1 code implementation • 24 Apr 2024 • Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang
Humans effortlessly interpret images by parsing them into part-whole hierarchies; deep learning excels in learning multi-level feature spaces, but they often lack explicit coding of part-whole relations, a prominent property of medical imaging.
1 code implementation • 27 Sep 2023 • Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang
Human anatomy is the foundation of medical imaging and boasts one striking characteristic: its hierarchy in nature, exhibiting two intrinsic properties: (1) locality: each anatomical structure is morphologically distinct from the others; and (2) compositionality: each anatomical structure is an integrated part of a larger whole.
1 code implementation • CVPR 2022 • Fatemeh Haghighi, Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang
Discriminative learning, restorative learning, and adversarial learning have proven beneficial for self-supervised learning schemes in computer vision and medical imaging.
1 code implementation • 15 Apr 2022 • Mohammad Reza Hosseinzadeh Taher, Fatemeh Haghighi, Michael B. Gotway, Jianming Liang
Our extensive experiments demonstrate that CAiD (1) enriches representations learned from existing instance discrimination methods; (2) delivers more discriminative features by adequately capturing finer contextual information from individual medial images; and (3) improves reusability of low/mid-level features compared to standard instance discriminative methods.
2 code implementations • 12 Aug 2021 • Mohammad Reza Hosseinzadeh Taher, Fatemeh Haghighi, Ruibin Feng, Michael B. Gotway, Jianming Liang
Transfer learning from supervised ImageNet models has been frequently used in medical image analysis.
4 code implementations • 21 Feb 2021 • Fatemeh Haghighi, Mohammad Reza Hosseinzadeh Taher, Zongwei Zhou, Michael B. Gotway, Jianming Liang
This paper introduces a new concept called "transferable visual words" (TransVW), aiming to achieve annotation efficiency for deep learning in medical image analysis.
2 code implementations • 14 Jul 2020 • Fatemeh Haghighi, Mohammad Reza Hosseinzadeh Taher, Zongwei Zhou, Michael B. Gotway, Jianming Liang
To this end, we train deep models to learn semantically enriched visual representation by self-discovery, self-classification, and self-restoration of the anatomy underneath medical images, resulting in a semantics-enriched, general-purpose, pre-trained 3D model, named Semantic Genesis.
Ranked #1 on Lung Nodule Detection on LUNA2016 FPRED