An investigation of quantitative accuracy for deep learning based denoising in oncological PET

Lu, Wenzhuo; Onofrey, John A.; Lu, Yihuan; Shi, Luyao; Ma, Tianyu; Liu, Yaqiang; Liu, Chi

doi:10.1088/1361-6560/ab3242

Cited by 106 publications

(98 citation statements)

References 47 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several novel aspects of this study. The majority of other related work has been performed in 2D since processing times are faster, fewer GPU memory issues are encountered, and the availability of pretrained 2D networks provides additional options in the choice of training objectives [23][24][25][26]. However, volumetric 3D PET data are the medical standard, and inclusion of the additional dimension of data was expected to improve training stability and robustness of the network performance [27].…”

Section: Discussionmentioning

confidence: 99%

“…The noise in PET images is generally assumed to follow Gaussian and/or Poisson distributions, and deep learning is especially well positioned to address this since the characteristic features of the noise, regardless of the assumed model, are inherently learned through training. Several techniques have previously been applied successfully for denoising PET images [23][24][25][26], to date however, there are very few studies exploring CNNs which handle 3D data. Due to the volumetric nature of data, it is expected that the performance of CNNs could be improved [27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional neural networks for improving image quality with noisy PET data

et al. 2020

View full text Add to dashboard Cite

Goal PET is a relatively noisy process compared to other imaging modalities, and sparsity of acquisition data leads to noise in the images. Recent work has focused on machine learning techniques to improve PET images, and this study investigates a deep learning approach to improve the quality of reconstructed image volumes through denoising by a 3D convolution neural network. Potential improvements were evaluated within a clinical context by physician performance in a reading task. Methods A wide range of controlled noise levels was emulated from a set of chest PET data in patients with lung cancer, and a convolutional neural network was trained to denoise the reconstructed images using the full-count reconstructions as the ground truth. The benefits, over conventional Gaussian smoothing, were quantified across all noise levels by observer performance in an image ranking and lesion detection task. Results The CNN-denoised images were generally ranked by the physicians equal to or better than the Gaussian-smoothed images for all count levels, with the largest effects observed in the lowest-count image sets. For the CNN-denoised images, overall lesion contrast recovery was 60% and 90% at the 1 and 20 million count levels, respectively. Notwithstanding the reduced lesion contrast recovery in noisy data, the CNN-denoised images also yielded better lesion detectability in low count levels. For example, at 1 million true counts, the average true positive detection rate was around 40% for the CNN-denoised images and 30% for the smoothed images. Conclusion Significant improvements were found for CNN-denoising for very noisy images, and to some degree for all noise levels. The technique presented here offered however limited benefit for detection performance for images at the count levels routinely encountered in the clinic.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Convolutional neural networks for improving image quality with noisy PET data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…By communicating these times to patients can result in enhanced patient satisfaction, and it also helps to identify process improvement opportunities diligently; therefore, augment the number of tests accomplished by any resource [19]. At the time of point of care for medical decision support in requests for imaging, AI algorithms can be used to scrutinize a patient's medical records and decide the suitableness of imaging and provide advice for which imaging exam would be most appropriate [20]. Some AI systems have demonstrated assurance in de-noising data obtained at notably lower radiation levels than previously required, resulting in image acquisition optimization with dramatically low radiation exposure [21].…”

