HNHirohiko Niioka

Hirohiko Niioka

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hirohiko Niioka has a total of 221 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Automated acquisition of thyroid cytology image features using self-supervised learning and application to image classification

    by Masatoshi Abe, Ayana Suzuki, Kumiko Kamada, Toshiya Kanno, Mayu Shimasaki, Toshinori Mori, Hajime Nagahara, Akira Miyauchi, Takashi Akamizu, Mitsuyoshi Hirokawa, et al.

    Background: Thyroid fine-needle aspiration cytology is widely used to evaluate thyroid nodules before surgery. Recent advances in deep learning have increased the potential for artificial intelligence-assisted cytological diagnosis. However, developing accurate models usually requires large numbers of images labelled by experts, making dataset preparation time-consuming and costly. We investigate whether self-supervised learning can improve thyroid cytology image classification while reducing the need for labelled data. Methods: We retrospectively analysed cytology images from 393 thyroid nodules and extracted 142,158 image patches. Three self-supervised learning methods were used to pre-train vision transformer models on unlabelled images, followed by classification training with different amounts of labelled data. Performance in classifying eight lesion types was assessed using five-fold cross-validation, precision–recall area under the curve, and macro-averaged F1 scores. Model performance was compared with ImageNet-pretrained models and four cytotechnologists. Results: Here we show that self-supervised learning maintains high classification performance when labelled training data are limited and consistently outperforms ImageNet pre-training. With 1% of the labelled data, the best self-supervised model achieves a precision–recall area under the curve of 0.899, compared with 0.707 for ImageNet pre-training. The diagnostic pipeline achieves an average class-specific accuracy of 0.94, exceeding that of the four participating cytotechnologists. Self-supervised image representations also form lesion-specific clusters without diagnostic labels. Conclusions: Self-supervised learning enables accurate classification of thyroid cytology images while substantially reducing the need for expert annotation. This approach may facilitate the development of more efficient artificial intelligence-assisted cytology systems, although validation using data from multiple institutions is needed.

  • Open Access

    Semantic Segmentation for Pixel-Wise Visualization of Breast Cancer in Deep Ultraviolet-Excited Fluorescence Images

    by Tomoya Matsui, Ryuta Nakao, Shunsuke Tomimoto, Junya Sato, Hirohiko Niioka, Ippei Takada, Yoshinori Harada, Hideo Tanaka, Eiichi Konishi, Hajime Nagahara, et al.

    Microscopy with ultraviolet surface excitation (MUSE) enables rapid fluorescence imaging of tissue surfaces, but MUSE images differ markedly from conventional hematoxylin and eosin images, making cancer delineation challenging for routine pathological practice. We investigated the feasibility of deep learning-based semantic segmentation, which assigns a class label to each pixel, for pixel-wise breast cancer detection in MUSE images. Fresh breast tissues from 30 mastectomy patients with breast cancer were stained with terbium and Hoechst and imaged by MUSE. A total of 150 cancerous images (five per case) were manually annotated into cancerous and non-cancerous classes, and 300 non-cancerous images (ten per case) were collected. Models were trained and evaluated using five-fold nested cross-validation, comparing a cancer-only (CO) model trained solely on cancerous images with a cancer plus non-cancer (CN) model trained on both cancerous and non-cancerous images. The CO model achieved a higher Dice score than the CN model (CO, 0.7478; CN, 0.7343). Sliding window-based majority voting post-processing reduced scattered false-positive areas and improved Dice scores (CO, 0.7984; CN, 0.7849). These results support the feasibility of deep learning-based semantic segmentation for visualizing breast cancer regions and provide a basis for future quantitative applications using MUSE images.

