Systems and methods for segmentation and measurement of a skin abnormality
A method is proposed for identifying (“segmenting”) at least one portion of the skin of an animal which is a region of interest (e.g. a portion which is subject to an abnormality such as a tumor). The method uses at least a temperature dataset obtained by measuring the temperature of each of a plurality of points of a region of the skin. An initial segmentation may be performed using the temperature data based on a statistical model, in which each point is segmented based on its temperature and optionally that of its neighbors. The initial segmentation based on the temperature data may be improved using a three-dimensional model of the profile of the skin, and the enhanced segmentation may be used to improve the three-dimensional model.
1. A method of deriving one or more numerical parameters characterizing an abnormality under the skin of an animal, the method comprising:
identifying, from a three-dimensional model of the profile of a region of the skin of the animal, a portion of the skin which is subject to the abnormality and a portion of the skin which is not subject to the abnormality;
forming a baseline surface extending throughout the region of the skin which is subject to the abnormality, the baseline surface being an estimate of the portion of the skin excluding deformation caused by the abnormality; and
deriving, from the three-dimensional model of the profile of the skin and the baseline surface, the one or more numerical parameters characterizing the skin abnormality of the animal.
2. The method according to claim 1 , wherein the step of identifying, from the three-dimensional model of the profile of a region of the skin of the animal, the portion of the skin which is subject to the abnormality and the portion of the skin which is not subject to the abnormality comprises:
identifying, as the portion of the skin which is subject to the abnormality, a portion of the skin which does not satisfy a continuity criterion; and
identifying, as the portion of the skin which is not subject to the abnormality, a portion of the skin which satisfies the continuity criterion.
3. The method according to claim 2 , wherein satisfying the continuity criterion indicates that the portion of skin has a curvature below a threshold value and is spatially uniform throughout the portion.
4. The method according to claim 1 , wherein the one or more numerical parameters comprise a value indicative of a volume between the three-dimensional model and the baseline surface.
5. The method according to claim 1 , wherein the baseline surface comprises the portion of the skin which is not subject to the abnormality and one or more portions which are formed by interpolation using said portion of the skin which is not subject to the abnormality.
6. The method according to claim 1 , wherein the portion of the skin which is not subject to the abnormality surrounds the portion of the skin which is subject to the abnormality.
7. The method according to claim 1 further comprising an initial step of receiving a temperature dataset indicating the temperature of each of a plurality of points on the skin of the animal,
and wherein the portion of the skin which is subject to the abnormality and the portion of the skin which is not subject to the abnormality are identified from a three-dimensional model of the profile of a region of the skin of the animal and based on the temperature dataset.
8. The method according to claim 7 further comprising capturing the temperature data.
9. A system comprising a processor and a data storage device storing program instructions operative, when implemented by the processor, to cause the processor to derive one or more numerical parameters characterizing an abnormality under the skin of an animal, by:
identifying, from a three-dimensional model of the profile of a region of the skin of the animal, a portion of the skin which is subject to the abnormality and a portion of the skin which is not subject to the abnormality;
forming a baseline surface extending throughout the region of the skin which is subject to the abnormality, the baseline surface being an estimate of the portion of the skin excluding deformation caused by the abnormality; and
deriving, from the three-dimensional model of the profile of the skin and the baseline surface, the one or more numerical parameters characterizing the skin abnormality of the animal.
10. The system according to claim 9 further comprising a thermal imaging system for generating the temperature dataset.