Publications

2022

Maier-Hein L, Eisenmann M, Sarikaya D, März K, Collins T, Malpani A, Fallert J, Feussner H, Giannarou S, Mascagni P, Nakawala H, Park A, Pugh C, Stoyanov D, Vedula SS, Cleary K, Fichtinger G, Forestier G, Gibaud B, Grantcharov T, Hashizume M, Heckmann-Nötzel D, Kenngott HG, Kikinis R, Mündermann L, Navab N, Onogur S, Roß T, Sznitman R, Taylor RH, Tizabi MD, Wagner M, Hager GD, Neumuth T, Padoy N, Collins J, Gockel I, Goedeke J, Hashimoto DA, Joyeux L, Lam K, Leff DR, Madani A, Marcus HJ, Meireles O, Seitel A, Teber D, Ückert F, Müller-Stich BP, Jannin P, Speidel S. Surgical Data Science - From Concepts Toward Clinical Translation. Med Image Anal. 2022;76:102306.
Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process.
Guttuso T, Sirica D, Tosun D, Zivadinov R, Pasternak O, Weintraub D, Baglio F, Bergsland N. Thalamic Dorsomedial Nucleus Free Water Correlates with Cognitive Decline in Parkinson’s Disease. Mov Disord. 2022;37(3):490–501.
BACKGROUND: Brain diffusion tensor imaging (DTI) has been shown to reflect cognitive changes in early Parkinson s disease (PD) but the diffusion-based measure free water (FW) has not been previously assessed. OBJECTIVES: To assess if FW in the thalamic nuclei primarily involved with cognition (ie, the dorsomedial [DMN] and anterior [AN] nuclei), the nucleus basalis of Meynert (nbM), and the hippocampus correlates with and is associated with longitudinal cognitive decline and distinguishes cognitive status at baseline in early PD. Also, to explore how FW compares with conventional DTI, FW-corrected DTI, and volumetric assessments for these outcomes. METHODS: Imaging data and Montreal Cognitive Assessment (MoCA) scores from the Parkinson’s Progression Markers Initiative database were analyzed using partial correlations and ANCOVA. Primary outcome multiple comparisons were corrected for false discovery rate (q value). RESULTS: Thalamic DMN FW changes over 1 year correlated with MoCA changes over both 1 and 3 years (partial correlations -0.222, q = 0.040, n = 130; and - 0.229, q = 0.040, n = 123, respectively; mean PD duration at baseline = 6.85 months). NbM FW changes over 1 year only correlated with MoCA changes over 3 years (-0.222, q = 0.040). Baseline hippocampal FW was associated with cognitive impairment at 3 years (q = 0.040) and baseline nbM FW distinguished PD-normal cognition (MoCA >=26) from PD-cognitive impairment (MoCA
Zaks N, Velikonja T, Parvaz MA, Zinberg J, Done M, Mathalon DH, Addington J, Cadenhead K, Cannon T, Cornblatt B, McGlashan T, Perkins D, Stone WS, Tsuang M, Walker E, Woods SW, Keshavan MS, Buysse DJ, Velthorst E, Bearden CE. Sleep Disturbance in Individuals at Clinical High Risk for Psychosis. Schizophr Bull. 2022;48(1):111–21.
INTRODUCTION: Disturbed sleep is a common feature of psychotic disorders that is also present in the clinical high risk (CHR) state. Evidence suggests a potential role of sleep disturbance in symptom progression, yet the interrelationship between sleep and CHR symptoms remains to be determined. To address this knowledge gap, we examined the association between disturbed sleep and CHR symptoms over time. METHODS: Data were obtained from the North American Prodrome Longitudinal Study (NAPLS)-3 consortium, including 688 CHR individuals and 94 controls (mean age 18.25, 46% female) for whom sleep was tracked prospectively for 8 months. We used Cox regression analyses to investigate whether sleep disturbances predicted conversion to psychosis up to >2 years later. With regressions and cross-lagged panel models, we analyzed longitudinal and bidirectional associations between sleep (the Pittsburgh Sleep Quality Index in conjunction with additional sleep items) and CHR symptoms. We also investigated the independent contribution of individual sleep characteristics on CHR symptom domains separately and explored whether cognitive impairments, stress, depression, and psychotropic medication affected the associations. RESULTS: Disturbed sleep at baseline did not predict conversion to psychosis. However, sleep disturbance was strongly correlated with heightened CHR symptoms over time. Depression accounted for half of the association between sleep and symptoms. Importantly, sleep was a significant predictor of CHR symptoms but not vice versa, although bidirectional effect sizes were similar. DISCUSSION: The critical role of sleep disturbance in CHR symptom changes suggests that sleep may be a promising intervention target to moderate outcome in the CHR state.
