Automated Detection, Segmentation, and Classification of Pleural Effusion From Computed Tomography Scans Using Machine Learning.

OBJECTIVE: This study trained and evaluated algorithms to detect, segment, and classify simple and complex pleural effusions on computed tomography (CT) scans. MATERIALS AND METHODS: For detection and segmentation, we randomly selected 160 chest CT scans out of all consecutive patients (January 2016-January 2021, n = 2659) with reported pleural effusion. Effusions were manually segmented and a negative cohort of chest CTs from 160 patients without effusions was added. A deep convolutional neural network (nnU-Net) was trained and cross-validated (n = 224; 70%) for segmentation and tested on a separate subset (n = 96; 30%) with the same distribution of reported pleural complexity features as in the training cohort (eg, hyperdense fluid, gas, pleural thickening and loculation). On a separate consecutive cohort with a high prevalence of pleural complexity features (n = 335), a random forest model was implemented for classification of segmented effusions with Hounsfield unit thresholds, density distribution, and radiomics-based features as input. As performance measures, sensitivity, specificity, and area under the curves (AUCs) for detection/classifier evaluation (per-case level) and Dice coefficient and volume analysis for the segmentation task were used. RESULTS: Sensitivity and specificity for detection of effusion were excellent at 0.99 and 0.98, respectively (n = 96; AUC, 0.996, test data). Segmentation was robust (median Dice, 0.89; median absolute volume difference, 13 mL), irrespective of size, complexity, or contrast phase. The sensitivity, specificity, and AUC for classification in simple versus complex effusions were 0.67, 0.75, and 0.77, respectively. CONCLUSION: Using a dataset with different degrees of complexity, a robust model was developed for the detection, segmentation, and classification of effusion subtypes. The algorithms are openly available at https://github.com/usb-radiology/pleuraleffusion.git.

Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds.

CT patterns of viral pneumonia are usually only qualitatively described in radiology reports. Artificial intelligence enables automated and reliable segmentation of lungs with chest CT. Based on this, the purpose of this study was to derive meaningful imaging biomarkers reflecting CT patterns of viral pneumonia and assess their potential to discriminate between healthy lungs and lungs with viral pneumonia. This study used non-enhanced and CT pulmonary angiograms (CTPAs) of healthy lungs and viral pneumonia (SARS-CoV-2, influenza A/B) identified by radiology reports and RT-PCR results. After deep learning segmentation of the lungs, histogram-based and threshold-based analyses of lung attenuation were performed and compared. The derived imaging biomarkers were correlated with parameters of clinical and biochemical severity (modified WHO severity scale; c-reactive protein). For non-enhanced CTs (n = 526), all imaging biomarkers significantly differed between healthy lungs and lungs with viral pneumonia (all p < 0.001), a finding that was not reproduced for CTPAs (n = 504). Standard deviation (histogram-derived) and relative high attenuation area [600-0 HU] (HU-thresholding) differed most. The strongest correlation with disease severity was found for absolute high attenuation area [600-0 HU] (r = 0.56, 95% CI = 0.46-0.64). Deep-learning segmentation-based histogram and HU threshold analysis could be deployed in chest CT evaluation for the differentiating of healthy lungs from AP lungs.

Assessment of a Deep Learning Algorithm for the Detection of Rib Fractures on Whole-Body Trauma Computed Tomography.

OBJECTIVE: To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. MATERIALS AND METHODS: We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). RESULTS: All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. CONCLUSION: We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

Early Prediction of Treatment Response of Neuroendocrine Hepatic Metastases after Peptide Receptor Radionuclide Therapy with 90Y-DOTATOC Using Diffusion Weighted and Dynamic Contrast-Enhanced MRI.

The purpose of this study was to determine if parameters derived from diffusion-weighted (DW-) and dynamic contrast-enhanced (DCE-) magnetic resonance imaging (MRI) can help to assess early response to peptide receptor radionuclide therapy (PRRT) with 90Y-DOTATOC in neuroendocrine hepatic metastases (NET-HM). Twenty patients (10 male; 10 female; mean age: 59.2 years) with NET-HM were prospectively enrolled in this single-center imaging study. DW-MRI and DCE-MRI studies were performed just before and 48 hours after therapy with 90Y-DOTATOC. Abdominal SPECT/CT was performed 24 hours after therapy. This MRI imaging and therapy session was repeated after a mean interval of 10 weeks. Up to four lesions per patient were evaluated. Response to therapy was evaluated using metastasis sizes at the first and second therapy session as standard for comparison (regressive, stable, and progressive). DW-MRI analysis included the apparent diffusion coefficient (ADC) and parameters related to intravoxel incoherent motion (IVIM), namely, diffusion (D), perfusion fraction (f) and pseudo-diffusion (D ∗ ). DCE-MRI analysis comprised Ktrans, v e and k ep. For statistical analysis of group differences, one-way analysis of variance (ANOVA) and appropriate post hoc testing was performed. A total of 51 lesions were evaluated. Seven of 51 lesions (14%) showed size progression, 18/51 (35%) regression, and 26/51 (51%) remained stable. The lesion-to-spleen uptake ratio in SPECT showed a decrease between the two treatment sessions that was significantly stronger in regressive lesions compared with stable (p = 0.013) and progressive lesions (p = 0.021). ANOVA showed significant differences in mean ADC after 48 h (p = 0.026), with higher ADC values for regressive lesions. Regarding IVIM, highest values for D at baseline were seen in regressive lesions (p = 0.023). In DCE-MRI, a statistically significant increase in v e after 10 weeks (p = 0.046) was found in regressive lesions. No differences were observed for the transfer constants Ktrans and k ep. Diffusion restriction quantified as ADC was able to differentiate regressive from progressive NET-HMs as early as 48 hours after PRRT. DW-MRI therefore may complement scintigraphy/SPECT for early assessment of response to PRRT. Assessment of perfusion parameters using IVIM and DCE-MRI did not show an additional benefit.