Shouhei Hanaoka

Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura et al.

From birth to death, we all experience surprisingly ubiquitous changes over time due to aging. If we can predict aging in the digital domain, that is, the digital twin of the human body, we would be able to detect lesions in their very early stages, thereby enhancing the quality of life and extending the life span. We observed that none of the previously developed digital twins of the adult human body explicitly trained longitudinal conversion rules between volumetric medical images with deep generative models, potentially resulting in poor prediction performance of, for example, ventricular volumes. Here, we establish a new digital twin of an adult human body that adopts longitudinally acquired head computed tomography (CT) images for training, enabling prediction of future volumetric head CT images from a single present volumetric head CT image. We, for the first time, adopt one of the three-dimensional flow-based deep generative models to realize this sequential three-dimensional digital twin. We show that our digital twin outperforms the latest methods of prediction of ventricular volumes in relatively short terms.

Hisaichi Shibata, Shouhei Hanaoka, Yang Cao et al.

Diagnostic radiologists need artificial intelligence (AI) for medical imaging, but access to medical images required for training in AI has become increasingly restrictive. To release and use medical images, we need an algorithm that can simultaneously protect privacy and preserve pathologies in medical images. To develop such an algorithm, here, we propose DP-GLOW, a hybrid of a local differential privacy (LDP) algorithm and one of the flow-based deep generative models (GLOW). By applying a GLOW model, we disentangle the pixelwise correlation of images, which makes it difficult to protect privacy with straightforward LDP algorithms for images. Specifically, we map images onto the latent vector of the GLOW model, each element of which follows an independent normal distribution, and we apply the Laplace mechanism to the latent vector. Moreover, we applied DP-GLOW to chest X-ray images to generate LDP images while preserving pathologies.

Takahiro Suzuki, Shouhei Hanaoka, Issei Sato

A computer-aided detection (CAD) system based on machine learning is expected to assist radiologists in making a diagnosis. It is desirable to build CAD systems for the various types of diseases accumulating daily in a hospital. An obstacle in developing a CAD system for a disease is that the number of medical images is typically too small to improve the performance of the machine learning model. In this paper, we aim to explore ways to address this problem through a sim2real transfer approach in medical image fields. To build a platform to evaluate the performance of sim2real transfer methods in the field of medical imaging, we construct a benchmark dataset that consists of $101$ chest X-images with difficult-to-identify pneumonia lesions judged by an experienced radiologist and a simulator based on fractal Perlin noise and the X-ray principle for generating pseudo pneumonia lesions. We then develop a novel domain randomization method, called Goldilocks-curriculum domain randomization (GDR) and evaluate our method in this platform.

Tomohiro Kikuchi, Shouhei Hanaoka, Takahiro Nakao et al.

The generation of synthetic medical records using Generative Adversarial Networks (GANs) is becoming crucial for addressing privacy concerns and facilitating data sharing in the medical domain. In this paper, we introduce a novel method to create synthetic hybrid medical records that combine both image and non-image data, utilizing an auto-encoding GAN (alphaGAN) and a conditional tabular GAN (CTGAN). Our methodology encompasses three primary steps: I) Dimensional reduction of images in a private dataset (pDS) using the pretrained encoder of the αGAN, followed by integration with the remaining non-image clinical data to form tabular representations; II) Training the CTGAN on the encoded pDS to produce a synthetic dataset (sDS) which amalgamates encoded image features with non-image clinical data; and III) Reconstructing synthetic images from the image features using the alphaGAN's pretrained decoder. We successfully generated synthetic records incorporating both Chest X-Rays (CXRs) and thirteen non-image clinical variables (comprising seven categorical and six numeric variables). To evaluate the efficacy of the sDS, we designed classification and regression tasks and compared the performance of models trained on pDS and sDS against the pDS test set. Remarkably, by leveraging five times the volume of sDS for training, we achieved classification and regression results that were comparable, if slightly inferior, to those obtained using the native pDS. Our method holds promise for publicly releasing synthetic datasets without undermining the potential for secondary data usage.

Yosuke Yamagishi, Atsushi Takamatsu, Yasunori Hamaguchi et al.

