Tomohiro Kikuchi

Dr. Tomohiro Kikuchi

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 March 2024 in JMIR Medical Education
Verified
Journal Article
Open access
TNTakahiro Nakao
Takahiro Nakao
SMSoichiro Miki
Soichiro Miki
YNYuta Nakamura
Yuta Nakamura
TKTomohiro Kikuchi
Tomohiro Kikuchi
YNYukihiro Nomura
Yukihiro Nomura
OAOsamu Abe
Osamu Abe
Background: Previous research applying large language models (LLMs) to medicine was focused on text-based information. Recently, multimodal variants of LLMs acquired the capability of recognizing images. Objective: We aim to evaluate the image recognition capability of generative pretrained transformer (GPT)-4V, a recent multimodal LLM developed by OpenAI, in the medical field by testing how visual information affects its performance to answer questions in the 117th Japanese National Medical Licensing Examination. Methods: We focused on 108 questions that had 1 or more images as part of a question and presented GPT-4V with the same questions under two conditions: (1) with both the question text and associated images and (2) with the question text only. We then compared the difference in accuracy between the 2 conditions using the exact McNemar test. Results: Among the 108 questions with images, GPT-4V’s accuracy was 68% (73/108) when presented with images and 72% (78/108) when presented without images (P=.36). For the 2 question categories, clinical and general, the accuracies with and those without images were 71% (70/98) versus 78% (76/98; P=.21) and 30% (3/10) versus 20% (2/10; P≥.99), respectively. Conclusions: The additional information from the images did not significantly improve the performance of GPT-4V in the Japanese National Medical Licensing Examination.

11 May 2024 in Japanese Journal of Radiology
Verified
Journal Article
Open access
PDF file
YHYuichiro Hirano
Yuichiro Hirano
SHShouhei Hanaoka
Shouhei Hanaoka
TNTakahiro Nakao
Takahiro Nakao
SMSoichiro Miki
Soichiro Miki
TKTomohiro Kikuchi
Tomohiro Kikuchi
OAOsamu Abe
Osamu Abe
Purpose: To assess the performance of GPT-4 Turbo with Vision (GPT-4TV), OpenAI’s latest multimodal large language model, by comparing its ability to process both text and image inputs with that of the text-only GPT-4 Turbo (GPT-4 T) in the context of the Japan Diagnostic Radiology Board Examination (JDRBE). Materials and methods: The dataset comprised questions from JDRBE 2021 and 2023. A total of six board-certified diagnostic radiologists discussed the questions and provided ground-truth answers by consulting relevant literature as necessary. The following questions were excluded: those lacking associated images, those with no unanimous agreement on answers, and those including images rejected by the OpenAI application programming interface. The inputs for GPT-4TV included both text and images, whereas those for GPT-4 T were entirely text. Both models were deployed on the dataset, and their performance was compared using McNemar’s exact test. The radiological credibility of the responses was assessed by two diagnostic radiologists through the assignment of legitimacy scores on a five-point Likert scale. These scores were subsequently used to compare model performance using Wilcoxon's signed-rank test. Results: The dataset comprised 139 questions. GPT-4TV correctly answered 62 questions (45%), whereas GPT-4 T correctly answered 57 questions (41%). A statistical analysis found no significant performance difference between the two models (P = 0.44). The GPT-4TV responses received significantly lower legitimacy scores from both radiologists than the GPT-4 T responses. Conclusion: No significant enhancement in accuracy was observed when using GPT-4TV with image input compared with that of using text-only GPT-4 T for JDRBE questions.

16 April 2022 in Cancer Immunology, Immunotherapy
Verified
Journal Article
Open access
PDF file
AKAkinao Kaneta
Akinao Kaneta
SNShotaro Nakajima
Shotaro Nakajima
HOHirokazu Okayama
Hirokazu Okayama
TMTakuro Matsumoto
Takuro Matsumoto
KSKatsuharu Saito
Katsuharu Saito
KKKoji Kono
Koji Kono
Deficient mismatch repair (dMMR)/microsatellite instability (MSI) colorectal cancer (CRC) has high immunogenicity and better prognosis compared with proficient MMR (pMMR)/microsatellite stable (MSS) CRC. Although the activation of the cyclic GMP-AMP synthase (cGAS)-stimulator of interferon genes (STING) pathway has been considered to contribute to the high number of CD8+ TILs, its role in dMMR/MSI CRC is largely unknown. In this study, to examine the role of the cGAS-STING pathway on the recruitment of CD8+ TILs in dMMR/MSI CRC, we used public datasets and clinical tissue samples in our cohorts to evaluate the expression of cGAS, STING, and CD8+ TILs in pMMR/MSS and dMMR/MSI CRCs. According to the analysis of public datasets, the expression of cGAS-STING, CD8 effector gene signature, and CXCL10-CCL5, chemoattractants for CD8+ TILs which regulated by the cGAS-STING pathway, was significantly upregulated in dMMR/MSI CRC, and the expression of cGAS-STING was significantly associated with the expression of CD8 effector gene signature. Immunohistochemistry staining of the clinical tissue samples (n = 283) revealed that cGAS-STING was highly expressed in tumor cells of dMMR CRC, and higher expression of cGAS-STING in tumor cells was significantly associated with the increased number of CD8+ TILs. Moreover, we demonstrated that the downregulation of MMR gene in human CRC cell lines enhanced the activation of the cGAS-STING pathway. Taken together, for the first time, we found that dMMR/MSI CRC has maintained a high level of cGAS-STING expression in tumor cells, which might contribute to abundant CD8+ TILs and immune-active TME.

