Information processing system, endoscope system, information storage medium, and information processing method

A non-transitory information storage medium storing therein a trained model, the trained model being used for causing a computer to function to execute detection processing of accepting an input of a detection image to a neural network and detecting an object, and cause a display device to display detected information indicating a position and shape of the object in the detection image superimposed on the detection image, the neural network comprising:

• an input layer taking input data:
• an intermediate layer executing computation processing on the data input through the input layer;
• and
• an output layer outputting data based on a computed result output from the intermediate layer, and
• the trained model being trained to output the position and shape of the object in the training image based on training data, the training data being provided with an annotation indicating the position and shape of the object, the annotation being attached to the training image captured with an angle of view including an object whose position and shape are not clearly displayed in an image.

An information processing method of executing detection processing based on a trained model, the trained model being trained to output the position and shape of the object in the training image based on training data, the training data being provided with an annotation indicating the position and shape of the object, the annotation being attached to the training image captured with an angle of view including an object whose position and shape are not clearly displayed in an image,

• the method comprising:
• executing the detection processing based on the trained model on a detection image captured with an angle of view including the object, to output detected information indicating the position and shape of the object;
• and
• causing a display device to display the detected information superimposed on the detection image.