It is clinically important to detect liver fat content as it is related to cardiac complications and cardiovascular disease mortality. However, existing methods are associated with high cost and/or medical complications (e.g., liver biopsy, medical imaging technology) or only roughly estimate the grades of steatosis. In this paper, we propose a deep neural network to accurately estimate liver fat percentage using only body shapes. The proposed framework is composed of a flexible baseline regression network and a lightweight attention module. The attention module is trained to generate discriminative and diverse features, thus significantly improving performance. To validate our proposed method, we perform extensive tests on medical datasets. The experimental results validate our method and prove the efficacy of designing neural networks to predict liver fat using only body shape. Since body shapes can be acquired using inexpensive and readily available optical scanners, the proposed method promised to make accurate assessment of hepatic steatosis more accessible.