Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks

Sánchez-Brizuela, Guillermo; Santos-Criado, Francisco-Javier; Sanz-Gobernado, Daniel; López, Eusebio de la Fuente; Fraile, Juan-Carlos; Pérez-Turiel, Javier; Cisnal, Ana

doi:10.3390/s22145180

Cited by 12 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Real-time monitoring of surgical procedures could enhance the safety of surgical procedures and prevent instances of retained sponges. In [36], a laparoscopic video was utilized to obtain 4003 hand-labeled frames to be used as a segmentation dataset. Several baselines were analyzed to prove the dataset potential: detection with YOLOv3, segmentation using U-Net, and coarse segmentation.…”

Section: Preventionmentioning

confidence: 99%

See 1 more Smart Citation

Minimization of occurrence of retained surgical items using machine learning and deep learning techniques: a review

Abo-Zahhad,

El-Malek,

Sayed

et al. 2024

BioData Mining

View full text Add to dashboard Cite

Retained surgical items (RSIs) pose significant risks to patients and healthcare professionals, prompting extensive efforts to reduce their incidence. RSIs are objects inadvertently left within patients’ bodies after surgery, which can lead to severe consequences such as infections and death. The repercussions highlight the critical need to address this issue. Machine learning (ML) and deep learning (DL) have displayed considerable potential for enhancing the prevention of RSIs through heightened precision and decreased reliance on human involvement. ML techniques are finding an expanding number of applications in medicine, ranging from automated imaging analysis to diagnosis. DL has enabled substantial advances in the prediction capabilities of computers by combining the availability of massive volumes of data with extremely effective learning algorithms. This paper reviews and evaluates recently published articles on the application of ML and DL in RSIs prevention and diagnosis, stressing the need for a multi-layered approach that leverages each method’s strengths to mitigate RSI risks. It highlights the key findings, advantages, and limitations of the different techniques used. Extensive datasets for training ML and DL models could enhance RSI detection systems. This paper also discusses the various datasets used by researchers for training the models. In addition, future directions for improving these technologies for RSI diagnosis and prevention are considered. By merging ML and DL with current procedures, it is conceivable to substantially minimize RSIs, enhance patient safety, and elevate surgical care standards.

show abstract

Section: Preventionmentioning

confidence: 99%

“…In [36], the dataset contains 42 video files, 30 of which have RSIs and 12 of which do not. There are 33 min of RSI videos and 13 min of non-RSI videos.…”

Section: Table 4 (Continued)mentioning

confidence: 99%

Minimization of occurrence of retained surgical items using machine learning and deep learning techniques: a review

Abo-Zahhad,

El-Malek,

Sayed

et al. 2024

BioData Mining

View full text Add to dashboard Cite

show abstract

“…An image based gauze detection and segmentation approach is proposed by Sanchez et al [234] where pretrained models are employed to test the novel dataset of 4003 video provided by authors. The InceptionV3, MobileNetV2, and ResNet-50 managed to reach an accuracy value of 77.68%, 75.67%, 90.16%, respectively.…”

Section: E Othersmentioning

confidence: 99%

Deep Learning Based Image Processing for Robot Assisted Surgery: A Systematic Literature Survey

et al. 2022

View full text Add to dashboard Cite

The recent advancements in the surging field of Deep Learning (DL) have revolutionized every sphere of life, and the healthcare domain is no exception. The enormous success of DL models, particularly with image data, has led to the development of image-guided Robot Assisted Surgery (RAS) systems. By and large, the number of studies concerning image-driven computer assisted surgical systems using DL has increased exponentially. Additionally, the contemporary availability of surgical datasets has also boosted the DL applications in RAS. Inspired by the latest trends and contributions in surgery, this literature survey presents a summarized analysis of recent innovations of DL in image-guided RAS systems. After a thorough review, a sum of 184 articles are selected and grouped into four categories, based on the literature and the relevancy of the task in the articles, comprising 1) Surgical Tools, 2) Surgical Processes, 3) Surgical Surveillance, and 4) Surgical Performance. The survey also discusses publicly available surgical datasets and highlights the basics of the DL models. Furthermore, the legal, ethical, and technological challenges together with the intuitive predictions and recommendations related to the autonomous RAS systems are also presented. The study reveals that Convolutional Neural Network (CNN) is most widely adopted architecture, whereas, JIGSAWS is most employed dataset in RAS. The study suggests fusing kinematic data along with image data, which produces better accuracy and precision, particularly in gesture and trajectory segmentation tasks. Additionally, CNN and Long Short Term Memory (LSTM) networks have shown remarkable performance, however, authors recommend employing these gigantic architectures only when simpler models have failed to produce satisfactory results. The simpler models, despite their limitations, are time and cost effective and yield considerable outcomes even on the smaller datasets.

show abstract

“…Understandingly, this has induced the prolific growth of robotic surgery and computer assisted surgery, with growing acceptance [11][12][13][14]. However, regarding acceptance, robotic surgery still encounters challenges posed mainly due to cost, operation, safety, and effectiveness [15,16]. Taking this concern into consideration, the MU-Laparobot project has been developed for computer-assisted MIS under the platform of robotics surgery.…”

Section: Introductionmentioning

confidence: 99%

Interactive 3D Force/Torque Parameter Acquisition and Correlation Identification during Primary Trocar Insertion in Laparoscopic Abdominal Surgery: 5 Cases

Nillahoot

Pillai

Sharma

et al. 2022

Sensors

View full text Add to dashboard Cite

Laparoscopic procedures have become indispensable in gastrointestinal surgery. As a minimally invasive process, it begins with primary trocar insertion. However, this step poses the threat of injuries to the gastrointestinal tract and blood vessels. As such, the comprehension of the insertion process is crucial to the development of robotic-assisted/automated surgeries. To sustain robotic development, this research aims to study the interactive force/torque (F/T) behavior between the trocar and the abdomen during the trocar insertion process. For force/torque (F/T) data acquisition, a trocar interfaced with a six-axis F/T sensor was used by surgeons for the insertion. The study was conducted during five abdominal hernia surgical cases in the Department of Surgery, Faculty of Medicine, Ramathibodi Hospital, Mahidol University. The real-time F/T data were further processed and analyzed. The fluctuation in the force/torque (F/T) parameter was significant, with peak force ranging from 16.83 N to 61.86 N and peak torque ranging from 0.552 Nm to 1.76 Nm. The force parameter was observed to positively correlate with procedural time, while torque was found to be negatively correlated. Although during the process a surgeon applied force and torque in multiple axes, for a robotic system, the push and turn motion in a single axis was observed to be sufficient. For minimal tissue damage in less procedural time, a system with low push force and high torque was observed to be advantageous. These understandings will eventually benefit the development of computer-assisted or robotics technology to improve the outcome of the primary trocar insertion procedure.

show abstract

Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks

Cited by 12 publications

References 47 publications

Minimization of occurrence of retained surgical items using machine learning and deep learning techniques: a review

Minimization of occurrence of retained surgical items using machine learning and deep learning techniques: a review

Deep Learning Based Image Processing for Robot Assisted Surgery: A Systematic Literature Survey

Interactive 3D Force/Torque Parameter Acquisition and Correlation Identification during Primary Trocar Insertion in Laparoscopic Abdominal Surgery: 5 Cases

Contact Info

Product

Resources

About