Since the advent of deep convolutional neural networks (DNNs), computer vision has seen an extremely rapid progress that has led to huge advances in medical imaging. Every year, many new methods are ...reported at conferences such as the International Conference on Medical Image Computing and Computer-Assisted Intervention and Machine Learning for Medical Image Reconstruction, or published online at the preprint server arXiv. There is a plethora of surveys on applications of neural networks in medical imaging (see
1
for a relatively recent comprehensive survey). This article does not aim to cover all aspects of the field, but focuses on a particular topic,
image-to-image translation
. Although the topic may not sound familiar, it turns out that many seemingly irrelevant applications can be understood as instances of image-to-image translation. Such applications include (1) noise reduction, (2) super-resolution, (3) image synthesis, and (4) reconstruction. The same underlying principles and algorithms work for various tasks. Our aim is to introduce some of the key ideas on this topic from a uniform viewpoint. We introduce core ideas and jargon that are specific to image processing by use of DNNs. Having an intuitive grasp of the core ideas of applications of neural networks in medical imaging and a knowledge of technical terms would be of great help to the reader for understanding the existing and future applications. Most of the recent applications which build on image-to-image translation are based on one of two fundamental architectures, called pix2pix and CycleGAN, depending on whether the available training data are
paired
or
unpaired
(see Sect.
1.3
). We provide codes (
2
,
3
) which implement these two architectures with various enhancements. Our codes are available online with use of the very permissive MIT license. We provide a hands-on tutorial for training a model for denoising based on our codes (see Sect.
6
). We hope that this article, together with the codes, will provide both an overview and the details of the key algorithms and that it will serve as a basis for the development of new applications.
Purpose
Cone‐beam computed tomography (CBCT) offers advantages over conventional fan‐beam CT in that it requires a shorter time and less exposure to obtain images. However, CBCT images suffer from ...low soft‐tissue contrast, noise, and artifacts compared to conventional fan‐beam CT images. Therefore, it is essential to improve the image quality of CBCT.
Methods
In this paper, we propose a synthetic approach to translate CBCT images with deep neural networks. Our method requires only unpaired and unaligned CBCT images and planning fan‐beam CT (PlanCT) images for training. The CBCT images and PlanCT images may be obtained from other patients as long as they are acquired with the same scanner settings. Once trained, three‐dimensionally reconstructed CBCT images can be directly translated into high‐quality PlanCT‐like images.
Results
We demonstrate the effectiveness of our method with images obtained from 20 prostate patients, and provide a statistical and visual comparison. The image quality of the translated images shows substantial improvement in voxel values, spatial uniformity, and artifact suppression compared to those of the original CBCT. The anatomical structures of the original CBCT images were also well preserved in the translated images.
Conclusions
Our method produces visually PlanCT‐like images from CBCT images while preserving anatomical structures.
To date, many gait generation strategies have been designed for robots with leg configurations that model those of natural creatures. However, their leg configurations are limited to the ...<inline-formula><tex-math notation="LaTeX">2\times N</tex-math></inline-formula> type, such as hexapod or myriapod; hence, simultaneously, the potential ability of legged robots is implicitly limited. We consider single-legged modular robots that can be arranged to form a cluster with arbitrary 2-D leg configurations. By choosing configurations appropriately, these robots have the potential to perform several types of tasks, as is the case for reconfigurable modular robots. However, to use appropriate configurations for a given task, a unified gait generation system for various configurations of a cluster is required. In this article, we propose an autonomous distributed control system for each single-legged modular robot to collectively achieve static walking of the cluster with various leg configurations on planar ground. Moreover, our system is an autonomous distributed system with scalability and fault tolerance, in which each module determines the moving pattern of its foot through local communication without global information, such as the entire leg configuration of the cluster. We verified that several types of clusters achieved static walking using our system not only in dynamic simulations, but also in real robot experiments.
This paper presents an algorithmic approach for the conceptual design of architectural surfaces represented by triangulated meshes. Specifically, we propose a method to optimise a surface according ...to user-specified geometric properties including the distribution of the Gaussian curvature and preferable boundary location. Designing a surface manually with specific Gaussian curvatures can be a time-consuming task, and the proposed method automates this task. Also, in the proposed approach, the resulting mesh could be encouraged to form a regular tessellation or kept close to those of the initial one. Our method relies on the idea in computational conformal geometry called circle packing and the discrete Ricch energy, which have been used for surface modelling. We develop a least-squares-based optimisation scheme by introducing a variant of the Ricci energy to accommodate flexibility in specifying design constraints such as boundary locations and convexity of the spanned surface, which are essential to architectural applications. We provide an open-source implementation of our method in Python.
