Rationale: Intratidal changes in regional lung aeration, as assessed with dynamic four-dimensional computed tomography (CT; 4DCT), may indicate the processes of recruitment and derecruitment, thus portending atelectrauma during mechanical ventilation. In this study, we characterized the time constants associated with deaeration during the expiratory phase of pressure-controlled ventilation in pigs before and after acute lung injury using respiratory-gated 4DCT and image registration. Methods: Eleven pigs were mechanically ventilated in pressure-controlled mode under baseline conditions and following an oleic acid model of acute lung injury. Dynamic 4DCT scans were acquired without interrupting ventilation. Automated segmentation of lung parenchyma was obtained by a convolutional neural network. Respiratory structures were aligned using 4D image registration. Exponential regression was performed on the time-varying CT density in each aligned voxel during exhalation, resulting in regional estimates of intratidal aeration change and deaeration time constants. Regressions were also performed for regional and total exhaled gas volume changes. Results: Normally and poorly aerated lung regions demonstrated the largest median intratidal aeration changes during exhalation, compared to minimal changes within hyper- and non-aerated regions. Following lung injury, median time constants throughout normally aerated regions within each subject were greater than respective values for poorly aerated regions. However, parametric response mapping revealed an association between larger intratidal aeration changes and slower time constants. Lower aeration and faster time constants were observed for the dependent lung regions in the supine position. Regional gas volume changes exhibited faster time constants compared to regional density time constants, as well as better correspondence to total exhaled volume time constants. Conclusion: Mechanical time constants based on exhaled gas volume underestimate regional aeration time constants. After lung injury, poorly aerated regions experience larger intratidal changes in aeration over shorter time scales compared to normally aerated regions. However, the largest intratidal aeration changes occur over the longest time scales within poorly aerated regions. These dynamic 4DCT imaging data provide supporting evidence for the susceptibility of poorly aerated regions to ventilator-induced lung injury, and for the functional benefits of short exhalation times during mechanical ventilation of injured lungs.
Registering lung CT images is an important problem for many applications including tracking lung motion over the breathing cycle, tracking anatomical and function changes over time, and detecting abnormal mechanical properties of the lung. This paper compares and contrasts current-and varifold-based diffeomorphic image registration approaches for registering tree-like structures of the lung. In these approaches, curve-like structures in the lung - for example, the skeletons of vessels and airways segmentation - are represented by currents or varifolds in the dual space of a Reproducing Kernel Hilbert Space (RKHS). Current and varifold representations are discretized and are parameterized via of a collection of momenta. A momenta corresponds to a line segment via the coordinates of the center of the line segment and the tangent direction of the line segment at the center. A varifold-based registration approach is similar to currents except that two varifold representations are aligned independent of the tangent vector orientation. An advantage of varifolds over currents is that the orientation of the tangent vectors can be difficult to determine especially when the vessel and airway trees are not connected. In this paper, we examine the image registration sensitivity and accuracy of current-and varifold-based registration as a function of the number and location of momentum used to represent tree like-structures in the lung. The registrations presented in this paper were generated using the Deformetrica software package ([Durrleman et al. 2014]).
Abstract Objective To evaluate the diagnostic performance outcomes of a breast MRI screening program in high-risk women without prior history of breast cancer. Methods Retrospective cohort study of 1 405 consecutive screening breast MRI examinations in 681 asymptomatic women with high risk of breast cancer without prior history of breast cancer from January 1, 2015, to December 31, 2019. Outcomes (sensitivity, specificity, positive predictive value, negative predictive value, false-negative rate [FNR], cancer detection rate [CDR]) and characteristics of cancers were determined based on histopathology or 12-month follow-up. MRI examinations performed, BI-RADS assessments, pathology outcomes, and CDRs were analyzed overall and by age decade. Results in incidence screening round (MRI in last 18 months) and nonincidence round were compared. Results Breast MRI achieved CDR 20/1000, sensitivity 93.3% (28/30), and specificity 83.4% (1 147/1375). Twenty-eight (28/1 405, CDR 20/1000) screen-detected cancers were identified: 18 (64.3%, 18/28) invasive and 10 (35.7%, 10/28) ductal carcinoma in situ. Overall, 92.9% (26/28) of all cancers were stage 0 or 1 and 89.3% (25/28) were node negative. All 14 incidence screening round malignancies were stage 0 or 1 with N0 disease. Median size for invasive carcinoma was 8.0 mm and for ductal carcinoma in situ was 9.0 mm. There were two false-negative exams for an FNR 0.1% (2/1 405). Conclusion High-risk screening breast MRI was effective at detecting early breast cancer and associated with favorable outcomes.
Segmentation of the pulmonary lobes in computed tomography images is an important precursor for characterizing and quantifying disease patterns, regional functional analysis, and determining treatment interventions. With the increasing resolution and quantity of scans produced in the clinic automatic and reliable lobar segmentation methods are essential for efficient workflows. In this work, a deep learning framework is proposed that utilizes convolutional neural networks for segmentation of fissures and lobes in computed tomography images. A novel pipeline is proposed that consists of a series of 3D convolutional neural networks to marginally learn the lobe segmentation. The method was evaluated extensively on a dataset of 1076 CT images from the COPDGene clinical trial, consisting of scans acquired multiple institutions using various scanners. Overall the method achieved median Dice coefficient of 0.993 and a median average symmetric surface distance of 0.138 mm across all lobes. The results show the method is robust to different inspiration levels, pathologies, and image quality.
