RESUMEN
Systemic anticancer therapies (SACTs) are the leading cause of drug-induced interstitial lung disease (ILD). As more novel SACTs become approved, the incidence of this potentially life-threatening adverse event (AE) may increase. Early detection of SACT-related ILD allows for prompt implementation of drug-specific management recommendations, improving the likelihood of AE resolution and, in some instances, widening the patient's eligibility for future cancer treatment options. ILD requires a diagnosis of exclusion through collaboration with the patient's multidisciplinary team to rule out other possible etiologies of new or worsening respiratory signs and symptoms. At Grade 1, ILD is asymptomatic, and thus the radiologist is key to detecting the AE prior to the disease severity worsening. Planned computed tomography scans should be reviewed for the presence of ILD in addition to being assessed for tumor response to treatment, and when ILD is suspected, a high-resolution computed tomography (HRCT) scan should be requested immediately. An HRCT scan, with < 2-mm slice thickness, is the most appropriate method for detecting ILD. Multiple patterns of ILD exist, which can impact patient prognosis. The four main patterns include acute interstitial pneumonia / acute respiratory distress syndrome, organizing pneumonia, hypersensitivity pneumonitis, and non-specific interstitial pneumonia; their distinct radiological features, along with rarer patterns, are discussed here. Furthermore, HRCT is essential for following the course of ILD and might help to determine the intensity of AE management and the appropriateness of re-challenging with SACT, where indicated by drug-specific prescribing information. ILD events should be monitored closely until complete resolution. CRITICAL RELEVANCE STATEMENT: The incidence of potentially treatment-limiting and life-threatening systemic anticancer therapy-related interstitial lung disease (SACT-related ILD) events is likely increasing as more novel regimens become approved. This review provides best-practice recommendations for the early detection of SACT-related ILD by radiologists. KEY POINTS: Radiologists are crucial in detecting asymptomatic (Grade 1) ILD before severity/prognosis worsens. High-resolution computed tomography is the most appropriate method for detecting ILD. Drug-induced ILD is a diagnosis of exclusion, involving a multidisciplinary team. Familiarity with common HRCT patterns, described here, is key for prompt detection. Physicians should highlight systemic anticancer therapies (SACTs) with a known risk for interstitial lung diseases (ILD) on scan requisitions.
RESUMEN
BACKGROUND AND PURPOSE: Radiation-induced pneumonitis (RP), diagnosed 6-12 weeks after treatment, is a complication of lung tumor radiotherapy. So far, clinical and dosimetric parameters have not been reliable in predicting RP. We propose using non-contrast enhanced magnetic resonance imaging (MRI) based functional parameters acquired over the treatment course for patient stratification for improved follow-up. MATERIALS AND METHODS: 23 lung tumor patients received MR-guided hypofractionated stereotactic body radiation therapy at a 0.35T MR-Linac. Ventilation- and perfusion-maps were generated from 2D-cine MRI-scans acquired after the first and last treatment fraction (Fx) using non-uniform Fourier decomposition. The relative differences in ventilation and perfusion between last and first Fx in three regions (planning target volume (PTV), lung volume receiving more than 20Gy (V20) excluding PTV, whole tumor-bearing lung excluding PTV) and three dosimetric parameters (mean lung dose, V20, mean dose to the gross tumor volume) were investigated. Univariate receiver operating characteristic curve - area under the curve (ROC-AUC) analysis was performed (endpoint RP grade≥1) using 5000 bootstrapping samples. Differences between RP and non-RP patients were tested for statistical significance with the non-parametric Mann-Whitney U test (α=0.05). RESULTS: 14/23 patients developed RP of grade≥1 within 3 months. The dosimetric parameters showed no significant differences between RP and non-RP patients. In contrast, the functional parameters, especially the relative ventilation difference in the PTV, achieved a p-value<0.05 and an AUC value of 0.84. CONCLUSION: MRI-based functional parameters extracted from 2D-cine MRI-scans were found to be predictive of RP development in lung tumor patients.
