In measurement data selection, when a vector composed of measurement data obtained for respective combinations of light emitting positions, light detection positions, and resolving times in a time-resolved waveform is given as y, a vector in which pixel values of learning image data are components is given as x, and a system matrix for calculating internal image data from the measurement data is given as A1, the vector y which meets the conditional expressions (2) and (3) min∥y∥00  (2), ∥x−A1Ty∥22≦ε2  (3) or the conditional expression (4) min(∥y∥00+β∥x−A1Ty∥22)  (4) is determined, and upon measurement of a subject, only the measurement data corresponding to nonzero components of the vector y is used to prepare the internal image data.