  • Open Access

    Selective identification of polyploid hepatocellular carcinomas with poor prognosis by artificial intelligence-based pathological image recognition

    by Takanori Matsuura, Masatoshi Abe, Yoshiyuki Harada, Masahiro Kido, Hajime Nagahara, Yuzo Kodama, Yoshihide Ueda, Eiji Hara, Hirohiko Niioka, Tomonori Matsumoto

    Background Polyploidy is frequently observed in cancer cells and is closely associated with chromosomal instability, which can lead to cancer progression. Polyploid cancers are more aggressive than diploid cancers, and polyploidy has been shown to be a prognostic marker for hepatocellular carcinoma (HCC). However, polyploidy is challenging to diagnose. Currently, no clinically implementable methods are available for diagnosing polyploidy in cancer. Methods We established a method for assessing polyploidization in HCC using deep-learning-based artificial intelligence image recognition models to assess hematoxylin and eosin-stained pathological images. Using 44 HCCs whose ploidy status had been determined by chromosome fluorescence in situ hybridization, we evaluated the ability of our constructed deep learning models to detect HCC ploidy. We then tested the models on an independent group of 169 liver cancers and applied them to a publicly available dataset. Results Here we show that our constructed models effectively assess HCC ploidy in a separate cohort and identify a subset with poor prognosis based on the ploidy determinations for 169 HCCs. Our pipeline also identifies HCCs with poor prognosis in the external dataset, with a more significant difference than that for ploidy inferences by genomic analysis. By exploiting the high processing capacity of artificial intelligence, new aspects of polyploid HCC, such as the high prevalence of scirrhous structures, are identified. Conclusions Our findings suggest that ploidy assessment using artificial intelligence-based pathological image recognition can serve as a novel diagnostic tool for personalized medicine.


  • Open Access

    A deep learning approach to predict differentiation outcomes in hypothalamic-pituitary organoids

    by Tomoyoshi Asano, Hidetaka Suga, Hirohiko Niioka, Hiroshi Yukawa, Mayu Sakakibara, Shiori Taga, Mika Soen, Tsutomu Miwata, Hiroo Sasaki, Tomomi Seki, et al.

    We use three-dimensional culture systems of human pluripotent stem cells for differentiation into pituitary organoids. Three-dimensional culture is inherently characterized by its ability to induce heterogeneous cell populations, making it difficult to maintain constant differentiation efficiency. That is why the culture process involves empirical aspects. In this study, we use deep-learning technology to create a model that can predict from images of organoids whether differentiation is progressing appropriately. Our models using EfficientNetV2-S or Vision Transformer, employing VENUS-coupled RAX expression, predictively class bright-field images of organoids into three categories with 70% accuracy, superior to expert-observer predictions. Furthermore, the model obtained by ensemble learning with the two algorithms can predict RAX expression in cells without RAX::VENUS, suggesting that our model can be deployed in clinical applications such as transplantation.


  • Self-Supervised Learning for Feature Extraction from Glomerular Images and Disease Classification with Minimal Annotations

    by Masatoshi Abe, Hirohiko Niioka, Ayumi Matsumoto, Yusuke Katsuma, Atsuhiro Imai, Hiroki Okushima, Shingo Ozaki, Naohiko Fujii, Kazumasa Oka, Yusuke Sakaguchi, et al.

