Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes

Developing machine learning models for radiology requires large-scale imaging data sets with labels for abnormalities, but the process is challenging due to the size and complexity of the data as well as the cost of labeling. We curated and analyzed a chest computed tomography (CT) data set of 36,316 volumes from 20,201 unique patients. This is the largest multiply-annotated chest CT data set reported. To annotate this data set, we developed a rule-based method for automatically extracting abnormality labels from radiologist free-text reports with an average F-score of 0.976 (min 0.941, max 1.0). We also developed a model for multilabel abnormality classification of chest CT volumes that uses a deep convolutional neural network (CNN). This model reached a classification performance of AUROC greater than 0.90 for 18 abnormalities, with an average AUROC of 0.773 for all 83 abnormalities, demonstrating the feasibility of learning from unfiltered whole volume CT data. We show that training on more labels improves performance significantly: for a subset of 9 labels - nodule, opacity, atelectasis, pleural effusion, consolidation, mass, pericardial effusion, cardiomegaly, and pneumothorax - the model's average AUROC increased by 10 percent when the number of training labels was increased from 9 to all 83. All code for volume preprocessing, automated label extraction, and the volume abnormality prediction model will be made publicly available. The 36,316 CT volumes and labels will also be made publicly available pending institutional approval.

READ FULL TEXT

page 3

page 24

research
11/13/2019

Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection

Multiple instance learning (MIL) is a supervised learning methodology th...
research
09/19/2018

Deep Learning Based Rib Centerline Extraction and Labeling

Automated extraction and labeling of rib centerlines is a typically need...
research
08/16/2023

Prediction of post-radiotherapy recurrence volumes in head and neck squamous cell carcinoma using 3D U-Net segmentation

Locoregional recurrences (LRR) are still a frequent site of treatment fa...
research
05/25/2023

GenerateCT: Text-Guided 3D Chest CT Generation

Generative modeling has experienced substantial progress in recent years...
research
05/09/2023

Duke Spleen Data Set: A Publicly Available Spleen MRI and CT dataset for Training Segmentation

Spleen volumetry is primarily associated with patients suffering from ch...
research
07/01/2016

Automated 5-year Mortality Prediction using Deep Learning and Radiomics Features from Chest Computed Tomography

We propose new methods for the prediction of 5-year mortality in elderly...
research
11/24/2021

Explainable multiple abnormality classification of chest CT volumes with AxialNet and HiResCAM

Understanding model predictions is critical in healthcare, to facilitate...

Please sign up or login with your details

Forgot password? Click here to reset