須鎗 弘樹

Current deep learning-based cerebral aneurysm detection demonstrates high sensitivity, but produces numerous false-positives (FPs), which hampers clinical application of automated detection systems for time-of-flight magnetic resonance angiography. To reduce FPs while maintaining high sensitivity, we developed a multidimensional convolutional neural network (MD-CNN) designed to unite planar and stereoscopic information about aneurysms. This retrospective study enrolled time-of-flight magnetic resonance angiography images of cerebral aneurysms from three institutions from June 2006 to April 2019. In the internal test, 80% of the entire data set was used for model training and 20% for the test, while for the external tests, data from different pairs of the three institutions were used for training and the remaining one for testing. Images containing aneurysms > 15 mm and images without aneurysms were excluded. Three deep learning models [planar information-only (2D-CNN), stereoscopic information-only (3D-CNN), and multidimensional information (MD-CNN)] were trained to classify whether the voxels contained aneurysms, and they were evaluated on each test. The performance of each model was assessed using free-response operating characteristic curves. In total, 732 aneurysms (5.9 ± 2.5 mm) of 559 cases (327, 120, and 112 from institutes A, B, and C; 469 and 263 for 1.5T and 3.0T MRI) were included in this study. In the internal test, the highest sensitivities were 80.4, 87.4, and 82.5%, and the FPs were 6.1, 7.1, and 5.0 FPs/case at a fixed sensitivity of 80% for the 2D-CNN, 3D-CNN, and MD-CNN, respectively. In the external test, the highest sensitivities were 82.1, 86.5, and 89.1%, and 5.9, 7.4, and 4.2 FPs/cases for them, respectively. MD-CNN was a new approach to maintain sensitivity and reduce the FPs simultaneously.

<title>Abstract</title>The selection of genes that are important for obtaining gene expression data is challenging. Here, we developed a deep learning-based feature selection method suitable for gene selection. Our novel deep learning model includes an additional feature-selection layer. After model training, the units in this layer with high weights correspond to the genes that worked effectively in the processing of the networks. Cancer tissue samples and adjacent normal pancreatic tissue samples were collected from 13 patients with pancreatic ductal adenocarcinoma during surgery and subsequently frozen. After processing, gene expression data were extracted from the specimens using RNA sequencing. Task 1 for the model training was to discriminate between cancerous and normal pancreatic tissue in six patients. Task 2 was to discriminate between patients with pancreatic cancer (n = 13) who survived for more than one year after surgery. The most frequently selected genes were <italic>ACACB</italic>, <italic>ADAMTS6</italic>, <italic>NCAM1</italic>, and <italic>CADPS</italic> in Task 1, and <italic>CD1D</italic>, <italic>PLA2G16</italic>, <italic>DACH1</italic>, and <italic>SOWAHA</italic> in Task 2. According to The Cancer Genome Atlas dataset, these genes are all prognostic factors for pancreatic cancer. Thus, the feasibility of using our deep learning-based method for the selection of genes associated with pancreatic cancer development and prognosis was confirmed.

PURPOSE: Computed tomography (CT)-based attenuation correction (CTAC) in single-photon emission computed tomography (SPECT) is highly accurate, but it requires hybrid SPECT/CT instruments and additional radiation exposure. To obtain attenuation correction (AC) without the need for additional CT images, a deep learning method was used to generate pseudo-CT images has previously been reported, but it is limited because of cross-modality transformation, resulting in misalignment and modality-specific artifacts. This study aimed to develop a deep learning-based approach using non-attenuation-corrected (NAC) images and CTAC-based images for training to yield AC images in brain-perfusion SPECT. This study also investigated whether the proposed approach is superior to conventional Chang's AC (ChangAC). METHODS: In total, 236 patients who underwent brain-perfusion SPECT were randomly divided into two groups: the training group (189 patients; 80%) and the test group (47 patients; 20%). Two models were constructed using Autoencoder (AutoencoderAC) and U-Net (U-NetAC), respectively. ChangAC, AutoencoderAC, and U-NetAC approaches were compared with CTAC using qualitative analysis (visual evaluation) and quantitative analysis (normalized mean squared error [NMSE] and the percentage error in each brain region). Statistical analyses were performed using the Wilcoxon signed-rank sum test and Bland-Altman analysis. RESULTS: U-NetAC had the highest visual evaluation score. The NMSE results for the U-NetAC were the lowest, followed by AutoencoderAC and ChangAC (P < 0.001). Bland-Altman analysis showed a fixed bias for ChangAC and AutoencoderAC and a proportional bias for ChangAC. ChangAC underestimated counts by 30-40% in all brain regions. AutoencoderAC and U-NetAC produced mean errors of <1% and maximum errors of 3%, respectively. CONCLUSION: New deep learning-based AC methods for AutoencoderAC and U-NetAC were developed. Their accuracy was higher than that obtained by ChangAC. U-NetAC exhibited higher qualitative and quantitative accuracy than AutoencoderAC. We generated highly accurate AC images directly from NAC images without the need for intermediate pseudo-CT images. To verify our models' generalizability, external validation is required.