    Key Points: Self-supervised learning extracts meaningful glomerular features without teacher labels. Self-distillation with no labels–pretrained model outperformed conventional supervised learning in disease and clinical parameter classification. Self-distillation with no labels model enabled deep learning on small datasets, reducing annotation efforts. Background: Deep learning has great potential in digital kidney pathology. However, its effectiveness depends heavily on the availability of extensively labeled datasets, which are often limited because of the specialized knowledge and time required for their creation. This limitation hinders the widespread application of deep learning for the analysis of kidney biopsy images. Methods: We applied self-distillation with no labels (DINO), a self-supervised learning method, to a dataset of 10,423 glomerular images obtained from 384 periodic acid–Schiff-stained kidney biopsy slides. Glomerular features extracted from the DINO-pretrained backbone were visualized using principal component analysis. We then performed classification tasks by adding either k-nearest neighbor classifiers or linear head layers to the DINO-pretrained or ImageNet-pretrained backbones. These models were trained on our labeled classification dataset. Performance was evaluated using metrics such as the area under the receiver operating characteristic curve (ROC-AUC). The classification tasks encompassed four disease categories (minimal change disease, mesangial proliferative GN, membranous nephropathy, and diabetic nephropathy) and clinical parameters such as hypertension, proteinuria, and hematuria. Results: Principal component analysis visualization revealed distinct principal components corresponding to different glomerular structures, demonstrating the capability of the DINO-pretrained backbone to capture morphologic features. In disease classification, the DINO-pretrained transferred model (ROC-AUC=0.93) outperformed the ImageNet-pretrained fine-tuned model (ROC-AUC=0.89). When the labeled data were limited, the ImageNet-pretrained fine-tuned model's ROC-AUC dropped to 0.76 (95% confidence interval, 0.72 to 0.80), whereas the DINO-pretrained transferred model maintained superior performance (ROC-AUC, 0.88; 95% confidence interval, 0.86 to 0.90). The DINO-pretrained transferred model also exhibited higher AUCs for the classification of several clinical parameters. External validation using two independent datasets confirmed DINO pretraining's superiority, particularly when labeled data were limited. Conclusions: The application of DINO to unlabeled periodic acid–Schiff-stained glomerular images facilitated the extraction of histologic features that could be effectively used for disease classification.


  • Open Access

    Deep UV-excited fluorescence microscopy installed with CycleGAN-assisted image translation enhances precise detection of lymph node metastasis towards rapid intraoperative diagnosis

    by Junya Sato, Tatsuya Matsumoto, Ryuta Nakao, Hideo Tanaka, Hajime Nagahara, Hirohiko Niioka, Tetsuro Takamatsu

    Rapid and precise intraoperative diagnosing systems are required for improving surgical outcomes and patient prognosis. Because of the poor quality and time-intensive process of the prevalent frozen section procedure, various intraoperative diagnostic imaging systems have been explored. Microscopy with ultraviolet surface excitation (MUSE) is an inexpensive, maintenance-free, and rapid imaging technique that yields images like thin-sectioned samples without sectioning. However, pathologists find it nearly impossible to assign diagnostic labels to MUSE images of unfixed specimens; thus, AI for intraoperative diagnosis cannot be trained in a supervised learning manner. In this study, we propose a deep-learning pipeline model for lymph node metastasis detection, in which CycleGAN translate MUSE images of unfixed lymph nodes to formalin-fixed paraffin-embedded (FFPE) sample, and diagnostic prediction is performed using deep convolutional neural network trained on FFPE sample images. Our pipeline yielded an average accuracy of 84.6% when using each of the three deep convolutional neural networks, which is a 18.3% increase over the classification-only model without CycleGAN. The modality translation to FFPE sample images using CycleGAN can be applied to various intraoperative diagnostic imaging systems and eliminate the difficulty for pathologists in labeling new modality images in clinical sites. We anticipate our pipeline to be a starting point for accurate rapid intraoperative diagnostic systems for new imaging modalities, leading to healthcare quality improvement.


  • Open Access

    Application of deep learning as an ancillary diagnostic tool for thyroid FNA cytology

    by Mitsuyoshi Hirokawa, Hirohiko Niioka, Ayana Suzuki, Masatoshi Abe, Yusuke Arai, Hajime Nagahara, Akira Miyauchi, Takashi Akamizu

