Special Issue "Artificial Intelligence in Surgery"

A special issue of Bioengineering (ISSN 2306-5354).

Deadline for manuscript submissions: 30 April 2023 | Viewed by 1012

Special Issue Editors

Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, Pisa, Italy
Interests: artificial intelligence in surgery; artificial intelligence in medical imaging; surgical skills assessment; surgical simulation; telemedicine; surgical robots
Dr. Amin Madani
E-Mail Website
Guest Editor
Department of Surgery, University Health Network, Toronto, ON, Canada
Interests: artificial intelligence; technology assessment; simulation; decision analysis; performance measurement; computer vision; virtual reality; augmented reality
Department of Surgery, Hospital of the University of Pennsylvania, 3400 Spruce St, 4 Silverstein, Philadelphia, PA 19104, USA
Interests: artificial intelligence; computer vision; surgical endoscopy; laparoscopic surgery; robotic surgery

Special Issue Information

Dear Colleagues,

Surgical data science is a fast-growing research field in both the academic and industrial worlds, and will impact all aspects of surgery considerably: training, simulation, intraoperative decision making, and the prediction of events and outcomes, assisting surgeons in the preoperative planning of major operations and reinterventions, postoperative progress, and the management of complications.

In particular, minimal access surgery generates a considerable amount of data that can be processed by artificial intelligence (AI), including data at the preoperative (e.g., clinical, laboratory, and imaging tests of patients), intraoperative (e.g., video recordings and even kinematic data in cases of robot-assisted surgery), and postoperative phases (e.g., operative times).

The availability of more and more complex AI models has led to improvements in the metrics of surgical data science tasks. At the same time, progress in hardware has significantly reduced the computation times of these models.

We therefore invite you to submit original research papers and comprehensive reviews on the theory and applications of AI in surgery, from the development of AI models on existing or new datasets to their clinical applications in laparoscopy, robot-assisted surgery, and endovascular surgery.

Topics of interest for this Special Issue include, but are not limited to, the following:

  • Automatic skills assessment;
  • Autonomous surgical robots;
  • Computer vision;
  • Natural Language Processing (NLP);
  • Federated learning;
  • Imitation learning;
  • Intraoperative decision making;
  • Predictive modeling of risks, diseases, and patients' outcomes;
  • Segmentation of radiological images for preoperative planning;
  • Self-supervised learning;
  • Surgical simulation/training;
  • Video-based assessment of surgical procedures.

Dr. Andrea Moglia
Dr. Amin Madani
Dr. Daniel Hashimoto
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Bioengineering is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


Surgical Gesture Recognition in Laparoscopic Tasks Based on the Transformer Network and Self-Supervised Learning
Bioengineering 2022, 9(12), 737; https://doi.org/10.3390/bioengineering9120737 - 29 Nov 2022
Cited by 1 | Viewed by 657
In this study, we propose a deep learning framework and a self-supervision scheme for video-based surgical gesture recognition. The proposed framework is modular. First, a 3D convolutional network extracts feature vectors from video clips for encoding spatial and short-term temporal features. Second, the [...] Read more.
In this study, we propose a deep learning framework and a self-supervision scheme for video-based surgical gesture recognition. The proposed framework is modular. First, a 3D convolutional network extracts feature vectors from video clips for encoding spatial and short-term temporal features. Second, the feature vectors are fed into a transformer network for capturing long-term temporal dependencies. Two main models are proposed, based on the backbone framework: C3DTrans (supervised) and SSC3DTrans (self-supervised). The dataset consisted of 80 videos from two basic laparoscopic tasks: peg transfer (PT) and knot tying (KT). To examine the potential of self-supervision, the models were trained on 60% and 100% of the annotated dataset. In addition, the best-performing model was evaluated on the JIGSAWS robotic surgery dataset. The best model (C3DTrans) achieves an accuracy of 88.0%, a 95.2% clip level, and 97.5% and 97.9% (gesture level), for PT and KT, respectively. The SSC3DTrans performed similar to C3DTrans when training on 60% of the annotated dataset (about 84% and 93% clip-level accuracies for PT and KT, respectively). The performance of C3DTrans on JIGSAWS was close to 76% accuracy, which was similar to or higher than prior techniques based on a single video stream, no additional video training, and online processing. Full article
(This article belongs to the Special Issue Artificial Intelligence in Surgery)
Show Figures

Graphical abstract

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Neuroendovascular embolization procedure optimized for aneurysm subarachnoid hemorrhage healing by drug eluting biomedical devices and artificial intelligence
Authors: Daniel Gomez-Santos; Brandon Lucke-Wold
Affiliation: Lillian S Wells Department of Neurosurgery, University of Florida College of Medicine, Gainesville, FL, USA
Abstract: Aneurysm subarachnoid hemorrhage (aSAH) is a medical emergency that can lead to permanent brain damage or death if not treated promptly. The main symptom is a sudden severe headache. Treatment is typically surgery or catheter-based therapy. Recently, pioneers in neurosurgery have been able to perform coil embolization (a catheter-based therapy) to close abnormal blood flow in a blood vessel. The CorPath GRX robotic system just finished a global neuroendovascular clinical trial. This is the perfect time evaluate its ability to integrate artificial intelligence (AI) to optimize the robotic-assistance features during coil embolization. This AI robotic-assisted neuroendovascular surgery (NES) has the potential to be an autonomous neurosurgery that would raise the collective surgeon awareness to apply this in hospitals to address aSAH healing globally. A drug eluting biomedical device that has one chemokine (MCP-1) and one cytokine (OPN) in a dual-coated fashion is place on the coil prior to embolization. This allows for a healing modality to occur during and after the NES procedure. As surgical data science (SDS) progresses out of its infancy and is met with AI in surgery, there will be an enhancement in the operational theater where surgeons will be more informed preoperative, perioperative, intraoperative, and postoperative. This information will enable and empower the surgeon will key decision points and actionable insights. This advanced data-driven approach will allow the surgery to inform the science/engineering and the science/engineering to inform the surgery.

Back to TopTop