3D brain tumor segmentation using a two-stage optimal mass transport algorithm

Optimal mass transport (OMT) theory, the goal of which is to move any irregular 3D object (i.e., the brain) without causing significant distortion, is used to preprocess brain tumor datasets for the first time in this paper. The first stage of a two-stage OMT (TSOMT) procedure transforms the brain into a unit solid ball. The second stage transforms the unit ball into a cube, as it is easier to apply a 3D convolutional neural network to rectangular coordinates. Small variations in the local mass-measure stretch ratio among all the brain tumor datasets confirm the robustness of the transform. Additionally, the distortion is kept at a minimum with a reasonable transport cost. The original $$240 \times 240 \times 155 \times 4$$ 240 × 240 × 155 × 4 dataset is thus reduced to a cube of $$128 \times 128 \times 128 \times 4$$ 128 × 128 × 128 × 4 , which is a 76.6% reduction in the total number of voxels, without losing much detail. Three typical U-Nets are trained separately to predict the whole tumor (WT), tumor core (TC), and enhanced tumor (ET) from the cube. An impressive training accuracy of 0.9822 in the WT cube is achieved at 400 epochs. An inverse TSOMT method is applied to the predicted cube to obtain the brain results. The conversion loss from the TSOMT method to the inverse TSOMT method is found to be less than one percent. For training, good Dice scores (0.9781 for the WT, 0.9637 for the TC, and 0.9305 for the ET) can be obtained. Significant improvements in brain tumor detection and the segmentation accuracy are achieved. For testing, postprocessing (rotation) is added to the TSOMT, U-Net prediction, and inverse TSOMT methods for an accuracy improvement of one to two percent. It takes 200 seconds to complete the whole segmentation process on each new brain tumor dataset.

Dynamic Task Allocation Method of Swarm Robots Based on Optimal Mass Transport Theory

It is difficult for swarm robots to allocate tasks efficiently by self-organization in a dynamic unknown environment. The computational cost of swarm robots will be significantly increased for large-scale tasks, and the unbalanced task allocation of robots will also lead to a decrease in system efficiency. To address these issues, we propose a dynamic task allocation method of swarm robots based on optimal mass transport theory. The problem of large-scale tasks is solved by grouping swarm robots to complete regional tasks. The task reallocation mechanism realizes the balanced task allocation of individual robots. This paper solves the symmetric assignment between robot and task and between the robot groups and the regional tasks. Our simulation and experimental results demonstrate that the proposed method can make the swarm robots self-organize to allocate large-scale dynamic tasks effectively. The tasks can also be balanced allocated to each robot in the swarm of robots.

Enabling early detection of osteoarthritis from presymptomatic cartilage texture maps via transport-based learning

Many diseases have no visual cues in the early stages, eluding image-based detection. Today, osteoarthritis (OA) is detected after bone damage has occurred, at an irreversible stage of the disease. Currently no reliable method exists for OA detection at a reversible stage. We present an approach that enables sensitive OA detection in presymptomatic individuals. Our approach combines optimal mass transport theory with statistical pattern recognition. Eighty-six healthy individuals were selected from the Osteoarthritis Initiative, with no symptoms or visual signs of disease on imaging. On 3-y follow-up, a subset of these individuals had progressed to symptomatic OA. We trained a classifier to differentiate progressors and nonprogressors on baseline cartilage texture maps, which achieved a robust test accuracy of 78% in detecting future symptomatic OA progression 3 y prior to symptoms. This work demonstrates that OA detection may be possible at a potentially reversible stage. A key contribution of our work is direct visualization of the cartilage phenotype defining predictive ability as our technique is generative. We observe early biochemical patterns of fissuring in cartilage that define future onset of OA. In the future, coupling presymptomatic OA detection with emergent clinical therapies could modify the outcome of a disease that costs the United States healthcare system $16.5 billion annually. Furthermore, our technique is broadly applicable to earlier image-based detection of many diseases currently diagnosed at advanced stages today.