Vol.2 No.1, May 30, 2024
Due to the remarkable development of artificial intelligence technology, a lot of efforts are being actively made to utilize it in robotics field. Medical robots are being developed in various types such as serial robots, parallel robots, and continuous robots, taking into account the patient’s anatomy and surgical method. For the precise control, researches are being conducted on accurate kinematic modeling and advanced control algorithms. However, there are limitations in applying traditional numerical approaches to some robots due to their high nonlinearity. Recently, learning-based techniques for kinematics analysis have been reported, demonstrating their potential as a promising solution to overcome nonlinearity. In this paper, we analyze the scope of application and research trends of artificial intelligence technology used in serial robots, parallel robots, and continuous robots, and discuss the possibility of learning-based control in medical robots and future research directions.
The level of sedation required for endoscopic procedures is moderate sedation, which was previously referred to as conscious sedation. This level of sedation allows the patient to maintain their airway independently and respond appropriately to physical stimulation or verbal commands. However, because sedation is a continuous process, it is difficult to predict the patient's response accurately, and the patient may reach a deeper level of sedation than intended. Therefore, various methods have been attempted recently to achieve an appropriate level of sedation. This paper aims to explore computer-assisted sedation systems.
Jun-Ha Park , Young Jae Kim , Kwang Gi Kim
J Innov Med Technol 2024; 2(1): 11-19Background: Minimally invasive surgery (MIS) and robot-assisted surgery have gained recognition as procedures safer than traditional laparotomy which facilitate faster patient recovery. However, MIS limits the sense of the surgeon. Therefore, a computer-assisted algorithm is proposed to assist in this surgery. With the advent of convolutional neural networks, machine vision technology has become an attractive option.
Materials and Methods: We use four networks, TernausNet, TernausResNet, LinkNet, and DeepLab V3+, to predict organ segments in endoscopy images. Furthermore, endoscopy images have several issues such as noise, hemorrhage, and shading. Therefore, we perform preprocessing and draw parallels between the images with and without preprocessing.
Results: The network with the lowest performance is TernausNet; the performances of the other three networks show marginal differences. The most significant factor for predicting performance is the encoder network. All networks demonstrate reliable performance with a minimum intersection over union score of 0.68 in TernausNet.
Conclusion: The segmentation of organs in images can be used for the quantitative evaluation of surgery and to help surgeons understand anatomy.
Kyonglin Park , Hongrae Kim , Hyoung-Jun Kim , Yongdoo Choi , Sung-Jae Park , Jae-Suk Park , Min-Kyu Choi , Dae Kyung Sohn
J Innov Med Technol 2024; 2(1): 20-24Background: The innovative use of the fluorescent dye indocyanine green (ICG) represents a significant advancement in surgical oncology. This study aimed to assess the feasibility of ICG-coated clips for enhancing tumor localization during minimally invasive gastrointestinal surgery.
Materials and Methods: This study was conducted using female Yucatan miniature pigs, which approximate the human anatomy. Two pigs, each weighing 25–30 kg, underwent simulated gastrointestinal surgery. The ICG-coated clips used were VITTZ clips, which were not yet approved by the Korea Food and Drug Administration but utilized for research purposes. The visibility of the clips was evaluated using Stryker 1588 and 1688 Advanced Imaging Modalities platforms with SPY fluorescence technology. The procedure involved the endoscopic placement of clips in the stomach and colon, followed by laparoscopic visualization using ICG imaging systems.
Results: The ICG-coated clips demonstrated superior visibility in both the stomach and colon. In the stomach, the Endoscopic Near-Infrared Visualization (ENV) mode revealed four bright spots on the gastric wall, with two distinctly visible in the overlay mode. Three bright fluorescent lights were discernible in the sigmoid colon using both imaging modes. The fluorescence intensity was slightly clearer in the ENV mode than in the overlay mode.
Conclusion: ICG-coated clips can improve tumor localization, which is important during minimally invasive gastrointestinal surgery. This innovative approach may provide safer and more accurate alternatives.
Sein Song , Jeesun Kim , Han Jo Jeon , Amy Kyungwon Han
J Innov Med Technol 2024; 2(1): 25-28Respiratory rate is a critical vital sign that is highly informative yet often overlooked due to the unavailability of appropriate measuring devices in hospitals. This paper introduces a novel respiratory rate sensor employing an open-mask design, which offers greater comfort and less obstruction compared to traditional covered face masks or mouthpieces. The sensor operates by detecting changes in capacitance caused by the flow of exhaled air and maintains stable measurements even when the user’s head is in motion. Additionally, the sensor can be manufactured for less than 25 US cents, making it economically feasible for disposable use.
Sun Gyo Lim
J Innov Med Technol 2023;1: 10-14Jeong Seop Moon, Seung Jung Yu, Sam Ryong Jee
J Innov Med Technol 2023;1: 1-4journal@e-jimt.org