Purpose
Due to the potential risk of inducing cancer, radiation exposure by X‐ray CT devices should be reduced for routine patient scanning. However, in low‐dose X‐ray CT, severe artifacts typically ...occur due to photon starvation, beam hardening, and other causes, all of which decrease the reliability of the diagnosis. Thus, a high‐quality reconstruction method from low‐dose X‐ray CT data has become a major research topic in the CT community. Conventional model‐based de‐noising approaches are, however, computationally very expensive, and image‐domain de‐noising approaches cannot readily remove CT‐specific noise patterns. To tackle these problems, we want to develop a new low‐dose X‐ray CT algorithm based on a deep‐learning approach.
Method
We propose an algorithm which uses a deep convolutional neural network (CNN) which is applied to the wavelet transform coefficients of low‐dose CT images. More specifically, using a directional wavelet transform to extract the directional component of artifacts and exploit the intra‐ and inter‐ band correlations, our deep network can effectively suppress CT‐specific noise. In addition, our CNN is designed with a residual learning architecture for faster network training and better performance.
Results
Experimental results confirm that the proposed algorithm effectively removes complex noise patterns from CT images derived from a reduced X‐ray dose. In addition, we show that the wavelet‐domain CNN is efficient when used to remove noise from low‐dose CT compared to existing approaches. Our results were rigorously evaluated by several radiologists at the Mayo Clinic and won second place at the 2016 “Low‐Dose CT Grand Challenge.”
Conclusions
To the best of our knowledge, this work is the first deep‐learning architecture for low‐dose CT reconstruction which has been rigorously evaluated and proven to be effective. In addition, the proposed algorithm, in contrast to existing model‐based iterative reconstruction (MBIR) methods, has considerable potential to benefit from large data sets. Therefore, we believe that the proposed algorithm opens a new direction in the area of low‐dose CT research.
Noise is inherent to low-dose CT acquisition. We propose to train a convolutional neural network (CNN) jointly with an adversarial CNN to estimate routine-dose CT images from low-dose CT images and ...hence reduce noise. A generator CNN was trained to transform low-dose CT images into routine-dose CT images using voxelwise loss minimization. An adversarial discriminator CNN was simultaneously trained to distinguish the output of the generator from routine-dose CT images. The performance of this discriminator was used as an adversarial loss for the generator. Experiments were performed using CT images of an anthropomorphic phantom containing calcium inserts, as well as patient non-contrast-enhanced cardiac CT images. The phantom and patients were scanned at 20% and 100% routine clinical dose. Three training strategies were compared: the first used only voxelwise loss, the second combined voxelwise loss and adversarial loss, and the third used only adversarial loss. The results showed that training with only voxelwise loss resulted in the highest peak signal-to-noise ratio with respect to reference routine-dose images. However, CNNs trained with adversarial loss captured image statistics of routine-dose images better. Noise reduction improved quantification of low-density calcified inserts in phantom CT images and allowed coronary calcium scoring in low-dose patient CT images with high noise levels. Testing took less than 10 s per CT volume. CNN-based low-dose CT noise reduction in the image domain is feasible. Training with an adversarial network improves the CNNs ability to generate images with an appearance similar to that of reference routine-dose CT images.
In 2011, the U.S. National Lung Cancer Screening Trial (NLST) reported a 20% reduction of lung cancer mortality after regular screening by low‐dose computed tomography (LDCT), as compared to X‐ray ...screening. The introduction of lung cancer screening programs in Europe awaits confirmation of these first findings from European trials that started in parallel with the NLST. The German Lung cancer Screening Intervention (LUSI) is a randomized trial among 4,052 long‐term smokers, 50–69 years of age, recruited from the general population, comparing five annual rounds of LDCT screening (screening arm; n = 2,029 participants) with a control arm (n = 2,023) followed by annual postal questionnaire inquiries. Data on lung cancer incidence and mortality and vital status were collected from hospitals or office‐based physicians, cancer registries, population registers and health offices. Over an average observation time of 8.8 years after randomization, the hazard ratio for lung cancer mortality was 0.74 (95% CI: 0.46–1.19; p = 0.21) among men and women combined. Modeling by sex, however showed a statistically significant reduction in lung cancer mortality among women (HR = 0.31 95% CI: 0.10–0.96, p = 0.04), but not among men (HR = 0.94 95% CI: 0.54–1.61, p = 0.81) screened by LDCT (pheterogeneity = 0.09). Findings from LUSI are in line with those from other trials, including NLST, that suggest a stronger reduction of lung cancer mortality after LDCT screening among women as compared to men. This heterogeneity could be the result of different relative counts of lung tumor subtypes occurring in men and women.
