An artificial intelligence algorithm for pulmonary embolism detection on polychromatic computed tomography: performance on virtual monochromatic images.

OBJECTIVES: Virtual monochromatic images (VMI) are increasingly used in clinical practice as they improve contrast-to-noise ratio. However, due to their different appearances, the performance of artificial intelligence (AI) trained on conventional CT images may worsen. The goal of this study was to assess the performance of an established AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPI) to detect pulmonary embolism (PE) on VMI. METHODS: Paired 60 kiloelectron volt (keV) VMI and CPI of 114 consecutive patients suspected of PE, obtained with a detector-based spectral CT scanner, were retrospectively analyzed by an established AI algorithm. The CT pulmonary angiography (CTPA) were classified as positive or negative for PE on a per-patient level. The reference standard was established using a comprehensive method that combined the evaluation of the attending radiologist and three experienced cardiothoracic radiologists aided by two different detection tools. Sensitivity, specificity, positive and negative predictive values and likelihood ratios of the algorithm on VMI and CPI were compared. RESULTS: The prevalence of PE according to the reference standard was 35.1% (40 patients). None of the diagnostic accuracy measures of the algorithm showed a significant difference between CPI and VMI. Sensitivity was 77.5% (95% confidence interval (CI) 64.6-90.4%) and 85.0% (73.9-96.1%) (p = 0.08) on CPI and VMI respectively and specificity 96.0% (91.4-100.0%) and 94.6% (89.4-99.7%) (p = 0.32). CONCLUSIONS: Diagnostic performance of the AI algorithm that was trained on CPI did not drop on VMI, which is reassuring for its use in clinical practice. CLINICAL RELEVANCE STATEMENT: A commercially available AI algorithm, trained on conventional polychromatic CTPA, could be safely used on virtual monochromatic images. This supports the sustainability of AI-aided detection of PE on CT despite ongoing technological advances in medical imaging, although monitoring in daily practice will remain important. KEY POINTS: • Diagnostic accuracy of an AI algorithm trained on conventional polychromatic images to detect PE did not drop on virtual monochromatic images. • Our results are reassuring as innovations in hardware and reconstruction in CT are continuing, whilst commercial AI algorithms that are trained on older generation data enter healthcare.

External validation of the RSNA 2020 pulmonary embolism detection challenge winning deep learning algorithm.

PURPOSE: To evaluate the diagnostic performance and generalizability of the winning DL algorithm of the RSNA 2020 PE detection challenge to a local population using CTPA data from two hospitals. MATERIALS AND METHODS: Consecutive CTPA images from patients referred for suspected PE were retrospectively analysed. The winning RSNA 2020 DL algorithm was retrained on the RSNA-STR Pulmonary Embolism CT (RSPECT) dataset. The algorithm was tested in hospital A on multidetector CT (MDCT) images of 238 patients and in hospital B on spectral detector CT (SDCT) and virtual monochromatic images (VMI) of 114 patients. The output of the DL algorithm was compared with a reference standard, which included a consensus reading by at least two experienced cardiothoracic radiologists for both hospitals. Areas under the receiver operating characteristic curve (AUCs) were calculated. Sensitivity and specificity were determined using the maximum Youden index. RESULTS: According to the reference standard, PE was present in 73 patients (30.7%) in hospital A and 33 patients (29.0%) in hospital B. For the DL algorithm the AUC was 0.96 (95% CI 0.92-0.98) in hospital A, 0.89 (95% CI 0.81-0.94) for conventional reconstruction in hospital B and 0.87 (95% CI 0.80-0.93) for VMI. CONCLUSION: The RSNA 2020 pulmonary embolism detection on CTPA challenge winning DL algorithm, retrained on the RSPECT dataset, showed high diagnostic accuracy on MDCT images. A somewhat lower performance was observed on SDCT images, which suggest additional training on novel CT technology may improve generalizability of this DL algorithm.

A 20-Year-Old Woman With Thoracic Pain and Progressive Dyspnea on Exertion.

CASE PRESENTATION: A 20-year-old woman presented with dry cough, right-sided thoracic pain, and gradually progressive dyspnea on exertion. She had no hemoptysis or fever. There was no relevant medical history. She was a never smoker and used no medication besides oral contraceptives. There were no other risk factors for a pulmonary embolism. There was a family history of ovarian and breast cancer. Physical examination showed a mildly ill-looking woman, with shallow breathing and normal blood oxygen saturation. Auscultation revealed normal breath sounds without crackles or wheezing. Laboratory testing showed a significantly increased D-dimer (4,560 µg/L [normal, < 500 µg/L]), elevated C-reactive protein (131 mg/L [normal, < 5 mg/L]), normal leucocytes, and elevated lactate dehydrogenase (825 units/L [normal, 50 to 250 units/L).

Mild brain lesions do not affect brain volumes in moderate-late preterm infants.

