Convolutional Neural Networks for Immediate Surgical Needle Automatic Detection in Craniofacial X-Ray Images.

Abstract

Immediate X-ray examination is necessary while the surgical needle falls off during operation. In this study, one convolutional neural network (CNN) model was introduced for automatically surgical needle detection in craniofacial X-ray images. The craniofacial surgical needle (5-0, ETHICON, USA) was localized in 8 different anatomic regions of 2 pig heads for bilateral X-ray examination separately. Thirty-two images were obtained finally which were cropped into fragmented images and divided into the training dataset and the test dataset. Then, one immediate needle detection CNN model was developed and trained. Its performance was quantitatively evaluated using the precision rate, the recall rate, and the f2-score. One 8-fold cross-validation experiment was performed. The detection rate and the time it took were calculated to quantify the degree of difference between the automatic detection and the manual detection by 3 experienced clinicians. The precision rate, the recall rate, and the f2-score of the CNN model on fragmented images were 98.99%, 92.67%, and 93.85% respectively. For the 8-fold cross-validation experiments, 26 cases of all the 32 X-ray images were automatically marked the right position of the needle (detection rate of 81.25%). The average time of automatically detecting one image was 5.8 seconds. For the 3 clinicians, 65 images of all the 32× 3 images were checked right (detection rate of 67.7%) with the average time-consuming of 33 seconds. In summary, after training with a large dataset, the CNN model showed potential for immediate surgical needle automatic detection in craniofacial X-ray images with better detection accuracy and efficiency than the conventional manual method.