Ultrasound technologies allow for a non-invasive assessment of mammary gland (MG) development, the differentiation between the tissue types of the MG, and the evaluation of changes in its composition. This study aimed to work out a detailed description of the different stages of MG development that are visually discernible by ultrasonography for providing a template to classify the different structures. With this basis, the qualitative categorization of the developmental stage, as well as further quantitative assessments via pixel densities in the structures of interest, should be facilitated. Ultrasonic images were acquired from all four quarters of 37 German Holstein heifer calves fed either at a high feeding level of milk replacer (MR; 14% solids) at 10 L/day (1.4 kg MR/day; HI, n = 18) or at a restrictive low level of 5.7 L/day (0.8 kg MR/day; RES, n = 19) until linear weaning from week 13 to 14 of life. Ultrasound MG scans were performed first in week 3 of life, fortnightly from week 8-16, and in week 20 of life, in standing position, of each quarter, using a B-mode ultrasound device equipped with a linear probe (18 MHz). The developmental stages of the mammary gland parenchyma (PAR), visible in ultrasound images, obtained over 20 weeks of life, were categorized, described, and drawn by hand. On this basis, a template for classifying the visible categories of mammary PAR development and its surrounding tissue (SURR), and for measuring their pixel brightness was created thus providing an ultrasonographic atlas of the developing bovine MG, describing 11 categories. The ultrasound images were further classified by PAR structure, and pixel brightness was measured in PAR and SURR by using ImageJ Fiji. The difference in pixel brightness between PAR and SURR, the delta (Δ) pixel value was calculated. With increasing age, higher atlas categories of PAR developmental stages were shown. Pixel values, i.e. the brightness of PAR, its SURR, and Δ pixel value changed with age but were neither affected by the feeding group nor by a group × time interaction. With progressing PAR development, its pixel brightness increased from week 10 to 20 of life, i.e., the PAR became more hyperechoic since it spread and grew into its SURR. The atlas can serve as a template for the categorization and qualitative assessment of MG structures and for the quantitative assessment of PAR's development by measuring pixel brightness. With our study, we could show the structural development in PAR as well as in SURR in MG simultaneously in early life and confirm the spreading of PAR into its SURR by ultrasound scanning.