Researcher Database

（Last updated : 2022-09-23 19:33:47）

LI YINHAO

Department / Course College of Information Science and Engineering Department of Information Science and Engineering

Title / Position Assistant Professor

Academic background
1.	2018/04～2021/03	Doctoral Program (2nd Semester) │ Department of Information Science and Engineering │ Graduate School of Information Science and Engineering │ Ritsumeikan University │ Completed Doctor（Engineering）
2.	2016/04～2018/03	Doctoral Program (1st Semester) │ Department of Information Science and Engineering │ Graduate School of Information Science and Engineering │ Ritsumeikan University │ Completed Master（Engineering）

Business career
1.	2022/04/01 ～	Assistant Professor │ College of Information Science and Engineering │ Ritsumeikan University
2.	2021/05 ～ 2022/03	Post doctor │ │ Zhejiang Lab (Hangzhou, China)
3.	2019/04 ～ 2021/03	│ │ Ritsumeikan University

Subject of research
1.	Liver imaging reporting and data system (LI-RADS) is a comprehensive system for standardizing the terminology, technique, interpretation, reporting, and data collection of liver imaging. The system develops a standardized process for judging the malignancy of liver tumors and reduces variability in physician interpretation of imaging findings. However, doctors have to spend a long time due to complicated procedures when making judgments based on LI-RADS. Recently, some studies have used deep learning to perform LI-RADS-based liver lesion classification, confirming the possibility of intelligent liver lesion grading. However, existing methods are not sufficient for clinical use due to the low accuracy. Besides, existing methods only provide classification results and lack classification basis, so it is difficult to be trusted by doctors, which hinders the promotion to practical application. In this research, a reliable and intelligent LI-RADS based on multi-task convolutional neural networks will be proposed. Manual LI-RADS classification is mainly judged according to four pathological features, so this study uses a multi-task model to establish four branch structures to extract and analyze different pathological features respectively, providing a richer and more effective deep features for the main task (i.e., LI-RADS classification), which improves the performance of the model. On the other hand, each branch can provide the analysis results of the major features, and in actual use, the results of major features can be provided to doctors accompanied by the LI-RADS classification results, so as to provide a reference for the reliability of the grading results obtained by intelligent analysis. This study is the first to propose a multi-task deep learning framework to achieve reliable and high-precision classification for LI-RADS.

Present specialized field
Perceptual information processing, Intelligent informatics (Keyword：Image Processing, Artificial Intelligence)

Books
1.	2020	Medical Image Enhancement Using Deep Learning │ Deep Learning in Healthcare │ ,pp.53-76 (Co-authored)

Papers
1.	2021	VolumeNet: A Lightweight Parallel Network for Super-Resolution of Medical Volumetric Data │ 30,pp.4840-4854 (Co-authored)
2.	2019	Novel image restoration method based on multi-frame super-resolution for atmospherically distorted images │ 14 (1),pp.168-175 (Co-authored)
3.	2018	Computer Simulation of Image Distortion by Atmospheric Turbulence Using Time-Series Image Data with 250-Million-Pixels │ 10 (1),pp.53-61 (Co-authored)

Academic conference presentation
1.	2022/06/20	A Unified Framework for Preoperative Early Recurrence Prediction of Hepatocellular Carcinoma with Multi-phase CT Images (Innovation in Medicine and Healthcare)
2.	2021/09/27	Patch-Free 3D Medical Image Segmentation Driven by Super-Resolution Technique and Self-Supervised Guidance (International Conference on Medical Image Computing and Computer-Assisted Intervention)
3.	2020/11/30	Parallel-Connected Residual Channel Attention Network for Remote Sensing Image Super-Resolution (ACCV Workshop on Machine Learning and Computing for Visual Semantic Analysis)
4.	2020/10/13	A Lightweight Deep Network for 3D Medical Image Segmentation (2020 IEEE 9th Global Conference on Consumer Electronics (GCCE))
5.	2018/01/12	Multi-Frame Super Resolution Using Frame Selection and Multiple Fusion for 250 Million Pixel Images (Proc. of IEEE International Conference on Consumer Electronics)
Display All（6）

Winning science prize
1.	2018/01	ICCE2018 Best Poster Video Award
2.	2018/01	IEEE CE East Japan Chapter ICCE Young Scientist Paper Award

Grants-in-Aid for Scientific Research -KAKENHI-
1.	2019/04/01 ～ 2021/03/31	Enhancement of Remote Sensing Images Using Deep Convolutional Neural Networks Incorporated with an Atmospherically Distorted Image Model │ Grant-in-Aid for JSPS Fellows

E-Mail Address

Department laboratory expense researcher number
90962465

researchmap Researcher code
R000037218

External Researcher ID
ORCID ID
0000-0002-8924-5279