Assistive AI in Lung Cancer Screening: A Retrospective Multinational Study in the United States and Japan.

Purpose To evaluate the impact of an artificial intelligence (AI) assistant for lung cancer screening on multinational clinical workflows. Materials and Methods An AI assistant for lung cancer screening was evaluated on two retrospective randomized multireader multicase studies where 627 (141 cancer-positive cases) low-dose chest CT cases were each read twice (with and without AI assistance) by experienced thoracic radiologists (six U.S.-based or six Japan-based radiologists), resulting in a total of 7524 interpretations. Positive cases were defined as those within 2 years before a pathology-confirmed lung cancer diagnosis. Negative cases were defined as those without any subsequent cancer diagnosis for at least 2 years and were enriched for a spectrum of diverse nodules. The studies measured the readers' level of suspicion (on a 0-100 scale), country-specific screening system scoring categories, and management recommendations. Evaluation metrics included the area under the receiver operating characteristic curve (AUC) for level of suspicion and sensitivity and specificity of recall recommendations. Results With AI assistance, the radiologists' AUC increased by 0.023 (0.70 to 0.72; P = .02) for the U.S. study and by 0.023 (0.93 to 0.96; P = .18) for the Japan study. Scoring system specificity for actionable findings increased 5.5% (57% to 63%; P < .001) for the U.S. study and 6.7% (23% to 30%; P < .001) for the Japan study. There was no evidence of a difference in corresponding sensitivity between unassisted and AI-assisted reads for the U.S. (67.3% to 67.5%; P = .88) and Japan (98% to 100%; P > .99) studies. Corresponding stand-alone AI AUC system performance was 0.75 (95% CI: 0.70, 0.81) and 0.88 (95% CI: 0.78, 0.97) for the U.S.- and Japan-based datasets, respectively. Conclusion The concurrent AI interface improved lung cancer screening specificity in both U.S.- and Japan-based reader studies, meriting further study in additional international screening environments. Keywords: Assistive Artificial Intelligence, Lung Cancer Screening, CT Supplemental material is available for this article. Published under a CC BY 4.0 license.

Deep learning for distinguishing normal versus abnormal chest radiographs and generalization to two unseen diseases tuberculosis and COVID-19.

Chest radiography (CXR) is the most widely-used thoracic clinical imaging modality and is crucial for guiding the management of cardiothoracic conditions. The detection of specific CXR findings has been the main focus of several artificial intelligence (AI) systems. However, the wide range of possible CXR abnormalities makes it impractical to detect every possible condition by building multiple separate systems, each of which detects one or more pre-specified conditions. In this work, we developed and evaluated an AI system to classify CXRs as normal or abnormal. For training and tuning the system, we used a de-identified dataset of 248,445 patients from a multi-city hospital network in India. To assess generalizability, we evaluated our system using 6 international datasets from India, China, and the United States. Of these datasets, 4 focused on diseases that the AI was not trained to detect: 2 datasets with tuberculosis and 2 datasets with coronavirus disease 2019. Our results suggest that the AI system trained using a large dataset containing a diverse array of CXR abnormalities generalizes to new patient populations and unseen diseases. In a simulated workflow where the AI system prioritized abnormal cases, the turnaround time for abnormal cases reduced by 7-28%. These results represent an important step towards evaluating whether AI can be safely used to flag cases in a general setting where previously unseen abnormalities exist. Lastly, to facilitate the continued development of AI models for CXR, we release our collected labels for the publicly available dataset.

Author Correction: End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.

With an estimated 160,000 deaths in 2018, lung cancer is the most common cause of cancer death in the United States1. Lung cancer screening using low-dose computed tomography has been shown to reduce mortality by 20-43% and is now included in US screening guidelines1-6. Existing challenges include inter-grader variability and high false-positive and false-negative rates7-10. We propose a deep learning algorithm that uses a patient's current and prior computed tomography volumes to predict the risk of lung cancer. Our model achieves a state-of-the-art performance (94.4% area under the curve) on 6,716 National Lung Cancer Screening Trial cases, and performs similarly on an independent clinical validation set of 1,139 cases. We conducted two reader studies. When prior computed tomography imaging was not available, our model outperformed all six radiologists with absolute reductions of 11% in false positives and 5% in false negatives. Where prior computed tomography imaging was available, the model performance was on-par with the same radiologists. This creates an opportunity to optimize the screening process via computer assistance and automation. While the vast majority of patients remain unscreened, we show the potential for deep learning models to increase the accuracy, consistency and adoption of lung cancer screening worldwide.

