Feasibility of artificial intelligence-supported assessment of bone marrow infiltration using dual-energy computed tomography in patients with evidence of monoclonal protein - a retrospective observational study.

OBJECTIVES: To demonstrate the feasibility of an automated, non-invasive approach to estimate bone marrow (BM) infiltration of multiple myeloma (MM) by dual-energy computed tomography (DECT) after virtual non-calcium (VNCa) post-processing. METHODS: Individuals with MM and monoclonal gammopathy of unknown significance (MGUS) with concurrent DECT and BM biopsy between May 2018 and July 2020 were included in this retrospective observational study. Two pathologists and three radiologists reported BM infiltration and presence of osteolytic bone lesions, respectively. Bone mineral density (BMD) was quantified CT-based by a CE-certified software. Automated spine segmentation was implemented by a pre-trained convolutional neural network. The non-fatty portion of BM was defined as voxels > 0 HU in VNCa. For statistical assessment, multivariate regression and receiver operating characteristic (ROC) were conducted. RESULTS: Thirty-five patients (mean age 65 ± 12 years; 18 female) were evaluated. The non-fatty portion of BM significantly predicted BM infiltration after adjusting for the covariable BMD (p = 0.007, r = 0.46). A non-fatty portion of BM > 0.93% could anticipate osteolytic lesions and the clinical diagnosis of MM with an area under the ROC curve of 0.70 [0.49-0.90] and 0.71 [0.54-0.89], respectively. Our approach identified MM-patients without osteolytic lesions on conventional CT with a sensitivity and specificity of 0.63 and 0.71, respectively. CONCLUSIONS: Automated, AI-supported attenuation assessment of the spine in DECT VNCa is feasible to predict BM infiltration in MM. Further, the proposed method might allow for pre-selecting patients with higher pre-test probability of osteolytic bone lesions and support the clinical diagnosis of MM without pathognomonic lesions on conventional CT. KEY POINTS: • The retrospective study provides an automated approach for quantification of the non-fatty portion of bone marrow, based on AI-supported spine segmentation and virtual non-calcium dual-energy CT data. • An increasing non-fatty portion of bone marrow is associated with a higher infiltration determined by invasive biopsy after adjusting for bone mineral density as a control variable (p = 0.007, r = 0.46). • The non-fatty portion of bone marrow might support the clinical diagnosis of multiple myeloma when conventional CT images are negative (sensitivity 0.63, specificity 0.71).

Automatic Detection of Post-Operative Clips in Mammography Using a U-Net Convolutional Neural Network.

BACKGROUND: After breast conserving surgery (BCS), surgical clips indicate the tumor bed and, thereby, the most probable area for tumor relapse. The aim of this study was to investigate whether a U-Net-based deep convolutional neural network (dCNN) may be used to detect surgical clips in follow-up mammograms after BCS. METHODS: 884 mammograms and 517 tomosynthetic images depicting surgical clips and calcifications were manually segmented and classified. A U-Net-based segmentation network was trained with 922 images and validated with 394 images. An external test dataset consisting of 39 images was annotated by two radiologists with up to 7 years of experience in breast imaging. The network's performance was compared to that of human readers using accuracy and interrater agreement (Cohen's Kappa). RESULTS: The overall classification accuracy on the validation set after 45 epochs ranged between 88.2% and 92.6%, indicating that the model's performance is comparable to the decisions of a human reader. In 17.4% of cases, calcifications have been misclassified as post-operative clips. The interrater reliability of the model compared to the radiologists showed substantial agreement (κreader1 = 0.72, κreader2 = 0.78) while the readers compared to each other revealed a Cohen's Kappa of 0.84, thus showing near-perfect agreement. CONCLUSIONS: With this study, we show that surgery clips can adequately be identified by an AI technique. A potential application of the proposed technique is patient triage as well as the automatic exclusion of post-operative cases from PGMI (Perfect, Good, Moderate, Inadequate) evaluation, thus improving the quality management workflow.