    Background: Several studies have used artificial intelligence (AI) to analyze cytology images, but AI has yet to be adopted in clinical practice. The objective of this study was to demonstrate the accuracy of AI‐based image analysis for thyroid fine‐needle aspiration cytology (FNAC) and to propose its application in clinical practice.Methods: In total, 148,395 microscopic images of FNAC were obtained from 393 thyroid nodules to train and validate the data, and EfficientNetV2‐L was used as the image‐classification model. The 35 nodules that were classified as atypia of undetermined significance (AUS) were predicted using AI training.Results: The precision‐recall area under the curve (PR AUC) was >0.95, except for poorly differentiated thyroid carcinoma (PR AUC = 0.49) and medullary thyroid carcinoma (PR AUC = 0.91). Poorly differentiated thyroid carcinoma had the lowest recall (35.4%) and was difficult to distinguish from papillary thyroid carcinoma, medullary thyroid carcinoma, and follicular thyroid carcinoma. Follicular adenomas and follicular thyroid carcinomas were distinguished from each other by 86.7% and 93.9% recall, respectively. For two‐dimensional mapping of the data using t‐distributed stochastic neighbor embedding, the lymphomas, follicular adenomas, and anaplastic thyroid carcinomas were divided into three, two, and two groups, respectively. Analysis of the AUS nodules showed 94.7% sensitivity, 14.4% specificity, 56.3% positive predictive value, and 66.7% negative predictive value.Conclusions: The authors developed an AI‐based approach to analyze thyroid FNAC cases encountered in routine practice. This analysis could be useful for the clinical management of AUS and follicular neoplasm nodules (e.g., an online AI platform for thyroid cytology consultations).


  • Open Access

    Extracting Phylogenetic Information of Human Mitochondrial DNA by Linear Autoencoder

    by Takuto Shimazaki, Kazuki Nishimoto, Hirohiko Niioka, Jun Miyake

    We used a linear autoencoder (LAE) and its learning dynamics to analyze the high-order structure of human mitochondrial DNA (mtDNA). A total of 360 complete human mtDNA sequences were collected from the MITOMAP database and transformed into 1024-dimensional vectors of pentanucleotide frequencies. We compressed those into a three-dimensional (3D) coordinates by an LAE at each step of training by gradient descent with respect to the quadratic error function. Along the time axis of training epochs, the compressed 3D coordinates were gradually clustered and separated in accordance with the order of the genetic distance in the phylogenetic tree of human mtDNA haplogroups. This suggests that there is an association between the learning dynamics of LAE and the high-dimensional structure of human mtDNA sequences, similar to that of phylogenetic analysis and evolutionary pathways: the five clusters eventually contained only a single haplogroup of L0, M, N, R, and U, while the L3 cluster contained a small number of M members and The packing was comparable to that realized in learning dynamics similar to genetic classification and evolutionary pathways by LAE in principal component analysis (PCA), but somewhat denser than PCA.

  • Open Access

    Cluster Analysis of SARS-CoV-2 Gene using Deep Learning Autoencoder: Gene Profiling for Mutations and Transitions

    by Jun Miyake, Takaaki Sato, Shunsuke Baba, Hayao Nakamura, Hirohiko Niioka, Yoshihisa Nakazawa

    We report on a method for analyzing the variant of coronavirus genes using autoencoder. Since coronaviruses have mutated rapidly and generated a large number of genotypes, an appropriate method for understanding the entire population is required. The method using autoencoder meets this requirement and is suitable for understanding how and when the variants emarge and disappear. For the over 30,000 SARS-CoV-2 ORF1ab gene sequences sampled globally from December 2019 to February 2021, we were able to represent a summary of their characteristics in a 3D plot and show the expansion, decline, and transformation of the virus types over time and by region. Based on ORF1ab genes, the SARS-CoV-2 viruses were classified into five major types (A, B, C, D, and E in the order of appearance): the virus type that originated in China at the end of 2019 (type A) practically disappeared in June 2020; two virus types (types B and C) have emerged in the United States and Europe since February 2020, and type B has become a global phenomenon. Type C is only prevalent in the U.S. and is suspected to be associated with high mortality, but this type also disappeared at the end of June. Type D is only found in Australia. Currently, the epidemic is dominated by types B and E.


  • Open Access

    Author Correction: Improvement of nerve imaging speed with coherent anti-Stokes Raman scattering rigid endoscope using deep-learning noise reduction

    by Naoki Yamato, Hirohiko Niioka, Jun Miyake, Mamoru Hashimoto

    An amendment to this paper has been published and can be accessed via a link at the top of the paper.