Related Experiment Video
Updated: Jul 12, 2025
09:33
Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
Published on: July 28, 2013
28.5K
Wasserstein HOG: Local Directionality Extraction via Optimal Transport.
IEEE Transactions on Medical Imaging
|October 24, 2023
Summary
This study introduces a novel method to extract robust radiomic features from medical images, improving cancer outcome prediction. Higher image directionality entropy correlates with worse survival, while reduction in entropy indicates better outcomes.
Area of Science:
- Radiology and Medical Imaging
- Computational Biology
- Oncology
Background:
- Directionally sensitive radiomic features like Histogram of Oriented Gradients (HOG) show promise in cancer outcome prediction.
- Radiomic features are often sensitive to imaging variability, limiting clinical applicability.
- Robust extraction of local directionality features is crucial for reliable quantitative imaging biomarkers.
Purpose of the Study:
- To develop a robust, training-free method for extracting local directionality features from medical images.
- To assess the utility of these features in quantifying tumor heterogeneity and predicting outcomes across different cancer types.
- To investigate the correlation between image directionality entropy and patient survival in glioblastoma, head and neck cancer, and lung cancer.
Main Methods:
- A novel approach using optimal transport to map image patches to iso-intense patches, decomposing the transport map into directional components.
- Evaluation on MRI scans of glioblastoma, CT scans of head and neck squamous cell carcinoma, and longitudinal CT scans of lung cancer patients.
- Quantification of tumor heterogeneity by analyzing the entropy of extracted local directionality within tumor regions.
Main Results:
- Higher image directionality entropy within tumors was significantly associated with worse overall survival across all three evaluated cancer datasets.
- A reduction in entropy from baseline CT scans in lung cancer patients undergoing immunotherapy correlated with longer overall survival (HR=1.95, p=1.65e-5).
- The proposed method demonstrated robustness and training-free characteristics for quantifying local image directionality.
Conclusions:
- Local image directionality, quantified by entropy, serves as a potential imaging biomarker for tumor malignancy and patient prognosis.
- The developed optimal transport-based method offers a robust and versatile tool for extracting reliable radiomic features.
- This approach has the potential to enhance clinical decision-making by providing objective measures of tumor characteristics and treatment response.
Related Concept Videos
01:14Extraction: Partition and Distribution Coefficients
2.5K
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an...
For extracting a solute from an aqueous phase into an...
2.5K
01:24Reynolds Transport Theorem
1.2K
The Reynolds transport theorem provides a framework to relate the time rate of change of an extensive property within a system to that in a control volume, which is crucial for analyzing fluid dynamics. Extensive properties, such as mass, velocity, acceleration, temperature, and momentum, can be expressed in terms of the mass of a fluid portion. These properties are called extensive because they depend on the system's size, while intensive properties are their corresponding values per unit...
1.2K
01:42Directionality of Nuclear Transport
3.3K
Ras-related nuclear protein or Ran is a small G protein that cycles between its GTP and GDP bound states. Ran specific regulators, a Ran GTPase Activating Protein or RanGAP present in the cytosol and a Ran guanine nucleotide exchange factor or RanGEF present inside the nucleus regulate GTP/GDP exchange. A high concentration of GTP inside the cells, in addition to this asymmetric distribution of Ran-specific regulators, leads to a higher RanGTP concentration inside the nucleus. This...
3.3K
02:12Short-distance Transport of Resources
16.1K
Short-distance transport refers to transport that occurs over a distance of just 2-3 cells, crossing the plasma membrane in the process. Small uncharged molecules, such as oxygen, carbon dioxide, and water, can diffuse across the plasma membrane on their own. In contrast, ions and larger molecules require the assistance of transport proteins due to their charge or size. Transport across membranes also occurs within individual cells, playing a variety of essential roles for the plant as a whole.
16.1K
01:06Divergence and Stokes' Theorems
1.7K
The divergence and Stokes' theorems are a variation of Green's theorem in a higher dimension. They are also a generalization of the fundamental theorem of calculus. The divergence theorem and Stokes' theorem are in a way similar to each other; The divergence theorem relates to the dot product of a vector, while Stokes' theorem relates to the curl of a vector. Many applications in physics and engineering make use of the divergence and Stokes' theorems, enabling us to write...
1.7K
01:18Uniform Depth Channel Flow: Problem Solving
70
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
70