Descriptive Model for Phase Prediction & ML for Laparoscopic Surgery
Priyanka Tayde1, Durgesh Mishra2

1Priyanka Tayde, Computer Science and Engineering, RGPV, Sri Aurobindo Institute, Indore, MP, India.
2Dr Durgesh Mishra, Computer Science and Engineering, RGPV, Sri Aurobindo Institute, Indore, MP, India.
Manuscript received on March 01, 2019. | Revised Manuscript Received on March 20, 2019. | Manuscript published on March 20, 2019. | PP: 7-10 | VVolume-5 Issue-3, March 2019. | Retrieval Number: C0874035319/19©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: In area of non-invasive diagnosis of endometriosis is now accurately obtained by laparoscopic surgery. It involves the excision of the endometriosis, scar tissue and developed adhesions. In this surgery doctor visualize abdominal-pelvic region via laparoscope, telescopic lens, light sources and video camera.In our paper we demonstrate a system that uses descriptive model for phases that are generated from segmented form of video through extended use of corsets with effective non-monotonic phase sequences, which is an interactive model for visual summary of laparoscopic and robot-assisted surgeries. Such model may reduce learning curves in the OR for junior surgeons with limited access to complex laparoscopic procedures as a primary operator. In this procedure we are using a combination of SVM (Support Vector Machine) and HMM (Hidden Markov Model).We generated a formal descriptive model of surgical phases which is required for laparoscopic surgery for better understanding of surgical training and to improve patient outcomes. We used descriptive model of machine learning for high accuracy in Phase predictions and bag-of-words (BOW) model for final frame representation. We evaluated our system in various experiments in real time operating environment of surgery room as well as collected data sets
Keywords: SVM; HMM; BOW, PRONET; Index Terms: About four key words or phrases in alphabetical order, separated by commas.