Atlas-guided brain projection tracts: From regions of interest to tractography 3D rendering.

The use of diffusion tensor imaging (DTI) has seen significant development over the last two decades, in particular with the development of the tractography of association tracts for preoperative planning of surgery. However, projection tracts are difficult to differentiate from one another and tractography studies have failed to reconstruct these ascending/descending pathways from/to the spinal cord. The present study proposes an atlas of regions of interest (ROIs) designed specifically for projection tracts tractography. Forty-nine healthy subjects were included in this prospective study. Brain DTI was acquired using the same 3 T MRI scanner, with 32 diffusion directions. Distortions were corrected using the FSL software package. ROIs were drawn using the anterior commissure (AC)-posterior commissure (PC) line on the following landmarks: the pyramid for the corticospinal tract, the medio-caudal part of the red nucleus for the rubrospinal tract, the pontine reticular nucleus for corticoreticular tract, the superior and inferior cerebellar peduncles for, respectively, the anterior and posterior spinocerebellar tract, the gracilis and cuneatus nucleus for the dorsal columns, and the ventro-posterolateral nucleus for the spinothalamic tract. Fiber tracking was performed using a deterministic algorithm using DSI Studio software. ROI coordinates, according to AC-PC line, were given for each tract. Tractography was obtained for each tract, allowing tridimensional rendering and comparison of tracking metrics between tracts. The present study reports the accurate design of specific ROIs for tractography of each projection tract. This could be a useful tool in order to differentiate projection tracts at the spinal cord level.

Value of Spinal Cord Diffusion Imaging and Tractography in Providing Predictive Factors for Tumor Resection in Patients with Intramedullary Tumors: A Pilot Study.

This pilot study aimed to investigate the interest of high angular resolution diffusion imaging (HARDI) and tractography of the spinal cord (SC) in the management of patients with intramedullary tumors by providing predictive elements for tumor resection. Eight patients were included in a prospective study. HARDI images of the SC were acquired using a 3T MRI scanner with a reduced field of view. Opposed phase-encoding directions allowed distortion corrections. SC fiber tracking was performed using a deterministic approach, with extraction of tensor metrics. Then, regions of interest were drawn to track the spinal pathways of interest. HARDI and tractography added value by providing characteristics about the microstructural organization of the spinal white fibers. In patients with SC tumors, tensor metrics demonstrated significant changes in microstructural architecture, axonal density, and myelinated fibers (all, p < 0.0001) of the spinal white matter. Tractography aided in the differentiation of tumor histological types (SC-invaded vs. pushed back by the tumor), and differentiation of the spinal tracts enabled the determination of precise anatomical relationships between the tumor and the SC, defining the tumor resectability. This study underlines the value of using HARDI and tractography in patients with intramedullary tumors, to show alterations in SC microarchitecture and to differentiate spinal tracts to establish predictive factors for tumor resectability.

Monte Carlo simulation of water diffusion through cardiac tissue models.

Monte Carlo diffusion simulations are commonly used to establish a reliable ground truth of tissue microstructure, including for the validation of diffusion-weighted MRI. However, selecting simulation parameters is challenging and affects validity and reproducibility. We conducted experiments to investigate critical conditions in Monte Carlo simulations, such as tissue representation complexity, simulated molecules, update duration, and compartment size. Results show significant changes in microstructure characteristics when parameters are altered, emphasizing the importance of careful control for a reliable ground truth.

Modeling and hexahedral meshing of cerebral arterial networks from centerlines.

Computational fluid dynamics (CFD) simulation provides valuable information on blood flow from the vascular geometry. However, it requires extracting precise models of arteries from low-resolution medical images, which remains challenging. Centerline-based representation is widely used to model large vascular networks with small vessels, as it encodes both the geometric and topological information and facilitates manual editing. In this work, we propose an automatic method to generate a structured hexahedral mesh suitable for CFD directly from centerlines. We addressed both the modeling and meshing tasks. We proposed a vessel model based on penalized splines to overcome the limitations inherent to the centerline representation, such as noise and sparsity. The bifurcations are reconstructed using a parametric model based on the anatomy that we extended to planar n-furcations. Finally, we developed a method to produce a volume mesh with structured, hexahedral, and flow-oriented cells from the proposed vascular network model. The proposed method offers better robustness to the common defects of centerlines and increases the mesh quality compared to state-of-the-art methods. As it relies on centerlines alone, it can be applied to edit the vascular model effortlessly to study the impact of vascular geometry and topology on hemodynamics. We demonstrate the efficiency of our method by entirely meshing a dataset of 60 cerebral vascular networks. 92% of the vessels and 83% of the bifurcations were meshed without defects needing manual intervention, despite the challenging aspect of the input data. The source code is released publicly.