PURPOSE: It is unknown whether frequently occurring mild brain lesions affect brain volumes in moderate (MP2; 32+0-33+6 weeks' gestation) and late (LP3; 34+0-35+6 weeks' gestation) preterm infants. Therefore, we aimed to investigate the effect of mild brain lesions on brain volumes in moderate-late preterm (MLPT4) infants and to compare brain volumes between MP and LP infants. METHODS: From August 2017 to November 2019, eligible MLPT infants born at Isala Women and Children's Hospital were enrolled in a prospective cohort study (Brain Imaging in Moderate-late Preterm infants 'BIMP-study'). MRI was performed around term equivalent age (TEA5). MRI scans were assessed for (mild) brain lesions. T2-weighted images were used for automatic segmentation of eight brain structures. Linear regression analysis was performed to compare absolute and relative brain volumes between infants with and without mild brain lesions and between MP and LP infants. RESULTS: 36 MP and 68 LP infants were included. In infants with mild brain lesions, intracranial volume (B = 27.4 cm3, p = 0.02), cerebrospinal fluid (B = 8.78 cm3, p = 0.01) and cerebellar volumes (B = 1.70 cm3, p = 0.03) were significantly larger compared to infants without mild brain lesions. After correction for weight and postmenstrual age at MRI, these volumes were no longer significantly different. LP infants had larger brain volumes than MP infants, but differences were not significant. Relative brain volumes showed no significant differences in both analyses. CONCLUSION: Neither having mild brain lesions, nor being born moderate prematurely affected brain volumes at TEA in MLPT infants.

Incidence of brain lesions in moderate-late preterm infants assessed by cranial ultrasound and MRI: The BIMP-study.

PURPOSE: To evaluate the incidence and characteristics of brain lesions in moderate-late preterm (MLPT) infants, born at 32-36 weeks' gestation using cranial ultrasound (cUS) and magnetic resonance imaging (MRI). METHODS: Prospective cohort study carried out at Isala Women and Children's Hospital between August 2017 and November 2019. cUS was performed at postnatal day 3-4 (early-cUS), before discharge and repeated at term equivalent age (TEA) in MLPT infants born between 32+0 and 35+6 weeks' gestation. At TEA, MRI was also performed. Several brain lesions were assessed e.g. hemorrhages, white matter and deep gray matter injury. Brain maturation was visually evaluated. Lesions were classified as mild or moderate-severe. Incidences and confidence intervals were calculated. RESULTS: 166 MLPT infants were included of whom 127 underwent MRI. One or more mild lesions were present in 119/166 (71.7 %) and moderate-severe lesions in 6/166 (3.6 %) infants on cUS and/or MRI. The most frequent lesions were signs suggestive of white matter injury: inhomogeneous echogenicity in 50/164 infants (30.5 %) at early-cUS, in 12/148 infants (8.1 %) at TEA-cUS and diffuse white matter signal changes (MRI) in 27/127 (23.5 %) infants. Cerebellar hemorrhage (MRI) was observed in 16/127 infants (12.6 %). Delayed maturation (MRI) was seen in 17/117 (13.4 %) infants. Small hemorrhages and punctate white matter lesions were more frequently detected on MRI than on cUS. CONCLUSIONS: In MLPT infants mild brain lesions were frequently encountered, especially signs suggestive of white matter injury and small hemorrhages. Moderate-severe lesions were less frequently seen.

A systematic review on brain injury and altered brain development in moderate-late preterm infants.

OBJECTIVES: To provide a systematic review of brain injury and altered brain development in moderate-late preterm (MLPT) infants as compared to very preterm and term infants. STUDY DESIGN: A systematic search in five databases was performed in January 2020. Original research papers on incidence of brain injury and papers using quantitative data on brain development in MLPT infants were selected. The Johanna Briggs Institute 'Critical Appraisal Checklist for Studies Reporting Prevalence Data' was used for quality appraisal. Data extraction included: imaging modality, incidences of brain injury, brain volumes, 2D-measurements and diffusivity values. RESULTS: In total, 24 studies were eligible. Most studies had a moderate quality. Twenty studies reported on the incidence of brain injury in MLPT infants. The incidence of intraventricular hemorrhage (IVH) ranged from 0.0% to 23.5% and of white matter injury (WMI) from 0.5% to 10.8%. One study reported the incidence of arterial infarction (0.3%) and none of cerebellar hemorrhage. Eleven studies compared incidences of brain injury between MLPT infants and very preterm or term infants. Five studies reported signs of altered brain development in MLPT infants. CONCLUSIONS: The incidences of IVH and WMI in MLPT infants varied widely between studies. Other abnormalities were sparsely reported. Evidence regarding a higher or lower incidence of brain injury in MLPT infants compared to very preterm or term infants is weak due to moderate methodological quality of reported studies. There is limited evidence suggesting a difference in brain development between MLPT and term infants.