Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Auto-GAN: Self-Supervised Collaborative Learning for Medical Image Synthesis

Authors: Bing Cao, Han Zhang, Nannan Wang, Xinbo Gao, Dinggang Shen10486-10493

AAAI 2020 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental With experiments on multiple medical image databases, we demonstrate a great generalization ability as well as specialty of our method compared with other state-of-the-arts.
Researcher Affiliation Academia 1State Key Laboratory of Integrated Services Networks, Xidian University, Xi an, China 2Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, USA
Pseudocode No The paper describes the proposed framework and components in detail but does not include any explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository.
Open Datasets Yes We conduct the first experiment on the Bra TS database (Menze et al. 2015), which consists of four MRI modalities: T1, T1-C, T2, and T2-FLAIR. For CT image translation, we evaluate our method on the Alzheimer s Disease Neuroimaging Initiative (ADNI) database, which has two modalities: T1 and CT.
Dataset Splits Yes We randomly select 80% subjects as a training set; the remaining 20% subjects are taken as a testing set. Such a process is repeated by 10 times.
Hardware Specification Yes We conduct all the experiments under the environment of Python 3.7 and Py Torch 1.0 on a Ubuntu 18.04 system with NVIDIA TITAN Xp GPU.
Software Dependencies Yes We conduct all the experiments under the environment of Python 3.7 and Py Torch 1.0 on a Ubuntu 18.04 system with NVIDIA TITAN Xp GPU.
Experiment Setup Yes In the training phase, the input images are resized to 256 256 and then cropped to the size of 240 240. In the testing phase, the input images are not resized. The trade-off parameter Ξ»1 is set to 0.5 and Ξ»2 is set to 10 in our experiments.