Daisuke Kawahara

Hiroshima University | HU · Hiroshima University Hospital

This study aims to synthesize fluid-attenuated inversion recovery (FLAIR) and diffusion-weighted images (DWI) with a deep conditional adversarial network from T1- and T2-weighted magnetic resonance imaging (MRI) images. A total of 1980 images of 102 patients were split into two datasets: 1470 (68 patients) in a training set and 510 (34 patients) in...

Background: Artificial intelligence (AI)-based gamma passing rate (GPR) prediction has been proposed as a time-efficient virtual patient-specific QA method for the delivery of volumetric modulation arc therapy (VMAT). However, there is a limitation that the GPR value loses the locational information of dose accuracy. Purpose: The objective was t...

Objectives To develop an imaging prognostic model for idiopathic pulmonary fibrosis (IPF) patients using hybrid auto-segmentation radiomics analysis, and compare the predictive ability between the radiomics analysis and conventional visual score methods. Methods Data from 72 IPF patients who had undergone CT were analyzed. In the radiomics analysi...

Objective We evaluated the radiobiological effect of the irradiation time with the interruption time of stereotactic radiosurgery (SRS) using CyberKnife ® (CK) systemfor brain metastases. Methods We used the DICOM data and irradiation log file of the 10 patients with brain metastases from non–small-cell lung cancer (NSCLC) who underwent brain SRS....

Daily dose distributions for adaptive radiotherapy (ART) using helical tomotherapy (HT) are calculated using megavoltage computed tomography (MVCT). Generally, the MVCT number is converted to mass density (MD) using an MD calibration table (MVCT-MD table). The aims of this study are to calculate the tolerance levels of the MD for ART and to evaluat...

Purpose/Objective(s) Respiratory motion affects the robustness of the dose distribution. For esophageal cancer (EC) near the esophagogastric junction, respiratory motion causes unintentional over- or under- dose distributions for the target. Although four-dimensional computed tomography (4DCT) is useful for robust evaluation, it increases the expos...

This study aims to evaluate the effect of different air computed tomography (CT) numbers of the image value density table (IVDT) on the retrospective dose calculation of head-and-neck (HN) radiotherapy using TomoTherapy megavoltage CT (MVCT) images. The CT numbers of the inside and outside air and each tissue-equivalent plug of the "Cheese" phantom...

Background: The purpose of this study was to improve the biological dosimetric margin (BDM) corresponding to different planning target volume (PTV) margins in homogeneous and nonhomogeneous tumor regions using an improved biological conversion factor (BCF) model for stereotactic body radiation therapy (SBRT). Materials and methods: The PTV margi...

Background: The effective atomic numbers obtained from dual-energy computed tomography (DECT) can aid in characterization of materials. In this study, an effective atomic number image reconstructed from a DECT image was synthesized using an equivalent single-energy CT image with a deep convolutional neural network (CNN)-based generative adversaria...

Word segmentation, part-of-speech (POS) tagging, and syntactic parsing are three fundamental Chinese analysis tasks for Chinese language processing, which are also crucial for various downstream tasks such as machine translation and information extraction. To achieve high accuracy for these tasks, treebanks that contain sentences manually annotated...

To predict the gamma passing rate (GPR) of the three-dimensional (3D) detector array-based volumetric modulated arc therapy (VMAT) quality assurance (QA) for prostate cancer using a convolutional neural network (CNN) with the 3D dose distribution. One hundred thirty-five VMAT plans for prostate cancer were selected: 110 plans were used for training...

Background: The current study aims to predict the recurrence of cervical cancer patients treated with radiotherapy from radiomics features on pretreatment T1- and T2-weighted MR images. Methods: A total of 89 patients were split into model training (63 patients) and model testing (26 patients). The predictors of recurrence were selected using th...

The aim of this study was to propose optimal robust planning by comparing the robustness with setup error with the robustness of a conventional planning target volume (PTV)‐based plan and to compare the robust plan to the PTV‐based plan for the target and organ at risk (OAR). Data from 13 patients with intermediate‐to‐high‐risk localized prostate c...

