An image conversion unit includes a selector and a plurality of image converters. Each image converter is formed from an estimator of machine learning type, and estimates, based on an image acquired under a first observation condition and as a reference image, an image which is presumed to be acquired under a second observation condition. When a particular reference image is selected from among a plurality of reference images displayed on a display, a second observation condition corresponding to the selected reference image is set in an observation mechanism as a next observation condition.