Background: Accurate translation of radiology reports is important for multilingual research, clinical communication, and radiology education, but the validity of LLM-based evaluation remains unclear. Objective: To evaluate the educational suitability of LLM-generated Japanese translations of chest CT reports and compare radiologist assessments with LLM-as-a-judge evaluations. Methods: We analyzed 150 chest CT reports from the CT-RATE-JPN validation set. For each English report, a human-edited Japanese translation was compared with an LLM-generated translation by DeepSeek-V3.2. A board-certified radiologist and a radiology resident independently performed blinded pairwise evaluations across 4 criteria: terminology accuracy, readability, overall quality, and radiologist-style authenticity. In parallel, 3 LLM judges (DeepSeek-V3.2, Mistral Large 3, and GPT-5) evaluated the same pairs. Agreement was assessed using QWK and percentage agreement. Results: Agreement between radiologists and LLM judges was near zero (QWK=-0.04 to 0.15). Agreement between the 2 radiologists was also poor (QWK=0.01 to 0.06). Radiologist 1 rated terminology as equivalent in 59% of cases and favored the LLM translation for readability (51%) and overall quality (51%). Radiologist 2 rated readability as equivalent in 75% of cases and favored the human-edited translation for overall quality (40% vs 21%). All 3 LLM judges strongly favored the LLM translation across all criteria (70%-99%) and rated it as more radiologist-like in >93% of cases. Conclusions: LLM-generated translations were often judged natural and fluent, but the 2 radiologists differed substantially. LLM-as-a-judge showed strong preference for LLM output and negligible agreement with radiologists. For educational use of translated radiology reports, automated LLM-based evaluation alone is insufficient; expert radiologist review remains important.

Yosuke Yamagishi, Shouhei Hanaoka, Tomohiro Kikuchi et al.

Objectives: To evaluate the zero-shot performance of Segment Anything Model 2 (SAM 2) in 3D segmentation of abdominal organs in CT scans, and to investigate the effects of prompt settings on segmentation results. Materials and 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: 123 patients (mean age, 60.7 \pm 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 \pm 0.192, right kidney 0.862 \pm 0.212, left kidney 0.870 \pm 0.154, and spleen 0.891 \pm 0.131. Smaller organs showed lower performance: gallbladder 0.531 \pm 0.291, pancreas 0.361 \pm 0.197, and adrenal glands, right 0.203 \pm 0.222, left 0.308 \pm 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. Conclusion: 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.

Yosuke Yamagishi, Shouhei Hanaoka

In this work, we present our solution for the MICCAI 2024 CXR-LT challenge, achieving 4th place in Subtask 2 and 5th in Subtask 1. We leveraged an ensemble of ConvNeXt V2 and MaxViT models, pretrained on an external chest X-ray dataset, to address the long-tailed distribution of chest findings. The proposed method combines state-of-the-art image classification techniques, asymmetric loss for handling class imbalance, and view-based prediction aggregation to enhance classification performance. Through experiments, we demonstrate the advantages of our approach in improving both detection accuracy and the handling of the long-tailed distribution in CXR findings. The code is available at https://github.com/yamagishi0824/cxrlt24-multiview-pp.

Shannon L. Walston, Hiroshi Seki, Hirotaka Takita et al.

Medicine and deep learning-based artificial intelligence (AI) engineering represent two distinct fields each with decades of published history. With such history comes a set of terminology that has a specific way in which it is applied. However, when two distinct fields with overlapping terminology start to collaborate, miscommunication and misunderstandings can occur. This narrative review aims to give historical context for these terms, accentuate the importance of clarity when these terms are used in medical AI contexts, and offer solutions to mitigate misunderstandings by readers from either field. Through an examination of historical documents, including articles, writing guidelines, and textbooks, this review traces the divergent evolution of terms for data sets and their impact. Initially, the discordant interpretations of the word 'validation' in medical and AI contexts are explored. Then the data sets used for AI evaluation are classified, namely random splitting, cross-validation, temporal, geographic, internal, and external sets. The accurate and standardized description of these data sets is crucial for demonstrating the robustness and generalizability of AI applications in medicine. This review clarifies existing literature to provide a comprehensive understanding of these classifications and their implications in AI evaluation. This review then identifies often misunderstood terms and proposes pragmatic solutions to mitigate terminological confusion. Among these solutions are the use of standardized terminology such as 'training set,' 'validation (or tuning) set,' and 'test set,' and explicit definition of data set splitting terminologies in each medical AI research publication. This review aspires to enhance the precision of communication in medical AI, thereby fostering more effective and transparent research methodologies in this interdisciplinary field.