STUDY DESIGN: Retrospective analysis of magnetic resonance imaging (MRI). OBJECTIVE: The aim of this study was to evaluate the performance of our convolutional neural network (CNN) in differentiating between spinal schwannoma and meningioma on MRI. We compared the performance of the CNN and that of two expert radiologists. SUMMARY OF BACKGROUND DATA: Preoperative discrimination between spinal schwannomas and meningiomas is crucial because different surgical procedures are required for their treatment. A deep-learning approach based on CNNs is gaining interest in the medical imaging field. METHODS: We retrospectively reviewed data from patients with spinal schwannoma and meningioma who had undergone MRI and tumor resection. There were 50 patients with schwannoma and 34 patients with meningioma. Sagittal T2-weighted magnetic resonance imaging (T2WI) and sagittal contrast-enhanced T1-weighted magnetic resonance imaging (T1WI) were used for the CNN training and validation. The deep learning framework Tensorflow was used to construct the CNN architecture. To evaluate the performance of the CNN, we plotted the receiver-operating characteristic (ROC) curve and calculated the area under the curve (AUC). We calculated and compared the sensitivity, specificity, and accuracy of the diagnosis by the CNN and two board-certified radiologists. RESULTS: . The AUC of ROC curves of the CNN based on T2WI and contrast-enhanced T1WI were 0.876 and 0.870, respectively. The sensitivity of the CNN based on T2WI was 78%; 100% for radiologist 1; and 95% for radiologist 2. The specificity was 82%, 26%, and 42%, respectively. The accuracy was 80%, 69%, and 73%, respectively. By contrast, the sensitivity of the CNN based on contrast-enhanced T1WI was 85%; 100% for radiologist 1; and 96% for radiologist 2. The specificity was 75%, 56, and 58%, respectively. The accuracy was 81%, 82%, and 81%, respectively. CONCLUSION: We have successfully differentiated spinal schwannomas and meningiomas using the CNN with high diagnostic accuracy comparable to that of experienced radiologists. LEVEL OF EVIDENCE: 4.

We study large deviation properties of probability distributions with either a compact support or a fat tail by comparing them with q-deformed exponential distributions. Our main result is a large deviation property for probability distributions with a fat tail. (C) 2015 Elsevier B.V. All rights reserved.

The law of multiplicative error is presented for independent observations and correlated observations represented by the q-product, respectively. We obtain the standard log-normal distribution in the former case and the log-q-normal distribution in the latter case. Queiros' q-log normal distribution is also reconsidered in the framework of the law of error. These results are presented with mathematical conditions to give rise to these distributions.

An axiomatic definition is given for the q-gamma function Gamma(q)(x), q is an element of R, q &gt; 0, x is an element of R of Tsallis (non-extensive) statistical physics, the continuous analogue of the q-factorial of Suyari [H. Suyari, Physica A 368 (1) (2006) 63], and the q-analogue of the gamma function Gamma(x) of Euler and Gauss. A working definition in closed form, based oil the Hurwitz and Riemann zeta functions (including their analytic continuous), is shown to Satisfy this definition. Several relations involving the q-gamma and other functions are obtained. The (q,q)-polygamma functions psi((m))(q,q) (x), m is an element of N, defined by successive derivatives of In(q) Gamma(q)(x), where In(q) a = (1 - q)(-1)(a(1-q) - 1), a &gt; 0 is the q-logarithmic function, are also reported. The new functions are used to calculate the inferred probabilities and multipliers for Tsallis systems with finite numbers of particles N &lt;&lt; infinity. Crown Copyright (C) 2009 Published by Elsevier B.V. All rights reserved.

We present q-Stirling's formula, q-multinomial coefficient, one-to-one correspondence between q-multinominal coefficient and Tsallis entropy, q-Pascal's triangle and a conjecture on the q-central limit theorem in Tsallis statistics for the generalization of the well-known fundamental formulas to systems exhibiting power-law behaviors. The main approach is based on the q-product, uniquely determined by Tsallis entropy, which has already been successfully applied to our recent proof of the law of error in Tsallis statistics. (c) 2006 Elsevier B.V. All rights reserved.

In order to theoretically explain the ubiquitous existence of power-law behavior such as chaos and fractals in nature, Tsallis entropy has been successfully applied to the generalization of the traditional Boltzmann-Gibbs statistics, the fundamental information measure of which is Shannon entropy. Tsallis entropy S-q is a one-parameter generalization of Shannon entropy S-1 in the sense that lim(q--&gt;1) S-q = S-1. The generalized statistics using Tsallis entropy are referred to as Tsallis statistics. In order to present the law of error in Tsallis statistics as a generalization of Gauss' law of error and prove it mathematically, we apply the new multiplication operation determined by q-logarithm and q-exponential, the fundamental functions in Tsallis statistics, to the definition of the likelihood function in Gauss' law of error. The present maximum-likelihood principle (MLP) leads us to determine the so-called q-Gaussian distribution, which coincides with one of the Tsallis distributions derived from the maximum entropy principle for Tsallis entropy under the second moment constraint.

Tsallis entropy, one-parameter generalization of Shannon entropy, has been often discussed in statistical physics as a new information measure. This new information measure has provided many satisfactory physical interpretations in nonextensive systems exhibiting chaos or fractal. We present the generalized Shannon-Khinchin axioms to nonextensive systems and prove the uniqueness theorem rigorously. Our results show that Tsallis entropy is the simplest among all nonextensive entropies. By the detailed comparisons of our axioms with the previously presented two sets of axioms, we reveal the peculiarity of pseudoadditivity as an axiom. In this correspondence, the most fundamental basis for Tsallis entropy as information measure is established in the information-theoretic framework.

1994年, Bell研のShorは公開鍵暗号の基礎である素因数分解を量子コンピュータ上で多項式時間で解くことのできるアルゴリズムを発見した.この発見を機に, 量子コンピュータの研究が一躍脚光をあびることとなった.そして, 今日まで多くの研究者が「古典的な計算機では膨大な計算量を要する問題を量子コンピュータで解くと, どれほどその計算量が減少するか」という問題に挑んでいる.本論文では, 組合せ最適化問題を解くために, その組合せ最適化問題の目的関数の値すべてを多項式時間で計算できる量子回路を構成する.