What's new?
Low‐dose computed tomography (LDCT) is an emerging tool for early lung cancer detection. Here, as part of the German Lung Cancer Screening Intervention trial, the benefits of annual LDCT screening were examined in long‐term smokers ages 50 to 69. In men and women combined, no statistically significant reduction in lung cancer mortality was observed after five annual rounds of LDCT screening compared to controls. Separate analyses by sex, however, revealed significant reductions in lung cancer mortality among the women who underwent LDCT. The findings support the systematic use of LDCT in lung cancer screening, though critical optimization strategies await investigation.
Lithium is an effective mood stabiliser, but its mechanism of action is incompletely defined. Even at very low doses, lithium may have neuroprotective effects, but it is not clear if these relate to ...brain lithium concentration in vivo. We have developed magnetic resonance imaging (7Li-MRI) methods to detect lithium in the brain following supplementation at a very low dose.
Lithium orotate supplements were taken by nine healthy adult male subjects (5 mg daily) for up to 28 days, providing 2–7 % of the lithium content of a typical therapeutic lithium carbonate dose. One-dimensional 7Li-images were acquired on a 3.0 T MRI scanner. All subjects were scanned on day 14 or 28; seven were scanned on both, one at baseline and one after 7-days washout.
7Li-MR signal amplitude was broadly stable between days 14 and 28. Two subjects had notably higher 7Li-signal intensities (approximately 2–4×) compared to other study participants.
Lithium adherence was self-reported by all participants without formal validation. The coarse spatial resolution necessary for detection of low concentrations of 7Li exhibits imperfect spatial separation of signal from adjacent pixels.
7Li-MRI performed using a clinical 3T scanner demonstrated detection of lithium in the brain at very low concentration, in the range of approximately 10–60 mM. The methods are suited to studies assessing low dose lithium administration in psychiatric and neurodegenerative disorders, and permit the comparison of different lithium salt preparations at a time of emerging interest in the field.
•7Li-MRI permits direct, non-invasive, longitudinal measurement of brain lithium.•Brain lithium was detected after administration of very low dose lithium orotate.•Brain 7Li-signal was stable between two- and four-weeks of supplementation.•A subset of individuals showed notably higher brain 7Li-signal intensity.
Low‐dose CT image and projection dataset Moen, Taylor R.; Chen, Baiyu; Holmes, David R. ...
Medical physics (Lancaster),
February 2021, Letnik:
48, Številka:
2
Journal Article
Recenzirano
Odprti dostop
Purpose
To describe a large, publicly available dataset comprising computed tomography (CT) projection data from patient exams, both at routine clinical doses and simulated lower doses.
Acquisition ...and Validation Methods
The library was developed under local ethics committee approval. Projection and image data from 299 clinically performed patient CT exams were archived for three types of clinical exams: noncontrast head CT scans acquired for acute cognitive or motor deficit, low‐dose noncontrast chest scans acquired to screen high‐risk patients for pulmonary nodules, and contrast‐enhanced CT scans of the abdomen acquired to look for metastatic liver lesions. Scans were performed on CT systems from two different CT manufacturers using routine clinical protocols. Projection data were validated by reconstructing the data using several different reconstruction algorithms and through use of the data in the 2016 Low Dose CT Grand Challenge. Reduced dose projection data were simulated for each scan using a validated noise‐insertion method. Radiologists marked location and diagnosis for detected pathologies. Reference truth was obtained from the patient medical record, either from histology or subsequent imaging.
