Program, information processing method, and information processing device
A program causes a computer to execute processing including: acquiring an endoscope image captured by an endoscope; inputting the acquired endoscope image into a plurality of learning models learned so as to output diagnosis support information regarding a lesion included in the endoscope image; acquiring a plurality of pieces of diagnosis support information output from each of the learning models; and outputting a plurality of pieces of the acquired diagnosis support information and information regarding each of the learning models in association with each other. Alternatively, the program causes the computer to execute the processing of inputting the acquired endoscope image into one learning model, executing a plurality of determination logics to acquire a plurality of pieces of output diagnosis support information, and outputting a plurality of pieces of the acquired diagnosis support information and information regarding each of the learning models in association with each other is executed.
1. A non-transitory computer-readable storage medium containing a program for causing a computer to execute processing comprising:
acquiring an endoscope image captured by an endoscope including
an inserter having
a distal tip with an image sensor,
a bending section, and
a proximal section, the bending section being positioned between the distal tip and the proximal section;
a bend-preventer having a first end connected to the proximal section of the inserter, and a second end;
an operator having a first end connected to the second end of the bend-preventer, and a bender connected to the bending section of the inserter and configured to actuate bending of the bending section;
a processor; and
a cord one having one end connected to the operator and another end connected to the processor;
inputting, with the processor, the acquired endoscope image into a plurality of learning models learned so as to output diagnosis support information regarding a lesion included in the endoscope image;
acquiring, with the processor, a plurality of pieces of diagnosis support information output from each of the plurality of learning models; and
outputting, with the processor, a plurality of pieces of the acquired diagnosis support information and information regarding each of the plurality of learning models in association with each other, wherein
at least two learning models among the plurality of learning models include neural networks having the same layer configuration, and
each piece of training data for learning the two learning models is different.
2. The non-transitory computer-readable storage medium containing a program according to claim 1 , wherein
the information regarding each of the plurality of learning models includes information regarding a difference between the plurality of learning models.
3. The non-transitory computer-readable storage medium containing a program according to claim 1 , wherein
the endoscope image includes a plurality of endoscope images captured by the endoscope after a lapse of a predetermined period,
each of the plurality of endoscope images is input into each of the plurality of learning models,
a plurality of pieces of diagnosis support information for each of the plurality of endoscope images output from each of the plurality of learning models is acquired, and
a plurality of pieces of the acquired diagnosis support information and information regarding time points at which the plurality of endoscope images was captured are output in association with each other.
4. The non-transitory computer-readable storage medium containing a program according to claim 1 , wherein
an operation of selecting any learning model among the plurality of learning models is received,
diagnosis support information output from the selected learning model is acquired, and
the acquired diagnosis support information and information regarding the selected learning model are output in association with each other.
5. The non-transitory computer-readable storage medium containing a program according to claim 4 , wherein
information regarding the cumulative number of uses of each of the plurality of learning models is displayed.
6. The non-transitory computer-readable storage medium containing a program according to claim 1 , wherein
diagnosis support information regarding a lesion included in the endoscope image output from each of the plurality of learning models is the same type of information including at least one of the presence or absence of a lesion, the type of symptom of the lesion, a stage of symptom of the lesion, and a location of the lesion included in the endoscope image.
7. An information processing method for causing a computer to execute processing comprising:
providing an endoscope including
an inserter having
a distal tip with an image sensor,
a bending section, and
a proximal section, the bending section being positioned between the distal tip and the proximal section;
a bend-preventer having a first end connected to the proximal section of the inserter, and a second end;
an operator having a first end connected to the second end of the bend-preventer, and a bender connected to the bending section of the inserter and configured to actuate bending of the bending section;
a processor; and
a cord one having one end connected to the operator and another end connected to the processor;
acquiring, with the processor, an endoscope image captured by an endoscope;
inputting, with the processor, the acquired endoscope image into a plurality of learning models learned so as to output diagnosis support information regarding a lesion included in the endoscope image;
acquiring, with the processor, a plurality of pieces of diagnosis support information output from each of the plurality of learning models; and
outputting, with the processor, a plurality of pieces of the acquired diagnosis support information and information regarding each of the plurality of learning models in association with each other, wherein
at least two learning models among the plurality of learning models include neural networks having the same layer configuration, and
each piece of training data for learning the two learning models is different.
8. An information processing apparatus comprising:
an inserter having
a distal tip with an image sensor,
a bending section, and
a proximal section, the bending section being positioned between the distal tip and the proximal section;
a bend-preventer having a first end connected to the proximal section of the inserter, and a second end;
an operator having a first end connected to the second end of the bend-preventer, and a bender connected to the bending section of the inserter and configured to actuate bending of the bending section;
a processor; and
a cord one having one end connected to the operator and another end connected to the processor,
wherein the processor is configured to
acquire an endoscope image captured by the image sensor,
input the acquired endoscope image into a plurality of learning models learned so as to output diagnosis support information regarding a lesion included in the endoscope image, and
acquire a plurality of pieces of diagnosis support information output from each of the plurality of learning models, and output a plurality of pieces of the acquired diagnosis support information and information regarding each of the plurality of learning models in association with each other, wherein
at least two learning models among the plurality of learning models include neural networks having the same layer configuration, and
each piece of training data for learning the two learning models is different.