Objective To investigate the effects of accelerated repetitive transcranial magnetic stimulation （arTMS） based on resting-state functional magnetic resonance imaging （rs-fMRI） in patients with melancholic depressive disorder and to characterize the functional brain imaging changes. Methods Forty patients who visited the Second People's Hospital of Guizhou Province from August 2021 to November 2023 and were diagnosed with melancholic depressive disorder were selected for the study. The patients were randomly divided into study group and pseudo-stimulation group using the random number table method， with 20 cases in each group. Conventional medication was given to both groups， where patients in study group were given arTMS for five consecutive days， and pseudo-stimulation was given to pseudo-stimulation group. Patients in both groups received one 24-item Hamilton Depression Scale （HAMD-24） assessment and rs-fMRI scan before treatment and on the day of the end of treatment. The changes of HAMD-24 scores and regional homogeneity （ReHo） values and functional connectivity （FC） values before and after treatment were analyzed in both groups， and the correlation between rs-fMRI indexes and HAMD-24 score reduction rate was further calculated using Pearson correlation. Results Thirty-six patients were finally included， 19 in study group and 17 in pseudo-stimulation group. Before treatment， the difference in HAMD-24 scores between the two groups was not statistically significant （P ＞ 0.05）. After treatment， the HAMD-24 scores of patients in both groups were lower than those before treatment， and the HAMD-24 scores of patients in study group were lower than those in pseudo-stimulation group， and the differences were statistically significant （all P ＜ 0.05）. There was no statistically significant difference in the ReHo values of brain regions before and after treatment in pseudo-stimulation group （P ＞ 0.05）. After five days of arTMS， the ReHo value of the right fusiform gyrus of the patients in study group was statistically reduced （t=-4.723， P ＜ 0.05）， and the FC value of the right fusiform gyrus with the right middle temporal gyrus and the right angular gyrus was statistically reduced （P ＜ 0.05）. Correlation analysis showed that the pre-treatment FC values of the right middle temporal gyrus and the right fusiform gyrus were negatively correlated with the HAMD-24 score reduction rate in study group patients， and the difference was statistically significant （r=-0.50， P＜ 0.05）. Conclusions arTMS improves depressive symptoms in patients with melancholic depressive disorder. arTMS treatment may affect patients' right fusiform gyrus function， and the pre-treatment FC values of the right fusiform gyrus and the right middle temporal gyrus can be used as a predictor of efficacy of arTMS in the treatment of melancholic depressive disorder.