Nemoto, Takafumi

写真a

Affiliation

School of Medicine, Department of Radiology (Radiation Oncology) (Shinanomachi)

Position

Instructor

Career 【 Display / hide

  • 2014.04
    -
    2016.03

    Iwate Prefectural Iwai Hospital, Resident

  • 2016.04
    -
    2017.03

    National Hospital Organization Tokyo Medical Center, Department of Radiology, Resident

  • 2017.04
    -
    2019.03

    Keio University School of Medicine, Department of Radiology, Resident

  • 2019.04
    -
    2020.03

    Saiseikai Yokohamashi Tobu Hospital, Department of Radiation Oncology, Radiation Oncologist

  • 2020.04
    -
    2022.03

    Keio University School of Medicine, Department of Radiology (Radiation Oncology), 助教

display all >>

Academic Background 【 Display / hide

  • 2008.04
    -
    2014.03

    Tohoku University School of Medicine

  • 2019.04
    -
    2022.09

    Keio University Graduate School of Medicine

 

Research Areas 【 Display / hide

  • Life Science / Radiological sciences

Research Keywords 【 Display / hide

  • Radiation Oncology

  • Machine Learning

  • Deep Learning

 

Books 【 Display / hide

  • 放射線科ではAI Chatはこう使う!RadFan 2024 February Vol.22 No.2

    Takafumi Nemoto, Natsumi Futakami, メディカルアイ, 2024.02

Papers 【 Display / hide

  • Effect on Heart and Lung Doses Reduction of Abdominal and Thoracic Deep Inspiratory Breath-hold Assuming Involved-field Radiation Therapy in Patients with Simulated Esophageal Cancer

    Eride Mutu, Takeshi Akiba, Yoshitsugu Matsumoto, Etsuo Kunieda, Ryuta Nagao, Tsuyoshi Fukuzawa, Tomomi Katsumata, Toshihisa Kuroki, Tatsuya Mikami, Yoji Nakano, Shigeto Kabuki, Natsumi Futakami, Takafumi Nemoto, Yuri Toyoda, Tsuyoshi Takazawa, Akitomo Sugawara

    Tokai J Exp Clin Med. 48 ( 1 ) 32 - 37 2023

    Accepted,  ISSN  03850005

     View Summary

    Purpose: The purpose of this study was to evaluate the lung and heart doses in volumetric-modulated arc therapy (VMAT) using involved-field irradiation in patients with middle-to-lower thoracic esophageal cancer during free breathing (FB), abdominal deep inspiratory breath-hold (A-DIBH), and thoracic DIBH (T-DIBH) images. Methods: Computed tomography images of A-DIBH, T-DIBH, and FB from 25 patients with breast cancer were used to simulate patients with esophageal cancer. The irradiation field was set at an involved-field, and target and risk organs were outlined according to uniform criteria. VMAT optimization was performed, and lung and heart doses were evaluated. Results: A-DIBH had a lower lung V20 Gy than FB and a lower lung V40 Gy, V30 Gy, V20 Gy than T-DIBH. The heart all dose indices were lower in T-DIBH than FB, and the heart V10 Gy was lower in A-DIBH than FB. However, the heart Dmean was comparable with A-DIBH and T-DIBH. Conclusions: A-DIBH had significant dose advantages for lungs compared to FB and T-DIBH, and the heart Dmean was comparable to T-DIBH. Therefore, when performing DIBH, A-DIBH is suggested for radiotherapy in patients with middle-to-lower thoracic esophageal cancer, excluding irradiation of the prophylactic area.

  • Relationship between Dose Prescription Methods and Local Control Rate in Stereotactic Body Radiotherapy for Early Stage Non-Small-Cell Lung Cancer: Systematic Review and Meta-Analysis

    Takahisa Eriguchi, Atsuya Takeda, Takafumi Nemoto, Yuichiro Tsurugai, Naoko Sanuki, Yudai Tateishi, Yuichi Kibe, Takeshi Akiba, Mari Inoue, Kengo Nagashima, Nobuyuki Horita

    Cancers (MDPI AG)  14 ( 15 ) 3815 - 3815 2022.08

    Accepted

     View Summary

    Variations in dose prescription methods in stereotactic body radiotherapy (SBRT) for early stage non-small-cell lung cancer (ES-NSCLC) make it difficult to properly compare the outcomes of published studies. We conducted a comprehensive search of the published literature to summarize the outcomes by discerning the relationship between local control (LC) and dose prescription sites. We systematically searched PubMed to identify observational studies reporting LC after SBRT for peripheral ES-NSCLC. The correlations between LC and four types of biologically effective doses (BED) were evaluated, which were calculated from nominal, central, and peripheral prescription points and, from those, the average BED. To evaluate information on SBRT for peripheral ES-NSCLC, 188 studies were analyzed. The number of relevant articles increased over time. The use of an inhomogeneity correction was mentioned in less than half of the articles, even among the most recent. To evaluate the relationship between the four BEDs and LC, 33 studies were analyzed. Univariate meta-regression revealed that only the central BED significantly correlated with the 3-year LC of SBRT for ES-NSCLC (p = 0.03). As a limitation, tumor volume, which might affect the results of this study, could not be considered due to a lack of data. In conclusion, the central dose prescription is appropriate for evaluating the correlation between the dose and LC of SBRT for ES-NSCLC. The standardization of SBRT dose prescriptions is desirable.

