A Deep Learning-Based Radiomic Classifier for Usual Interstitial Pneumonia

BACKGROUND

Because chest CT scan has largely supplanted surgical lung biopsy for diagnosing most cases of interstitial lung disease (ILD), tools to standardize CT scan interpretation are urgently needed.

RESEARCH QUESTION

Does a deep learning (DL)-based classifier for usual interstitial pneumonia (UIP) derived using CT scan features accurately discriminate radiologist-determined visual UIP?

STUDY DESIGN AND METHODS

A retrospective cohort study was performed. Chest CT scans acquired in individuals with and without ILD were drawn from a variety of public and private data sources. Using radiologist-determined visual UIP as ground truth, a convolutional neural network was used to learn discrete CT scan features of UIP, with outputs used to predict the likelihood of UIP using a linear support vector machine. Test performance characteristics were assessed in an independent performance cohort and multicenter ILD clinical cohort. Transplant-free survival was compared between UIP classification approaches using the Kaplan-Meier estimator and Cox proportional hazards regression.

RESULTS

A total of 2,907 chest CT scans were included in the training (n = 1,934), validation (n = 408), and performance (n = 565) data sets. The prevalence of radiologist-determined visual UIP was 12.4% and 37.1% in the performance and ILD clinical cohorts, respectively. The DL-based UIP classifier predicted visual UIP in the performance cohort with sensitivity and specificity of 93% and 86%, respectively, and in the multicenter ILD clinical cohort with 81% and 77%, respectively. DL-based and visual UIP classification similarly discriminated survival, and outcomes were consistent among cases with positive DL-based UIP classification irrespective of visual classification.

INTERPRETATION

A DL-based classifier for UIP demonstrated good test performance across a wide range of UIP prevalence and similarly discriminated survival when compared with radiologist-determined UIP. This automated tool could efficiently screen for UIP in patients undergoing chest CT scan and identify a high-risk phenotype among those with known ILD.

Vascular and Parenchymal Enhancement Assessment by Dual-Phase Dual-Energy CT in the Diagnostic Investigation of Pulmonary Hypertension

Purpose

To evaluate pulmonary hypertension (PH) determination by dual-phase dual-energy CT pulmonary angiography vascular enhancement and perfused blood volume (PBV) quantification.

Materials and Methods

In this prospective study, consecutive participants who underwent both right heart catheterization and dual-phase dual-energy CT pulmonary angiography were included between 2012 and 2014. CT evaluation comprised a standard pulmonary arterial phase dual-energy CT pulmonary angiography acquisition (termed series 1) followed 7 seconds after series 1 completion by a second dual-energy CT pulmonary angiography acquisition limited to the central 10 cm of the pulmonary vasculature (termed series 2). In both series, enhancement in the main pulmonary artery (PAenh), the descending aorta (DAenh), and whole-lung PBV (WLenh) was calculated from dual-energy CT pulmonary angiography iodine images. Dual-energy CT pulmonary angiography and standard cardiovascular metrics were correlated to mean pulmonary artery pressure (mPAP) and pulmonary vascular resistance (PVR) with additional receiver operating characteristic curve analysis.

Results

A total of 102 participants (median age, 70; range, 58-78 years; 60 women) were included. Sixty-five participants had PH defined by mPAP of greater than or equal to 25 mm Hg, and 51 participants had PH defined by PVR of greater than 3 Wood units. By either definition, participants with PH had higher PAenh/WLenh ratio and lower WLenh and DAenh in series 1 (P < .05) and higher PAenh and WLenh in series 2 (P < .05). Change in WLenh determined highest diagnostic accuracy to define disease by mPAP (area under the receiver operating characteristic curve [AUC], 0.78) and PVR (AUC, 0.79) and the best mPAP correlation (r = 0.62). PAenh series 2 correlated best with PVR (r = 0.49). Multiple linear regression analysis incorporating WLenh and series 1 DAenh improved PVR correlation (r = 0.56). Combining these dual-energy CT pulmonary angiography metrics with main pulmonary artery size and right-to-left ventricular ratio achieved the highest correlations (mPAP, r = 0.71; PVR, r = 0.64).

Conclusion

Dual-phase dual-energy CT pulmonary angiography enhancement quantification appears to improve mPAP and PVR prediction in noninvasive PH evaluation.Supplemental material is available for this article.See also the commentary by Kay in this issue.© RSNA, 2020.

Lung cancer screening: nodule identification and characterization

The accurate identification and characterization of small pulmonary nodules at low-dose CT is an essential requirement for the implementation of effective lung cancer screening. Individual reader detection performance is influenced by nodule characteristics and technical CT parameters but can be improved by training, the application of CT techniques, and by computer-aided techniques. However, the evaluation of nodule detection in lung cancer screening trials differs from the assessment of individual readers as it incorporates multiple readers, their inter-observer variability, reporting thresholds, and reflects the program accuracy in identifying lung cancer. Understanding detection and interpretation errors in screening trials aids in the implementation of lung cancer screening in clinical practice. Indeed, as CT screening moves to ever lower radiation doses, radiologists must be cognisant of new technical challenges in nodule assessment. Screen detected lung cancers demonstrate distinct morphological features from incidentally or symptomatically detected lung cancers. Hence characterization of screen detected nodules requires an awareness of emerging concepts in early lung cancer appearances and their impact on radiological assessment and malignancy prediction models. Ultimately many nodules remain indeterminate, but further imaging evaluation can be appropriate with judicious utilization of contrast enhanced CT or MRI techniques or functional evaluation by PET-CT.

Multidetector dual-energy CT evaluation of combined partial anomalous pulmonary venous return and bronchial atresia

Partial anomalous venous return (PAPVR) and bronchial atresia (BA) represent rare congenital abnormalities of the lung. Missed diagnosis and misdiagnosis are very common in these patients. Although usually distinct entities, it appears that, in rare cases, they may co-exist owing to inter-related complex embryogenic development. We report a case of a 59-year-old male with both PAPVR and BA that were incidentally detected during a CT pulmonary angiogram and review the literature to suggest the pathogenetic developmental mechanism for this entity. This case demonstrates the utility of multidetector dual-energy CT in delineating the vascular and bronchial anatomy of this complex lung and vascular anomaly. Although uncommon, radiologists should be aware of PAPVR and BA and the coexistence of these two rare lung congenital abnormalities.