Abstract
ABSTRACT Surgical workflow analysis has gained greater attention in enhancing patient safety and obtaining optimal surgery results. However, automated recognition and classification of surgical phases are highly challenging due to several problems like higher computational complexities, increased time consumption, reduced learning ability, etc. Thus, the proposed study intends to develop an effective surgical workflow recognition and classification mechanism. Initially, the video annotation software is used convert the laparoscopic input videos into several frames for developing a proper recognition system. Then, an Exaggerated Series Wiener Bilateral Filtering (E-SWBF) approach is used in the pre-processing stage for preserving the edges removing the noises. After pre-processing, the spatial and temporal features are extracted through the attention-based convolutional Inception Bi-directional Long Short Term Memory (Attn_conv Inc_2DLSTM) model. Next, the feature dimensionality issue is reduced by selecting significant features through an Enhanced binary Aquila optimization (EBiAO) algorithm. Finally, the surgical phases are recognized and classified by the proposed Gated capsule tweaked autoencoder model (Gcaps_TAE). The obtained values of accuracy 98.95%, precision 96.55%, sensitivity 96.90%, specificity 99.23%, F1-score 96.72%, MSE 0.30%, and MAE 0.101% shows that the proposed model is superior to other existing methods.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call