Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation

Authors: Yuan Li, Xiaodan Liang, Zhiting Hu, Eric P. Xing

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show that our approach achieves the state-of-the-art results on two medical report datasets, generating well-balanced structured sentences with robust coverage of heterogeneous medical report contents. We conduct extensive experiments on two medical image report dataset [8]. Our HRGR-Agent achieves the state-of-the-art performance on both datasets under three kinds of evaluation metrics: automatic metrics such as CIDEr [33], BLEU [25] and ROUGE [20], human evaluation, and detection precision of medical terminologies.
Researcher Affiliation Collaboration Christy Y. Li Duke University yl558@duke.edu Xiaodan Liang Carnegie Mellon University xiaodan1@cs.cmu.edu Zhiting Hu Carnegie Mellon University zhitingh@cs.cmu.edu Eric P. Xing Petuum, Inc epxing@cs.cmu.edu
Pseudocode No The paper states 'Detailed policy update algorithm is provides in supplementary materials,' but does not include pseudocode or an algorithm block within the main body of the paper.
Open Source Code No The paper does not provide an explicit statement about releasing its source code for the described methodology, nor does it include a direct link to a code repository.
Open Datasets Yes First, Indiana University Chest X-Ray Collection (IU X-Ray) [8] is a public dataset consists of 7,470 frontal and lateral-view chest x-ray images paired with their corresponding diagnostic reports.
Dataset Splits Yes On both datasets, we randomly split the data by patients into training, validation and testing by a ratio of 7:1:2.
Hardware Specification Yes We implement our model on Py Torch and train on a Ge Force GTX TITAN GPU.
Software Dependencies No The paper mentions 'Py Torch' as the implementation framework, but does not provide specific version numbers for PyTorch or any other software dependencies.
Experiment Setup Yes We first train all models with cross entropy loss for 30 epochs with an initial learning rate of 5e-4, and then fine-tune the retrieval policy module and generation module of HRGR-Agent via RL with a fixed learning rate 5e-5 for another 30 epochs. We use 512 as dimension of all hidden states and word embeddings, and batch size 16. We set the maximum number of sentences of a report and maximum number of tokens in a sentence as 18 and 44 for CX-CHR and 7 and 15 for IU X-Ray.