Breast cancer, a pervasive and life-threatening malignancy, predominantly affects women worldwide. Despite the widespread adoption of imaging technologies such as mammography for early-stage breast cancer detection, access to such specialized imaging equipment remains limited in low-income countries. Conversely, ultrasound imaging has demonstrated its efficacy as a cost-effective tool for tumor identification. The advent of portable ultrasound devices facilitates rapid and precise lesion diagnosis in the breast, circumventing the need for hospital visits. Nevertheless, the images procured by portable ultrasound devices are typically necessitated to be transmitted in a compressed format for remote evaluation by physicians. This compression process often introduces artifacts in medical images, complicating the delineation of tumorous regions. To address this challenge, we introduce a deep-learning solution in this paper. A novel wavelet convolutional neural network (CNN) architecture is conceived to learn and subsequently diminish the artifacts present in compressed ultrasound images. To achieve this, a diverse dataset comprising various types of breast ultrasound imagesmalignant, benign, and normalis utilized. Experimental outcomes indicate that the proposed method surpasses the denoising CNN in mitigating artifacts in compressed ultrasound images. This improved performance is particularly evident in the most compressed images, which are of significant interest. This research underscores the potential of deploying deep-learning techniques to enhance the quality of compressed medical images, thereby facilitating more accurate and efficient remote diagnoses.