1
1
Our codes are publicly available at
https://github.com/shizuo-kaji/ricci_flow
The security of lattice-based cryptography relies on the hardness of solving lattice problems. Lattice basis reduction is a strong tool for solving lattice problems, and the block Korkine–Zolotarev ...(BKZ) reduction algorithm is the de facto standard in cryptanalysis. We propose a parallel algorithm of BKZ-type reduction based on randomization. Randomized copies of an input lattice basis are independently reduced in parallel, while several basis vectors are shared asynchronously among all processes. There is a trade-off between randomization and information sharing; if a substantial amount of information is shared, all processes might work on the same problem, which diminishes the benefit of parallelization. To monitor the balance between randomness and sharing, we propose a new metric to quantify the variety of lattice bases, and we empirically find an optimal parameter of sharing for high-dimensional lattices. We also demonstrate the effectiveness of our parallel algorithm and metric through experiments from multiple perspectives.
There is considerable heterogeneity among patients with emphysematous chronic obstructive pulmonary disease (COPD). We hypothesised that in addition to emphysema severity, ventilation distribution in ...emphysematous regions would be associated with clinical-physiological impairments in these patients.
To evaluate whether the discordance between respiratory volume change distributions (from expiration to inspiration) in emphysematous and non-emphysematous regions affects COPD outcomes using two cohorts.
Emphysema was quantified using a low attenuation volume percentage on inspiratory CT (iLAV%). Local respiratory volume changes were calculated using non-rigidly registered expiratory/inspiratory CT. The Ventilation Discordance Index (VDI) represented the log-transformed Wasserstein distance quantifying discordance between respiratory volume change distributions in emphysematous and non-emphysematous regions.
Patients with COPD in the first cohort (n=221) were classified into minimal emphysema (iLAV% <10%; n=113) and established emphysema with high VDI and low VDI groups (n=46 and 62, respectively). Forced expiratory volume in 1 s (FEV
) was lower in the low VDI group than in the other groups, with no difference between the high VDI and minimal emphysema groups. Higher iLAV%, more severe airway disease and hyperventilated emphysematous regions in the upper-middle lobes were independently associated with lower VDI. The second cohort analyses (n=93) confirmed these findings and showed greater annual FEV
decline and higher mortality in the low VDI group than in the high VDI group independent of iLAV% and airway disease on CT.
Lower VDI is associated with severe airflow limitation and higher mortality independent of emphysema severity and airway morphological changes in patients with emphysematous COPD.
The newly coined term
supoza
(giving up mathematics, 수포자, 數抛者) describes a critical social issue that needs to be addressed in South Korea’s educational policy. Although the term has not received ...precise definition, it refers to students who have given up on learning mathematics. A precise definition would require detailing the current
supoza
situation and identifying its characteristics. This study therefore conducted a statistical investigation of commonalities among students who have given up on learning mathematics; the study results revealed that these students can be characterized by their affective domain for mathematics learning. We found that a statistical model could determine the likelihood that a particular student would report having given up mathematics based on responses to questions related to the affective domain of mathematics learning. This aspect suggests the possibility of understanding
supoza
with the exclusive use of affective factors and emphasizes the significance of the affective domain of mathematics learning. Additionally, this study provides a working example to show how exploratory analysis using big data can be used in relation to mathematical education.
In this study, we developed the world's first artificial intelligence (AI) system that assesses the dysplasia of blood cells on bone marrow smears and presents the result of AI prediction for one of ...the most representative dysplasia-decreased granules (DG). We photographed field images from the bone marrow smears from patients with myelodysplastic syndrome (MDS) or non-MDS diseases and cropped each cell using an originally developed cell detector. Two morphologists labelled each cell. The degree of dysplasia was evaluated on a four-point scale: 0-3 (e.g., neutrophil with severely decreased granules were labelled DG3). We then constructed the classifier from the dataset of labelled images. The detector and classifier were based on a deep neural network pre-trained with natural images. We obtained 1797 labelled images, and the morphologists determined 134 DGs (DG1: 46, DG2: 77, DG3: 11). Subsequently, we performed a five-fold cross-validation to evaluate the performance of the classifier. For DG1-3 labelled by morphologists, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were 91.0%, 97.7%, 76.3%, 99.3%, and 97.2%, respectively. When DG1 was excluded in the process, the sensitivity, specificity, PPV, NPV, and accuracy were 85.2%, 98.9%, 80.6%, and 99.2% and 98.2%, respectively.