From Dose Reduction to Contrast Maximization: Can Deep Learning Amplify the Impact of Contrast Media on Brain Magnetic Resonance Image Quality? A Reader Study.

OBJECTIVES: The aim of this study was to evaluate a deep learning method designed to increase the contrast-to-noise ratio in contrast-enhanced gradient echo T1-weighted brain magnetic resonance imaging (MRI) acquisitions. The processed images are quantitatively evaluated in terms of lesion detection performance. MATERIALS AND METHODS: A total of 250 multiparametric brain MRIs, acquired between November 2019 and March 2021 at Gustave Roussy Cancer Campus (Villejuif, France), were considered for inclusion in this retrospective monocentric study. Independent training (107 cases; age, 55 ± 14 years; 58 women) and test (79 cases; age, 59 ± 14 years; 41 women) samples were defined. Patients had glioma, brain metastasis, meningioma, or no enhancing lesion. Gradient echo and turbo spin echo with variable flip angles postcontrast T1 sequences were acquired in all cases. For the cases that formed the training sample, "low-dose" postcontrast gradient echo T1 images using 0.025 mmol/kg injections of contrast agent were also acquired. A deep neural network was trained to synthetically enhance the low-dose T1 acquisitions, taking standard-dose T1 MRI as reference. Once trained, the contrast enhancement network was used to process the test gradient echo T1 images. A read was then performed by 2 experienced neuroradiologists to evaluate the original and processed T1 MRI sequences in terms of contrast enhancement and lesion detection performance, taking the turbo spin echo sequences as reference. RESULTS: The processed images were superior to the original gradient echo and reference turbo spin echo T1 sequences in terms of contrast-to-noise ratio (44.5 vs 9.1 and 16.8; P < 0.001), lesion-to-brain ratio (1.66 vs 1.31 and 1.44; P < 0.001), and contrast enhancement percentage (112.4% vs 85.6% and 92.2%; P < 0.001) for cases with enhancing lesions. The overall image quality of processed T1 was preferred by both readers (graded 3.4/4 on average vs 2.7/4; P < 0.001). Finally, the proposed processing improved the average sensitivity of gradient echo T1 MRI from 88% to 96% for lesions larger than 10 mm ( P = 0.008), whereas no difference was found in terms of the false detection rate (0.02 per case in both cases; P > 0.99). The same effect was observed when considering all lesions larger than 5 mm: sensitivity increased from 70% to 85% ( P < 0.001), whereas false detection rates remained similar (0.04 vs 0.06 per case; P = 0.48). With all lesions included regardless of their size, sensitivities were 59% and 75% for original and processed T1 images, respectively ( P < 0.001), and the corresponding false detection rates were 0.05 and 0.14 per case, respectively ( P = 0.06). CONCLUSION: The proposed deep learning method successfully amplified the beneficial effects of contrast agent injection on gradient echo T1 image quality, contrast level, and lesion detection performance. In particular, the sensitivity of the MRI sequence was improved by up to 16%, whereas the false detection rate remained similar.

Can Deep Learning Replace Gadolinium in Neuro-Oncology?: A Reader Study.

MATERIALS AND METHODS: This monocentric retrospective study leveraged 200 multiparametric brain MRIs acquired between November 2019 and February 2020 at Gustave Roussy Cancer Campus (Villejuif, France). A total of 145 patients were included: 107 formed the training sample (55 ± 14 years, 58 women) and 38 the separate test sample (62 ± 12 years, 22 women). Patients had glioma, brain metastases, meningioma, or no enhancing lesion. T1, T2-FLAIR, diffusion-weighted imaging, low-dose, and standard-dose postcontrast T1 sequences were acquired. A deep network was trained to process the precontrast and low-dose sequences to predict "virtual" surrogate images for contrast-enhanced T1. Once trained, the deep learning method was evaluated on the test sample. The discrepancies between the predicted virtual images and the standard-dose MRIs were qualitatively and quantitatively evaluated using both automated voxel-wise metrics and a reader study, where 2 radiologists graded image qualities and marked all visible enhancing lesions. RESULTS: The automated analysis of the test brain MRIs computed a structural similarity index of 87.1% ± 4.8% between the predicted virtual sequences and the reference contrast-enhanced T1 MRIs, a peak signal-to-noise ratio of 31.6 ± 2.0 dB, and an area under the curve of 96.4% ± 3.1%. At Youden's operating point, the voxel-wise sensitivity (SE) and specificity were 96.4% and 94.8%, respectively. The reader study found that virtual images were preferred to standard-dose MRI in terms of image quality (P = 0.008). A total of 91 reference lesions were identified in the 38 test T1 sequences enhanced with full dose of contrast agent. On average across readers, the brain lesion SE of the virtual images was 83% for lesions larger than 10 mm (n = 42), and the associated false detection rate was 0.08 lesion/patient. The corresponding positive predictive value of detected lesions was 92%, and the F1 score was 88%. Lesion detection performance, however, dropped when smaller lesions were included: average SE was 67% for lesions larger than 5 mm (n = 74), and 56% with all lesions included regardless of their size. The false detection rate remained below 0.50 lesion/patient in all cases, and the positive predictive value remained above 73%. The composite F1 score was 63% at worst. CONCLUSIONS: The proposed deep learning method for virtual contrast-enhanced T1 brain MRI prediction showed very high quantitative performance when evaluated with standard voxel-wise metrics. The reader study demonstrated that, for lesions larger than 10 mm, good detection performance could be maintained despite a 4-fold division in contrast agent usage, unveiling a promising avenue for reducing the gadolinium exposure of returning patients. Small lesions proved, however, difficult to handle for the deep network, showing that full-dose injections remain essential for accurate first-line diagnosis in neuro-oncology.