Association of Blood Biomarkers of Inflammation With Penumbra Consumption After Mechanical Thrombectomy in Patients With Acute Ischemic Stroke.

BACKGROUND AND OBJECTIVES: The objective of this study was to assess the relationship between blood biomarkers of inflammation and lesion growth within the penumbra in acute ischemic stroke (AIS) patients treated with mechanical thrombectomy (MT). METHODS: The HIBISCUS-STROKE cohort enrolled patients admitted in the Lyon Stroke Center for an anterior circulation AIS treated with MT after brain MRI assessment. Lesion growth within the penumbra was assessed on day 6 MRI using a voxel-based nonlinear coregistration method and dichotomized into low and high according to the median value. C-reactive protein, interleukin (IL)-6, IL-8, IL-10, monocyte chemoattractant protein-1, soluble tumor necrosis factor receptor I, soluble form suppression of tumorigenicity 2 (sST2), soluble P-selectin, vascular cellular adhesion molecule-1, and matrix metalloproteinase-9 were measured in sera at 4 time points within the first 48 hours. Reperfusion was considered as successful if Thrombolysis in Cerebral Infarction score was 2b/2c/3. A multiple logistic regression model was performed to detect any association between area under the curve (AUC) of these biomarkers within the first 48 hours and a high lesion growth within the penumbra. RESULTS: Ninety patients were included. The median lesion growth within the penumbra was 2.3 (0.7-6.2) mL. On multivariable analysis, a high sST2 AUC (OR 3.77, 95% CI 1.36-10.46), a high baseline DWI volume (OR 3.65, 95% CI 1.32-10.12), and a lack of successful reperfusion (OR 0.19, 95% CI 0.04-0.92) were associated with a high lesion growth within the penumbra. When restricting analyses to patients with successful reperfusion (n = 76), a high sST2 AUC (OR 5.03, 95% CI 1.64-15.40), a high baseline DWI volume (OR 3.74, 95% CI 1.22-11.53), and a high penumbra volume (OR 3.25, 95% CI 1.10-9.57) remained associated with a high lesion growth within the penumbra. DISCUSSION: High sST2 levels within the first 48 hours are associated with a high lesion growth within the penumbra.

Full cervical cord tractography: A new method for clinical use.

Despite recent improvements in diffusion-weighted imaging, spinal cord tractography is not used in routine clinical practice because of difficulties in reconstructing tractograms, with a pertinent tri-dimensional-rendering, in a long post-processing time. We propose a new full tractography approach to the cervical spinal cord without extensive manual filtering or multiple regions of interest seeding that could help neurosurgeons manage various spinal cord disorders. Four healthy volunteers and two patients with either cervical intramedullary tumors or spinal cord injuries were included. Diffusion-weighted images of the cervical spinal cord were acquired using a Philips 3 Tesla machine, 32 diffusion directions, 1,000 s/mm2 b-value, 2 × 2 × 2 mm voxel size, reduced field-of-view (ZOOM), with two opposing phase-encoding directions. Distortion corrections were then achieved using the FSL software package, and tracking of the full cervical spinal cord was performed using the DSI Studio software (quantitative anisotropy-based deterministic algorithm). A unique region of avoidance was used to exclude everything that is not of the nervous system. Fiber tracking parameters used adaptative fractional anisotropy from 0.015 to 0.045, fiber length from 10 to 1,000 mm, and angular threshold of 90°. In all participants, a full cervical cord tractography was performed from the medulla to the C7 spine level. On a ventral view, the junction between the medulla and spinal cord was identified with its pyramidal bulging, and by an invagination corresponding to the median ventral sulcus. On a dorsal view, the fourth ventricle-superior, middle, and inferior cerebellar peduncles-was seen, as well as its floor and the obex; and gracile and cuneate tracts were recognized on each side of the dorsal median sulcus. In the case of the intramedullary tumor or spinal cord injury, the spinal tracts were seen to be displaced, and this helped to adjust the neurosurgical strategy. This new full tractography approach simplifies the tractography pipeline and provides a reliable 3D-rendering of the spinal cord that could help to adjust the neurosurgical strategy.

