Background: Digital breast tomosynthesis (DBT) and abbreviated breast MRI (AB-MRI) offer superior diagnostic performance compared to conventional mammography in screening women with intermediate risk of breast cancer due to dense breast tissue. The aim of this model-based economic evaluation was to analyze whether AB-MRI is cost-effective in this cohort compared to DBT. Methods: Decision analysis and Markov simulations were used to model the cumulative costs and quality-adjusted life-years (QALYs) over a time horizon of 30 years. Model input parameters were adopted from recent literature. Deterministic and probabilistic sensitivity analyses were applied to test the stability of the model. Results: In the base-case scenario, the costs of an AB-MRI examination were defined to equal the costs of a full protocol acquisition. Two-yearly screening of women with dense breasts resulted in cumulative discounted costs of $8798 and $9505 for DBT and AB-MRI, and cumulative discounted effects of 19.23 and 19.27 QALYs, respectively, with an incremental cost-effectiveness ratio of $20,807 per QALY gained in the base-case scenario. By reducing the cost of an AB-MRI examination below a threshold of $241 in sensitivity analyses, AB-MRI would become cost-saving compared to DBT. Conclusion: In comparison to DBT, AB-MRI can be considered cost-effective up to a price per examination of $593 in screening patients at intermediate risk of breast cancer.

Objectives To develop a pipeline for automated body composition analysis and skeletal muscle assessment with integrated quality control for large-scale application in opportunistic imaging. Methods First, a convolutional neural network for extraction of a single slice at the L3/L4 lumbar level was developed on CT scans of 240 patients applying the nnU-Net framework. Second, a 2D competitive dense fully convolutional U-Net for segmentation of visceral and subcutaneous adipose tissue (VAT, SAT), skeletal muscle (SM), and subsequent determination of fatty muscle fraction (FMF) was developed on single CT slices of 1143 patients. For both steps, automated quality control was integrated by a logistic regression model classifying the presence of L3/L4 and a linear regression model predicting the segmentation quality in terms of Dice score. To evaluate the performance of the entire pipeline end-to-end, body composition metrics, and FMF were compared to manual analyses including 364 patients from two centers. Results Excellent results were observed for slice extraction (z-deviation = 2.46 ± 6.20 mm) and segmentation (Dice score for SM = 0.95 ± 0.04, VAT = 0.98 ± 0.02, SAT = 0.97 ± 0.04) on the dual-center test set excluding cases with artifacts due to metallic implants. No data were excluded for end-to-end performance analyses. With a restrictive setting of the integrated segmentation quality control, 39 of 364 patients were excluded containing 8 cases with metallic implants. This setting ensured a high agreement between manual and fully automated analyses with mean relative area deviations of ΔSM = 3.3 ± 4.1%, ΔVAT = 3.0 ± 4.7%, ΔSAT = 2.7 ± 4.3%, and ΔFMF = 4.3 ± 4.4%. Conclusions This study presents an end-to-end automated deep learning pipeline for large-scale opportunistic assessment of body composition metrics and sarcopenia biomarkers in clinical routine. Key Points • Body composition metrics and skeletal muscle quality can be opportunistically determined from routine abdominal CT scans. • A pipeline consisting of two convolutional neural networks allows an end-to-end automated analysis. • Machine-learning-based quality control ensures high agreement between manual and automatic analysis.

Early detection of the autosomal dominant polycystic kidney disease (ADPKD) is crucial as it is one of the most common causes of end-stage renal disease (ESRD) and kidney failure. The total kidney volume (TKV) can be used as a biomarker to quantify disease progression. The TKV calculation requires accurate delineation of kidney volumes, which is usually performed manually by an expert physician. However, this is time-consuming and automated segmentation is warranted. Furthermore, the scarcity of large annotated datasets hinders the development of deep learning solutions. In this work, we address this problem by implementing three attention mechanisms into the U-Net to improve TKV estimation. Additionally, we implement a cosine loss function that works well on image classification tasks with small datasets. Lastly, we apply a technique called sharpness aware minimization (SAM) that helps improve the generalizability of networks. Our results show significant improvements (p-value < 0.05) over the reference kidney segmentation U-Net. We show that the attention mechanisms and/or the cosine loss with SAM can achieve a dice score (DSC) of 0.918, a mean symmetric surface distance (MSSD) of 1.20 mm with the mean TKV difference of −1.72%, and R2 of 0.96 while using only 100 MRI datasets for training and testing. Furthermore, we tested four ensembles and obtained improvements over the best individual network, achieving a DSC and MSSD of 0.922 and 1.09 mm, respectively.