Transcriptomic Profiling Analysis of Arabidopsis thaliana Treated with Exogenous Myo-Inositol.

Myo-insositol (MI) is a crucial substance in the growth and developmental processes in plants. It is commonly added to the culture medium to promote adventitious shoot development. In our previous work, MI was found in influencing Agrobacterium-mediated transformation. In this report, a high-throughput RNA sequencing technique (RNA-Seq) was used to investigate differently expressed genes in one-month-old Arabidopsis seedling grown on MI free or MI supplemented culture medium. The results showed that 21,288 and 21,299 genes were detected with and without MI treatment, respectively. The detected genes included 184 new genes that were not annotated in the Arabidopsis thaliana reference genome. Additionally, 183 differentially expressed genes were identified (DEGs, FDR ≤0.05, log2 FC≥1), including 93 up-regulated genes and 90 down-regulated genes. The DEGs were involved in multiple pathways, such as cell wall biosynthesis, biotic and abiotic stress response, chromosome modification, and substrate transportation. Some significantly differently expressed genes provided us with valuable information for exploring the functions of exogenous MI. RNA-Seq results showed that exogenous MI could alter gene expression and signaling transduction in plant cells. These results provided a systematic understanding of the functions of exogenous MI in detail and provided a foundation for future studies.

Overexpression of a Chimeric Gene, OsDST-SRDX, Improved Salt Tolerance of Perennial Ryegrass.

The Drought and Salt Tolerance gene (DST) encodes a C2H2 zinc finger transcription factor, which negatively regulates salt tolerance in rice (Oryza sativa). Phylogenetic analysis of six homologues of DST genes in different plant species revealed that DST genes were conserved evolutionarily. Here, the rice DST gene was linked to an SRDX domain for gene expression repression based on the Chimeric REpressor gene-Silencing Technology (CRES-T) to make a chimeric gene (OsDST-SRDX) construct and introduced into perennial ryegrass by Agrobacterium-mediated transformation. Integration and expression of the OsDST-SRDX in transgenic plants were tested by PCR and RT-PCR, respectively. Transgenic lines overexpressing the OsDST-SRDX fusion gene showed obvious phenotypic differences and clear resistance to salt-shock and to continuous salt stresses compared to non-transgenic plants. Physiological analyses including relative leaf water content, electrolyte leakage, proline content, malondialdehyde (MDA) content, H2O2 content and sodium and potassium accumulation indicated that the OsDST-SRDX fusion gene enhanced salt tolerance in transgenic perennial ryegrass by altering a wide range of physiological responses. To our best knowledge this study is the first report of utilizing Chimeric Repressor gene-Silencing Technology (CRES-T) in turfgrass and forage species for salt-tolerance improvement.

Bandlimited reconstruction of multidimensional images from irregular samples.

We examine different sampling lattices and their respective bandlimited spaces for reconstruction of irregularly sampled multidimensional images. Considering an irregularly sampled dataset, we demonstrate that the non-tensor-product bandlimited approximations corresponding to the body-centered cubic and face-centered cubic lattices provide a more accurate reconstruction than the tensor-product bandlimited approximation associated with the commonly-used Cartesian lattice. Our practical algorithm uses multidimensional sinc functions that are tailored to these lattices and a regularization scheme that provides a variational framework for efficient implementation. Using a number of synthetic and real data sets we record improvements in the accuracy of reconstruction in a practical setting.

Dictionary learning on the manifold of square root densities and application to reconstruction of diffusion propagator fields.

In this paper, we present a novel dictionary learning framework for data lying on the manifold of square root densities and apply it to the reconstruction of diffusion propagator (DP) fields given a multi-shell diffusion MRI data set. Unlike most of the existing dictionary learning algorithms which rely on the assumption that the data points are vectors in some Euclidean space, our dictionary learning algorithm is designed to incorporate the intrinsic geometric structure of manifolds and performs better than traditional dictionary learning approaches when applied to data lying on the manifold of square root densities. Non-negativity as well as smoothness across the whole field of the reconstructed DPs is guaranteed in our approach. We demonstrate the advantage of our approach by comparing it with an existing dictionary based reconstruction method on synthetic and real multi-shell MRI data.

AN OVER-COMPLETE DICTIONARY BASED REGULARIZED RECONSTRUCTION OF A FIELD OF ENSEMBLE AVERAGE PROPAGATORS.