Bayat A, Pace DF, Sekuboyina A, Payer C, Stern D, Urschler M, Kirschke JS, Menze BH. Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs. Tomography. 2022;8(1):479–96.
An important factor for the development of spinal degeneration, pain and the outcome of spinal surgery is known to be the balance of the spine. It must be analyzed in an upright, standing position to ensure physiological loading conditions and visualize load-dependent deformations. Despite the complex 3D shape of the spine, this analysis is currently performed using 2D radiographs, as all frequently used 3D imaging techniques require the patient to be scanned in a prone position. To overcome this limitation, we propose a deep neural network to reconstruct the 3D spinal pose in an upright standing position, loaded naturally. Specifically, we propose a novel neural network architecture, which takes orthogonal 2D radiographs and infers the spine’s 3D posture using vertebral shape priors. In this work, we define vertebral shape priors using an atlas and a spine shape prior, incorporating both into our proposed network architecture. We validate our architecture on digitally reconstructed radiographs, achieving a 3D reconstruction Dice of 0.95, indicating an almost perfect 2D-to-3D domain translation. Validating the reconstruction accuracy of a 3D standing spine on real data is infeasible due to the lack of a valid ground truth. Hence, we design a novel experiment for this purpose, using an orientation invariant distance metric, to evaluate our model’s ability to synthesize full-3D, upright, and patient-specific spine models. We compare the synthesized spine shapes from clinical upright standing radiographs to the same patient’s 3D spinal posture in the prone position from CT.
Wang S, Zhang F, Huang P, Hong H, Jiaerken Y, Yu X, Zhang R, Zeng Q, Zhang Y, Kikinis R, Rathi Y, Makris N, Lou M, Pasternak O, Zhang M, Donnell LJO. Superficial White Matter Microstructure Affects Processing Speed in Cerebral Small Vessel Disease. Hum Brain Mapp. 2022;43(17):5310–25.
White matter hyperintensities (WMH) are a typical feature of cerebral small vessel disease (CSVD), which contributes to about 50% of dementias worldwide. Microstructural alterations in deep white matter (DWM) have been widely examined in CSVD. However, little is known about abnormalities in superficial white matter (SWM) and their relevance for processing speed, the main cognitive deficit in CSVD. In 141 CSVD patients, processing speed was assessed using Trail Making Test Part A. White matter abnormalities were assessed by WMH burden (volume on T2-FLAIR) and diffusion MRI measures. SWM imaging measures had a large contribution to processing speed, despite a relatively low SWM WMH burden. Across all imaging measures, SWM free water (FW) had the strongest association with processing speed, followed by SWM mean diffusivity (MD). SWM FW was the only marker to significantly increase between two subgroups with the lowest WMH burdens. When comparing two subgroups with the highest WMH burdens, the involvement of WMH in the SWM was accompanied by significant differences in processing speed and white matter microstructure. Mediation analysis revealed that SWM FW fully mediated the association between WMH volume and processing speed, while no mediation effect of MD or DWM FW was observed. Overall, results suggest that the SWM has an important contribution to processing speed, while SWM FW is a sensitive imaging marker associated with cognition in CSVD. This study extends the current understanding of CSVD-related dysfunction and suggests that the SWM, as an understudied region, can be a potential target for monitoring pathophysiological processes.
Pujol S, Cabeen RP, Yelnik J, François C, Vidal SF, Karachi C, Bardinet E, Cosgrove R, Kikinis R. Somatotopic Organization of Hyperdirect Pathway Projections From the Primary Motor Cortex in the Human Brain. Front Neurol. 2022;13:791092.