13 December 2023 in medRxiv
Verified
Preprint
Open access
PDF file
YNYuta Nakamura
Yuta Nakamura
TKTomohiro Kikuchi
Tomohiro Kikuchi
YYYosuke Yamagishi
Yosuke Yamagishi
SHShouhei Hanaoka
Shouhei Hanaoka
TNTakahiro Nakao
Takahiro Nakao
OAOsamu Abe
Osamu Abe
Objectives: CT imaging is essential in the initial staging of lung cancer. However, free-text radiology reports do not always directly mention clinical TNM stages. We explored the capability of OpenAI’s ChatGPT to automate lung cancer staging from CT radiology reports. Methods: We used MedTxt-RR-JA, a public de-identified dataset of 135 CT radiology reports for lung cancer. Two board-certified radiologists assigned clinical TNM stage for each radiology report by consensus. We used a part of the dataset to empirically determine the optimal prompt to guide ChatGPT. Using the remaining part of the dataset, we (i) compared the performance of two ChatGPT models (GPT-3.5 Turbo and GPT-4), (ii) compared the performance when the TNM classification rule was or was not presented in the prompt, and (iii) performed subgroup analysis regarding the T category. Results: The best accuracy scores were achieved by GPT-4 when it was presented with the TNM classification rule (52.2%, 78.9%, and 86.7% for the T, N, and M categories). Most ChatGPT’s errors stemmed from challenges with numerical reasoning and insufficiency in anatomical or lexical knowledge. Conclusions: ChatGPT has the potential to become a valuable tool for automating lung cancer staging. It can be a good practice to use GPT-4 and incorporate the TNM classification rule into the prompt. Future improvement of ChatGPT would involve supporting numerical reasoning and complementing knowledge. Clinical relevance statement: ChatGPT’s performance for automating cancer staging still has room for enhancement, but further improvement would be helpful for individual patient care and secondary information usage for research purposes. Key points: ChatGPT, especially GPT-4, has the potential to automatically assign clinical TNM stage of lung cancer based on CT radiology reports. It was beneficial to present the TNM classification rule to ChatGPT to improve the performance. ChatGPT would further benefit from supporting numerical reasoning or providing anatomical knowledge. Graphical

29 April 2025 in JMIR AI
Verified
Journal Article
Open access
YYYosuke Yamagishi
Yosuke Yamagishi
SHShouhei Hanaoka
Shouhei Hanaoka
TKTomohiro Kikuchi
Tomohiro Kikuchi
TNTakahiro Nakao
Takahiro Nakao
YNYuta Nakamura
Yuta Nakamura
OAOsamu Abe
Osamu Abe
Background: Medical image segmentation is crucial for diagnosis and treatment planning in radiology, but it traditionally requires extensive manual effort and specialized training data. With its novel video tracking capabilities, the Segment Anything Model 2 (SAM 2) presents a potential solution for automated 3D medical image segmentation without the need for domain-specific training. However, its effectiveness in medical applications, particularly in abdominal computed tomography (CT) imaging remains unexplored. Objective: The aim of this study was to evaluate the zero-shot performance of SAM 2 in 3D segmentation of abdominal organs in CT scans and to investigate the effects of prompt settings on segmentation results. Methods: In this retrospective study, we used a subset of the TotalSegmentator CT dataset from eight institutions to assess SAM 2’s ability to segment eight abdominal organs. Segmentation was initiated from three different z-coordinate levels (caudal, mid, and cranial levels) of each organ. Performance was measured using the dice similarity coefficient (DSC). We also analyzed the impact of “negative prompts,” which explicitly exclude certain regions from the segmentation process, on accuracy. Results: A total of 123 patients (mean age 60.7, SD 15.5 years; 63 men, 60 women) were evaluated. As a zero-shot approach, larger organs with clear boundaries demonstrated high segmentation performance, with mean DSCs as follows: liver, 0.821 (SD 0.192); right kidney, 0.862 (SD 0.212); left kidney, 0.870 (SD 0.154); and spleen, 0.891 (SD 0.131). Smaller organs showed lower performance: gallbladder, 0.531 (SD 0.291); pancreas, 0.361 (SD 0.197); and adrenal glands—right, 0.203 (SD 0.222) and left, 0.308 (SD 0.234). The initial slice for segmentation and the use of negative prompts significantly influenced the results. By removing negative prompts from the input, the DSCs significantly decreased for six organs. Conclusions: SAM 2 demonstrated promising zero-shot performance in segmenting certain abdominal organs in CT scans, particularly larger organs. Performance was significantly influenced by input negative prompts and initial slice selection, highlighting the importance of optimizing these factors.

20 April 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HSHisaichi Shibata
Hisaichi Shibata
SHShouhei Hanaoka
Shouhei Hanaoka
TNTakahiro Nakao
Takahiro Nakao
TKTomohiro Kikuchi
Tomohiro Kikuchi
YNYuta Nakamura
Yuta Nakamura
OAOsamu Abe
Osamu Abe
Local differential privacy algorithms combined with deep generative models can enhance secure medical image sharing among researchers in the public domain without central administrators; however, these images were limited to the generation of low-resolution images, which are very insufficient for diagnosis by medical doctors. To enhance the performance of deep generative models so that they can generate high-resolution medical images, we propose a large-scale diffusion model that can, for the first time, unconditionally generate high-resolution (256×256×256) volumetric medical images (head magnetic resonance images). This diffusion model has 19 billion parameters, but to make it easy to train it, we temporally divided the model into 200 submodels, each of which has 95 million parameters. Moreover, on the basis of this new diffusion model, we propose another formulation of image anonymization with which the processed images can satisfy provable Gaussian local differential privacy and with which we can generate images semantically different from the original image but belonging to the same class. We believe that the formulation of this new diffusion model and the implementation of local differential privacy algorithms combined with the diffusion models can contribute to the secure sharing of practical images upstream of data processing.