  • Applying Artificial Neural Networks to Develop a Decision Support Tool for Tis–4N0M0 Non–Small-Cell Lung Cancer Treated With Stereotactic Body Radiotherapy

    Takafumi Nemoto, Atsuya Takeda, Yukinori Matsuo, Noriko Kishi, Takahisa Eriguchi, Etsuo Kunieda, Ryusei Kimura, Naoko Sanuki, Yuichiro Tsurugai, Masamichi Yagi, Yousuke Aoki, Yohei Oku, Yuto Kimura, Changhee Han, Naoyuki Shigematsu

    JCO Clinical Cancer Informatics (American Society of Clinical Oncology (ASCO))  6 ( 6 ) e2100176 2022.06

    Accepted

     View Summary

    PURPOSE

    Clear evidence indicating whether surgery or stereotactic body radiation therapy (SBRT) is best for non–small-cell lung cancer (NSCLC) is lacking. SBRT has many advantages. We used artificial neural networks (NNs) to predict treatment outcomes for patients with NSCLC receiving SBRT, aiming to aid in decision making.

    PATIENTS AND METHODS

    Among consecutive patients receiving SBRT between 2005 and 2019 in our institution, we retrospectively identified those with Tis–T4N0M0 NSCLC. We constructed two NNs for prediction of overall survival (OS) and cancer progression in the first 5 years after SBRT, which were tested using an internal and an external test data set. We performed risk group stratification, wherein 5-year OS and cancer progression were stratified into three groups.

    RESULTS

    In total, 692 patients in our institution and 100 patients randomly chosen in the external institution were enrolled. The NNs resulted in concordance indexes for OS of 0.76 (95% CI, 0.73 to 0.79), 0.68 (95% CI, 0.60 to 0.75), and 0.69 (95% CI, 0.61 to 0.76) and area under the curve for cancer progression of 0.80 (95% CI, 0.75 to 0.84), 0.72 (95% CI, 0.60 to 0.83), and 0.70 (95% CI, 0.57 to 0.81) in the training, internal test, and external test data sets, respectively. The survival and cumulative incidence curves were significantly stratified. NNs selected low-risk cancer progression groups of 5.6%, 6.9%, and 7.0% in the training, internal test, and external test data sets, respectively, suggesting that 48% of patients with peripheral Tis–4N0M0 NSCLC can be at low-risk for cancer progression.

    CONCLUSION

    Predictions of SBRT outcomes using NNs were useful for Tis–4N0M0 NSCLC. Our results are anticipated to open new avenues for NN predictions and provide decision-making guidance for patients and physicians.

  • Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs

    Takafumi Nemoto, Natsumi Futakami, Etsuo Kunieda, Masamichi Yagi, Atsuya Takeda, Takeshi Akiba, Eride Mutu, Naoyuki Shigematsu

    Radiological Physics and Technology (Springer Science and Business Media LLC)  14 ( 3 ) 318 - 327 2021.09

    Accepted,  ISSN  18650333

     View Summary

    Abstract
    Deep learning has demonstrated high efficacy for automatic segmentation in contour delineation, which is crucial in radiation therapy planning. However, the collection, labeling, and management of medical imaging data can be challenging. This study aims to elucidate the effects of sample size and data augmentation on the automatic segmentation of computed tomography images using U-Net, a deep learning method. For the chest and pelvic regions, 232 and 556 cases are evaluated, respectively. We investigate multiple conditions by changing the sum of the training and validation datasets across a broad range of values: 10–200 and 10–500 cases for the chest and pelvic regions, respectively. A U-Net is constructed, and horizontal-flip data augmentation, which produces left and right inverse images resulting in twice the number of images, is compared with no augmentation for each training session. All lung cases and more than 100 prostate, bladder, and rectum cases indicate that adding horizontal-flip data augmentation is almost as effective as doubling the number of cases. The slope of the Dice similarity coefficient (DSC) in all organs decreases rapidly until approximately 100 cases, stabilizes after 200 cases, and shows minimal changes as the number of cases is increased further. The DSCs stabilize at a smaller sample size with the incorporation of data augmentation in all organs except the heart. This finding is applicable to the automation of radiation therapy for rare cancers, where large datasets may be difficult to obtain.

  • Repeated Stereotactic Body Radiation Therapy for Hepatocellular Carcinoma

    Takahisa Eriguchi, Nobuhiro Tsukamoto, Nobuko Kuroiwa, Takafumi Nemoto, Takeru Ogata, Yusuke Okubo, Shigeru Nakano, Akitomo Sugawara

    Practical Radiation Oncology (Elsevier BV)  11 ( 1 ) 44 - 52 2021.01

    Accepted,  ISSN  18798500

     View Summary

    Abstract
    Purpose
    In clinical practice, whether cirrhotic livers in patients with hepatocellular carcinoma (HCC) can withstand repeated stereotactic body radiation therapy (SBRT) remains unclear. This study aimed to evaluate the outcomes and toxicities in these patients.