CT-derived lung vessel morphology correlates with prognostic markers in precapillary pulmonary hypertension.

BACKGROUND: While computed tomography pulmonary angiography (CTPA) is an integral part of the work-up in patients with suspected pulmonary hypertension (PH), there is no established CTPA-derived prognostic marker. We aimed to assess whether quantitative readouts of lung vessel morphology correlate with established prognostic indicators in PH. METHODS: We applied a fully-automatic in-house developed algorithm for segmentation of arteries and veins to determine lung vessel morphology in patients with precapillary PH who underwent right heart catheterization and CTPA between May 2016 and May 2019. Primary endpoint of this retrospective study was the calculation of receiver operating characteristics for identifying low and high mortality risk according to the 3-strata risk assessment model presented in the current guidelines. RESULTS: We analyzed 73 patients, median age 65 years (interquartile range (IQR): 54-76), female/male ratio 35/38, median mean pulmonary arterial pressure 37 mm Hg (IQR: 30-46), and found significant correlations with important prognostic factors in pulmonary arterial hypertension. N-terminal pro-brain natriuretic peptide, cardiac index, mixed venous oxygen saturation, and 6-minute walking distance were correlated with the ratio of the number of arteries over veins with vessel diameters of 6-10 mm (Spearman correlation coefficients ρ = 0.64, p < 0.001; ρ = -0.60, p < 0.001; ρ = -0.47, p = 0.005; ρ = -0.45, p = 0.001, respectively). This ratio predicted a low- and high-risk score with an area under the curve of 0.73 (95% confidence interval (CI): 0.56-0.90) and 0.86 (95% CI: 0.74-0.97), respectively. CONCLUSIONS: The ratio of the number of arteries over veins with diameters between 6 and 10 mm is significantly correlated with prognostic markers in pulmonary hypertension and predicts low and high mortality risk.

Seizure after surgical treatment of chronic subdural hematoma-Associated factors and effect on outcome.

Introduction: Chronic subdural hematoma (cSDH) is becoming more prevalent due to population aging and the increasing use of antithrombotic drugs. Postoperative seizure in cSDH have a negative effect on outcome, and there currently no consensus regarding prophylactic anti-epileptic drug (AED) treatment. The objective of this study was to evaluate predisposing and triggering factors associated with postoperative epileptic seizure in patients with cSDH. Methods: All patients, who were surgically treated for cSDH in a single tertiary care center between 2015 and 2019, were considered for inclusion. Relevant patient- and hematoma-specific characteristics were retrospectively extracted from hospital records. Paroxysmal events categorized by the treating physician as suspected postoperative seizures were noted. The clinical outcome was extracted from the last available follow-up visit and classified according to the Glasgow outcome scale (GOS). Results: Of the included 349 patients, 54 (15.5%) developed suspected postoperative epileptic complications in the form of early seizure (≤ 7 days) in 11 patients (3.2%) and late seizure (>7 days) in 43 patients (12.3%). In the logistic regression analysis, solely depressed brain volume (supratentorial volume (ml) not filled with re-expanded brain) was independently associated with postoperative seizure (odds ratio [OR] 1.006, 95% CI: 1.001-1.011; p = 0.034). The occurrence of postoperative seizure (OR 6.210, 95% CI: 2.704-14.258; p < 0.001) and preoperative Markwalder grading (OR 2.919, 95% CI: 1.538-5.543; p = 0.001) were independently associated with unfavorable (GOS1-3) outcome. Conclusion: Larger postoperative depressed brain volume was the only factor independently associated with suspected postoperative seizure, and it could help identify a subgroup of patients with higher susceptibility to epileptic events. Based on our data, no formal recommendation can be made regarding the prophylactic use of anti-epileptic drugs. Nevertheless, the relative safety of new generation AEDs and the detrimental effect of postoperative seizure on outcome may justify its use in a selected patient population.