Section: Ai Affecting Radiologymentioning

confidence: 99%

Is Artificial Intelligence the New Friend for Radiologists? A Review Article

Gampala¹,

Vankeshwaram²,

Gadula³

2020

Cureus

View full text Add to dashboard Cite

Artificial intelligence (AI) is a path-breaking advancement for many industries, including the health care sector. The expeditious development of information technology and data processing has led to the formation of recent tools known as artificial intelligence. Radiology has been a portal for medical technological advancements, and AI will likely be no dissimilar. Radiology is the platform for many technological advances in the medical field; AI can undoubtedly impact every step of a radiologist's workflow. AI can simplify every activity like ordering and scheduling, protocoling and acquisition, image interpretation, reporting, communication, and billing. AI has eminent potential to augment efficiency and accuracy throughout radiology, but it also possesses inherent drawbacks and biases. We collected studies that were published in the past five years using PubMed as our database. We chose studies that were relevant to artificial intelligence in radiology. We mainly focused on the overview of AI in radiology, components included in the functioning of AI, AI assisting in the radiologists' workflow, ethical aspects of AI, challenges, and biases that AI experiencing together with some clinical applications of AI. Of all 33 studies, we found 15 articles discussed the overview and components of AI, five articles about AI affecting radiologist's workflow, five articles related to challenges and biases in AI, two articles discussed ethical aspects of AI, and six articles about practical implications of AI. We found out that the application of AI could make time-dependent tasks that can be performed effortlessly, permitting radiologists more time and opportunities to engage in patient care via increased time for consultation and development in imaging and extracting useful data from those images. AI could only be an aid to radiologists but will not replace a radiologist. Radiologists who use AI to their benefit, rather than to avoid it out of fear, might supersede those radiologists who do not. Substantial research should be done regarding the practical implications of AI algorithms for residents curriculum and the benefits of AI in radiology.

show abstract

“…Lu et al utilized various networks, such as CAE, 2D U-Net, 2.5D U-Net, 3D U-Net, and GAN, to predict standard-dose brain PET images from low-dose PET images. 26 Their results showed that optimal deep learning networks are task-based and differ depending on the desired application. Furthermore, their studies showed comparable visual image quality between CAE, U-Net (2.5D and 3D), and GAN.…”

Section: Modelmentioning

confidence: 99%

“…Both models were trained on 35 subjects with leaveone-out cross validation. For non-CNN-based denoising methods, we applied a 3D 5-mm FWHM Gaussian filtering method 25,26 and compared it to both CNN models. Comparison of these three models was evaluated through objective imaging metrics: PSNR, SSIM, and MAPE.…”

Section: Introductionmentioning

confidence: 99%

Full‐count PET recovery from low‐count image using a dilated convolutional neural network

et al. 2020

View full text Add to dashboard Cite

Purpose: Positron emission tomography (PET) is an essential technique in many clinical applications that allows for quantitative imaging at the molecular level. This study aims to develop a denoising method using a novel dilated convolutional neural network (CNN) to recover full-count images from low-count images. Methods: We adopted similar hierarchical structures as the conventional U-Net and incorporated dilated kernels in each convolution to allow the network to observe larger, more robust features within the image without the requirement of downsampling and upsampling internal representations. Our dNet was trained alongside a U-Net for comparison. Both models were evaluated using a leaveone-out cross-validation procedure on a dataset of 35 subjects (~3500 slabs), which were obtained from an ongoing 18 F-Fluorodeoxyglucose (FDG) study. Low-count PET data (10% count) were generated by randomly selecting one-tenth of all events in the associated listmode file. Analysis was done on the static image from the last 10 minutes of emission data. Both low-count PET and full-count PET were reconstructed using ordered subset expectation maximization (OSEM). Objective image quality metrics, including mean absolute percent error (MAPE), peak signal-to-noise ratio (PSNR), and structural similarity index metric (SSIM), were used to analyze the deep learning methods. Both deep learning methods were further compared to a traditional Gaussian filtering method. Further, region of interest (ROI) quantitative analysis was also used to compare U-Net and dNet architectures. Results: Both the U-Net and our proposed network were successfully trained to synthesize fullcount PET images from the generated low-count PET images. Compared to low-count PET and Gaussian filtering, both deep learning methods improved MAPE, PSNR, and SSIM. Our dNet also systematically outperformed U-Net on all three metrics (MAPE: 4.99 AE 0.68 vs 5.31 AE 0.76, P < 0.01; PSNR: 31.55 AE 1.31 dB vs 31.05 AE 1.39, P < 0.01; SSIM: 0.9513 AE 0.0154 vs 0.9447 AE 0.0178, P < 0.01). ROI quantification showed greater quantitative improvements using dNet over U-Net. Conclusion: This study proposed a novel approach of using dilated convolutions for recovering fullcount PET images from low-count PET images.

show abstract

An investigation of quantitative accuracy for deep learning based denoising in oncological PET

Cited by 106 publications

References 47 publications

Convolutional neural networks for improving image quality with noisy PET data

Convolutional neural networks for improving image quality with noisy PET data

Is Artificial Intelligence the New Friend for Radiologists? A Review Article

Full‐count PET recovery from low‐count image using a dilated convolutional neural network

Contact Info

Product

Resources

About