Medical image segmentation is one of the most challenging tasks in medical image analysis and has been widely developed for many clinical applications. Most of the existing metrics have been first designed for natural images and then extended to medical images. While object surface plays an important role in medical segmentation and quantitative analysis i.e. analyze brain tumor surface, measure gray matter volume, most
of the existing metrics are limited when it comes to analyzing the object surface, especially to tell about surface smoothness or roughness of a given volumetric object or to analyze the topological errors. In this paper, we first analysis both pros and cons of all existing medical image segmentation metrics, specially on volumetric data. We then propose an appropriate roughness index and roughness distance for medical
image segmentation analysis and evaluation. Our proposed method addresses two kinds of segmentation errors, i.e. (i) topological errors on boundary/surface and (ii) irregularities on the boundary/surface. The contribution of this work is four-fold: (i) detect irregular spikes/holes on a surface, (ii) propose roughness index to measure surface roughness of a given object, (iii) propose a roughness distance to measure the distance of two boundaries/surfaces by utilizing the proposed roughness index and (iv) suggest an algorithm which helps to remove the irregular spikes/holes to smooth the surface. Our proposed roughness index and roughness distance are built upon the solid surface roughness parameter which has been successfully developed in the civil engineering.
more »
« less
Uncertainty quantification of TMS simulations considering MRI segmentation errors
Abstract Objective. Transcranial magnetic stimulation (TMS) is a non-invasive brain stimulation method that is used to study brain function and conduct neuropsychiatric therapy. Computational methods that are commonly used for electric field (E-field) dosimetry of TMS are limited in accuracy and precision because of possible geometric errors introduced in the generation of head models by segmenting medical images into tissue types. This paper studies E-field prediction fidelity as a function of segmentation accuracy. Approach. The errors in the segmentation of medical images into tissue types are modeled as geometric uncertainty in the shape of the boundary between tissue types. For each tissue boundary realization, we then use an in-house boundary element method to perform a forward propagation analysis and quantify the impact of tissue boundary uncertainties on the induced cortical E-field. Main results. Our results indicate that predictions of E-field induced in the brain are negligibly sensitive to segmentation errors in scalp, skull and white matter (WM), compartments. In contrast, E-field predictions are highly sensitive to possible cerebrospinal fluid (CSF) segmentation errors. Specifically, the segmentation errors on the CSF and gray matter interface lead to higher E-field uncertainties in the gyral crowns, and the segmentation errors on CSF and WM interface lead to higher uncertainties in the sulci. Furthermore, the uncertainty of the average cortical E-fields over a region exhibits lower uncertainty relative to point-wise estimates. Significance. The accuracy of current cortical E-field simulations is limited by the accuracy of CSF segmentation accuracy. Other quantities of interest like the average of the E-field over a cortical region could provide a dose quantity that is robust to possible segmentation errors.
more »
« less
- NSF-PAR ID:
- 10350677
- Date Published:
- Journal Name:
- Journal of Neural Engineering
- Volume:
- 19
- Issue:
- 2
- ISSN:
- 1741-2560
- Page Range / eLocation ID:
- 026022
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In many mechanistic medical, biological, physical, and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs), especially for diffusion, fluid flow and mechanical relaxation, can make simulations impractically slow. Biological models of tissues and organs often require the simultaneous calculation of the spatial variation of concentration of dozens of diffusing chemical species. One clinical example where rapid calculation of a diffusing field is of use is the estimation of oxygen gradients in the retina, based on imaging of the retinal vasculature, to guide surgical interventions in diabetic retinopathy. Furthermore, the ability to predict blood perfusion and oxygenation may one day guide clinical interventions in diverse settings, i.e., from stent placement in treating heart disease to BOLD fMRI interpretation in evaluating cognitive function (Xie et al., 2019 ; Lee et al., 2020 ). Since the quasi-steady-state solutions required for fast-diffusing chemical species like oxygen are particularly computationally costly, we consider the use of a neural network to provide an approximate solution to the steady-state diffusion equation. Machine learning surrogates, neural networks trained to provide approximate solutions to such complicated numerical problems, can often provide speed-ups of several orders of magnitude compared to direct calculation. Surrogates of PDEs could enable use of larger and more detailed models than are possible with direct calculation and can make including such simulations in real-time or near-real time workflows practical. Creating a surrogate requires running the direct calculation tens of thousands of times to generate training data and then training the neural network, both of which are computationally expensive. Often the practical applications of such models require thousands to millions of replica simulations, for example for parameter identification and uncertainty quantification, each of which gains speed from surrogate use and rapidly recovers the up-front costs of surrogate generation. We use a Convolutional Neural Network to approximate the stationary solution to the diffusion equation in the case of two equal-diameter, circular, constant-value sources located at random positions in a two-dimensional square domain with absorbing boundary conditions. Such a configuration caricatures the chemical concentration field of a fast-diffusing species like oxygen in a tissue with two parallel blood vessels in a cross section perpendicular to the two blood vessels. To improve convergence during training, we apply a training approach that uses roll-back to reject stochastic changes to the network that increase the loss function. The trained neural network approximation is about 1000 times faster than the direct calculation for individual replicas. Because different applications will have different criteria for acceptable approximation accuracy, we discuss a variety of loss functions and accuracy estimators that can help select the best network for a particular application. We briefly discuss some of the issues we encountered with overfitting, mismapping of the field values and the geometrical conditions that lead to large absolute and relative errors in the approximate solution.more » « less