Purpose Treatment planning for ion therapy involves the conversion of computed tomography number (CTN) into a stopping-power ratio (SPR) relative to water. The purpose of this study was to create a CTN-to-SPR calibration table using a stoichiometric CTN calibration model with a three-parameter fit model for ion therapy, and to demonstrate its effec...

Background: The current study aims to investigate the DNA strand breaks based on the Monte Carlo simulation within and around the Lipiodol with flattening filter (FF) and flattening filter-free (FFF) photon beams. Materials and methods: The dose-mean lineal energy (yD) and DNA single- and double strand breaks (DSB/SSB) based on spatial patterns...

Objectives To propose deep learning (DL)-based predictive model for pathological complete response rate for resectable locally advanced esophageal squamous cell carcinoma (SCC) after neoadjuvant chemoradiotherapy (NCRT) with endoscopic images. Methods and Material This retrospective study analyzed 98 patients with locally advanced esophagus cancer...

Flashcard systems are effective tools for learning words but have their limitations in teaching word usage. To overcome this problem, we suggest that a flashcard system shows a new example sentence on each repetition. This extension requires high-quality example sentences, automatically extracted from a huge corpus. To do this, we use a Determinant...

Objective To expand the BCF model which covert physical dosimetric margin (PDM) to biological dosimetric margin (BDM) for point prescription with 3DCRT and the marginal prescription method with volumetric-modulated radiotherapy (VMAT).MaterialsCoplanar VMAT of marginal prescription and non-coplanar 3D-CRT of point prescription with lung stereotacti...

Purpose To predict the gamma passing rate (GPR) of the three-dimensional (3D) detector array-based volumetric modulated arc therapy (VMAT) quality assurance (QA) for prostate cancer using a convolutional neural network (CNN) with the 3D dose distribution. Methods One hundred thirty-five VMAT plans for prostate cancer were selected: 110 plans were...

Purpose: Adaptive radiotherapy requires auto-segmentation in patients with head and neck (HN) cancer. In the current study, we propose an auto-segmentation model using a generative adversarial network (GAN) on magnetic resonance (MR) images of HN cancer for MR-guided radiotherapy (MRgRT). Material and methods: In the current study, we used a dat...

Objective The current study aims to propose the auto-segmentation model on CT images of head and neck cancer using a stepwise deep neural network (stepwise-net). Material and methods Six normal tissue structures in the head and neck region of 3D CT images: Brainstem, optic nerve, parotid glands (left and right), and submandibular glands (left and...

【Objective】 To predict the recurrence of advanced cervical cancer patients treated with radiotherapy from radiomics features on pre-treatment T1- and T2-weighted MRI images. 【Methods】 A total of 90 patients were split into two sets: 67 patients for model training and 23 patients for model testing. The patient outcome was classified into two groups...

We investigated the effects of indirect apoptotic cell death due to vascular damage on tumor response to a single large dose with an improved two-dimensional cellular automata model. The tumor growth was simulated by considering the oxygen and nutrients supplied to the tumor through the blood vessels. The cell damage processes were modeled by takin...

Objective We aimed to develop a predictive model for occult cervical lymph node metastasis (OCLNM) in patients with tongue cancer using radiomics and machine learning from pretreatment contrast-enhanced computed tomography (CT). Study Design This study included 161 patients with tongue cancer who received local treatment. CT images were transferre...

Automatically solving math word problems is a critical task in the field of natural language processing. Recent models have reached their performance bottleneck and require more high-quality data for training. We propose a novel data augmentation method that reverses the mathematical logic of math word problems to produce new high-quality math prob...

Purpose/Objective(s) Whole pelvis irradiation (WPI) is the standard radiation technique for locally advanced cervical cancer without para-aortic lymph node (PALN) metastasis. PALN is one of the most common late failure sites in patients treated with WPI. Although there are several reports about the utility of prophylactic extended-field irradiation...

