Physicians usually diagnose the pathology of the thyroid gland by its volume. However, even if the thyroid glands are found and the shapes are hand-marked from ultrasound (US) images, most physicians still depend on computed tomography (CT) images, which are expensive to obtain, for precise measurements of the volume of the thyroid gland. This approach relies heavily on the experience of the physicians and is very time consuming. Patients are exposed to high radiation when obtaining CT images. In contrast, US imaging does not require ionizing radiation and is relatively inexpensive. US imaging is thus one of the most commonly used auxiliary tools in clinical diagnosis. The present study proposes a complete solution to estimate the volume of the thyroid gland directly from US images. The radial basis function neural network is used to classify blocks of the thyroid gland. The integral region is acquired by applying a specific-region-growing method to potential points of interest. The parameters for evaluating the thyroid volume are estimated using a particle swarm optimization algorithm. Experimental results of the thyroid region segmentation and volume estimation in US images show that the proposed approach is very promising.