Deep learning enabled in vitro predicting biological tissue thickness using force measurement device

Accurate perception of biological tissues (BT) thickness is essential for preliminary evaluation of medical diagnosis and animal nutrition. However, traditional thickness measuring approaches of BT require complex operation, high-cost, and trigger biological stress response. Herein this study, an novel in vitro BT thickness measuring approach integrated with force test system (FST) and the discrete multiwavelet transform convolutional neural network (DMWA-CNN) prediction model based on deep learning are proposed. Simultaneously, several comprehensive experiments and model comparisons are conducted to demonstrate the superiority of the proposed approach. By establishing a DMWA-CNN demonstrates higher estimation accuracy than other traditional algorithm, achieving 100 % accuracy for artificial BT. Moreover, the experimental results indicate that proposed approach is robust to elastic modulus variation (E), external load variation (F), and small thickness differences (T_s). In addition, four kinds of the pork' thickness are experimentally measured, and the accuracy value is not less than 98.2 %. The thickness of BT determined using the FST and DMWA-CNN algorithm demonstrate potential application in the biomechanical parameter prediction.