Implementable Deep Learning for Multi-sequence Proton MRI Lung Segmentation: A Multi-center, Multi-vendor, and Multi-disease Study.

BACKGROUND: Recently, deep learning via convolutional neural networks (CNNs) has largely superseded conventional methods for proton (1 H)-MRI lung segmentation. However, previous deep learning studies have utilized single-center data and limited acquisition parameters. PURPOSE: Develop a generalizable CNN for lung segmentation in 1 H-MRI, robust to pathology, acquisition protocol, vendor, and center. STUDY TYPE: Retrospective. POPULATION: A total of 809 1 H-MRI scans from 258 participants with various pulmonary pathologies (median age (range): 57 (6-85); 42% females) and 31 healthy participants (median age (range): 34 (23-76); 34% females) that were split into training (593 scans (74%); 157 participants (55%)), testing (50 scans (6%); 50 participants (17%)) and external validation (164 scans (20%); 82 participants (28%)) sets. FIELD STRENGTH/SEQUENCE: 1.5-T and 3-T/3D spoiled-gradient recalled and ultrashort echo-time 1 H-MRI. ASSESSMENT: 2D and 3D CNNs, trained on single-center, multi-sequence data, and the conventional spatial fuzzy c-means (SFCM) method were compared to manually delineated expert segmentations. Each method was validated on external data originating from several centers. Dice similarity coefficient (DSC), average boundary Hausdorff distance (Average HD), and relative error (XOR) metrics to assess segmentation performance. STATISTICAL TESTS: Kruskal-Wallis tests assessed significances of differences between acquisitions in the testing set. Friedman tests with post hoc multiple comparisons assessed differences between the 2D CNN, 3D CNN, and SFCM. Bland-Altman analyses assessed agreement with manually derived lung volumes. A P value of <0.05 was considered statistically significant. RESULTS: The 3D CNN significantly outperformed its 2D analog and SFCM, yielding a median (range) DSC of 0.961 (0.880-0.987), Average HD of 1.63 mm (0.65-5.45) and XOR of 0.079 (0.025-0.240) on the testing set and a DSC of 0.973 (0.866-0.987), Average HD of 1.11 mm (0.47-8.13) and XOR of 0.054 (0.026-0.255) on external validation data. DATA CONCLUSION: The 3D CNN generated accurate 1 H-MRI lung segmentations on a heterogenous dataset, demonstrating robustness to disease pathology, sequence, vendor, and center. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: Stage 1.

'Munchausen's syndrome by proxy' or a 'miscarriage of justice'? An initial application of functional neuroimaging to the question of guilt versus innocence.

'Munchausen's syndrome by proxy' characteristically describes women alleged to have fabricated or induced illnesses in children under their care, purportedly to attract attention. Where conclusive evidence exists the condition's aetiology remains speculative, where such evidence is lacking diagnosis hinges upon denial of wrong-doing (conduct also compatible with innocence). How might investigators obtain objective evidence of guilt or innocence? Here, we examine the case of a woman convicted of poisoning a child. She served a prison sentence but continues to profess her innocence. Using a modified fMRI protocol (previously published in 2001) we scanned the subject while she affirmed her account of events and that of her accusers. We hypothesized that she would exhibit longer response times in association with greater activation of ventrolateral prefrontal and anterior cingulate cortices when endorsing those statements she believed to be false (i.e., when she 'lied'). The subject was scanned 4 times at 3 Tesla. Results revealed significantly longer response times and relatively greater activation of ventrolateral prefrontal and anterior cingulate cortices when she endorsed her accusers' version of events. Hence, while we have not 'proven' that this subject is innocent, we demonstrate that her behavioural and functional anatomical parameters behave as if she were.