Longitudinal Multimodal Transformer Integrating Imaging and Latent
Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification
- URL: http://arxiv.org/abs/2304.02836v5
- Date: Thu, 29 Jun 2023 20:56:31 GMT
- Title: Longitudinal Multimodal Transformer Integrating Imaging and Latent
Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification
- Authors: Thomas Z. Li, John M. Still, Kaiwen Xu, Ho Hin Lee, Leon Y. Cai,
Aravind R. Krishnan, Riqiang Gao, Mirza S. Khan, Sanja Antic, Michael Kammer,
Kim L. Sandler, Fabien Maldonado, Bennett A. Landman, Thomas A. Lasko
- Abstract summary: We propose a transformer-based multimodal strategy to integrate repeat imaging with longitudinal clinical signatures from EHRs for solitary pulmonary nodule (SPN) classification.
We perform unsupervised disentanglement of latent clinical signatures and leverage time-distance scaled self-attention to jointly learn from clinical signatures expressions and chest computed tomography (CT) scans.
- Score: 4.002181247287472
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: The accuracy of predictive models for solitary pulmonary nodule (SPN)
diagnosis can be greatly increased by incorporating repeat imaging and medical
context, such as electronic health records (EHRs). However, clinically routine
modalities such as imaging and diagnostic codes can be asynchronous and
irregularly sampled over different time scales which are obstacles to
longitudinal multimodal learning. In this work, we propose a transformer-based
multimodal strategy to integrate repeat imaging with longitudinal clinical
signatures from routinely collected EHRs for SPN classification. We perform
unsupervised disentanglement of latent clinical signatures and leverage
time-distance scaled self-attention to jointly learn from clinical signatures
expressions and chest computed tomography (CT) scans. Our classifier is
pretrained on 2,668 scans from a public dataset and 1,149 subjects with
longitudinal chest CTs, billing codes, medications, and laboratory tests from
EHRs of our home institution. Evaluation on 227 subjects with challenging SPNs
revealed a significant AUC improvement over a longitudinal multimodal baseline
(0.824 vs 0.752 AUC), as well as improvements over a single cross-section
multimodal scenario (0.809 AUC) and a longitudinal imaging-only scenario (0.741
AUC). This work demonstrates significant advantages with a novel approach for
co-learning longitudinal imaging and non-imaging phenotypes with transformers.
Code available at https://github.com/MASILab/lmsignatures.
Related papers
- Improved Esophageal Varices Assessment from Non-Contrast CT Scans [15.648325577912608]
Esophageal varices (EV) is a serious health concern resulting from portal hypertension.
Despite non-contrast computed tomography (NC-CT) imaging being a less expensive and non-invasive imaging modality, it has yet to gain full acceptance as a primary clinical diagnostic tool for EV evaluation.
We present the Multi-Organ-cOhesion-Network (MOON), a novel framework enhancing the analysis of critical organ features in NC-CT scans for effective assessment of EV.
arXiv Detail & Related papers (2024-07-18T06:49:10Z) - HGT: A Hierarchical GCN-Based Transformer for Multimodal Periprosthetic
Joint Infection Diagnosis Using CT Images and Text [0.0]
Prosthetic Joint Infection (PJI) is a prevalent and severe complication.
Currently, a unified diagnostic standard incorporating both computed tomography (CT) images and numerical text data for PJI remains unestablished.
This study introduces a diagnostic method, HGT, based on deep learning and multimodal techniques.
arXiv Detail & Related papers (2023-05-29T11:25:57Z) - Time-distance vision transformers in lung cancer diagnosis from
longitudinal computed tomography [4.924544172166966]
longitudinal medical imaging presents the unique challenge of sparse, irregular time intervals in data acquisition.
We propose two interpretations of a time-distance vision transformer (ViT) by using vector embeddings of continuous time and a temporal emphasis model to scale self-attention weights.
This work represents the first self-attention-based framework for classifying longitudinal medical images.
arXiv Detail & Related papers (2022-09-04T19:08:44Z) - Self-supervised contrastive learning of echocardiogram videos enables
label-efficient cardiac disease diagnosis [48.64462717254158]
We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos.
When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS)
EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
arXiv Detail & Related papers (2022-07-23T19:17:26Z) - Single volume lung biomechanics from chest computed tomography using a
mode preserving generative adversarial network [10.406580531987418]
We propose a generative adversarial learning approach for estimating local tissue expansion directly from a single CT scan.
The proposed framework was trained and evaluated on 2500 subjects from the SPIROMICS cohort.
Our model achieved an overall PSNR of 18.95 decibels, SSIM of 0.840, and Spearman's correlation of 0.61 at a high spatial resolution of 1 mm3.
arXiv Detail & Related papers (2021-10-15T06:17:52Z) - CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for
Non-Contrast to Contrast CT Translation [56.622832383316215]
We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans.
Our approach is based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran.
Our empirical results show that CyTran outperforms all competing methods.
arXiv Detail & Related papers (2021-10-12T23:25:03Z) - M3Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia
Screening from CT Imaging [85.00066186644466]
We propose a Multi-task Multi-slice Deep Learning System (M3Lung-Sys) for multi-class lung pneumonia screening from CT imaging.
In addition to distinguish COVID-19 from Healthy, H1N1, and CAP cases, our M 3 Lung-Sys also be able to locate the areas of relevant lesions.
arXiv Detail & Related papers (2020-10-07T06:22:24Z) - Co-Heterogeneous and Adaptive Segmentation from Multi-Source and
Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion
Segmentation [48.504790189796836]
We present a novel segmentation strategy, co-heterogenous and adaptive segmentation (CHASe)
We propose a versatile framework that fuses appearance based semi-supervision, mask based adversarial domain adaptation, and pseudo-labeling.
CHASe can further improve pathological liver mask Dice-Sorensen coefficients by ranges of $4.2% sim 9.4%$.
arXiv Detail & Related papers (2020-05-27T06:58:39Z) - Diagnosis of Coronavirus Disease 2019 (COVID-19) with Structured Latent
Multi-View Representation Learning [48.05232274463484]
Recently, the outbreak of Coronavirus Disease 2019 (COVID-19) has spread rapidly across the world.
Due to the large number of affected patients and heavy labor for doctors, computer-aided diagnosis with machine learning algorithm is urgently needed.
In this study, we propose to conduct the diagnosis of COVID-19 with a series of features extracted from CT images.
arXiv Detail & Related papers (2020-05-06T15:19:15Z) - Detecting Pancreatic Ductal Adenocarcinoma in Multi-phase CT Scans via
Alignment Ensemble [77.5625174267105]
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers among the population.
Multiple phases provide more information than single phase, but they are unaligned and inhomogeneous in texture.
We suggest an ensemble of all these alignments as a promising way to boost the performance of PDAC detection.
arXiv Detail & Related papers (2020-03-18T19:06:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.