Objectives The aim of this study is to perform tooth numbering using deep learning algorithms on digital dental photographs, and to evaluate the success of these algorithms in determining the presence of frenulum, gingival hyperplasia and gingival inflammation which play an important role in periodontal treatment planning. Materials and Methods Six-hundred-fifty-four (n = 654) intraoral photographs were included in the study. A total of 16795 teeth in all photographs were segmented and the numbering of the teeth was carried out according to the FDI system. Two-thousand-four-hundred-and-ninety-three frenulum attachments (n = 2493), 1211 gingival hyperplasia areas and 2956 gingival inflammation areas in the photographs were labeled using the segmentation method. Images were sized before artificial intelligence (AI) training and data set was separated as training, validation and test groups. Yolov5 architecture were used in the creation of the models. The confusion matrix system and ROC analysis were used in the statistical evaluation of the results. Results When results of study were evaluated; sensitivity, precision, F1 score and AUC for tooth numbering were 0.990, 0.784, 0.875, 0.989; for frenulum attachments were 0.894, 0.775, 0.830 and 0.827; for gingival hyperplasia were 0.757, 0.675, 0.714, 0.774; for gingival inflammation were 0.737, 0.823, 0.777, 0.802 (respectively). Conclusions There is a need for more comprehensive studies to be carried out on this subject by increasing the number of data and the number of parameters evaluated. Clinical relevance The current study showed that in the future, periodontal problem determination from dental photographs could be performed using AI systems.