Background: The subthalamic nucleus (STN) is an effective neurosurgical target to improve motor symptoms in Parkinson s Disease (PD) patients. MR-guided Focused Ultrasound (MRgFUS) subthalamotomy is being explored as a therapeutic alternative to Deep Brain Stimulation (DBS) of the STN. The hyperdirect pathway provides a direct connection between the cortex and the STN and is likely to play a key role in the therapeutic effects of MRgFUS intervention in PD patients. Objective: This study aims to investigate the topography and somatotopy of hyperdirect pathway projections from the primary motor cortex (M1). Methods: We used advanced multi-fiber tractography and high-resolution diffusion MRI data acquired on five subjects of the Human Connectome Project (HCP) to reconstruct hyperdirect pathway projections from M1. Two neuroanatomy experts reviewed the anatomical accuracy of the tracts. We extracted the fascicles arising from the trunk, arm, hand, face and tongue area from the reconstructed pathways. We assessed the variability among subjects based on the fractional anisotropy (FA) and mean diffusivity (MD) of the fibers. We evaluated the spatial arrangement of the different fascicles using the Dice Similarity Coefficient (DSC) of spatial overlap and the centroids of the bundles. Results: We successfully reconstructed hyperdirect pathway projections from M1 in all five subjects. The tracts were in agreement with the expected anatomy. We identified hyperdirect pathway fascicles projecting from the trunk, arm, hand, face and tongue area in all subjects. Tract-derived measurements showed low variability among subjects, and similar distributions of FA and MD values among the fascicles projecting from different M1 areas. We found an anterolateral somatotopic arrangement of the fascicles in the corona radiata, and an average overlap of 0.63 in the internal capsule and 0.65 in the zona incerta. Conclusion: Multi-fiber tractography combined with high-resolution diffusion MRI data enables the identification of the somatotopic organization of the hyperdirect pathway. Our preliminary results suggest that the subdivisions of the hyperdirect pathway projecting from the trunk, arm, hand, face, and tongue motor area are intermixed at the level of the zona incerta and posterior limb of the internal capsule, with a predominantly overlapping topographical organization in both regions. Subject-specific knowledge of the hyperdirect pathway somatotopy could help optimize target definition in MRgFUS intervention.
Berger M, Pirpamer L, Hofer E, Ropele S, Duering M, Gesierich B, Pasternak O, Enzinger C, Schmidt R, Koini M. Free Water Diffusion MRI and Executive Function With a Speed Component in Healthy Aging. Neuroimage. 2022;257:119303.
Extracellular free water (FW) increases are suggested to better provide pathophysiological information in brain aging than conventional biomarkers such as fractional anisotropy. The aim of the present study was to determine the relationship between conventional biomarkers, FW in white matter hyperintensities (WMH), FW in normal appearing white matter (NAWM) and in white matter tracts and executive functions (EF) with a speed component in elderly persons. We examined 226 healthy elderly participants (median age 69.83 years, IQR: 56.99-74.42) who underwent brain MRI and neuropsychological examination. FW in WMH and in NAWM as well as FW corrected diffusion metrics and measures derived from conventional MRI (white matter hyperintensities, brain volume, lacunes) were used in partial correlation (adjusted for age) to assess their correlation with EF with a speed component. Random forest analysis was used to assess the relative importance of these variables as determinants. Lastly, linear regression analyses of FW in white matter tracts corrected for risk factors of cognitive and white matter deterioration, were used to examine the role of specific tracts on EF with a speed component, which were then ranked with random forest regression. Partial correlation analyses revealed that almost all imaging metrics showed a significant association with EF with a speed component (r = -0.213 - 0.266). Random forest regression highlighted FW in WMH and in NAWM as most important among all diffusion and structural MRI metrics. The fornix (R2=0.421, p = 0.018) and the corpus callosum (genu (R2 = 0.418, p = 0.021), prefrontal (R2 = 0.416, p = 0.026), premotor (R2 = 0.418, p = 0.021)) were associated with EF with a speed component in tract based regression analyses and had highest variables importance. In a normal aging population FW in WMH and NAWM is more closely related to EF with a speed component than standard DTI and brain structural measures. Higher amounts of FW in the fornix and the frontal part of the corpus callosum leads to deteriorating EF with a speed component.
