Responsible DL Approaches to Modelling Metabolic Plasticity and Heterogeneity in Melanoma using Digital Pathology and Hyperion data
Encadrants : Daniel Racoceanu
Disponible : NON
Spécialité : IMA
Nombre d'étudiants : 1
Description :
Historically, melanoma was once a rare cancer. However, over the past few decades, it has evolved to become one of the fastest growing cancers and accounts for the majority of skin cancer-related deaths globally. The MALMO Project (Mathematical Approaches to Modelling Metabolic Plasticity and Heterogeneity in Melanoma), supported by the ITMO Cancer, aims to use image processing and artificial intelligence (AI) in understanding the initial conditions and progression of the disease using multi-modal digital pathology imaging. Our goal is to bring these tools to a higher level of AI interpretability / explicability / responsibility.
Pré-requis : Python, PyTorch, OpenCV, CUDA
Travail demandé : 1. Bibliographic study: Conduct a search of the literature regarding explainable and responsible AI. Analyze and summarize the current scope of studies.
2. Data preparation: Image pre-processing involves the correction of image acquisition artefacts. Identify the most suitable combination of pre-processing techniques to improve image quality and prepare data for AI training. Python will be used.
3. Data annotation: You will be trained by an experienced pathologist and will assist in the annotation of pathology slides. QuPath will be used.
2. Data preparation: Image pre-processing involves the correction of image acquisition artefacts. Identify the most suitable combination of pre-processing techniques to improve image quality and prepare data for AI training. Python will be used.
3. Data annotation: You will be trained by an experienced pathologist and will assist in the annotation of pathology slides. QuPath will be used.
Liens complémentaires : Barredo Arrieta, Alejandro, Natalia Díaz-Rodríguez, Javier Del Ser, Adrien Bennetot, Siham Tabik, Alberto Barbado, Salvador Garcia, et al. « Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI ». Information Fusion 58 (juin 2020): 82‑115. https://doi.org/10.1016/j.inffus.2019.12.012.
E. Tjoa and C. Guan, "A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI," in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2020.3027314.
E. Tjoa and C. Guan, "A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI," in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2020.3027314.
