Endoscope apparatus, endoscope operation method, and program

An endoscope apparatus comprising one or more processors, configured to:

• acquire, in a case where a lesion is detected from time-series images captured during an endoscopic examination period, acquired lesion information that indicates at least one of a first lesion image representing the detected lesion or a feature value indicating a feature of the first lesion image;
• identify a lesion from the time-series images;
• count a lesion count, which is the number of lesions detected in a single endoscopic examination;
• display the lesion count counted;
• output a division instruction for dividing the endoscopic examination into a first examination that is performed at the time of insertion of a scope and a second examination that is performed at the time of withdrawal of the scope;
• in the first examination,
• compare existing lesion information, which is the acquired lesion information previously, with the a newly acquired lesion information and determine whether the newly acquired lesion information indicates the same lesion indicated by the existing lesion information, and
• increment the lesion count counted by one when the one or more processors determines that the newly acquired lesion information does not indicate the same lesion indicated by the existing lesion information, and
• in the second examination that follows the first examination,
• compare the existing lesion information previously acquired in the first examination with the acquired lesion information newly acquired in the second examination and determine whether the newly acquired lesion information indicates the same lesion indicated by the existing lesion information previously acquired in the first examination,
• decrement a remaining lesion count by one to update the remaining lesion count, the remaining lesion count being the lesion count when the first examination is completed, in a case where the one or more processors determines that the newly acquired lesion information indicates the same lesion indicated by the existing lesion information previously acquired in the first examination, and
• display the remaining lesion count on the basis of the remaining lesion count.

An endoscope operation method comprising:

• acquiring, in a case where a lesion is detected from time-series images captured during an endoscopic examination period, acquired lesion information that indicates at least one of a first lesion image representing the detected lesion or a feature value indicating a feature of the first lesion image;
• comparing an existing feature value indicating a feature of a second lesion image in existing lesion information, which is the acquired lesion information previously, with the feature value that indicates the feature of the first lesion image in a newly acquired lesion information and determining whether the newly acquired lesion information indicates the same lesion indicated by the existing lesion information on basis of whether a similarity between the existing feature value and the feature value is equal to or higher than a threshold value;
• counting a lesion count, which is the number of lesions detected in a single endoscopic examination;
• controlling to display the lesion count;
• and
• incrementing the lesion count by one when determining that the newly acquired lesion information does not indicate the same lesion indicated by the existing lesion information.

A non-transitory computer readable recording medium storing a program causing a computer to perform an endoscope operation process comprising:

• acquiring, in a case where a lesion is detected from time-series images captured during an endoscopic examination period, acquired lesion information that indicates at least one of a first lesion image representing the detected lesion or a feature value indicating a feature of the first lesion image;
• comparing an existing feature value indicating a feature of a second lesion image in existing lesion information, which is the acquired lesion information previously, with the feature value that indicates the feature of the first lesion image in a newly acquired lesion information and determining whether the newly acquired lesion information indicates the same lesion indicated by the existing lesion information on basis of whether a similarity between the existing feature value and the feature value is equal to or higher than a threshold value;
• counting a lesion count, which is the number of lesions detected in a single endoscopic examination;
• controlling to display the lesion count;
• and
• incrementing the lesion count by one when determining that the newly acquired lesion information does not correspond to the same lesion indicated by the existing lesion information.