ICMHI 2024

Invited Speakers

 

 

Wen-Wei Chang

Chung Shan Medical University, Taichung, Taiwan

---

 

Biography---Wen-Wei Chang, Ph.D., is a Professor at Chung Shan Medical University in Taichung, Taiwan, where he specializes in cancer biology. He earned his B.S. in Biology from National Cheng Kung University, Taiwan, and later obtained his Ph.D. in Basic Medical Sciences from the same institution. Dr. Chang's career began as a Post-doctoral fellow at Academia Sinica, Taiwan, followed by various academic positions, culminating in his current role as a Professor. He served as the Secretary-General of the Taiwan Society for Stem Cell Research from 2017/11 to 2019/10. Dr. Chang has published more than 70 scientific papers and serves as an academic editor for several scientific journals including Scientific Reports, BMC Cancer, Biomedicines, etc. His research focuses on cancer stem cell biology, with an aim to develop novel therapeutic strategies using phytochemicals and probiotics.

 

Speech title "Oncogenic role of Tribbles pseudokinase 3 in cancers"

 

Tribbles pseudokinase 3 (TRIB3) is an intracellular protein scaffold and is known for its role in regulating signal transduction. However, its role in carcinogenesis is controversial. Cancer stem cells (CSCs) are famous for their high tumorigenicity, drug resistance, and metastasis characteristics. The involvement of TRIB3 in the maintenance of CSCs is little known. Our studies focus on oral squamous cell carcinoma (OSCC) and endometrial cancer (EC), and the results reveal that TRIB3 could positively regulate the maintenance of CSCs in these two types of cancer cells. We found that TRIB3 expression level increased in the CSCs of OSCC and EC. In OSCC, we have demonstrated that TRIB3 could play a role in maintaining SOX2 and EGFR expression, which are important for cancer stemness. In EC, our data have explored that TRIB3 interacts with ELF4 to regulate the transcription of β-catenin positively. We also found that elevated TRIB3 expression was associated with poorer patient outcomes in both OSCC and EC, which uncovers its potential as a novel diagnostic marker and therapeutic target. Our work suggests that targeting TRIB3 could disrupt the maintenance of CSCs, which indicates the potential improvement of the prognosis of OSCC and EC patients by TRIB3 targeting agents. In summary, our research provides an understanding of TRIB3's role in cancers, establishing it as a critical regulator in cancer stemness and highlighting its promise as a target in the treatment and diagnosis of OSCC and EC.

 

 

Ahmet Murat Ozbayoglu

TOBB University of Economics and Technology, Ankara, Turkey

---

 

Biography---A.M. Ozbayoglu graduated from the Department of Electrical Engineering at METU, Ankara, Turkey in 1991, then he got his Msc and PhD degrees from the department of Engineering Management at Missouri University of Science and Technology, USA in 1993 and 1996, respectively. After graduation, he joined MEMC Electronics (now became SunEdison), USA as a software project engineer, programmer and analyst working on silicon wafer manufacturing software and data automation projects. In 2005, he went back to academia by joining the Department of Computer Engineering of TOBB University of Economics and Technology, in Ankara, Turkey. His research interests include machine learning, pattern recognition, deep learning, financial forecasting, computational intelligence, machine vision. He has conducted 20 MSc and 2 PhD theses in theoretical and applied machine learning. He has published more than 40 journal and 100 international conference papers along with numerous white papers and technical reports. He has served in many academic and industrial projects as principal investigator, researcher and consultant. Also, he has been actively involved in social and technical committes both on and off-campus. He is a member of ACM and IEEE Computational Intelligence Society.

 

Speech title "Performance Comparison of CNN based feature extraction and Autoencoder for Hepatocellular Carcinoma (HCC) Recurrence estimation"

 

Hepatocellular Carcinoma (HCC) recurrence estimation is crucial for early detection for improving the quality of life, effective post-treatment management and patient prognosis. In this study, we investigate the performance of Convolutional Neural Network (CNN)-based feature extraction/segmentation and Autoencoder methodologies for HCC recurrence estimation. The CNN-based feature extraction leverages the hierarchical representation learning capabilities of deep convolutional architectures to extract discriminative features from medical images through convolution and pooling layers for dimensional reduction based on local proximity. Throughout our work, we examined several different CNN models like ResNet, LeNet, U-Net and compared their performances.

On the other hand, Autoencoder (AE) , an unsupervised learning technique, focuses on learning compressed representations of input data and subsequently reconstructing it, aiming to capture intrinsic data patterns. The basic difference between the two approaches is CNN based models use local information for information retrieval, whereas AE based models are mostly fully connected using the global representation and connectivity all together.

In our comparative analysis, we evaluate the effectiveness of these methods using a dataset comprising medical images of HCC patients with recurrence labels obtained from Taiwan Cancer Registry database. We are also planning to compare our findings with patient data from Turkish hospitals. Performance metrics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC) are employed to assess the predictive capabilities of both approaches. Furthermore, we analyze the interpretability of the extracted features to gain insights into the underlying characteristics contributing to HCC recurrence prediction. Our findings shed light on the comparative efficacy of CNN-based feature extraction and Autoencoder methodologies in HCC recurrence estimation, providing valuable insights for advancing computational approaches in oncology research and clinical practice.