The University of Tokyo · Medicine
Professor Shota Tanaka's research lab specializes in medical image analysis and computational oncology, focusing on leveraging radiomics and machine learning to improve the preoperative differentiation of bone tumors such as chordoma and chondrosarcoma. The lab also develops innovative algorithms for forecasting research trends in neuro-oncology using text-mining and impact factor-based analytics. Additionally, it explores biological mechanisms of early-life survival in fish populations through otolith-based growth analysis, demonstrating interdisciplinary applications of data science. The lab emphasizes translational research, integrating clinical imaging, artificial intelligence, and biomedical data analytics to enhance patient outcomes and scientific foresight.
Figures are computed from collected data and may differ slightly.
Chordoma and chondrosarcoma share common radiographic characteristics yet are distinct clinically. A radiomic machine learning model differentiating these tumors preoperatively would help plan surgery. MR images were acquired from 57 consecutive patients with chordoma (N = 32) or chondrosarcoma (N = 25) treated at the University of Tokyo Hospital between September 2012 and February 2020. Preoperative T1-weighted images with gadolinium enhancement (GdT1) and T2-weighted images were analyzed. Data
In conducting medical research, a system which can objectively predict the future trends of the given research field is awaited. This study aims to establish a novel and versatile algorithm that predicts the latest trends in neuro-oncology. Seventy-nine neuro-oncological research fields were selected with computational sorting methods such as text-mining analyses. Thirty journals that represent the recent trends in neuro-oncology were also selected. As a novel concept, the annual impact (AI) of
Abstract Johan Hjort's “critical period” hypothesis, which postulates that year‐class strength is determined in the short period following the onset of exogenous feeding, has rarely been supported by empirical data. Instead, the current understanding is that recruitment is determined by cumulative mortality throughout early life. Recent studies relied on the measure of growth autocorrelation derived from otolith daily increment widths to test the link between growth rate achieved during the post
The newly developed MDASI-BT-Japanese has demonstrated feasibility, reliability and validity in evaluation of clinical benefit in Japanese-speaking brain tumor patients.
Open papers in the app to read, cite, and organize with AI.