Mingquan Lin, Gregory Holste, Song Wang et al.

The CXR-LT series is a community-driven initiative designed to enhance lung disease classification using chest X-rays (CXR). It tackles challenges in open long-tailed lung disease classification and enhances the measurability of state-of-the-art techniques. The first event, CXR-LT 2023, aimed to achieve these goals by providing high-quality benchmark CXR data for model development and conducting comprehensive evaluations to identify ongoing issues impacting lung disease classification performance. Building on the success of CXR-LT 2023, the CXR-LT 2024 expands the dataset to 377,110 chest X-rays (CXRs) and 45 disease labels, including 19 new rare disease findings. It also introduces a new focus on zero-shot learning to address limitations identified in the previous event. Specifically, CXR-LT 2024 features three tasks: (i) long-tailed classification on a large, noisy test set, (ii) long-tailed classification on a manually annotated "gold standard" subset, and (iii) zero-shot generalization to five previously unseen disease findings. This paper provides an overview of CXR-LT 2024, detailing the data curation process and consolidating state-of-the-art solutions, including the use of multimodal models for rare disease detection, advanced generative approaches to handle noisy labels, and zero-shot learning strategies for unseen diseases. Additionally, the expanded dataset enhances disease coverage to better represent real-world clinical settings, offering a valuable resource for future research. By synthesizing the insights and innovations of participating teams, we aim to advance the development of clinically realistic and generalizable diagnostic models for chest radiography.

Yosuke Yamagishi, Yuta Nakamura, Tomohiro Kikuchi et al.

Background: Recent advances in large language models highlight the need for high-quality multilingual medical datasets. While Japan leads globally in CT scanner deployment and utilization, the lack of large-scale Japanese radiology datasets has hindered the development of specialized language models for medical imaging analysis. Objective: To develop a comprehensive Japanese CT report dataset through machine translation and establish a specialized language model for structured finding classification. Additionally, to create a rigorously validated evaluation dataset through expert radiologist review. Methods: We translated the CT-RATE dataset (24,283 CT reports from 21,304 patients) into Japanese using GPT-4o mini. The training dataset consisted of 22,778 machine-translated reports, while the validation dataset included 150 radiologist-revised reports. We developed CT-BERT-JPN based on "tohoku-nlp/bert-base-japanese-v3" architecture for extracting 18 structured findings from Japanese radiology reports. Results: Translation metrics showed strong performance with BLEU scores of 0.731 and 0.690, and ROUGE scores ranging from 0.770 to 0.876 for Findings and from 0.748 to 0.857 for Impression sections. CT-BERT-JPN demonstrated superior performance compared to GPT-4o in 11 out of 18 conditions, including lymphadenopathy (+14.2%), interlobular septal thickening (+10.9%), and atelectasis (+7.4%). The model maintained F1 scores exceeding 0.95 in 14 out of 18 conditions and achieved perfect scores in four conditions. Conclusions: Our study establishes a robust Japanese CT report dataset and demonstrates the effectiveness of a specialized language model for structured finding classification. The hybrid approach of machine translation and expert validation enables the creation of large-scale medical datasets while maintaining high quality.

Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura et al.