CNN-LSTM Based Multimodal MRI and Clinical Data Fusion for Predicting Functional Outcome in Stroke Patients.

Clinical outcome prediction plays an important role in stroke patient management. From a machine learning point-of-view, one of the main challenges is dealing with heterogeneous data at patient admission, i.e. the image data which are multidimensional and the clinical data which are scalars. In this paper, a multimodal convolutional neural network - long short-term memory (CNN-LSTM) based ensemble model is proposed. For each MR image module, a dedicated network provides preliminary prediction of the clinical outcome using the modified Rankin scale (mRS). The final mRS score is obtained by merging the preliminary probabilities of each module dedicated to a specific type of MR image weighted by the clinical metadata, here age or the National Institutes of Health Stroke Scale (NIHSS). The experimental results demonstrate that the proposed model surpasses the baselines and offers an original way to automatically encode the spatio-temporal context of MR images in a deep learning architecture. The highest AUC (0.77) was achieved for the proposed model with NIHSS. Clinical Relevance- - We present the first deep learning approach predicting the clinical outcome of stroke patients treated by mechanical thrombectomy which integrates imaging data at the voxel level with key clinical metadata. Combining clinical and imaging data to evaluate the potential benefit from therapy closely mirrors the clinical decision process. Our promising results suggest our predictive model could assist in acute stroke management.

A Software to Visualize, Edit, Model and Mesh Vascular Networks.

Computational fluid dynamics (CFD) is a key tool for a wide range of research areas, beyond the computer science community. In particular, CFD is used in medicine to measure blood flow from patient specific models of arteries. In this field, the creation of accurate meshes remains the most challenging step, as it is based on the segmentation of medical images, a time-consuming task which often requires manual intervention by medical doctors. In this context, user-friendly, interactive softwares are valuable. They enable to spread the new advances in numerical treatment to the medical community and enrich them with the expert knowledge (e.g anatomical knowledge) of clinicians. In this work, we present a user interface dedicated to the meshing of vascular networks from centerlines. It allows for the 3D visualization and edition of input centerlines, which constitute a simplified, easy-to-manipulate representation of vascular networks. The surface of the artery can be reconstructed from the modified centerlines by an editable parametric model and then meshed with high quality hexahedral elements. At every step of the process, the network can be confronted with medical images with enhanced visualization. The software will be released publicly. Clinical relevance- This tool facilitates the manual extraction and editing of vascular networks by medical doctors. It opens the generation of hexahedral meshes for computational fluid dynamics studies to non-expert users.

On the robustness of machine learning algorithms toward microfluidic distortions for cell classification via on-chip fluorescence microscopy.

Single-cell imaging and sorting are critical technologies in biology and clinical applications. The power of these technologies is increased when combined with microfluidics, fluorescence markers, and machine learning. However, this quest faces several challenges. One of these is the effect of the sample flow velocity on the classification performances. Indeed, cell flow speed affects the quality of image acquisition by increasing motion blur and decreasing the number of acquired frames per sample. We investigate how these visual distortions impact the final classification task in a real-world use-case of cancer cell screening, using a microfluidic platform in combination with light sheet fluorescence microscopy. We demonstrate, by analyzing both simulated and experimental data, that it is possible to achieve high flow speed and high accuracy in single-cell classification. We prove that it is possible to overcome the 3D slice variability of the acquired 3D volumes, by relying on their 2D sum z-projection transformation, to reach an efficient real time classification with an accuracy of 99.4% using a convolutional neural network with transfer learning from simulated data. Beyond this specific use-case, we provide a web platform to generate a synthetic dataset and to investigate the effect of flow speed on cell classification for any biological samples and a large variety of fluorescence microscopes (https://www.creatis.insa-lyon.fr/site7/en/MicroVIP).

Automation of Cranial Nerve Tractography by Filtering Tractograms for Skull Base Surgery.

