Development of detection method for automatic hemostasis using machine learning with abdominal cavity irrigation
DOI:
https://doi.org/10.18203/2349-2902.isj20202547Keywords:
Endoscopic image processing, Support vector machine, Urology, WaFLESAbstract
Background: Abdominal cavity irrigation is a more minimally invasive surgery than that using a gas. Minimally invasive surgery improves the quality of life of patients; however, it demands higher skills from the doctors. Therefore, the study aimed to reduce the burden by assisting and automating the hemostatic procedure a highly frequent procedure by taking advantage of the clearness of the endoscopic images and continuous bleeding point observations in the liquid. We aimed to construct a method for detecting organs, bleeding sites, and hemostasis regions.
Methods: We developed a method to perform real-time detection based on machine learning using laparoscopic videos. Our training dataset was prepared from three experiments in pigs. Linear support vector machine was applied using new color feature descriptors. In the verification of the accuracy of the classifier, we performed five-part cross-validation. Classification processing time was measured to verify the real-time property. Furthermore, we visualized the time series class change of the surgical field during the hemostatic procedure.
Results: The accuracy of our classifier was 98.3% and the processing cost to perform real-time was enough. Furthermore, it was conceivable to quantitatively indicate the completion of the hemostatic procedure based on the changes in the bleeding region by ablation and the hemostasis regions by tissue coagulation.
Conclusions: The organs, bleeding sites, and hemostasis regions classification was useful for assisting and automating the hemostatic procedure in the liquid. Our method can be adapted to more hemostatic procedures.
References
Navaratnam A, Muhsin AH, Humphreys M. Updates in urologic robot assisted surgery. 2018;(7):1000.
Greco F, Cadeddu JA, Gill IS. Current perspectives in the use of molecular imaging to target surgical treatments for genitourinary cancers. Eur Urol. 2014;65:947-64.
Gcurr O, Lazzara S, Barbera A, Cogliandolo A. The Aquamantys® system as alternative for parenchymal division and hemostasis in liver resection for hepatocellular carcinoma: a preliminary study. Eur Rev Med Pharmacol Sci. 2014(18):2-5.
Takahashi H, Haraguchi N, Nishimura J. A novel suction/coagulation integrated probe for achieving better hemostasis: development and clinical use. Surg Today. 2018;48:649-55.
Emiliani E, Talso M, Haddad M. The true ablation effect of holmium YAG Laser on soft tissue. J Endourol. 2018;32:230-5.
Huusmann S, Wolters M, Kramer MW. Tissue damage by laser radiation: an in vitro comparison between Tm: YAG and Ho: YAG laser on a porcine kidney model. Springerplus. 2016;5:266.
Igarashi T, Ishii T, Aoe T, Yu W. Small-incision laparoscopy-assisted surgery under abdominal cavity irrigation in a porcine model. J Laparoendosc Adv Surg Tech A. 2016;26:122-8.
Lee YT, Ryu YW, Lee DM. Comparative analysis of the efficacy and safety of conventional transurethral resection of the prostate, transurethral resection of the prostate in saline (TURIS), and TURIS-plasma vaporization for the treatment of benign prostatic hyperplasia: a pilot study. Korean J Urol. 2011;52:763-8.
Igarashi T, Shimomura Y, Yamaguchi T. Water-filled laparoendoscopic surgery (Wafles): feasibility study in porcine model. J Laparoendosc Adv Surg Tech A. 2012;22:70-5.
Liu J, Yuan X. Obscure bleeding detection in endoscopy images using support vector machines. Optim Eng. 2009;10:289-99.
Yanan F, Zhang W, Mandal M. Computer-aided bleeding detection in WCE video. IEEE J Biomed Health Inf. 2014;8:636-42.
Kumar R, Zhao Q, Seshamani S. Assessment of Crohn’s disease lesions in wireless capsule endoscopy images. IEEE Trans Biomed Eng. 2012;59:355-62.
Li B, Meng MQ. Computer-aided detection of bleeding regions for capsule endoscopy images. IEEE Trans Biomed Eng. 2009;56:1032-9.
Li B, Meng MQ, Lau JY. Computer-aided small bowel tumor detection for capsule endoscopy. Artif Intell Med. 2011;52:11-6.
Li B, Meng MQ. Tumor recognition in wireless capsule endoscopy images using textural features and SVM-based feature selection. IEEE Trans Inf Technol Biomed. 2012;16:323-9.
Hassan AR, Haque MA. Computer-aided gastrointestinal hemorrhage detection in wireless capsule endoscopy videos. Comput Methods Programs Biomed. 2015;122:341-53.
Okamoto T, Ohnishi T, Kawahira H. Real-time identification of blood regions for hemostasis support in laparoscopic surgery. Signal Image Video Process. 2019;13:405-12.
Vapnik VN. Statistical Learning Theory, New York, Wiley; 1998: 375-570.
Allwein E, Schapire R, Singer Y. Reducing multiclass to binary: a unifying approach for margin classifiers. J Mach Learn Res. 2000;1:113-410.
Smith AR. Color gamut transform pairs. ACM Siggraph Computer Graphics. 1987;12:12-9.
Weiss SM. Small sample error rate estimation for k-nearest neighbor classiers. IEEE Transactions Pattern Analysis Machine Intel ligence. 1991;13(3): 285-9.
Nikfarjam M, Kimchi ET, Gusani NJ. Reduction of surgical site infections by use of pulsatile lavage irrigation after prolonged intra-abdominal surgical procedures. Am J Surg. 2009;198:381-6.
Tovar RJ, Santos J, Arroyo A. Effect of peritoneal lavage with clindamycin-gentamicin solution on infections after elective colorectal cancer surgery. J Am Coll Surg. 2012;214:202-7.
Hesami MA, Alipour H, Nikoupour DH. Irrigation of abdomen with imipenem solution decreases surgical site infections in patients with perforated appendicitis: a randomized clinical trial. Iran Red Crescent Med J. 2014;16:12732.
Artal MR, Montiel JMM, Tardos JD. ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans Robot. 2015;31:1147-63.
Baker S, Scharstein D, Lewis JP, Roth S, Black MJ, Szeliski R. A database and evaluation methodology for optical flow. Int J Comput Vis. 2011;92:1-31.