Zhang F, Wells WM, Donnell LJO. Deep Diffusion MRI Registration (DDMReg): A Deep Learning Method for Diffusion MRI Registration. IEEE Trans Med Imaging. 2022;41(6):1454–67.
In this paper, we present a deep learning method, DDMReg, for accurate registration between diffusion MRI (dMRI) datasets. In dMRI registration, the goal is to spatially align brain anatomical structures while ensuring that local fiber orientations remain consistent with the underlying white matter fiber tract anatomy. DDMReg is a novel method that uses joint whole-brain and tract-specific information for dMRI registration. Based on the successful VoxelMorph framework for image registration, we propose a novel registration architecture that leverages not only whole brain information but also tract-specific fiber orientation information. DDMReg is an unsupervised method for deformable registration between pairs of dMRI datasets: it does not require nonlinearly pre-registered training data or the corresponding deformation fields as ground truth. We perform comparisons with four state-of-the-art registration methods on multiple independently acquired datasets from different populations (including teenagers, young and elderly adults) and different imaging protocols and scanners. We evaluate the registration performance by assessing the ability to align anatomically corresponding brain structures and ensure fiber spatial agreement between different subjects after registration. Experimental results show that DDMReg obtains significantly improved registration performance compared to the state-of-the-art methods. Importantly, we demonstrate successful generalization of DDMReg to dMRI data from different populations with varying ages and acquired using different acquisition protocols and different scanners.
Laurent D, Riek J, Sinclair CDJ, Houston P, Roubenoff R, Papanicolaou DA, Nagy A, Pieper S, Yousry TA, Hanna MG, Thornton JS, Machado PM. Longitudinal Changes in MRI Muscle Morphometry and Composition in People With Inclusion Body Myositis. Neurology. 2022;99(9):e865-e876.
BACKGROUND AND OBJECTIVES: Limited data suggest that quantitative MRI (qMRI) measures have potential to be used as trial outcome measures in sporadic inclusion body myositis (sIBM) and as a noninvasive assessment tool to study sIBM muscle pathologic processes. Our aim was to evaluate changes in muscle structure and composition using a comprehensive multiparameter set of qMRI measures and to assess construct validity and responsiveness of qMRI measures in people with sIBM.
Bridge CP, Gorman C, Pieper S, Doyle SW, Lennerz JK, Kalpathy-Cramer J, Clunie DA, Fedorov AY, Herrmann MD. Highdicom: a Python Library for Standardized Encoding of Image Annotations and Machine Learning Model Outputs in Pathology and Radiology. J Digit Imaging. 2022;35(6):1719–37.
Machine learning (ML) is revolutionizing image-based diagnostics in pathology and radiology. ML models have shown promising results in research settings, but the lack of interoperability between ML systems and enterprise medical imaging systems has been a major barrier for clinical integration and evaluation. The DICOM® standard specifies information object definitions (IODs) and services for the representation and communication of digital images and related information, including image-derived annotations and analysis results. However, the complexity of the standard represents an obstacle for its adoption in the ML community and creates a need for software libraries and tools that simplify working with datasets in DICOM format. Here we present the highdicom library, which provides a high-level application programming interface (API) for the Python programming language that abstracts low-level details of the standard and enables encoding and decoding of image-derived information in DICOM format in a few lines of Python code. The highdicom library leverages NumPy arrays for efficient data representation and ties into the extensive Python ecosystem for image processing and machine learning. Simultaneously, by simplifying creation and parsing of DICOM-compliant files, highdicom achieves interoperability with the medical imaging systems that hold the data used to train and run ML models, and ultimately communicate and store model outputs for clinical use. We demonstrate through experiments with slide microscopy and computed tomography imaging, that, by bridging these two ecosystems, highdicom enables developers and researchers to train and evaluate state-of-the-art ML models in pathology and radiology while remaining compliant with the DICOM standard and interoperable with clinical systems at all stages. To promote standardization of ML research and streamline the ML model development and deployment process, we made the library available free and open-source at https://github.com/herrmannlab/highdicom .