-
more » « less
In this paper we propose a novel neurostimulation protocol that provides an intervention-based assessment to distinguish the contributions of different motor control networks in the cortico-spinal system. Specifically, we use a combination of non-invasive brain stimulation and neuromuscular stimulation to probe neuromuscular system behavior with targeted impulse-response system identification. In this protocol, we use an in-house developed human-machine interface (HMI) for an isotonic wrist movement task, where the user controls a cursor on-screen. During the task, we generate unique motor evoked potentials based on triggered cortical or spinal level perturbations. Externally applied brain-level perturbations are triggered through TMS to cause wrist flexion/extension during the volitional task. The resultant contraction output and related reflex responses are measured by the HMI. These movements also include neuromodulation in the excitability of the brain-muscle pathway via transcranial direct current stimulation. Colloquially, spinal-level perturbations are triggered through skin-surface neuromuscular stimulation of the wrist muscles. The resultant brain-muscle and spinal-muscle pathways perturbed by the TMS and NMES, respectively, demonstrate temporal and spatial differences as manifested through the human-machine interface. This then provides a template to measure the specific neural outcomes of the movement tasks, and in decoding differences in the contribution of cortical- (long-latency) and spinal-level (short-latency) motor control. This protocol is part of the development of a diagnostic tool that can be used to better understand how interaction between cortical and spinal motor centers changes with learning, or injury such as that experienced following stroke.
-
Individual differences in expertise with non-face objects has been positively related to neural selectivity for these objects in several brain regions, including in the fusiform face area (FFA). Recently, we reported that FFA’s cortical thickness is also positively correlated with expertise for non-living objects, while FFA’s cortical thickness is negatively correlated with face recognition ability. These opposite relations between structure and visual abilities, obtained in the same subjects, were postulated to reflect the earlier experience with faces relative to cars, with different mechanisms of plasticity operating at these different developmental times. Here we predicted that variability for faces, presumably reflecting pruning, would be found selectively in deep cortical layers. In 13 men selected to vary in their performance with faces, we used ultra-high field imaging (7 Tesla), we localized the FFA functionally and collected and averaged 6 ultra-high resolution susceptibility weighed images (SWI). Voxel dimensions were 0.194x0.194x1.00mm, covering 20 slices with 0.1mm gap. Images were then processed by two operators blind to behavioral results to define the gray matter/white matter (deep) and gray matter/CSF (superficial) cortical boundaries. Internal boundaries between presumed deep, middle and superficial cortical layers were obtained with an automated method based on image intensities. We used an extensive battery of behavioral tests to quantify both face and object recognition ability. We replicate prior work with face and non-living object recognition predicting large and independent parts of the variance in cortical thickness of the right FFA, in different directions. We also find that face recognition is specifically predicted by the thickness of the deep cortical layers in FFA, whereas recognition of vehicles relates to the thickness of all cortical layers. Our results represent the most precise structural correlate of a behavioral ability to date, linking face recognition ability to a specific layer of a functionally-defined area.more » « less
-
more » « less
Abstract We present BrainNet which, to our knowledge, is the first multi-person non-invasive direct brain-to-brain interface for collaborative problem solving. The interface combines electroencephalography (EEG) to record brain signals and transcranial magnetic stimulation (TMS) to deliver information noninvasively to the brain. The interface allows three human subjects to collaborate and solve a task using direct brain-to-brain communication. Two of the three subjects are designated as “Senders” whose brain signals are decoded using real-time EEG data analysis. The decoding process extracts each Sender’s decision about whether to rotate a block in a Tetris-like game before it is dropped to fill a line. The Senders’ decisions are transmitted via the Internet to the brain of a third subject, the “Receiver,” who cannot see the game screen. The Senders’ decisions are delivered to the Receiver’s brain via magnetic stimulation of the occipital cortex. The Receiver integrates the information received from the two Senders and uses an EEG interface to make a decision about either turning the block or keeping it in the same orientation. A second round of the game provides an additional chance for the Senders to evaluate the Receiver’s decision and send feedback to the Receiver’s brain, and for the Receiver to rectify a possible incorrect decision made in the first round. We evaluated the performance of BrainNet in terms of (1) Group-level performance during the game, (2) True/False positive rates of subjects’ decisions, and (3) Mutual information between subjects. Five groups, each with three human subjects, successfully used BrainNet to perform the collaborative task, with an average accuracy of 81.25%. Furthermore, by varying the information reliability of the Senders by artificially injecting noise into one Sender’s signal, we investigated how the Receiver learns to integrate noisy signals in order to make a correct decision. We found that like conventional social networks, BrainNet allows Receivers to learn to trust the Sender who is more reliable, in this case, based solely on the information transmitted directly to their brains. Our results point the way to future brain-to-brain interfaces that enable cooperative problem solving by humans using a “social network” of connected brains.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1088/1741-2552/ac5586