Fiber tractography enables the in vivo reconstruction of white matter fibers in 3 dimensions using data collected by diffusion tensor imaging, thereby helping to understand functional neuroanatomy. In a pre-operative context, it provides essential information on the trajectory of fiber bundles of medical interest, such as cranial nerves. However, the optimization of tractography parameters is a time-consuming process and requires expert neuroanatomical knowledge, making the use of tractography difficult in clinical routine. Tractogram filtering is a method used to isolate the most relevant fibers. In this work, we propose to use filtering as a post-processing of tractography to avoid the manual optimization of tracking parameters and therefore making a step forward automation of tractography. To question the feasibility of automated tractography of cranial nerves, we perform an analysis of main cranial nerves on a series of patients with skull base tumors. A quantitative evaluation of the filtering performance of two state-of-the-art and a new entropy-based methods is carried out on the basis of reference tractograms produced by experts. Our approach proves to be more stable in the selection of the optimal filtering threshold and turns out to be interesting in terms of computational time complexity.

The Contribution of Machine Learning in the Validation of Commercial Wearable Sensors for Gait Monitoring in Patients: A Systematic Review.

Gait, balance, and coordination are important in the development of chronic disease, but the ability to accurately assess these in the daily lives of patients may be limited by traditional biased assessment tools. Wearable sensors offer the possibility of minimizing the main limitations of traditional assessment tools by generating quantitative data on a regular basis, which can greatly improve the home monitoring of patients. However, these commercial sensors must be validated in this context with rigorous validation methods. This scoping review summarizes the state-of-the-art between 2010 and 2020 in terms of the use of commercial wearable devices for gait monitoring in patients. For this specific period, 10 databases were searched and 564 records were retrieved from the associated search. This scoping review included 70 studies investigating one or more wearable sensors used to automatically track patient gait in the field. The majority of studies (95%) utilized accelerometers either by itself (N = 17 of 70) or embedded into a device (N = 57 of 70) and/or gyroscopes (51%) to automatically monitor gait via wearable sensors. All of the studies (N = 70) used one or more validation methods in which "ground truth" data were reported. Regarding the validation of wearable sensors, studies using machine learning have become more numerous since 2010, at 17% of included studies. This scoping review highlights the current state of the ability of commercial sensors to enhance traditional methods of gait assessment by passively monitoring gait in daily life, over long periods of time, and with minimal user interaction. Considering our review of the last 10 years in this field, machine learning approaches are algorithms to be considered for the future. These are in fact data-based approaches which, as long as the data collected are numerous, annotated, and representative, allow for the training of an effective model. In this context, commercial wearable sensors allowing for increased data collection and good patient adherence through efforts of miniaturization, energy consumption, and comfort will contribute to its future success.

Impact of the reperfusion status for predicting the final stroke infarct using deep learning.

BACKGROUND: Predictive maps of the final infarct may help therapeutic decisions in acute ischemic stroke patients. Our objectives were to assess whether integrating the reperfusion status into deep learning models would improve their performance, and to compare them to current clinical prediction methods. METHODS: We trained and tested convolutional neural networks (CNNs) to predict the final infarct in acute ischemic stroke patients treated by thrombectomy in our center. When training the CNNs, non-reperfused patients from a non-thrombectomized cohort were added to the training set to increase the size of this group. Baseline diffusion and perfusion-weighted magnetic resonance imaging (MRI) were used as inputs, and the lesion segmented on day-6 MRI served as the ground truth for the final infarct. The cohort was dichotomized into two subsets, reperfused and non-reperfused patients, from which reperfusion status specific CNNs were developed and compared to one another, and to the clinically-used perfusion-diffusion mismatch model. Evaluation metrics included the Dice similarity coefficient (DSC), precision, recall, volumetric similarity, Hausdorff distance and area-under-the-curve (AUC). RESULTS: We analyzed 109 patients, including 35 without reperfusion. The highest DSC were achieved in both reperfused and non-reperfused patients (DSC = 0.44 ± 0.25 and 0.47 ± 0.17, respectively) when using the corresponding reperfusion status-specific CNN. CNN-based models achieved higher DSC and AUC values compared to those of perfusion-diffusion mismatch models (reperfused patients: AUC = 0.87 ± 0.13 vs 0.79 ± 0.17, P < 0.001; non-reperfused patients: AUC = 0.81 ± 0.13 vs 0.73 ± 0.14, P < 0.01, in CNN vs perfusion-diffusion mismatch models, respectively). CONCLUSION: The performance of deep learning models improved when the reperfusion status was incorporated in their training. CNN-based models outperformed the clinically-used perfusion-diffusion mismatch model. Comparing the predicted infarct in case of successful vs failed reperfusion may help in estimating the treatment effect and guiding therapeutic decisions in selected patients.

Effect of distortion corrections on the tractography quality in spinal cord diffusion-weighted imaging.

