Dataset Information

A machine learning framework for automated diagnosis and computer-assisted planning in plastic and reconstructive surgery.

ABSTRACT: Current computational tools for planning and simulation in plastic and reconstructive surgery lack sufficient precision and are time-consuming, thus resulting in limited adoption. Although computer-assisted surgical planning systems help to improve clinical outcomes, shorten operation time and reduce cost, they are often too complex and require extensive manual input, which ultimately limits their use in doctor-patient communication and clinical decision making. Here, we present the first large-scale clinical 3D morphable model, a machine-learning-based framework involving supervised learning for diagnostics, risk stratification, and treatment simulation. The model, trained and validated with 4,261 faces of healthy volunteers and orthognathic (jaw) surgery patients, diagnoses patients with 95.5% sensitivity and 95.2% specificity, and simulates surgical outcomes with a mean accuracy of 1.1 ± 0.3 mm. We demonstrate how this model could fully-automatically aid diagnosis and provide patient-specific treatment plans from a 3D scan alone, to help efficient clinical decision making and improve clinical understanding of face shape as a marker for primary and secondary surgery.

SUBMITTER: Knoops PGM

PROVIDER: S-EPMC6753131 | biostudies-literature | 2019 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A machine learning framework for automated diagnosis and computer-assisted planning in plastic and reconstructive surgery.

Knoops Paul G M PGM Papaioannou Athanasios A Borghi Alessandro A Breakey Richard W F RWF Wilson Alexander T AT Jeelani Owase O Zafeiriou Stefanos S Steinbacher Derek D Padwa Bonnie L BL Dunaway David J DJ Schievano Silvia S

Scientific reports 20190919 1

Current computational tools for planning and simulation in plastic and reconstructive surgery lack sufficient precision and are time-consuming, thus resulting in limited adoption. Although computer-assisted surgical planning systems help to improve clinical outcomes, shorten operation time and reduce cost, they are often too complex and require extensive manual input, which ultimately limits their use in doctor-patient communication and clinical decision making. Here, we present the first large- ...[more]

PMID: 31537815

Similar Datasets

Project description:ObjectivesThis study aims to refine computer-assisted planning (CAP) of SEEG implantations by adding spatial constraints from prior SEEG trajectories ("Priors") to improve safety and reduce manual adjustments, without increasing planning time.MethodsRetrospective validation based on 159 previously implanted trajectories (11 cases) planned by the clinical standard CAP and CAP constrained with spatial priors ("CAP + Priors"). Constraints included 31 target and 51 entry zones, created from 98 consecutive patients (763 implanted SEEG trajectories). Each of the 159 previously implanted trajectories was planned by two fellows, once with CAP and once with CAP + Priors, in a randomized order. The time taken to generate the initial computer-generated plan (T1) and the user-edited final plan (T2) were recorded together with the proportions of electrodes that required subsequent adjustments. Clinical implantability was assessed via a blinded review of each trajectory by five independent epilepsy neurosurgeons with expertise in SEEG implantation.ResultsExpert raters considered 88.5% of trajectories implantable, with no difference in acceptability between CAP alone and CAP + Priors (p = 0.79). Median (IQR) T1 for CAP to produce complete automated implantation was 4.6 (0.85) min vs. CAP + Priors was 6.3 (2.6) min (p = 0.03). There was no significant difference in T2 (time to complete surgeon-edited plan): CAP median (IQR) 105 (22) min, and CAP + Priors median (IQR) 96 (68) min (p = 0.92). The CAP + Priors risk score was significantly lower than that for the previously actually implanted trajectories for the 11 plans analyzed (p = 0.004), and no different from CAP alone planning. A significant reduction was observed in manual adjustments required with CAP + Priors in the cingulate gyrus.ConclusionUsing spatial priors from previous implantations enhances SEEG CAP and increases the granularity of trajectory planning. This approach facilitates more standardized planning and allows for the incorporation of experience from multiple expert centers, decreasing the risk of the resultant trajectories and reducing the proportion of trajectories that require manual planning without significantly increasing planning time.

Project description:PurposeThe COVID-19 pandemic has brought unprecedented challenges for oculoplastic surgeons worldwide, in terms of care delivery, medical equipment and at-risk patient management. To date, there are no centralized or compiled international COVID-19 guidelines for oculoplastic surgeons.MethodsWe examined COVID-19 guidelines published by oculoplastic societies worldwide. All countries around the world were initially considered in this study, but only 9 oculoplastic societies met the inclusion criteria: (1) publicly available guidelines displayed on the oculoplastic society's website, or (2) guidelines received from the oculoplastic society after contacting them twice using the contact information on their website.ResultsThe 9 oculoplastic societies examined include: the American Society of Ophthalmic Plastic and Reconstructive Surgery, the British Oculoplastic Surgery Society, the Canadian Society of Oculoplastic Surgery, the European Society of Ophthalmic Plastic and Reconstructive Surgery, la Sociedad Española de Cirugía Plástica Ocular y Orbitaria, la Asociación Colombiana de Cirugía Plastica Ocular, the Asia Pacific Society of Ophthalmic Plastic & Reconstructive Surgery, the Oculoplastics Association of India, and the Philippine Society of Ophthalmic Plastic and Reconstructive Surgery. They all agree that urgent procedures should not be delayed, while non-necessary procedures (including all elective clinic services) should be postponed. When adequate protective equipment is available, oculoplastic surgeons must treat urgent cases. Eight out of 9 societies have provided recommendations on personal protective equipment use in order to prevent the spread of COVID-19 and to adequately protect mucous membranes. Other recommendations provided by certain societies are related to shelter in place measures, hand hygiene and surface disinfection protocols, patient triage, and thyroid eye disease management.ConclusionsAll 9 societies with published recommendations have provided valuable recommendations to their members, regarding urgency of care and infection control solutions (personal protective equipment, hand hygiene, telemedicine, and social isolation).

Dataset Information

A machine learning framework for automated diagnosis and computer-assisted planning in plastic and reconstructive surgery.

Publications

A machine learning framework for automated diagnosis and computer-assisted planning in plastic and reconstructive surgery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets