Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation

Last update: Dec 15, 2022

Related tags

Deep Learning ifcc

Overview

Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation

The reference code of Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation.

Implemented Models

CNN-RNN-RNN (Liu et al., 2019)
Knowing When to Look (Lu et al., 2017)
Meshed-Memory Transformer (Cornia et al., 2020)
Show, Attend and Tell (Xu et al., 2015)
TieNet (Wang et al., 2018)

Supported Radiology Report Datasets

MIMIC-CXR-JPG (Johnson et al., 2019)
Open-i (Demner-Fushman et al., 2012)

Radiology NLI Dataset

The Radiology NLI dataset (RadNLI) is available at a corresponding PhysioNet project.

Prerequisites

A Linux OS (tested on Ubuntu 16.04)
Memory over 24GB
A gpu with memory over 12GB (tested on NVIDIA Titan X and NVIDIA Titan XP)

Preprocesses

Python Setup

Create a conda environment

$ conda env create -f environment.yml

NOTE : environment.yml is set up for CUDA 10.1 and cuDNN 7.6.3. This may need to be changed depending on a runtime environment.

Resize MIMIC-CXR-JPG

Download MIMIC-CXR-JPG
Make a resized copy of MIMIC-CXR-JPG using resize_mimic-cxr-jpg.py (MIMIC_CXR_ROOT is a dataset directory containing mimic-cxr)
- $ python resize_mimic-cxr-jpg.py MIMIC_CXR_ROOT
Create the sections file of MIMIC-CXR (mimic_cxr_sectioned.csv.gz) with create_sections_file.py
Move mimic_cxr_sectioned.csv.gz to MIMIC_CXR_ROOT/mimic-cxr-resized/2.0.0/

Compute Document Frequencies

Pre-calculate document frequencies that will be used in CIDEr by:

$ python cider-df.py MIMIC_CXR_ROOT mimic-cxr_train-df.bin.gz

Recognize Named Entities

Pre-recognize named entities in MIMIC-CXR by:

$ python ner_reports.py --stanza-download MIMIC_CXR_ROOT mimic-cxr_ner.txt.gz

Download Pre-trained Weights

Download pre-trained CheXpert weights, pre-trained radiology NLI weights, and GloVe embeddings

$ cd resources
$ ./download.sh

Training a Report Generation Model

First, train the Meshed-Memory Transformer model with an NLL loss.

# NLL
$ python train.py --cuda --corpus mimic-cxr --cache-data cache --epochs 32 --batch-size 24 --entity-match mimic-cxr_ner.txt.gz --img-model densenet --img-pretrained resources/chexpert_auc14.dict.gz --cider-df mimic-cxr_train-df.bin.gz --bert-score distilbert-base-uncased --corpus mimic-cxr --lr-scheduler trans MIMIC_CXR_ROOT resources/glove_mimic-cxr_train.512.txt.gz out_m2trans_nll

Second, further train the model a joint loss using the self-critical RL to achieve a better performance.

# RL with NLL + BERTScore + EntityMatchExact
$ python train.py --cuda --corpus mimic-cxr --cache-data cache --epochs 32 --batch-size 24 --rl-epoch 1 --rl-metrics BERTScore,EntityMatchExact --rl-weights 0.01,0.495,0.495 --entity-match mimic-cxr_ner.txt.gz --baseline-model out_m2trans_nll/model_31-152173.dict.gz --img-model densenet --img-pretrained resources/chexpert_auc14.dict.gz --cider-df mimic-cxr_train-df.bin.gz --bert-score distilbert-base-uncased --lr 5e-6 --lr-step 32 MIMIC_CXR_ROOT resources/glove_mimic-cxr_train.512.txt.gz out_m2trans_nll-bs-emexact

# RL with NLL + BERTScore + EntityMatchNLI
$ python train.py --cuda --corpus mimic-cxr --cache-data cache --epochs 32 --batch-size 24 --rl-epoch 1 --rl-metrics BERTScore,EntityMatchNLI --rl-weights 0.01,0.495,0.495 --entity-match mimic-cxr_ner.txt.gz --baseline-model out_m2trans_nll/model_31-152173.dict.gz --img-model densenet --img-pretrained resources/chexpert_auc14.dict.gz --cider-df mimic-cxr_train-df.bin.gz --bert-score distilbert-base-uncased --lr 5e-6 --lr-step 32 MIMIC_CXR_ROOT resources/glove_mimic-cxr_train.512.txt.gz out_m2trans_nll-bs-emnli

Checking Result with TensorBoard

A training result can be checked with TensorBoard.