    Methods and materials
    This retrospective study included patients with HCC who were treated with SBRT at least twice between January 2012 and June 2019. Local control and overall survival rates were calculated. Liver function before and after irradiation was evaluated using the Child-Pugh score and modified albumin-bilirubin grade. All toxicities were assessed using the Common Terminology Criteria for Adverse Events (version 4.0).

    Results
    Fifty-two patients underwent 136 courses (148 lesions) of SBRT, which was mostly performed for out-of-field tumors but 3 in-field recurrences. The median follow-up duration from the first SBRT was 52.6 months (range, 15.7-89.3 months). The median gross tumor volume was 4.6 cm3 (range, 0.8-55.2 cm3) at the second SBRT. The 3-year local control rate was 94.5% (95% confidence interval, 88.0%-97.5%). The 3-year overall survival rate after the second course was 62.8% (95% confidence interval, 45.1%-76.2%). Although the Child-Pugh score did not deteriorate after the second course, deterioration of the modified albumin-bilirubin grade at 6, 12, and 24 months was statistically significant compared with that before the second course. One patient (1.9%) experienced grade 3 hypoalbuminemia and 2 patients (3.8%) had grade 3 thrombocytopenia 6 months after the second course. Mild fatigue and nausea were reported in 9 (17.3%) and 6 (11.5%) patients, respectively. One instance of grade 5 toxicity was observed. Two patients (1.5%) had grade 2 gastric ulcers. No other grade ≥3 gastrointestinal toxicities occurred.

    Conclusions
    Repeated SBRT is feasible and produces minimal toxicity in patients with HCC and Child-Pugh scores of ≤7 and a low normal liver dose.

display all >>

Reviews, Commentaries, etc. 【 Display / hide

  • [Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs].

    Takafumi Nemoto, Natsumi Futakami, Etsuo Kunieda, Masamichi Yagi, Atsuya Takeda, Takeshi Akiba, Eride Mutu, Naoyuki Shigematsu

    Igaku butsuri : Nihon Igaku Butsuri Gakkai kikanshi = Japanese journal of medical physics : an official journal of Japan Society of Medical Physics 43 ( 1 ) 19 - 19 2023

Research Projects of Competitive Funds, etc. 【 Display / hide

  • 画像自動解析を併用した非小細胞肺癌治療の革新的患者意思決定支援AIシステムの開発

    2023.08
    -
    2025.03

    日本学術振興会, 科学研究費助成事業, 研究活動スタート支援, Principal investigator

  • Applying deep learning to develop a decision support tool for non-small-cell lung cancer

    2022
    -
    2023

    Japan Society for the Promotion of Science, Overseas Challenge Program for Young Researchers 2022, Takafumi Nemoto, Principal investigator

  • AOCMP2022研究成果報告奨励金

    2022

    Japan Society of Medical Physics, Takafumi Nemoto, Principal investigator

  • 慶應義塾大学院医学研究科博士課程奨学金

    2021
    -
    2022

    Keio University, Takafumi Nemoto, Principal investigator

  • The decision support tool for T1–4N0M0 NSCLC patients treated with SBRT analyzing our accumulated database set using machine learning methods

    2020
    -
    2022

    Varian Medical Systems, Inc., Varian Research Grant, Atsuya Takeda, Takafumi Nemoto, Coinvestigator(s)

Awards 【 Display / hide

  • The AFOMP Journal Prize for the Best Paper

    Takafumi Nemoto, Natsumi Futakami, Etsuo Kunieda, Masamichi Yagi, Atsuya Takeda, Takeshi Akiba, Eride Mutu, Naoyuki Shigematsu, 2022.12, Asia-Oceania Federation of Organizations for Medical Physics (AFOMP)

    Type of Award: Award from international society, conference, symposium, etc.,  Country: Taiwan, Province of China

  • Doi Award (The best paper of the year in medical imaging)

    Takafumi Nemoto, Natsumi Futakami, Etsuo Kunieda, Masamichi Yagi, Atsuya Takeda, Takeshi Akiba, Eride Mutu, Naoyuki Shigematsu, 2022.04, Japan Society of Medical Physics, Japanese Society of Radiological Technology

 

Courses Previously Taught 【 Display / hide

  • Basic Programming I

    Tokyo College of Medico-Pharmaco-Nursing Technology

    2023

 

Social Activities 【 Display / hide

  • 市民公開講座「体にやさしい最新の放射線治療」

    公益社団法人 日本医学放射線学会、慶應義塾大学医学部 放射線科学教室, 第83回 日本医学放射線学会総会 レントゲン博士没後100周年記念「知っておきたい画像医学」, 

    2023.10