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

PURPOSE

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 ± 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 ± 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: atelectasis, 0.77 (95% CI: 0.74, 0.81); nodule, 0.65 (95% CI: 0.61, 0.69); emphysema, 0.89 (95% CI: 0.86, 0.92); effusion, 0.97 (95% CI: 0.96, 0.98); and no apparent disease, 0.89 (95% CI: 0.87, 0.91). AUCs for liver and gallbladder were as follows: hepatobiliary calcification, 0.62 (95% CI: 0.56, 0.67); lesion, 0.73 (95% CI: 0.69, 0.77); dilation, 0.87 (95% CI: 0.84, 0.90); fatty, 0.89 (95% CI: 0.86, 0.92); and no apparent disease, 0.82 (95% CI: 0.78, 0.85). AUCs for kidneys and ureters were as follows: stone, 0.83 (95% CI: 0.79, 0.87); atrophy, 0.92 (95% CI: 0.89, 0.94); lesion, 0.68 (95% CI: 0.64, 0.72); cyst, 0.70 (95% CI: 0.66, 0.73); and no apparent disease, 0.79 (95% CI: 0.75, 0.83).

CONCLUSION

Weakly supervised deep learning models were able to classify diverse diseases in multiple organ systems from CT scans.Keywords: CT, Diagnosis/Classification/Application Domain, Semisupervised Learning, Whole-Body Imaging© RSNA, 2022.

Automatic Diagnosis Labeling of Cardiovascular MRI by Using Semisupervised Natural Language Processing of Text Reports

PURPOSE

To assess whether the semisupervised natural language processing (NLP) of text from clinical radiology reports could provide useful automated diagnosis categorization for ground truth labeling to overcome manual labeling bottlenecks in the machine learning pipeline.

MATERIALS AND METHODS

In this retrospective study, 1503 text cardiac MRI reports from 2016 to 2019 were manually annotated for five diagnoses by clinicians: normal, dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy, myocardial infarction (MI), and myocarditis. A semisupervised method that uses bidirectional encoder representations from transformers (BERT) pretrained on 1.14 million scientific publications was fine-tuned by using the manually extracted labels, with a report dataset split into groups of 801 for training, 302 for validation, and 400 for testing. The model's performance was compared with two traditional NLP models: a rule-based model and a support vector machine (SVM) model. The models' F1 scores and receiver operating characteristic curves were used to analyze performance.

RESULTS

After 15 epochs, the F1 scores on the test set of 400 reports were as follows: normal, 84%; DCM, 79%; hypertrophic cardiomyopathy, 86%; MI, 91%; and myocarditis, 86%. The pooled F1 score and area under the receiver operating curve were 86% and 0.96, respectively. On the same test set, the BERT model had a higher performance than the rule-based model (F1 score, 42%) and SVM model (F1 score, 82%). Diagnosis categories classified by using the BERT model performed the labeling of 1000 MR images in 0.2 second.

CONCLUSION

The developed model used labels extracted from radiology reports to provide automated diagnosis categorization of MR images with a high level of performance.Keywords: Semisupervised Learning, Diagnosis/Classification/Application Domain, Named Entity Recognition, MRI Supplemental material is available for this article. © RSNA, 2021.

MRI-based Identification and Classification of Major Intracranial Tumor Types by Using a 3D Convolutional Neural Network: A Retrospective Multi-institutional Analysis

Purpose

To develop an algorithm to classify postcontrast T1-weighted MRI scans by tumor classes (high-grade glioma, low-grade glioma [LGG], brain metastasis, meningioma, pituitary adenoma, and acoustic neuroma) and a healthy tissue (HLTH) class.

Materials and Methods

In this retrospective study, preoperative postcontrast T1-weighted MR scans from four publicly available datasets-the Brain Tumor Image Segmentation dataset (n = 378), the LGG-1p19q dataset (n = 145), The Cancer Genome Atlas Glioblastoma Multiforme dataset (n = 141), and The Cancer Genome Atlas Low Grade Glioma dataset (n = 68)-and an internal clinical dataset (n = 1373) were used. In all, a total of 2105 images were split into a training dataset (n = 1396), an internal test set (n = 361), and an external test dataset (n = 348). A convolutional neural network was trained to classify the tumor type and to discriminate between images depicting HLTH and images depicting tumors. The performance of the model was evaluated by using cross-validation, internal testing, and external testing. Feature maps were plotted to visualize network attention. The accuracy, positive predictive value (PPV), negative predictive value, sensitivity, specificity, F1 score, area under the receiver operating characteristic curve (AUC), and area under the precision-recall curve (AUPRC) were calculated.

Results

On the internal test dataset, across the seven different classes, the sensitivities, PPVs, AUCs, and AUPRCs ranged from 87% to 100%, 85% to 100%, 0.98 to 1.00, and 0.91 to 1.00, respectively. On the external data, they ranged from 91% to 97%, 73% to 99%, 0.97 to 0.98, and 0.9 to 1.0, respectively.

Conclusion

The developed model was capable of classifying postcontrast T1-weighted MRI scans of different intracranial tumor types and discriminating images depicting pathologic conditions from images depicting HLTH.Keywords MR-Imaging, CNS, Brain/Brain Stem, Diagnosis/Classification/Application Domain, Supervised Learning, Convolutional Neural Network, Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2021.