Image compression may reduce storage needs whether in the lossless (reversible) or lossy (irreversible) form. The aims of the study were to evaluate (1) storage needs, (2) subjective image quality, and (3) accuracy of caries detection in digital radiographs compressed to various levels by a lossy compression method. The material consisted of 116 extracted human premolars and molars. The teeth were mounted three in a line and radiographed by the Digora system (Sorodex Medical Systems, Helsinki, Finland). The images were exported in tagged image file format and compressed with the Lempel-Ziv-Welch reversible and the Joint Photographic Experts Group irreversible compression algorithm on four levels. The total of 580 images were assessed by five observers on a 5-rank confidence scale for caries diagnosis. The observers subjectively judged image quality on an 11-point rank scale. With the reversible compression, images could be compressed to less than 50% of the original storage needs whereas the four irreversible compression factors compressed to 20%, 8%, 5%, and 3%, respectively. For occlusal surfaces, when receiver operating characteristic curve areas were increasingly smaller and the compression rate was higher. The difference between the original and the most compressed images was 14% (p = 0.1). The median quality score was above middle on the 11-point rank scale for all except the most compressed images (median score = 1). In conclusion, for caries diagnosis, compression ratio rates of 1:12 can be justified before accuracy and image quality is significantly affected.