PURPOSE: To assess the impact of a different distortion correction (DC) method and patient geometry (sagittal balance) on the quality of spinal cord tractography rendering according to different tractography approaches. METHODS: Forty-four adults free of spinal cord diseases underwent cervical diffusion-weighted imaging. The phase-encoding direction was head→foot. Sequence with opposed polarities (foot→head) was acquired to perform DC. Eddy-current, motion effects, and susceptibility artifact correction methods were used for DC, and two deterministic and one probabilistic tractography approaches were evaluated using MRtrix and DSI Studio tractography software. Fiber length and number of fibers were extracted to evaluate the quality of the tractography rendering. For each subject, cervical lordosis was measured to assess patient geometry. The angle between the main direction of the spinal cord and the orientation of the acquisition box were computed at each spine level to assess acquisition geometry and define an angle threshold for which a tractography of good quality is no longer possible. RESULTS: There was a significant improvement in tractography quality after performing DC with susceptibility artifact correction using a deterministic approach based on tensor. Before DC, the angle threshold was defined at C6 (15.2°) compared with C7 (21.9°) after corrections, demonstrating the importance of spinal cord angulation for DC. CONCLUSION: The impact of DC on tractography quality is greatly impacted by acquisition geometry. To obtain a good-quality tractography, we propose as a future perspective to adapt the acquisition geometry to that of the patient by automatically adjusting the acquisition box.

Overcoming challenges of the human spinal cord tractography for routine clinical use: a review.

The spinal cord (SC) is a dense network of billions of fibers in a small volume surrounded by bones that makes tractography difficult to perform. We aim to provide a review collecting all technical settings of SC tractography and propose the optimal set of parameters to perform a good SC tractography rendering. The MEDLINE database was searched for articles reporting "spinal cord" "tractography" in "humans". Studies were selected only when tractography rendering was displayed and MRI acquisition and tracking parameters detailed. From each study, clinical context, imaging acquisition settings, fiber tracking parameters, region of interest (ROI) design, and quality of the tractography rendering were extracted. Quality of tractography rendering was evaluated by several objective criteria proposed herein. According to the reported studies, to obtain a good tractography rendering, diffusion tensor imaging acquisition should be performed with 1.5 or 3 Tesla MRI, in the axial plane, with > 20 directions; b value: 1000 s mm-2; right-left phase-encoding direction for cervical SC; isotropic voxel size; and no slice gap. Concerning the tracking process, it should be performed with determinist approach, fractional anisotropy threshold between 0.15 and 0.2, and curvature threshold of 40°. ROI design is an essential step for providing good tractography rendering, and their placement has to consider partial volume effects, magnetic susceptibility effects, and motion artifacts. The review reported herein highlights that successful SC tractography depends on many factors (imaging acquisition settings, fiber tracking parameters, and ROI design) to obtain a good SC tractography rendering.

Machine learning-based prediction of glioma margin from 5-ALA induced PpIX fluorescence spectroscopy.

Gliomas are infiltrative brain tumors with a margin difficult to identify. 5-ALA induced PpIX fluorescence measurements are a clinical standard, but expert-based classification models still lack sensitivity and specificity. Here a fully automatic clustering method is proposed to discriminate glioma margin. This is obtained from spectroscopic fluorescent measurements acquired with a recently introduced intraoperative set up. We describe a data-driven selection of best spectral features and show how this improves results of margin prediction from healthy tissue by comparison with the standard biomarker-based prediction. This pilot study based on 10 patients and 50 samples shows promising results with a best performance of 77% of accuracy in healthy tissue prediction from margin tissue.

Simulated perfusion MRI data to boost training of convolutional neural networks for lesion fate prediction in acute stroke.

The problem of final tissue outcome prediction of acute ischemic stroke is assessed from physically realistic simulated perfusion magnetic resonance images. Different types of simulations with a focus on the arterial input function are discussed. These simulated perfusion magnetic resonance images are fed to convolutional neural network to predict real patients. Performances close to the state-of-the-art performances are obtained with a patient specific approach. This approach consists in training a model only from simulated images tuned to the arterial input function of a tested real patient. This demonstrates the added value of physically realistic simulated images to predict the final infarct from perfusion.

Detecting Differences of Fluorescent Markers Distribution in Single Cell Microscopy: Textural or Pointillist Feature Space?