Data Format and Usage Notes
Projection datasets were converted into the previously developed DICOM‐CT‐PD format, which is an extended DICOM format created to store CT projections and acquisition geometry in a nonproprietary format. Image data are stored in the standard DICOM image format and clinical data in a spreadsheet. Materials are provided to help investigators use the DICOM‐CT‐PD files, including a dictionary file, data reader, and user manual. The library is publicly available from The Cancer Imaging Archive (https://doi.org/10.7937/9npb‐2637).
Potential Applications
This CT data library will facilitate the development and validation of new CT reconstruction and/or denoising algorithms, including those associated with machine learning or artificial intelligence. The provided clinical information allows evaluation of task‐based diagnostic performance.
Purpose
In multiphase coronary CT angiography (CTA), a series of CT images are taken at different levels of radiation dose during the examination. Although this reduces the total radiation dose, the ...image quality during the low‐dose phases is significantly degraded. Recently, deep neural network approaches based on supervised learning technique have demonstrated impressive performance improvement over conventional model‐based iterative methods for low‐dose CT. However, matched low‐ and routine‐dose CT image pairs are difficult to obtain in multiphase CT. To address this problem, we aim at developing a new deep learning framework.
Method
We propose an unsupervised learning technique that can remove the noise of the CT images in the low‐dose phases by learning from the CT images in the routine dose phases. Although a supervised learning approach is not applicable due to the differences in the underlying heart structure in two phases, the images are closely related in two phases, so we propose a cycle‐consistent adversarial denoising network to learn the mapping between the low‐ and high‐dose cardiac phases.
Results
Experimental results showed that the proposed method effectively reduces the noise in the low‐dose CT image while preserving detailed texture and edge information. Moreover, thanks to the cyclic consistency and identity loss, the proposed network does not create any artificial features that are not present in the input images. Visual grading and quality evaluation also confirm that the proposed method provides significant improvement in diagnostic quality.
Conclusions
The proposed network can learn the image distributions from the routine‐dose cardiac phases, which is a big advantage over the existing supervised learning networks that need exactly matched low‐ and routine‐dose CT images. Considering the effectiveness and practicability of the proposed method, we believe that the proposed can be applied for many other CT acquisition protocols.
Purpose
Our goal was to use a generative adversarial network (GAN) with feature matching and task‐specific perceptual loss to synthesize standard‐dose amyloid Positron emission tomography (PET) ...images of high quality and including accurate pathological features from ultra‐low‐dose PET images only.
Methods
Forty PET datasets from 39 participants were acquired with a simultaneous PET/MRI scanner following injection of 330 ± 30 MBq of the amyloid radiotracer 18F‐florbetaben. The raw list‐mode PET data were reconstructed as the standard‐dose ground truth and were randomly undersampled by a factor of 100 to reconstruct 1% low‐dose PET scans. A 2D encoder‐decoder network was implemented as the generator to synthesize a standard‐dose image and a discriminator was used to evaluate them. The two networks contested with each other to achieve high‐visual quality PET from the ultra‐low‐dose PET. Multi‐slice inputs were used to reduce noise by providing the network with 2.5D information. Feature matching was applied to reduce hallucinated structures. Task‐specific perceptual loss was designed to maintain the correct pathological features. The image quality was evaluated by peak signal‐to‐noise ratio (PSNR), structural similarity (SSIM), and root mean square error (RMSE) metrics with and without each of these modules. Two expert radiologists were asked to score image quality on a 5‐point scale and identified the amyloid status (positive or negative).
Results
With only low‐dose PET as input, the proposed method significantly outperformed Chen et al.'s method (Chen et al. Radiology. 2018;290:649–656) (which shows the best performance in this task) with the same input (PET‐only model) by 1.87 dB in PSNR, 2.04% in SSIM, and 24.75% in RMSE. It also achieved comparable results to Chen et al.'s method which used additional magnetic resonance imaging (MRI) inputs (PET‐MR model). Experts' reading results showed that the proposed method could achieve better overall image quality and maintain better pathological features indicating amyloid status than both PET‐only and PET‐MR models proposed by Chen et al.
