no code implementations • 3 Jan 2022 • Parnian Afshar, Arash Mohammadi, Konstantinos N. Plataniotis, Keyvan Farahani, Justin Kirby, Anastasia Oikonomou, Amir Asif, Leonard Wee, Andre Dekker, Xin Wu, Mohammad Ariful Haque, Shahruk Hossain, Md. Kamrul Hasan, Uday Kamal, Winston Hsu, Jhih-Yuan Lin, M. Sohel Rahman, Nabil Ibtehaz, Sh. M. Amir Foisol, Kin-Man Lam, Zhong Guang, Runze Zhang, Sumohana S. Channappayya, Shashank Gupta, Chander Dev
Lung cancer is one of the deadliest cancers, and in part its effective diagnosis and treatment depend on the accurate delineation of the tumor.
no code implementations • 16 Sep 2021 • Junhua Chen, Leonard Wee, Andre Dekker, Inigo Bermejo
The trained GANs were applied to three scenarios: 1) improving radiomics reproducibility in simulated low dose CT images and 2) same-day repeat low dose CTs (RIDER dataset) and 3) improving radiomics performance in survival prediction.
no code implementations • 6 Sep 2021 • Junhua Chen, Inigo Bermejo, Andre Dekker, Leonard Wee
Generative models can improve the performance of low dose CT-based radiomics in different tasks.
1 code implementation • 30 Apr 2021 • Junhua Chen, Chong Zhang, Alberto Traverso, Ivan Zhovannik, Andre Dekker, Leonard Wee, Inigo Bermejo
Moreover, images with different noise levels can be denoised to improve the reproducibility using these models without re-training, as long as the noise intensity is equal or lower than that in high-noise CTs.
no code implementations • 29 Apr 2021 • Junhua Chen, Haiyan Zeng, Chong Zhang, Zhenwei Shi, Andre Dekker, Leonard Wee, Inigo Bermejo
In this article, we treat lung cancer diagnosis as a multiple instance learning (MIL) problem in order to better reflect the diagnosis process in the clinical setting and for the higher interpretability of the output.