Ideal Observer (IO) acting on imaging measurements has been evaluated and optimized by using objective measures of image quality (IQ) to guide the optimization of medical imaging systems.
Journal ArticleDOI
DEMIST: A deep-learning-based task-specific denoising approach for myocardial perfusion SPECT
TL;DR: In this paper , a detection task-specific deep-learning-based approach for denoising MPI SPECT images (DEMIST) is proposed to preserve features that influence observer performance on detection tasks.
References
More filters
Journal ArticleDOI
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TL;DR: Zhang et al. as mentioned in this paper proposed a feed-forward denoising convolutional neural networks (DnCNNs) to handle Gaussian denobling with unknown noise level.
Journal ArticleDOI
The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans.
Samuel G. Armato,Geoffrey McLennan,Luc Bidaut,Michael F. McNitt-Gray,Charles R. Meyer,Anthony P. Reeves,Binsheng Zhao,Denise R. Aberle,Claudia I. Henschke,Eric A. Hoffman,Ella A. Kazerooni,Heber MacMahon,Edwin J. R. van Beek,David F. Yankelevitz,Alberto Biancardi,Peyton H. Bland,Matthew S. Brown,Roger Engelmann,Gary E. Laderach,Daniel Max,Richard C. Pais,David Qing,Rachael Y. Roberts,Amanda R. Smith,Adam Starkey,Poonam Batra,Philip Caligiuri,Ali Farooqi,Gregory W. Gladish,C. Matilda Jude,Reginald F. Munden,Iva Petkovska,Leslie E. Quint,Lawrence H. Schwartz,Baskaran Sundaram,Lori E. Dodd,Charles Fenimore,David Gur,Nicholas Petrick,John Freymann,Justin Kirby,Brian Hughes,Alessi Vande Casteele,Sangeeta Gupte,Maha Sallam,Michael D. Heath,Michael Kuhn,Ekta Dharaiya,Richard Burns,David Fryd,Marcos Salganicoff,Vikram Anand,Uri Shreter,Stephen Vastagh,Barbara Y. Croft,Laurence P. Clarke +55 more
TL;DR: The goal of this process was to identify as completely as possible all lung nodules in each CT scan without requiring forced consensus and is expected to provide an essential medical imaging research resource to spur CAD development, validation, and dissemination in clinical practice.
Journal ArticleDOI
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TL;DR: Zhang et al. as discussed by the authors proposed a denoising convolutional neural network (DnCNN) to handle Gaussian denoizing with unknown noise level, which implicitly removes the latent clean image in the hidden layers.
Journal ArticleDOI
Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss
Qingsong Yang,Pingkun Yan,Yanbo Zhang,Hengyong Yu,Yongyi Shi,Xuanqin Mou,Mannudeep K. Kalra,Yi Zhang,Ling Sun,Ge Wang +9 more
TL;DR: Wang et al. as mentioned in this paper introduced a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity, which is capable of not only reducing the image noise level but also trying to keep the critical information at the same time.
Journal ArticleDOI
Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
Qingsong Yang,Pingkun Yan,Yanbo Zhang,Hengyong Yu,Yongyi Shi,Xuanqin Mou,Mannudeep K. Kalra,Ge Wang +7 more
TL;DR: This paper introduces a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity that is capable of not only reducing the image noise level but also trying to keep the critical information at the same time.