According to an embodiment, a medical image processing device includes a processor, and a memory. The memory that stores processor-executable instructions that, when executed by the processor, cause the processor to execute acquiring a first perspective image of a subject viewed in a first direction setting a first region and a second region on the first perspective image, the first region including a first group of pixels around a target pixel, the second region including a second group of pixels, the second group including a pixel not included in the first group calculating a likelihood of the target pixel, wherein the likelihood increases as a difference between pixel values included in the first group decreases and a difference between pixel values of the first group and the second group increases and detecting a position of an object in the subject based on the likelihood.