Evaluation of Deep Learning Techniques on a Novel Hierarchical Surgical Tool Dataset

Abstract

A new hierarchically organised dataset for artificial intelligence and machine learning research is presented, focusing on intelligent management of surgical tools. In addition to 360 surgical tool classes, we create a four level hierarchical structure for our dataset defined by 2 specialities, 12 packs and 35 sets. We employ different convolutional neural network training strategies to evaluate image classification and retrieval performance on this dataset, including the utilisation of prior information in the form of a taxonomic hierarchy tree structure. We evaluate the effects of image size and the number of images per class on model predictive performance. Experiments with the mapping of image features and class embeddings in semantic space using measures of semantic similarity between classes show that providing prior information results in a significant improvement in image retrieval performance on our dataset.

Minimization of occurrence of retained surgical items using machine learning and deep learning techniques: a review

“…Owing to their capability of extracting image features at different levels of hierarchy, convolutional neural networks (CNNs) Table 3 Machine learning methods key findings, prominent advantages, and disadvantages are crucial to image processing tasks [28]. One of the strengths of this model is that it is very useful for applications that require real-time tracking; thereby, it can be used for surgical tool detection during operations [29]. Spatial transformer networks (STNs) combine with convolutional neural networks to make it possible to adjust spatial data.…”

“…The authors in [29] developed a novel hierarchically organized dataset for research emphasizing intelligent surgical equipment management. A four-level hierarchical framework and 360 separate surgical instrument categories were applied to the dataset.…”

“…The HOS-PITools dataset in [29] contains 360 surgical instrument classifications organized hierarchically across four tiers, which is an essential resource for the study. CNNs and other DL approaches can be investigated for usage in image categorization and retrieval applications.…”

Surgical Tool Datasets for Machine Learning Research: A Survey

“…Further, all the datasets surveyed in our paper have a flat structure. Given that fact that surgery is organised along specialities (Table 7), and each speciality has separate underlying categories, a hierarchical classification of surgical tools in the datasets provided for machine learning research has been shown to be extremely valuable (Rodrigues et al, 2022(Rodrigues et al, , 2021a.…”