Ali Keshavarzi- Master of Science
- PhD Candidate at Télécom Paris
Ali Keshavarzi
- Master of Science
- PhD Candidate at Télécom Paris
About
4
Publications
52
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
0
Citations
Introduction
I am Ali, a Ph.D. candidate specializing in the application of AI to the medical field. My expertise lies in data science and AI, with a focus on designing topology-preserving loss functions and enhancing tubular structures modeling through vesselness filters and sparse representations. I am proficient in large-scale deep learning for medical applications, particularly in respiratory health.
Skills and Expertise
Current institution
Education
November 2022 - December 2025
Telecom Paris, Institut Polytechnique de Paris
Field of study
- Artificial Intelligence
Publications
Publications (4)
Automated airway segmentation from lung CT scans is vital for diagnosing and monitoring pulmonary diseases. Despite advancements, challenges like leakage, breakage, and class imbalance persist, particularly in capturing small airways and preserving topology. We propose the Boundary-Emphasized Loss (BEL), which enhances boundary preservation using a...
Despite advances with deep learning (DL), automated airway segmentation from chest CT scans continues to face challenges in segmentation quality and generalization across cohorts. To address these, we propose integrating Curriculum Learning (CL) into airway segmentation networks, distributing the training set into batches according to ad-hoc comple...
The lack of large annotated datasets in medical imaging is an intrinsic burden for supervised Deep Learning (DL) segmentation models. Few-shot learning approaches are cost-effective solutions to transfer pre-trained models using only limited annotated data. However, such methods can be prone to overfitting due to limited data diversity especially w...
The lack of large annotated datasets in medical imaging is an intrinsic burden for supervised Deep Learning (DL) segmentation models. Few-shot learning approaches are cost-effective solutions to transfer pre-trained models using only limited annotated data. However, such methods can be prone to overfitting due to limited data diversity especially w...