Purpose/Objective(s) This study evaluated the current status, quality assurance (QA) and technique of intensity-modulated radiotherapy (IMRT) in Japan. Materials/Methods IMRT is a new technique, introduced in the late 1990s. Since 2000, the number of institutions providing IMRT has increased. Therefore, to recognize the current status of IMRT in J...

Purpose/Objective(s) Although the use of volumetric modulated arc therapy (VMAT) is widespread, there are few reports on the impact of using VMAT on radiation pneumonitis (RP) in radiotherapy for locally advanced non-small cell lung cancer (NSCLC) patients especially for Asians. The administration of durvalumab after radical chemoradiotherapy has b...

Purpose/Objective(s) The purpose of this study was to evaluate the long-term treatment results of interstitial brachytherapy (IBT) in patients with locally advanced tongue cancer. Materials/Methods between 1994 and 2015, 60 patients (18 females and 42 males) with locally advanced tongue cancer treated by IBT using Ir-192 sources and Au-198 seeds w...

Purpose/Objective(s) In earlier stage of locally advanced unresectable cervical squamous cell carcinoma, the treatment outcomes of surgery and definitive radiotherapy are comparable. However, the past study reported that one third of patients would experience recurrence. Predicting the treatment response and the long-term treatment outcome presents...

Background: The use of volumetric modulated arc therapy is gradually widespread for locally advanced non-small cell lung cancer. The purpose of this study was to identify the factors that caused ≥ grade 2 radiation pneumonitis and evaluate the impact of using volumetric modulated arc therapy on the incidence of ≥ grade 2 radiation pneumonitis by c...

To predict grade ≥ 2 radiation pneumonitis (RP) in patients with locally advanced non-small cell lung cancer (NSCLC) using multi-region radiomics analysis. Data from 77 patients with NSCLC who underwent definitive radiotherapy between 2008 and 2018 were analyzed. Radiomic feature extraction from the whole lung (whole-lung radiomics analysis) and im...

Objective To propose the prediction model for degree of differentiation for locally advanced esophageal cancer patients from the planning CT image by radiomics analysis with machine learning. Methods Data of 104 patients with esophagus cancer, who underwent chemoradiotherapy followed by surgery at the Hiroshima University hospital from 2003 to 201...

Objectives We evaluated the radiobiological effectiveness based on the yields of DNA double-strand breaks (DSBs) of field induction with flattening filter (FF) and FF-free (FFF) photon beams. Methods We used the particle and heavy ion transport system (PHITS) and a water equivalent phantom (30 × 30 × 30 cm ³ ) to calculate the physical qualities o...

Background: This study aimed to propose a machine learning model to predict the local response of resectable locally advanced esophageal squamous cell carcinoma (LA-ESCC) treated by neoadjuvant chemoradiotherapy (NCRT) using pretreatment 18-fluorodeoxyglucose positron emission tomography (FDG PET) images. Methods: The local responses of 98 patie...

Objective To predict grade 2 radiation pneumonitis (RP) in locally advanced non-small cell lung cancer (NSCLC) patients with high accuracy by using multi-region radiomics analysis. Material and Methods Data from 77 patients with NSCLC who underwent definitive radiotherapy from 2008 to 2018 were analyzed. Radiomic feature extraction from the whole l...

Purpose: To develop a dosimetric internal target volume (ITV) margin (DIM) for respiratory motion in lung stereotactic body radiotherapy (SBRT) and to evaluate DIM with a nonuniform volume prescription (NVP) and the point prescription (PP). Methods: Volumetric modulated arc therapy (VMAT) treatment plans with PP and NVP were created on a heterog...

Background: The objective of this study was to propose an optimal input image quality for a conditional generative adversarial network (GAN) in T1-weighted and T2-weighted magnetic resonance imaging (MRI) images. Materials and methods: A total of 2,024 images scanned from 2017 to 2018 in 104 patients were used. The prediction framework of T1-wei...