Conclusion
Standard‐dose amyloid PET images can be synthesized from ultra‐low‐dose images using GAN. Applying adversarial learning, feature matching, and task‐specific perceptual loss are essential to ensure image quality and the preservation of pathological features.
The solid electrolyte interphase (SEI) dictates the cycling stability of lithium‐metal batteries. Here, direct atomic imaging of the SEI's phase components and their spatial arrangement is achieved, ...using ultralow‐dosage cryogenic transmission electron microscopy. The results show that, surprisingly, a lot of the deposited Li metal has amorphous atomic structure, likely due to carbon and oxygen impurities, and that crystalline lithium carbonate is not stable and readily decomposes when contacting the lithium metal. Lithium carbonate distributed in the outer SEI also continuously reacts with the electrolyte to produce gas, resulting in a dynamically evolving and porous SEI. Sulfur‐containing additives cause the SEI to preferentially generate Li2SO4 and overlithiated lithium sulfate and lithium oxide, which encapsulate lithium carbonate in the middle, limiting SEI thickening and enhancing battery life by a factor of ten. The spatial mapping of the SEI gradient amorphous (polymeric → inorganic → metallic) and crystalline phase components provides guidance for designing electrolyte additives.
Sulfur‐containing additives cause the solid electrolyte interphase (SEI) in lithium‐metal batteries to preferentially generate Li2SO4 and overlithiated lithium sulfate and lithium oxide, which encapsulates lithium carbonate in the middle, limiting SEI thickening and enhancing battery life by a factor of ten.
In HNSCC, survival with chemotherapy is dismal in a palliative setting. In LMICs, access to cetuximab and IO is less than 3%.1 Therefore, treatment options are limited to chemotherapy. There is ...evidence suggesting that low-dose nivolumab, in combination with triple metronomic chemotherapy (TMC), improves OS.2 Yet, real-world data on the use of low-dose nivolumab remains scarce. This retrospective study aims to evaluate response rates associated with the combination of TMC and low-dose nivolumab in HNSCC patients.
A retrospective analysis was conducted on 50 consecutive HNSCC patients with PS 0-1 who underwent combined TMC (Tab. Erlotinib 150mg once a day, Tab. Methotrexate 9mg/m2 once a week, Cap. Celecoxib 200mg twice a day) and low-dose nivolumab(20 mg every 21 days) therapy from August 2022 to June 2023 with palliative intent(recurrent/metastatic/inoperable).Platinum sensitivity was defined as >6 months of gap from platinum exposure or platinum naive.
Descriptive statistics were performed for demographic details. Response assessments, including complete response (CR), partial response (PR), stable disease (SD), and progressive disease (PD), were conducted according to RECIST 1.1 criteria at 3 months. Response rate (RR) and clinical benefit rate (CBR) was calculated as per intention to treat.
A total of 50 patients were included in this study, with 44 (88%) being male and 6 (12%) female. The median age was 49 years (35-78 years). ECOG PS-0 was observed in 3 (6%) patients, while 47 (94%) had ECOG PS-1. The primary site of malignancy was buccal mucosa in 33 (66%) patients, tongue in 12 (24%) patients, hard palate in 1 (2%) patient, and other primary sites in 4 (8%) patients. A history of surgery was present in 27 (54%) patients, and 26 (52%) had a history of radiation. 18 (36%) had no previous chemotherapy exposure. 31 (62%) had platinum exposure, and 21 (42%) had exposure to taxane. 30 (60%) were platinum-sensitive and 20 (40%) were platinum-resistant. In the whole cohort, 3 patients (1 in platinum sensitive and 2 in platinum resistant cohort) lost to follow up and 1 patient died (platinum resistant cohort).
In the whole cohort, the response rate (RR) was 64% (n=32), and the clinical benefit ratio (CBR) was 80% (n=40). RR and CBR in the platinum-sensitive cohort were 76.67% (n=23) and 90% (n=27) respectively. RR and CBR in the platinum-resistant cohort were 45% (n=9) and 65% (n=13) respectively. Display omitted
The novel combination of low dose nivolumab and TMC has clinically meaningful response rates in real world setting. It is useful options in resource constraint setting.