Visible near-infrared hyperspectral imaging and supervised classification for the detection of small intestinal necrosis tissue in vivo

Abstract

Complete recognition of necrotic areas during small bowel tissue resection remains challenging due to the lack of optimal intraoperative aid identification techniques. This research utilizes hyperspectral imaging techniques to automatically distinguish normal and necrotic areas of small intestinal tissue. Sample data were obtained from the animal model of small intestinal tissue of eight Japanese large-eared white rabbits developed by experienced physicians. A spectral library of normal and necrotic regions of small intestinal tissue was created and processed using six different supervised classification algorithms. The results show that hyperspectral imaging combined with supervised classification algorithms can be a suitable technique to automatically distinguish between normal and necrotic areas of small intestinal tissue. This new technique could aid physicians in objectively identify normal and necrotic areas of small intestinal tissue.

Discrimination between normal and necrotic small intestinal tissue using hyperspectral imaging and unsupervised classification

“…Depending on the spectral imaging method, there are four forms of HSI: whiskbroom, pushbroom, staring, and snapshot [20]. The HSI system for small intestine tissue was self‐constructed before data acquisition [39]. The hyperspectral camera (SOC710‐VP, USA) was built with a push‐sweep shape and was stably fixed on a horizontal rail.…”

“…In addition, the noise signals before 400 nm and after 1000 nm in the spectral band were removed, and the spectral information between 400 and 1000 nm was retained for subsequent analysis. The general framework of the above preprocessing is shown in Figure 4, and the specific preprocessing methods were described in detail in [39].…”

“…To develop a model of small intestinal tissue ischemia, the rabbits' abdomens were dissected. Therefore, the doctor must induce anesthesia in the rabbits before dissection [39].…”

Automatic detection of ischemic necrotic sites in small intestinal tissue using hyperspectral imaging and transfer learning

“…The data acquisition scenario is shown in Figure 2. The system was mainly composed of a hyperspectral camera (SOC710VP, San Diego, CA, USA), a halogen light source (LOWEL PRO, Burbank, CA, USA), the data acquisition software (SOC, San Diego, CA, USA) and the optical darkroom [37]. The power of the light source is 100 W. The spectral range of the hyperspectral camera is 376-1038 nm in 128 bands.…”

“…In the biomedical field, many researchers and scholars used HSI in combination with machine learning techniques to objectively identify tissues with different pathologies. Our previous studies have used HSI and machine learning to differentiate between normal and necrotic sites of small intestinal tissue [37]. Training a classification model using a priori information from multiple samples enables the automated identification of new samples.…”