Unsupervised and quantitative intestinal ischemia detection using conditional adversarial network in multimodal optical imaging

Authors

Yaning Wang, Johns Hopkins University, Department of Electrical and Computer Engineering, Baltimore, Maryland, United States.
Laura Tiusaba, Children's National Hospital, Division of Colorectal and Pelvic Reconstruction, Washington, District of Columbia, United States.
Shimon Jacobs, Children's National Hospital, Division of Colorectal and Pelvic Reconstruction, Washington, District of Columbia, United States.
Michele Saruwatari, Children's National Hospital, Sheikh Zayed Surgical Institute, Washington, District of Columbia, United States.
Bo Ning, Children's National Hospital, Sheikh Zayed Surgical Institute, Washington, District of Columbia, United States.
Marc Levitt, Children's National Hospital, Division of Colorectal and Pelvic Reconstruction, Washington, District of Columbia, United States.
Anthony D. Sandler, Children's National Hospital, Sheikh Zayed Surgical Institute, Washington, District of Columbia, United States.
So-Hyun Nam, Dong-A University Medical Center, Department of Surgery, Busan, Republic of Korea.
Jin U. Kang, Johns Hopkins University, Department of Electrical and Computer Engineering, Baltimore, Maryland, United States.
Jaepyeong Cha, Children's National Hospital, Sheikh Zayed Surgical Institute, Washington, District of Columbia, United States.

Document Type

Journal Article

Publication Date

11-1-2022

Journal

Journal of medical imaging (Bellingham, Wash.)

Volume

9

Issue

6

DOI

10.1117/1.JMI.9.6.064502

Keywords

deep learning; dye-free tissue perfusion assessment; generative adversarial network; laser speckle contrast imaging; multimodal optical imaging; unsupervised anomaly detection

Abstract

PURPOSE: Intraoperative evaluation of bowel perfusion is currently dependent upon subjective assessment. Thus, quantitative and objective methods of bowel viability in intestinal anastomosis are scarce. To address this clinical need, a conditional adversarial network is used to analyze the data from laser speckle contrast imaging (LSCI) paired with a visible-light camera to identify abnormal tissue perfusion regions. APPROACH: Our vision platform was based on a dual-modality bench-top imaging system with red-green-blue (RGB) and dye-free LSCI channels. Swine model studies were conducted to collect data on bowel mesenteric vascular structures with normal/abnormal microvascular perfusion to construct the control or experimental group. Subsequently, a deep-learning model based on a conditional generative adversarial network (cGAN) was utilized to perform dual-modality image alignment and learn the distribution of normal datasets for training. Thereafter, abnormal datasets were fed into the predictive model for testing. Ischemic bowel regions could be detected by monitoring the erroneous reconstruction from the latent space. The main advantage is that it is unsupervised and does not require subjective manual annotations. Compared with the conventional qualitative LSCI technique, it provides well-defined segmentation results for different levels of ischemia. RESULTS: We demonstrated that our model could accurately segment the ischemic intestine images, with a Dice coefficient and accuracy of 90.77% and 93.06%, respectively, in 2560 RGB/LSCI image pairs. The ground truth was labeled by multiple and independent estimations, combining the surgeons' annotations with fastest gradient descent in suspicious areas of vascular images. The total processing time was 0.05 s for an image size of . CONCLUSIONS: The proposed cGAN can provide pixel-wise and dye-free quantitative analysis of intestinal perfusion, which is an ideal supplement to the traditional LSCI technique. It has potential to help surgeons increase the accuracy of intraoperative diagnosis and improve clinical outcomes of mesenteric ischemia and other gastrointestinal surgeries.

APA Citation

Wang, Yaning; Tiusaba, Laura; Jacobs, Shimon; Saruwatari, Michele; Ning, Bo; Levitt, Marc; Sandler, Anthony D.; Nam, So-Hyun; Kang, Jin U.; and Cha, Jaepyeong, "Unsupervised and quantitative intestinal ischemia detection using conditional adversarial network in multimodal optical imaging" (2022). GW Authored Works. Paper 1985.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/1985

Department

Pediatrics