RESUMEN
BACKGROUND: Chest radiographs (CXRs) are still of crucial importance in primary diagnostics, but their interpretation poses difficulties at times. RESEARCH QUESTION: Can a convolutional neural network-based artificial intelligence (AI) system that interprets CXRs add value in an emergency unit setting? STUDY DESIGN AND METHODS: A total of 563 CXRs acquired in the emergency unit of a major university hospital were retrospectively assessed twice by three board-certified radiologists, three radiology residents, and three emergency unit-experienced nonradiology residents (NRRs). They used a two-step reading process: (1) without AI support; and (2) with AI support providing additional images with AI overlays. Suspicion of four suspected pathologies (pleural effusion, pneumothorax, consolidations suspicious for pneumonia, and nodules) was reported on a five-point confidence scale. Confidence scores of the board-certified radiologists were converted into four binary reference standards of different sensitivities. Performance by radiology residents and NRRs without AI support/with AI support were statistically compared by using receiver-operating characteristics (ROCs), Youden statistics, and operating point metrics derived from fitted ROC curves. RESULTS: NRRs could significantly improve performance, sensitivity, and accuracy with AI support in all four pathologies tested. In the most sensitive reference standard (reference standard IV), NRR consensus improved the area under the ROC curve (mean, 95% CI) in the detection of the time-critical pathology pneumothorax from 0.846 (0.785-0.907) without AI support to 0.974 (0.947-1.000) with AI support (P < .001), which represented a gain of 30% in sensitivity and 2% in accuracy (while maintaining an optimized specificity). The most pronounced effect was observed in nodule detection, with NRR with AI support improving sensitivity by 53% and accuracy by 7% (area under the ROC curve without AI support, 0.723 [0.661-0.785]; with AI support, 0.890 [0.848-0.931]; P < .001). Radiology residents had smaller, mostly nonsignificant gains in performance, sensitivity, and accuracy with AI support. INTERPRETATION: We found that in an emergency unit setting without 24/7 radiology coverage, the presented AI solution features an excellent clinical support tool to nonradiologists, similar to a second reader, and allows for a more accurate primary diagnosis and thus earlier therapy initiation.
Asunto(s)
Inteligencia Artificial , Servicio de Urgencia en Hospital , Radiografía Torácica , Humanos , Radiografía Torácica/métodos , Estudios Retrospectivos , Masculino , Femenino , Competencia Clínica , Persona de Mediana Edad , Curva ROC , Adulto , AncianoRESUMEN
Abstract Objective: To evaluate the performance of 1.5 T true fast imaging with steady state precession (TrueFISP) magnetic resonance imaging (MRI) sequences for the detection and characterization of pulmonary abnormalities caused by coronavirus disease 2019 (COVID-19). Materials and Methods: In this retrospective single-center study, computed tomography (CT) and MRI scans of 20 patients with COVID-19 pneumonia were evaluated with regard to the distribution, opacity, and appearance of pulmonary lesions, as well as bronchial changes, pleural effusion, and thoracic lymphadenopathy. McNemar's test was used in order to compare the COVID-19-associated alterations seen on CT with those seen on MRI. Results: Ground-glass opacities were better visualized on CT than on MRI (p = 0.031). We found no statistically significant differences between CT and MRI regarding the visualization/characterization of the following: consolidations; interlobular/intralobular septal thickening; the distribution or appearance of pulmonary abnormalities; bronchial pathologies; pleural effusion; and thoracic lymphadenopathy. Conclusion: Pulmonary abnormalities caused by COVID-19 pneumonia can be detected on TrueFISP MRI sequences and correspond to the patterns known from CT. Especially during the current pandemic, the portions of the lungs imaged on cardiac or abdominal MRI should be carefully evaluated to promote the identification and isolation of unexpected cases of COVID-19, thereby curbing further spread of the disease.
Resumo Objetivo: Avaliar o desempenho da ressonância magnética (RM) de 1,5 T true fast imaging with steady state precession (TrueFISP) para detecção e caracterização de anormalidades pulmonares causadas por doença do coronavírus 2019 (COVID-19). Materiais e Métodos: Neste estudo retrospectivo unicêntrico, imagens de tomografia computadorizada (TC) e RM de 20 pacientes com pneumonia COVID-19 foram avaliadas em relação a distribuição, opacidade e forma das lesões pulmonares, anormalidades brônquicas, derrame pleural e linfadenopatia torácica. O teste de McNemar foi usado para comparar os achados associados à COVID-19 na TC e na RM. Resultados: As opacidades em vidro fosco foram mais bem visualizadas na TC do que na RM (p = 0,031). Não foram encontradas diferenças estatisticamente significantes entre TC e RM em relação aos outros aspectos, ou seja, visualização de consolidações e espessamento septal interlobular/intralobular, distribuição ou forma de anormalidades pulmonares, doenças brônquicas, derrame pleural ou linfadenopatia torácica. Conclusão: As anomalias pulmonares causadas pela pneumonia por COVID-19 podem ser detectadas nas sequências TrueFISP e correspondem aos padrões conhecidos da TC. Especialmente em face da pandemia atual, as porções de imagem dos pulmões na RM cardíaca ou abdominal devem ser cuidadosamente avaliadas para apoiar a identificação e o isolamento de casos inesperados de COVID-19 e, assim, conter a disseminação.