We consider the detection of change in spatial distribution of fluorescent markers inside cells imaged by single cell microscopy. Such problems are important in bioimaging since the density of these markers can reflect the healthy or pathological state of cells, the spatial organization of DNA, or cell cycle stage. With the new super-resolved microscopes and associated microfluidic devices, bio-markers can be detected in single cells individually or collectively as a texture depending on the quality of the microscope impulse response. In this work, we propose, via numerical simulations, to address detection of changes in spatial density or in spatial clustering with an individual (pointillist) or collective (textural) approach by comparing their performances according to the size of the impulse response of the microscope. Pointillist approaches show good performances for small impulse response sizes only, while all textural approaches are found to overcome pointillist approaches with small as well as with large impulse response sizes. These results are validated with real fluorescence microscopy images with conventional resolution. This, a priori non-intuitive result in the perspective of the quest of super-resolution, demonstrates that, for difference detection tasks in single cell microscopy, super-resolved microscopes may not be mandatory and that lower cost, sub-resolved, microscopes can be sufficient.

Full tractography for detecting the position of cranial nerves in preoperative planning for skull base surgery: technical note.

OBJECTIVE: Diffusion imaging tractography has allowed the in vivo description of brain white matter. One of its applications is preoperative planning for brain tumor resection. Due to a limited spatial and angular resolution, it is difficult for fiber tracking to delineate fiber crossing areas and small-scale structures, in particular brainstem tracts and cranial nerves. New methods are being developed but these involve extensive multistep tractography pipelines including the patient-specific design of multiple regions of interest (ROIs). The authors propose a new practical full tractography method that could be implemented in routine presurgical planning for skull base surgery. METHODS: A Philips MRI machine provided diffusion-weighted and anatomical sequences for 2 healthy volunteers and 2 skull base tumor patients. Tractography of the full brainstem, the cerebellum, and cranial nerves was performed using the software DSI Studio, generalized-q-sampling reconstruction, orientation distribution function (ODF) of fibers, and a quantitative anisotropy-based generalized deterministic algorithm. No ROI or extensive manual filtering of spurious fibers was used. Tractography rendering was displayed in a tridimensional space with directional color code. This approach was also tested on diffusion data from the Human Connectome Project (HCP) database. RESULTS: The brainstem, the cerebellum, and the cisternal segments of most cranial nerves were depicted in all participants. In cases of skull base tumors, the tridimensional rendering permitted the visualization of the whole anatomical environment and cranial nerve displacement, thus helping the surgical strategy. CONCLUSIONS: As opposed to classical ROI-based methods, this novel full tractography approach could enable routine enhanced surgical planning or brain imaging for skull base tumors.

Probabilistic Tractography to Predict the Position of Cranial Nerves Displaced by Skull Base Tumors: Value for Surgical Strategy Through a Case Series of 62 Patients.

BACKGROUND: Predicting the displacement of cranial nerves by tumors could make surgery safer and the outcome better. Recent advances in imaging and processing have overcome some of the limits associated with cranial nerve tractography, such as spatial resolution and fiber crossing. Among others, probabilistic algorithms yield to a more accurate depiction of cranial nerve trajectories. OBJECTIVE: To report how cranial nerve probabilistic tractography can help the surgical strategy in a series of various skull base tumors. METHODS: After distortion correction and region of interest seeding, a probabilistic tractography algorithm used the constrained spherical deconvolution model and attempted the reconstruction of cranial nerve trajectories in both healthy and displaced conditions. RESULTS: Sixty-two patients were included and presented: vestibular schwannomas (n = 33); cerebellopontine angle meningiomas (n = 15); arachnoid or epidermoid cysts (n = 6); cavernous sinus and lower nerves schwannomas (n = 4); and other tumors (n = 4). For each patient, at least one 'displaced' cranial nerve was not clearly identified on classical anatomical MRI images. All 372 cranial nerves were successfully tracked on each healthy side; among the 175 cranial nerves considered 'displaced' by tumors, 152 (87%) were successfully tracked. Among the 127 displaced nerves of operated patients (n = 51), their position was confirmed intraoperatively for 118 (93%) of them. Conditions that led to tractography failure were detailed. On the basis of tractography, the surgical strategy was adjusted for 44 patients (71%). CONCLUSION: This study reports a cranial nerve probabilistic tractography pipeline that can: predict the position of most cranial nerves displaced by skull base tumors, help the surgical strategy, and thus be a pertinent tool for future routine clinical application.