Ultra sparse-view computed tomography (CT) algorithms can reduce radiation exposure of patients, but those algorithms lack an explicit cycle consistency loss minimization and an explicit log-likelihood maximization in testing. Here, we propose X2CT-FLOW for the maximum a posteriori (MAP) reconstruction of a three-dimensional (3D) chest CT image from a single or a few two-dimensional (2D) projection images using a progressive flow-based deep generative model, especially for ultra low-dose protocols. The MAP reconstruction can simultaneously optimize the cycle consistency loss and the log-likelihood. The proposed algorithm is built upon a newly developed progressive flow-based deep generative model, which is featured with exact log-likelihood estimation, efficient sampling, and progressive learning. We applied X2CT-FLOW to reconstruction of 3D chest CT images from biplanar projection images without noise contamination (assuming a standard-dose protocol) and with strong noise contamination (assuming an ultra low-dose protocol). With the standard-dose protocol, our images reconstructed from 2D projected images and 3D ground-truth CT images showed good agreement in terms of structural similarity (SSIM, 0.7675 on average), peak signal-to-noise ratio (PSNR, 25.89 dB on average), mean absolute error (MAE, 0.02364 on average), and normalized root mean square error (NRMSE, 0.05731 on average). Moreover, with the ultra low-dose protocol, our images reconstructed from 2D projected images and the 3D ground-truth CT images also showed good agreement in terms of SSIM (0.7008 on average), PSNR (23.58 dB on average), MAE (0.02991 on average), and NRMSE (0.07349 on average).

Yuta Nakamura, Shouhei Hanaoka, Yukihiro Nomura et al.

For the safe sharing pre-trained language models, no guidelines exist at present owing to the difficulty in estimating the upper bound of the risk of privacy leakage. One problem is that previous studies have assessed the risk for different real-world privacy leakage scenarios and attack methods, which reduces the portability of the findings. To tackle this problem, we represent complex real-world privacy leakage scenarios under a universal parameterization, \textit{Knowledge, Anonymization, Resource, and Target} (KART). KART parameterization has two merits: (i) it clarifies the definition of privacy leakage in each experiment and (ii) it improves the comparability of the findings of risk assessments. We show that previous studies can be simply reviewed by parameterizing the scenarios with KART. We also demonstrate privacy risk assessments in different scenarios under the same attack method, which suggests that KART helps approximate the upper bound of risk under a specific attack or scenario. We believe that KART helps integrate past and future findings on privacy risk and will contribute to a standard for sharing language models.

Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura et al.

In general, adversarial perturbations superimposed on inputs are realistic threats for a deep neural network (DNN). In this paper, we propose a practical generation method of such adversarial perturbation to be applied to black-box attacks that demand access to an input-output relationship only. Thus, the attackers generate such perturbation without invoking inner functions and/or accessing the inner states of a DNN. Unlike the earlier studies, the algorithm to generate the perturbation presented in this study requires much fewer query trials. Moreover, to show the effectiveness of the adversarial perturbation extracted, we experiment with a DNN for semantic segmentation. The result shows that the network is easily deceived with the perturbation generated than using uniformly distributed random noise with the same magnitude.

H. Shibata, S. Hanaoka, Y. Nomura et al.

Oversight in medical images is a crucial problem, and timely reporting of medical images is desired. Therefore, an all-purpose anomaly detection method that can detect virtually all types of lesions/diseases in a given image is strongly desired. However, few commercially available and versatile anomaly detection methods for medical images have been provided so far. Recently, anomaly detection methods built upon deep learning methods have been rapidly growing in popularity, and these methods seem to provide reasonable solutions to the problem. However, the workload to label the images necessary for training in deep learning remains heavy. In this study, we present an anomaly detection method based on two trained flow-based generative models. With this method, the posterior probability can be computed as a normality metric for any given image. The training of the generative models requires two sets of images: a set containing only normal images and another set containing both normal and abnormal images without any labels. In the latter set, each sample does not have to be labeled as normal or abnormal; therefore, any mixture of images (e.g., all cases in a hospital) can be used as the dataset without cumbersome manual labeling. The method was validated with two types of medical images: chest X-ray radiographs (CXRs) and brain computed tomographies (BCTs). The areas under the receiver operating characteristic curves for logarithm posterior probabilities of CXRs (0.868 for pneumonia-like opacities) and BCTs (0.904 for infarction) were comparable to those in previous studies with other anomaly detection methods. This result showed the versatility of our method.