Adaptive kernel selection network with attention constraint for surgical instrument classification

Abstract

Computer vision (CV) technologies are assisting the health care industry in many respects, i.e., disease diagnosis. However, as a pivotal procedure before and after surgery, the inventory work of surgical instruments has not been researched with the CV-powered technologies. To reduce the risk and hazard of surgical tools’ loss, we propose a study of systematic surgical instrument classification and introduce a novel attention-based deep neural network called SKA-ResNet which is mainly composed of: (a) A feature extractor with selective kernel attention module to automatically adjust the receptive fields of neurons and enhance the learnt expression and (b) A multi-scale regularizer with KL-divergence as the constraint to exploit the relationships between feature maps. Our method is easily trained end-to-end in only one stage with few additional calculation burdens. Moreover, to facilitate our study, we create a new surgical instrument dataset called SID19 (with 19 kinds of surgical tools consisting of 3800 images) for the first time. Experimental results show the superiority of SKA-ResNet for the classification of surgical tools on SID19 when compared with state-of-the-art models. The classification accuracy of our method reaches up to 97.703%, which is well supportive for the inventory and recognition study of surgical tools. Also, our method can achieve state-of-the-art performance on four challenging fine-grained visual classification datasets.

Guidewire Endpoint Detection Based on Pixel‐Adjacent Relation during Robot‐Assisted Intravascular Catheterization: In Vivo Mammalian Models

“…The parameter initialization method is used to generate random tensors according to Xavier normal distribution. The deep learning Adam optimizer [ 15 ] is selected. The following deep learning network provides fast iterations If the validation loss does not decrease for every 3 epochs, the learning rate is reduced to half of the original value.…”

“…[12] ResNet101 and ResNet152 are intuitive extensions of ResNet-50, and therefore, they can generate high-quality object predicting results of the image. [13][14][15] The Hourglass network model is one of the most popular models for instance segmentation and can accomplish instance detection and segmentation for each instance in a single model. [16] Zhou et al [17] introduced an enhanced RetinaNet network, incorporating an ResNet18-based encoder to generate feature maps and a dedicated subnetwork for needle detection.…”

Surgical Tool Datasets for Machine Learning Research: A Survey

“…The authors then developed RT-MDNet, a real-time multi-domain convolutional neural network with three convolutional layers, a Region of Interest Alignment (RoIAlign) layer and three fully connected layers, and tested it on the STT Dataset. Hou et al (2022) introduced an attention-based deep neural network-SKA-ResNet-composed of a feature extractor with a selective kernel attention module and a multi-scale regularizer to exploit the relationships between feature maps. Their SKA-ResNet was tested on a new surgical instrument dataset called SID19 for the classification of surgical tools.…”

The recognition of surgical tools based on attention mechanism

“…In their research, the types of devices included were unique, with significant differences between instruments categories, and there were no significant recognition difficulties. Hou et al [12] proposed a new deep neural network based on SKA attention to classify similar targets in 19 surgical instruments with an average accuracy of 97.042%. However, the captured instrument images have a simple background and do not have significant background interference.…”