Method and system for characterizing stool patterns of young infants
The invention provides a method of analysing the consistency of stool, including the steps of: providing stool of an infant, capturing, with a portable device comprising a camera, an image of the stool, providing the captured image to an input layer of a pre-trained convolutional neural network, CNN, processing the captured image using the CNN to obtain, from a final layer of the CNN, a classification vector and to obtain information about a predicted score from the classification vector, wherein at least the final layer of the CNN has been customized so that each element of the classification vector corresponds to a score of a stool analysis scale, and storing information about the predicted store.
1. A computer-implemented method of analysing the consistency of stool, comprising the steps of:
providing stool of an infant,
capturing, with a portable device comprising a camera, an image of the stool, wherein the image is a colour image,
providing the captured image to an input layer of a pre-trained convolutional neural network, CNN;
processing the captured image using the CNN to obtain, from a final layer of the CNN, a classification vector and to obtain a predicted score from the classification vector;
wherein at least the final layer of the CNN has been customized so that each element of the classification vector corresponds to a respective score of a stool analysis scale,
wherein processing the captured image includes,
detecting a colour of the stool,
observing a stool pattern, wherein the stool pattern includes the detected colour of the stool,
wherein each element of the classification vector includes a probability of the corresponding score of the stool analysis scale based on the observed stool pattern, and
wherein the predicted score is a score of the stool analysis scale corresponding to the element of the classification vector with the highest probability,
providing an indication, with the portable device comprising a display, based on the predicted score, that either everything is normal or that the stool is not behaving as expected, and
storing the predicted score and the captured image.
2. The method according to claim 1 , wherein the stool is provided in an open diaper.
3. The method according to claim 2 , wherein the predetermined conditions comprise at least one of a condition that the diaper is placed on a surface with a regular background or a condition that the diaper is the only object present in the image.
4. The method according to claim 1 , wherein the stool is provided in a potty, a bed pan, a toilet chair or a toilet with plateaus.
5. The method according to claim 1 , further comprising displaying, by the portable device, guiding information to meet predetermined conditions before capturing the image.
6. The method according to claim 5 , wherein the predetermined conditions comprise at least one of a condition that the stool is placed on a surface with a regular background or a condition that the stool is the only object present in the image.
7. The method according to claim 1 , wherein capturing the image comprises automatically capturing the image by the portable device when predetermined conditions are met.
8. The method according to claim 1 , wherein the information about the predicted score comprises at least one of the predicted score, the captured image of the stool, and the date and/or time at which the image was captured.
9. The method according to claim 1 , wherein processing the captured image using the CNN is performed by the portable device.
10. The method according to claim 1 , wherein processing the captured image using the CNN is performed by a server communicating with the portable device.
11. The method according to claim 1 , wherein the information about the predicted score is stored in at least one of the portable device or a server communicating with the portable device.
12. The method according to claim 1 , further comprising analysing a frequency in which the stool is produced, based on stored time information related to the predicted scores for a plurality of captured images.
13. Computer program product for analysing the consistency of stool, comprising:
a non-transitory computer readable medium comprising codes executable by at least one processor to execute a method according to claim 1 .
14. A system for analysing the consistency of stool, comprising:
a portable device comprising:
a camera configured to capture a colour image of a stool of an infant,
a controller configured to
provide the captured colour image to an input layer of a pre-trained convolutional neural network, CNN,
detect a colour of the stool based on the captured colour image,
observe a stool pattern, wherein the stool pattern includes the detected colour of the stool,
obtain from a final layer of the CNN, a classification vector; wherein at least the final layer of the CNN has been customized so that each element of the classification vector corresponds to a respective score of a stool analysis scale,
obtain information about a predicted score from the classification vector,
wherein each element of the classification vector includes a probability of the corresponding score of the stool analysis scale based on the observed stool pattern, and
wherein the predicted score is a score of the stool analysis scale corresponding to the element of the classification vector with the highest probability,
provide and indication, via a display of the portable device, based on the predicted score, that either everything is normal or that the stool is not behaving as expected, and
a memory for storing the predicted score and the captured image.
15. The system according to claim 14 , wherein the stool is provided in an open diaper.
16. The system according to claim 14 , wherein the stool is provided in a potty, a bed pan, a toilet chair, or a toilet with plateaus.
17. The system according to claim 14 , wherein the information about the predicted score comprises at least one of the predicted score, the captured image of the stool, and the date and/or time at which the image was captured.
18. The system according to claim 14 , further comprising a server for communicating with the portable device, wherein the server is configured to store the information about the predicted score.
19. The system according to claim 14 , wherein processing the captured image using the CNN to obtain the classification vector from a final layer of the CNN is performed by the portable device.
20. The system according to claim 14 ,
wherein the server is further configured to process the captured image using the CNN to obtain the classification vector from a final layer of the CNN, and
wherein the portable device is further configured to transmit the captured image to the server and to receive the predicted score from the server.