$ tensorboard --logdir out_m2trans_nll-bs-emnli/log
Serving TensorBoard on localhost; to expose to the network, use a proxy or pass --bind_all
TensorBoard 2.0.0 at http://localhost:6006/ (Press CTRL+C to quit)

Evaluation using CheXbert

NOTE: This evaluation assumes that CheXbert is set up in ./CheXbert.

First, extract reference reports to a csv file.

$ python extract_reports.csv MIMIC_CXR_ROOT/mimic-cxr-resized/2.0.0/mimic_cxr_sectioned.csv.gz MIMIC_CXR_ROOT/mimic-cxr-resized/2.0.0/mimic-cxr-2.0.0-split.csv.gz mimic-imp
$ mv mimic-imp CheXbert/src/

Second, convert generated reports to a csv file. (TEST_SAMPLES is a path to test samples. e.g., out_m2trans_nll-bs-emnli/test_31-152173_samples.txt.gz)

$ python convert_generated.py TEST_SAMPLES gen.csv
$ mv gen.csv CheXbert/src/

Third, run CheXbert against the reference reports.

$ cd CheXbert/src/
$ python label.py -d mimic-imp/reports.csv -o mimic-imp -c chexbert.pth

Fourth, run eval_prf.py to obtain CheXbert scores.

$ cp ../../eval_prf.py . 
$ python eval_prf.py mimic-imp gen.csv gen_chex.csv
2947 references
2347 generated
...
5-micro x.xxx x.xxx x.xxx
5-acc x.xxx

Inferring from a Checkpoint

An inference from a checkpoint can be done with infer.py. (CHECKPOINT is a path to the checkpoint)

$ python infer.py --cuda --corpus mimic-cxr --cache-data cache --batch-size 24 --entity-match mimic-cxr_ner.txt.gz --img-model densenet --img-pretrained resources/chexpert_auc14.dict.gz --cider-df mimic-cxr_train-df.bin.gz --bert-score distilbert-base-uncased --corpus mimic-cxr --lr-scheduler trans MIMIC_CXR_ROOT CHECKPOINT resources/glove_mimic-cxr_train.512.txt.gz out_infer

Pre-trained checkpoints for M2 Transformer can be obtained with a download script.

$ cd checkpoints
$ ./download.sh

Licence

See LICENSE and clinicgen/external/LICENSE_bleu-cider-rouge-spice for details.

Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation

Related tags

Overview

Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation

Implemented Models

Supported Radiology Report Datasets

Radiology NLI Dataset

Prerequisites

Preprocesses

Python Setup

Resize MIMIC-CXR-JPG

Compute Document Frequencies

Recognize Named Entities

Download Pre-trained Weights

Training a Report Generation Model

Checking Result with TensorBoard

Evaluation using CheXbert

Inferring from a Checkpoint

Licence

Owner

Attempt at implementation of a simple GAN using Keras

Spectrum Surveying: Active Radio Map Estimation with Autonomous UAVs

The openspoor package is intended to allow easy transformation between different geographical and topological systems commonly used in Dutch Railway

Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction.

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

rastrainer is a QGIS plugin to training remote sensing semantic segmentation model based on PaddlePaddle.

An open source Jetson Nano baseboard and tools to design your own.

Super Resolution for images using deep learning.

A list of all named GANs!

Chinese license plate recognition

Jittor Medical Segmentation Lib -- The assignment of Pattern Recognition course (2021 Spring) in Tsinghua University

PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

[NeurIPS 2021] Garment4D: Garment Reconstruction from Point Cloud Sequences

This package implements THOR: Transformer with Stochastic Experts.

Inference pipeline for our participation in the FeTA challenge 2021.

[KDD 2021, Research Track] DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

Some pvbatch (paraview) scripts for postprocessing OpenFOAM data

RIM: Reliable Influence-based Active Learning on Graphs.

[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.