Purpose: To synthesize a dual-energy computed tomography (DECT) image from an equivalent kilovoltage computed tomography (kV-CT) image using a deep convolutional adversarial network. Methods: A total of 18,084 images of 28 patients are categorized into training and test datasets. Monoenergetic CT images at 40, 70, and 140 keV and equivalent kV-C...

Purpose: The current study proposed a model to predict the response of brain metastases (BMs) treated by Gamma knife radiosurgery (GKRS) using a machine learning (ML) method with radiomics features. The model can be used as a decision tool by clinicians for the most desirable treatment outcome. Methods and material: Using MR image data taken by...

Generative Adversarial Networks (GANs) have been widely used and it is expected to use for the clinical examination and image. The objective of the current study was to synthesize material decomposition images of bone-water (bone(water)) and fat-water (fat(water)) reconstructed from dual-energy computed tomography (DECT) using an equivalent kilovol...

Correcting typographical errors (typos) is important to mitigate errors in downstream natural language processing tasks. Although a large number of typo–correction pairs are required to develop typo correction systems, no such dataset is available for the Japanese language. Previous studies on building French and English typo datasets have exploite...

Purpose: We sought to develop machine learning models to detect multileaf collimator (MLC) modeling errors with the use of radiomic features of fluence maps measured in patient-specific quality assurance (QA) for intensity-modulated radiation therapy (IMRT) with an electric portal imaging device (EPID). Methods: Fluence maps measured with EPID f...

Preoperative chemoradiotherapy with capecitabine or 5-fluorouracil is a standard treatment for locally advanced rectal cancer (LARC). S-1, a prodrug of 5-fluorouracil, is a candidate for this chemoradiotherapy regimen in Japan; however, treatment outcomes after S-1 treatment alone are not clear. This study aimed to assess the efficacy and tolerabil...

Objectives: To evaluate the effect of interruption in radiotherapy due to machine failure in patients and medical institutions using machine failure risk analysis (MFRA). Material and methods: The risk of machine failure during treatment is assigned to three scores (biological effect, B; occurrence, O; and cost of labor and repair parts, C) for...

Purpose: The interruption time is the irradiation interruption that occurs at sites and operations such as the gantry, collimator, couch rotation, and patient setup within the field in radiotherapy. However, the radiobiological effect of prolonging the treatment time by the interruption time for tumor cells is little evaluated. We investigated the...

Automatically solving math word problems is a critical task in the field of natural language processing. Recent models have reached their performance bottleneck and require more high-quality data for training. Inspired by human double-checking mechanism, we propose a reverse operation based data augmentation method that makes use of mathematical lo...

Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence generation. However, Seq2Seq enforces an unnecessary order on the unordered triplets and involves a large decoding length associated with error accumulation. These introduce...

The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education. Meanwhile, the COVID-19 condition is very different among the countries (e.g., policies and development of the epidemic), and thus citizens would be interested in news in foreign...

Background/aim: The present study aimed to analyze the treatment outcome after definitive radiotherapy (dRT) using volumetric-modulated arc therapy (VMAT) in patients with hypopharyngeal cancer (HPC), including an examination of late toxicities. Patients and methods: A total of 62 patients with HPC, who underwent dRT using VMAT, were analyzed. O...

The present study aimed to analyze treatment outcomes after induction chemotherapy followed by chemoradiotherapy (CRT) using volumetric-modulated arc therapy (VMAT) in patients with stage IVA-B oropharyngeal cancer (OPC) or hypopharyngeal cancer (HPC), with long-term observation, including examination of larynx preservation. A total of 60 patients...

Objective To evaluate the biological effectiveness of dose associated with interruption time; and propose the dose compensation method based on biological effectiveness when an interruption occurs during photon radiation therapy. Methods The lineal energy distribution for human salivary gland tumor was calculated by Monte Carlo simulation using a...

Background: We investigated the effect of the interruption time on the radiobiological effectiveness with photon beams based on a modified microdosimetric kinetic model. Background: The interruption time is used is that irradiation interruption occurs at sites and operations such as the gantry, collimator, couch rotation, and patient set-up in radi...