In this paper we present a dictionary-based framework for the reconstruction of a field of ensemble average propagators (EAPs), given a high angular resolution diffusion MRI data set. Existing techniques often consider voxel-wise reconstruction of the EAP field thereby leading to a noisy reconstruction across the field. We present a dictionary learning framework for achieving a smooth EAP reconstruction across the field wherein, the dictionary atoms are learned from the data via an initial regression using adaptive spline kernels. The formulation involves a two stage optimization where the first stage involves optimizing for a sparse dictionary using a K-SVD based updating and the second stage involves a quadratic cost function optimization with a non-local means based regularization across the field. The novelty lies in a dictionary based reconstruction as well as an NLM-based regularization that helps preserving features in the reconstructed field. We document experimental results on synthetic data from crossing fibers and real optic chiasm data set that demonstrate the advantages of the proposed approach.

An efficient interlaced multi-shell sampling scheme for reconstruction of diffusion propagators.

In this paper, we propose an interlaced multi-shell sampling scheme for the reconstruction of the diffusion propagator from diffusion weighted magnetic resonance imaging (DW-MRI). In standard multi-shell sampling schemes, sample points are uniformly distributed on several spherical shells in q-space. The distribution of sample points is the same for all shells, and is determined by the vertices of a selected polyhedron. We propose a more efficient interlaced scheme where sample points are different on alternating shells and are determined by the vertices of a pair of dual polyhedra. Since it samples more directions than the standard scheme, this method offers increased angular discrimination. Another contribution of this work is the application of optimal sampling lattices to q-space data acquisition and the proposal of a model-free reconstruction algorithm, which uses the lattice dependent sinc interpolation function. It is shown that under this reconstruction framework, the body centered cubic (BCC) lattice provides increased accuracy. The sampling scheme and the reconstruction algorithms were evaluated on simulated data as well as rat brain data collected on a 600 MHz (14.1T) Bruker imaging spectrometer.

A geometric construction of multivariate sinc functions.

We present a geometric framework for explicit derivation of multivariate sampling functions (sinc) on multidimensional lattices. The approach leads to a generalization of the link between sinc functions and the Lagrange interpolation in the multivariate setting. Our geometric approach also provides a frequency partition of the spectrum that leads to a nonseparable extension of the 1-D Shannon (sinc) wavelets to the multivariate setting. Moreover, we propose a generalization of the Lanczos window function that provides a practical and unbiased approach for signal reconstruction on sampling lattices. While this framework is general for lattices of any dimension, we specifically characterize all 2-D and 3-D lattices and show the detailed derivations for 2-D hexagonal body-centered cubic (BCC) and face-centered cubic (FCC) lattices. Both visual and numerical comparisons validate the theoretical expectations about superiority of the BCC and FCC lattices over the commonly used Cartesian lattice.

BOX SPLINE BASED 3D TOMOGRAPHIC RECONSTRUCTION OF DIFFUSION PROPAGATORS FROM MRI DATA.

This paper introduces a tomographic approach for reconstruction of diffusion propagators, P( r ), in a box spline framework. Box splines are chosen as basis functions for high-order approximation of P( r ) from the diffusion signal. Box splines are a generalization of B-splines to multivariate setting that are particularly useful in the context of tomographic reconstruction. The X-Ray or Radon transform of a (tensor-product B-spline or a non-separable) box spline is a box spline - the space of box splines is closed under the Radon transform.We present synthetic and real multi-shell diffusion-weighted MR data experiments that demonstrate the increased accuracy of P( r ) reconstruction as the order of basis functions is increased.

TOMOGRAPHIC RECONSTRUCTION OF DIFFUSION PROPAGATORS FROM DW-MRI USING OPTIMAL SAMPLING LATTICES.

This paper exploits the power of optimal sampling lattices in tomography based reconstruction of the diffusion propagator in diffusion weighted magnetic resonance imaging (DWMRI). Optimal sampling leads to increased accuracy of the tomographic reconstruction approach introduced by Pickalov and Basser [1]. Alternatively, the optimal sampling geometry allows for further reducing the number of samples while maintaining the accuracy of reconstruction of the diffusion propagator. The optimality of the proposed sampling geometry comes from the information theoretic advantages of sphere packing lattices in sampling multidimensional signals. These advantages are in addition to those accrued from the use of the tomographic principle used here for reconstruction. We present comparative results of reconstructions of the diffusion propagator using the Cartesian and the optimal sampling geometry for synthetic and real data sets.