EMS Derived Wheat Mutant BIG8-1 (Triticum aestivum L.)-A New Drought Tolerant Mutant Wheat Line.

Drought response in wheat is considered a highly complex process, since it is a multigenic trait; nevertheless, breeding programs are continuously searching for new wheat varieties with characteristics for drought tolerance. In a previous study, we demonstrated the effectiveness of a mutant known as RYNO3936 that could survive 14 days without water. In this study, we reveal another mutant known as BIG8-1 that can endure severe water deficit stress (21 days without water) with superior drought response characteristics. Phenotypically, the mutant plants had broader leaves, including a densely packed fibrous root architecture that was not visible in the WT parent plants. During mild (day 7) drought stress, the mutant could maintain its relative water content, chlorophyll content, maximum quantum yield of PSII (Fv/Fm) and stomatal conductance, with no phenotypic symptoms such as wilting or senescence despite a decrease in soil moisture content. It was only during moderate (day 14) and severe (day 21) water deficit stress that a decline in those variables was evident. Furthermore, the mutant plants also displayed a unique preservation of metabolic activity, which was confirmed by assessing the accumulation of free amino acids and increase of antioxidative enzymes (peroxidases and glutathione S-transferase). Proteome reshuffling was also observed, allowing slow degradation of essential proteins such as RuBisCO during water deficit stress. The LC-MS/MS data revealed a high abundance of proteins involved in energy and photosynthesis under well-watered conditions, particularly Serpin-Z2A and Z2B, SGT1 and Calnexin-like protein. However, after 21 days of water stress, the mutants expressed ABC transporter permeases and xylanase inhibitor protein, which are involved in the transport of amino acids and protecting cells, respectively. This study characterizes a new mutant BIG8-1 with drought-tolerant characteristics suited for breeding programs.

Phase transition and thermal stability of epitaxial PtSe2 nanolayer on Pt(111).

This work relates to direct synthesis of the two-dimensional (2D) transition metal dichalchogenide (TMD) PtSe2 using an original method based on chemical deposition during immersion of a Pt(111) surface into aqueous Na2Se solution. Annealing of the sample induces significant modifications in the structural and electronic properties of the resulting PtSe2 film. We report systematic investigations of temperature dependent phase transitions by combining synchrotron based high-resolution X-ray photoemission (XPS), low temperature scanning tunnelling microscopy (LT-STM) and low energy electron diffraction (LEED). From the STM images, a phase transition from TMD 2H-PtSe2 to Pt2Se alloy monolayer structure is observed, in agreement with the LEED patterns showing a transition from (4 × 4) to (√3 × âˆš3)R30° and then to a (2 × 2) superstructure. This progressive evolution of the surface reconstruction has been monitored by XPS through systematic de-convolution of the Pt4f and Se3d core level peaks at different temperatures. The present work provides an alternative method for the large scale fabrication of 2D transition metal dichalchogenide films.

Taking stock: A multistakeholder perspective on improving the delivery of care and the development of treatments for Alzheimer's disease.

Health-care stakeholders increasingly recognize that the scientific and economic challenges associated with Alzheimer's disease (AD) are simply too great for individual stakeholder groups to address solely from within their own silos. In the necessary spirit of collaboration, we present in this perspective a set of multicountry multistakeholder recommendations to improve the organization of existing AD and dementia care and the development of new treatments. In brief, the five recommendations are (1) health-care systems must make choices regarding the patient populations to be diagnosed and treated, (2) health-care systems should use an evidence-based standard of care, (3) increased collaboration between public and private institutions is needed to enhance research, (4) reimbursement end points need to be agreed on and validated, and (5) innovative business models should be used to spur the introduction of new medicines.