An NLP tool is practical when it is fast in addition to having high accuracy. We describe the architecture and the used methods to achieve 250× analysis speed improvement on the Juman++ morphological analyzer together with slight accuracy improvements. This information should be useful for implementors of high-performance NLP and machine-learning b...

Purpose: To develop a novel biological dosimetric margin (BDM) and to create a biological conversion factor (BCF) that compensates for the difference between physical dosimetric margin (PDM) and BDM, which provides a novel scheme of a direct estimation of the BDM from the physical dose (PD) distribution. Methods: The offset to isocenter was appl...

The aim of our study is to evaluate the metal artefact reduction techniques with the same contrast scale for different vendors’ dual-energy CT (DECT): kV-CT image with metal artefact reduction method and monoenergetic CT image using Canon’s DECT, and monoenergetic CT image with metal artefact reduction method using GE’s DECT. The kV-CT image and DE...

The current study aims to determine the optimal irradiation interval of fractionated stereotactic radiosurgery (SRS) by using an improved cellular automata (CA) model. The tumor growth process was simulated by considering the amount of oxygen and the density of blood vessels, which supplied oxygen and nutrient required for cell growth. Cancer cells...

This study aimed to evaluate the relationship between cardiac toxicity after definitive chemoradiotherapy (CRT) for esophageal cancer and the dose-volume histogram (DVH) of organs at risk (OARs) [using biological effective dose (BED)]. We analyzed the data of 83 patients with esophageal cancer treated using definitive CRT between 2001 and 2016. Fur...

456 Background: The pathologic complete response (PCR) rate by neoadjuvant chemoradiotherapy (NCRT) for resectable locally advanced esophageal squamous cell carcinoma (ESCC) is about 40%. If we could predict a PCR from pre-treatment image data, it might be possible to select patients who can be cured by organ-preserving CRT. The purpose of this stu...

Purpose: In photon radiation therapy, computed tomography (CT) numbers are converted into values for mass density (MD) or relative electron density to water (RED). CT-MD or CT-RED calibration tables are relevant for human body dose calculation in an inhomogeneous medium. CT-MD or CT-RED calibration tables are influenced by patient imaging (CT scan...

Objectives The aim of the current study was to evaluate effective atomic number (Zeff) values with a newly developed characteristic tissue phantom and contrast material of varying iodine concentrations using single-source fast kilovoltage switching type dual-energy CT (DECT). Methods A multi energy CT phantom that was a newly developed tissue char...

Purpose: We aim to develop a method to predict the gamma passing rate (GPR) of a three-dimensional (3D) dose distribution measured by the Delta4 detector system using the dose uncertainty potential (DUP) accumulation model. Methods: Sixty head-and-neck intensity-modulated radiation therapy (IMRT) treatment plans were created in the XiO treatment...

Background Previously, the physical dose-enhancement factor (DphysEF) enhancement was introduced. However, the dose enhancement considering the biological effectiveness was not shown. Purpose The aim of the current study was to evaluate the biological dose-enhancement factor (DbioEF) by the dose rate and to compare the DphysEF and the DbioEF in Li...

Objectives: The aim of the current study is to evaluate the accuracy and the precision of raw-data-based relative electron density (REDraw) and the calibration-based RED (REDcal) at a range of low-RED to high-RED for tissue-equivalent phantom materials by comparing them with reference RED (REDref) and to present the difference of REDraw and REDcal...

To communicate with humans in a human-like manner, systems need to understand behavior and psychological states in situations of human-machine interactions, such as in the cases of autonomous driving and nursing robots. We focus on driving situa- tions as they are part of our daily lives and concern safety. To develop such systems, a corpus annotat...

In a previous study, a phantom study of a contrast agent extraction system with computed tomography (CT) number and raw-data-based electron density (ED) was described. The current study improved this system with monochromatic CT (mCT) number and evaluated an anthropomorphic phantom for delineation of the contrast-enhanced region. Dual-energy CT ima...