Attention-guided classification of abnormalities in semi-structured computed tomography reports

Faryna, Khrystyna; Tushar, Fakrul Islam; D’Anniballe, Vincent M.; Hou, Rui; Rubin, Geoffrey D.; Lo, Joseph Y.

doi:10.1117/12.2551370

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complete classification dataset comprises of 1593 chest and chest-abdominal-pelvis CT scans selected randomly from over 26,000 scans conducted at Duke University Health System between January-April, 2017. Using their radiology reports, these scans have been labelled (as shown in Table 1) on a case-level basis with a pre-trained rule-based model [4,5], to provide weak supervision throughout the training stage. Normal to diseased lungs cases hold a ratio of 1:1.75, reflecting the actual prevalence (64.6%) of diseased cases in the hospital system.…”

Section: Methodology 21 Datasetmentioning

confidence: 99%

Weakly supervised 3D classification of chest CT using aggregated multi-resolution deep segmentation features

Saha

Tushar

Faryna

et al. 2020

Medical Imaging 2020: Computer-Aided Diagnosis

Self Cite

View full text Add to dashboard Cite

Weakly supervised disease classification of CT imaging suffers from poor localization owing to case-level annotations, where even a positive scan can hold hundreds to thousands of negative slices along multiple planes. Furthermore, although deep learning segmentation and classification models extract distinctly unique combinations of anatomical features from the same target class(es), they are typically seen as two independent processes in a computer-aided diagnosis (CAD) pipeline, with little to no feature reuse. In this research, we propose a medical classifier that leverages the semantic structural concepts learned via multi-resolution segmentation feature maps, to guide weakly supervised 3D classification of chest CT volumes. Additionally, a comparative analysis is drawn across two different types of feature aggregation to explore the vast possibilities surrounding feature fusion. Using a dataset of 1593 scans labeled on a case-level basis via rule-based model, we train a dual-stage convolutional neural network (CNN) to perform organ segmentation and binary classification of four representative diseases (emphysema, pneumonia/atelectasis, mass and nodules) in lungs. The baseline model, with separate stages for segmentation and classification, results in AUC of 0.791. Using identical hyperparameters, the connected architecture using static and dynamic feature aggregation improves performance to AUC of 0.832 and 0.851, respectively. This study advances the field in two key ways. First, case-level report data is used to weakly supervise a 3D CT classifier of multiple, simultaneous diseases for an organ. Second, segmentation and classification models are connected with two different feature aggregation strategies to enhance the classification performance.

show abstract

Section: Methodology 21 Datasetmentioning

confidence: 99%

Weakly supervised 3D classification of chest CT using aggregated multi-resolution deep segmentation features

Saha

Tushar

Faryna

et al. 2020

Medical Imaging 2020: Computer-Aided Diagnosis

Self Cite

View full text Add to dashboard Cite

show abstract

“…A related study performed classification of multiple chest diseases, but it was limited to noncontrast chest CT (15). Compared with our previous study on automated labeling (18), in the present study the rule-based algorithms were refined and the number of patients increased.…”

Section: Study Design and Overviewmentioning

confidence: 96%

“…Compared with prior works, this study demonstrates the feasibility of weak supervision to create multiple, organ-specific models that provide multidisease classification of body CT scans based on existing radiology reports. Body CT scans of the chest, abdomen, and Weakly Supervised Deep Learning for Multidisease Classification from Body CT Scans Disease Labeling and Dataset Mining Labels were extracted from the free-text radiology reports using a rule-based algorithm to label body CT studies performed between 2012 and 2017 (18). A total of 414 438 reports were initially included.…”

mentioning

confidence: 99%

Classification of Multiple Diseases on Body CT Scans Using Weakly Supervised Deep Learning

Tushar¹,

D’Anniballe²,

Hou³

et al. 2022

Radiology: Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

To design multidisease classifiers for body CT scans for three different organ systems using automatically extracted labels from radiology text reports. Materials and Methods:This retrospective study included a total of 12 092 patients (mean age, 57 years 6 18 [standard deviation]; 6172 women) for model development and testing. Rule-based algorithms were used to extract 19 225 disease labels from 13 667 body CT scans performed between 2012 and 2017. Using a three-dimensional DenseVNet, three organ systems were segmented: lungs and pleura, liver and gallbladder, and kidneys and ureters. For each organ system, a three-dimensional convolutional neural network classified each as no apparent disease or for the presence of four common diseases, for a total of 15 different labels across all three models. Testing was performed on a subset of 2158 CT volumes relative to 2875 manually derived reference labels from 2133 patients (mean age, 58 years 6 18; 1079 women). Performance was reported as area under the receiver operating characteristic curve (AUC), with 95% CIs calculated using the DeLong method.Results: Manual validation of the extracted labels confirmed 91%-99% accuracy across the 15 different labels. AUCs for lungs and pleura labels were as follows:

show abstract

“…Tariq et al 61 developed a 1-dimensional convolutional neural network classifier to predict CAD-Reporting and Data System scores from unstructured reports of CCTA reports. Khrystyna et al 62 designed a weakly supervised system for CT report classification with disease labels covering several organs including liver and lungs. Hassanpour et al 63 designed a pattern mining-based AI-based NLP module to automate the process of converting free-flowing information contained in reports to structured information in welldesigned databases.…”

Section: Nlp Approaches For Cardiologymentioning

confidence: 99%

Fusion Modeling: Combining Clinical and Imaging Data to Advance Cardiac Care

van Assen,

Tariq,

Razavi

et al. 2023

Circ: Cardiovascular Imaging

View full text Add to dashboard Cite

In addition to the traditional clinical risk factors, an increasing amount of imaging biomarkers have shown value for cardiovascular risk prediction. Clinical and imaging data are captured from a variety of data sources during multiple patient encounters and are often analyzed independently. Initial studies showed that fusion of both clinical and imaging features results in superior prognostic performance compared with traditional scores. There are different approaches to fusion modeling, combining multiple data resources to optimize predictions, each with its own advantages and disadvantages. However, manual extraction of clinical and imaging data is time and labor intensive and often not feasible in clinical practice. An automated approach for clinical and imaging data extraction is highly desirable. Convolutional neural networks and natural language processing can be utilized for the extraction of electronic medical record data, imaging studies, and free-text data. This review outlines the current status of cardiovascular risk prediction and fusion modeling; and in addition gives an overview of different artificial intelligence approaches to automatically extract data from images and electronic medical records for this purpose.

show abstract

Attention-guided classification of abnormalities in semi-structured computed tomography reports

Cited by 4 publications

References 0 publications

Weakly supervised 3D classification of chest CT using aggregated multi-resolution deep segmentation features

Weakly supervised 3D classification of chest CT using aggregated multi-resolution deep segmentation features

Classification of Multiple Diseases on Body CT Scans Using Weakly Supervised Deep Learning

Fusion Modeling: Combining Clinical and Imaging Data to Advance Cardiac Care

Contact Info

Product

Resources

About