Abstract: An image processing method according to an embodiment includes a specifying step, an inference step, and an integration step. In the specifying step, a first portion including a region corresponding to an anatomical site of a target and a second portion including a region different from the anatomical site are specified in the image. In the inference step, by using a deep learning model, segmentation of the region corresponding to the anatomical site is performed on the first portion and segmentation of the region different from the anatomical site is performed on the second portion, or classification and detection of an image including the region corresponding to the anatomical site is performed on the first portion and classification and detection of an image including the region different from the anatomical site is performed on the second portion. In the integration step, results of the respective processes are integrated for output.

Abstract: A model training device according to an embodiment of the present disclosure includes processing circuitry. The processing circuitry is configured to obtain an initial learning model by learning a data set including medical images as learning data. The processing circuitry is configured to evaluate the initial learning model by using a global metric, so as to obtain error data sets each having an outlier from among a plurality of data sets used in the evaluation. The processing circuitry is configured to obtain a plurality of error data set groups by grouping the plurality of error data sets while using a local metric. The processing circuitry is configured to specify model training information with respect to each of the error data set groups.