KUKoki Uchiyama

Koki Uchiyama

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Koki Uchiyama has a total of 14 co-authors. Here are the top co-authors by number of shared publications:

  • Dongheng Ma

    Molecular Oncology and Therapeutics, Osaka Metropolitan University Graduate School of Medicine, 1-4-3 Asahimachi, Abeno-ku, Osaka 545-8585, Japan

    2 shared publications
  • Hinano Nishikubo

    Molecular Oncology and Therapeutics, Osaka Metropolitan University Graduate School of Medicine, 1-4-3 Asahimachi, Abeno-ku, Osaka 545-8585, Japan

    2 shared publications
  • Masakazu Yashiro

    Molecular Oncology and Therapeutics, Osaka Metropolitan University Graduate School of Medicine, 1-4-3 Asahimachi, Abeno-ku, Osaka 545-8585, Japan

    2 shared publications
  • Takemi Ishidate

    Molecular Oncology and Therapeutics, Osaka Metropolitan University Graduate School of Medicine, 1-4-3 Asahimachi, Abeno-ku, Osaka 545-8585, Japan

    2 shared publications
  • Tomoya Sano

    Molecular Oncology and Therapeutics, Osaka Metropolitan University Graduate School of Medicine, 1-4-3 Asahimachi, Abeno-ku, Osaka 545-8585, Japan

    2 shared publications
  • Yukina Furukawa

    Molecular Oncology and Therapeutics, Osaka Metropolitan University Graduate School of Medicine, 1-4-3 Asahimachi, Abeno-ku, Osaka 545-8585, Japan

    2 shared publications

Latest Publications

  • Open Access

    Dual-Magnification Deep Learning Predicts KRASG12D Status from H&E Images of Pancreatic Cancer: A Multi-Cohort Study

    by Dongheng Ma, Tomoya Sano, Hinano Nishikubo, Yukina Furukawa, Koki Uchiyama, Daiki Imanishi, Takemi Ishidate, Hongdong Gao, Canfeng Fan, Yurie Yamamoto, et al.

    Background: KRAS mutations occur in over 90% of pancreatic ductal adenocarcinomas (PDAC), and KRASG12D is the most frequent variant. G12D-selective inhibitors are now in clinical development, but computational pathology has so far predicted mutation status only at the gene level, leaving allele-specific prediction unexplored. Because genomic testing can be time-consuming and costly, a tool that predicts KRASG12D mutation status from routine hematoxylin and eosin (H&E) images could help identify patients for confirmatory molecular testing and potential treatment with KRASG12D inhibitors. Here we present a multi-scale framework that predicts KRASG12D status from H&E whole-slide images, with integration of computed tomography (CT). Methods: Two public cohorts (TCGA, CPTAC) formed the training set, and an independent external cohort (Osaka Metropolitan University Hospital) served as validation. We developed a dual-magnification pipeline. In the high-magnification branch, a pathology foundation model (CONCH v1.5) was fine-tuned with low-rank adaptation (LoRA) and an attention-based multiple-instance learning head on 20× patches; in the low-magnification branch, a generative image model encoded a whole-slide overview. The two branches were integrated by late fusion into a multi-scale pathomics model, which was further combined with a radiomics model of CT. Results: The multi-scale pathomics model reached a pooled internal test area under the receiver operating characteristic curve (AUC) of 0.611 and an external AUC of 0.701. In the external patients with CT, the combined model reached an AUC of 0.772, compared with 0.753 for pathomics alone. Conclusions: KRASG12D status leaves a signal in routine H&E images and CT of PDAC that deep learning can detect and that transfers to an independent institution. After prospective validation, the framework might help prioritize patients for KRAS testing.

  • Open Access

    The Significance of Somatic Variants Involved in the Development of Pancreatic Cancer in Patients with HBOC-Associated Germline Variants

    by Koki Uchiyama, Hinano Nishikubo, Tomoya Sano, Yukina Furukawa, Dongheng Ma, Daiki Imanishi, Takemi Ishidate, Hongdong Gao, Canfeng Fan, Masakazu Yashiro

    Background: Hereditary cancer predisposition syndromes show a high risk of cancer development with germline pathogenic variants. Organ-specific surveillance has been recommended according to the causative gene. However, even among carriers of the same germline variants, developing cancer types are not always uniform. Tumor–normal paired comprehensive genomic profiling (CGP) enables the simultaneous assessment of germline and somatic variants in same patient. Correlations between germline variants and cancer types have been reported; however, the significance of combinations of a germline variant and somatic variants remain unclear in the development of cancer types. Methods: In this study, we analyzed the correlation between pancreatic cancer and somatic variant patterns in patients with hereditary cancer predisposition syndrome, especially in patients with germline variants on BRCA1, BRCA2, or ATM. Results: Here, we show the characteristic pancreatic cancer patterns according to co-existing somatic variants in patients with germline pathogenic variants. The tumor–normal paired genetic data from 18,732 patients who underwent tumor–normal paired CGP were analyzed, including 853 germline-positive patients registered in a Japanese database. The combination of the somatic TP53 variant and KRAS variant was closely correlated with the development of pancreatic cancer in patients with germline BRCA1, BRCA2, or ATM. In particular, the somatic KRAS variant was significantly associated with pancreatic cancer. Conclusions: These findings suggest that pancreatic cancer of hereditary cancer syndromes might be associated with co-existing somatic KRAS variants within the pancreas.