Revisiting the framework of the National Institute on Aging-Alzheimer's Association diagnostic criteria.

In 2011, the National Institute on Aging and the Alzheimer's Association (NIA-AA) proposed revising the criteria for diagnosing Alzheimer's disease (AD), which had been established more than 25 years earlier by the National Institute on Neurologic and Communicative Disorders and Stroke (NINCDS) and the Alzheimer's Disease and Related Disorders Association (ADRDA), now called the Alzheimer's Association. The NIA-AA initiative also built upon research criteria for AD proposed by the International Working Group (IWG) in 2007 and updated in 2010. These efforts to revise the criteria reflect the need to improve diagnostic accuracy, facilitate clinical trials, and establish a common set of criteria that are universally accepted across domains of clinical practice, research, and drug development. To ensure that the proposed NIA-AA criteria remain as current as possible, the Alzheimer's Association Research Roundtable convened a meeting in Washington, DC, on October 1 and 2, 2012, bringing together international stakeholders from industry, academia, and regulatory agencies to identify areas of agreement and research gaps respective of NIA-AA criteria and IWG recommendations.

Finding maximum colorful subtrees in practice.

In metabolomics and other fields dealing with small compounds, mass spectrometry is applied as a sensitive high-throughput technique. Recently, fragmentation trees have been proposed to automatically analyze the fragmentation mass spectra recorded by such instruments. Computationally, this leads to the problem of finding a maximum weight subtree in an edge-weighted and vertex-colored graph, such that every color appears, at most once in the solution. We introduce new heuristics and an exact algorithm for this Maximum Colorful Subtree problem and evaluate them against existing algorithms on real-world and artificial datasets. Our tree completion heuristic consistently scores better than other heuristics, while the integer programming-based algorithm produces optimal trees with modest running times. Our fast and accurate heuristic can help determine molecular formulas based on fragmentation trees. On the other hand, optimal trees from the integer linear program are useful if structure is relevant, for example for tree alignments.

A fast and specific alignment method for minisatellite maps.

BACKGROUND: Variable minisatellites count among the most polymorphic markers of eukaryotic and prokaryotic genomes. This variability can affect gene coding regions, like in the prion protein gene, or gene regulation regions, like for the cystatin B gene, and be associated or implicated in diseases: the Creutzfeld-Jakob disease and the myoclonus epilepsy type 1, for our examples. When it affects neutrally evolving regions, the polymorphism in length (i.e., in number of copies) of minisatellites proved useful in population genetics. MOTIVATION: In these tandem repeat sequences, different mutational mechanisms let the number of copies, as well as the copies themselves, vary. Especially, the interspersion of events of tandem duplication/contraction and of punctual mutation makes the succession of variant repeats much more informative than the sole allele length. To exploit this information requires the ability to align minisatellite alleles by accounting for both punctual mutations and tandem duplications. RESULTS: We propose a minisatellite maps alignment program that improves on previous solutions. Our new program is faster, simpler, considers an extended evolutionary model, and is available to the community. We test it on the data set of 609 alleles of the MSY1 (DYF155S1) human minisatellite and confirm its ability to recover known evolutionary signals. Our experiments highlight that the informativeness of minisatellites resides in their length and composition polymorphisms. Exploiting both simultaneously is critical to unravel the implications of variable minisatellites in the control of gene expression and diseases.

Improved parameterized complexity of the maximum agreement subtree and maximum compatible tree problems.

Given a set of evolutionary trees on a same set of taxa, the maximum agreement subtree problem (MAST), respectively, maximum compatible tree problem (MCT), consists of finding a largest subset of taxa such that all input trees restricted to these taxa are isomorphic, respectively compatible. These problems have several applications in phylogenetics such as the computation of a consensus of phylogenies obtained from different data sets, the identification of species subjected to horizontal gene transfers and, more recently, the inference of supertrees, e.g., Trees Of Life. We provide two linear time algorithms to check the isomorphism, respectively, compatibility, of a set of trees or otherwise identify a conflict between the trees with respect to the relative location of a small subset of taxa. Then, we use these algorithms as subroutines to solve MAST and MCT on rooted or unrooted trees of unbounded degree. More precisely, we give exact fixed-parameter tractable algorithms, whose running time is uniformly polynomial when the number of taxa on which the trees disagree is bounded. The improves on a known result for MAST and proves fixed-parameter tractability for MCT.