Automatic Method for Segmentation of Fluorescent Images Obtained in the Near-Infrared Region

Abstract

Introduction. Near-infrared fluorescence imaging technology is widely used in laparoscopic surgery. Intraoperative fluorescence navigation is based on accurate segmentation of fluorescent regions in near-infrared images (NIR images), thus increasing the accuracy and safety of surgical intervention. Moreover, it is an important auxiliary technology for laparoscopic surgery. Therefore, the search for an automatic method that allows for accurate segmentation of fluorescent regions in NIR images can contribute to an improved efficiency of intraoperative navigation.Aim. Development of a method for automatic segmentation of fluorescent images obtained in the near infrared range. Materials and methods. The proposed method consists of two stages. At the first stage, a preliminary segmentation of the image is performed based on the adaptive threshold found by Otsu’s method. At the second stage, the segmented area is refined using Otsu’s weighted method. The main advantage of the proposed method consists in the automatic determination of parameter α, which determines the performance of Otsu’s weighted method. Experiments were carried out using 276 actual laparoscopic images. The metric misclassification error (ME) was used to assess the quality of segmentation.Results. The average ME of the proposed method was found to be 10.4 %, compared to that obtained by the conventional Otsu’s method of 27.1 %.Conclusion. In comparison with Otsu’s method, the developed method shows an increased efficiency and accuracy of fluorescent image segmentation. This allows for a higher diagnostic accuracy and a more efficient navigation during laparoscopic surgery.