Page 44 - Read Online

Brenac et al. Art Int Surg 2024;4:296-315 https://dx.doi.org/10.20517/ais.2024.49 Page 308

targeting HDAC4 treatment method with broad applications in biomedical
(3) Develop a microneedle-mediated patch for fields
TSA delivery to improve treatment efficacy and
reduce secondary damage
3D and predictive Knoops A machine learning framework for 2019 Scientific Reports (1) Develop a ML framework for automated (1) This approach offers high diagnostic accuracy
[42]
modeling et al. automated diagnosis and diagnosis, risk stratification, and treatment in PRS (95.5% sensitivity and 95.2% specificity) and simulates
computer-assisted planning in (2) Enhance precision and efficiency in ML- surgical outcomes with a mean accuracy of 1.1 ± 0.3
plastic and reconstructive surgery assisted surgical planning to improve clinical mmc
decision making and outcomes (2) This framework can automate diagnosis and provide
patient-specific training from 3D models
[55]
Knoops et al. A novel soft tissue prediction 2018 PloS One (1) Develop a probabilistic FEM to predict (1) The probabilistic FEM was validated on 8 patients
methodology for orthognathic postoperative facial soft tissues following (2) The FEM accurately predicted changes in the nose
surgery based on probabilistic finite orthognathic surgery and upper lip but underestimated changes in the cheeks
element modeling (2) Addressing the limitations of prediction models and lower lip
by including variability and uncertainty in the (3) This model offers patients and surgeons a more
prediction process comprehensive understanding of surgical impacts
[62]
3D printing for Chae et al. 3D volumetric analysis for planning 2014 Breast Cancer (1) Develop a new approach to volumetric analysis (1) Multiple techniques for volumetric analysis for breast
planning and breast reconstructive surgery Research and for breast reconstructive surgery using 3D asymmetry were reported
implantation Treatment photography (2) Breast volumes can be visualized through 3D images,
(2) Improve accuracy in assessing breast volume, accurately calculated, and produced as 3D haptic models
shape, and projection compared to traditional 2D for operative guidance
photography

AI: Artificial intelligence; ASRM: American Society of Reconstructive Microsurgery; ASPS: American Society of Plastic Surgeons; NIH: National Institute of Health; AIVAs: artificial intelligence virtual assistants; FAQs:
frequently asked questions; CT: computed tomography; CV: computer vision; DIEP: deep inferior epigastric perforators; ML: machine learning; AUC: area under the curve; FACE-Q: Facial Appearance and Cosmetic
Surgery Quality of Life Questionnaire; CNN: convolutional neural networks; CS: craniosynostosis; 3DMM: 3D morphable model; BMI: body mass index; ED: emergency department; CTR: carpal tunnel release; TSA:
trichostatin A; HDAC4: histone deacetylase 4; PRS: plastic and reconstructive surgery; FEM: finite element model.

it can also be used as a tool for enhancing communication between patient and physician. ML has been explored in combination with photographic data to

[39]
maintain proper standardization of procedures and offer more precise postoperative assessment . Using pre- and postoperative pictures, Zhang et al. showed
[39]
that neural networks could identify preoperative age and facial age reduction following facelift surgery . A positive correlation between the algorithmically
determined result and patient satisfaction after facelift was identified, representing a validated method of quantifying postoperative results and efficacy for

[39]
plastic surgeons . In another study, Boonipat et al. used ML to assess postoperative facial expression improvement after facial reanimation surgery .
[40]
Recording of facial expressions was performed for each patient in a video clip and analyzed with ML software to detect facial expressions . ML algorithms
[40]
were found to be capable of reading facial emotional expressions and providing a quantification of those expressions. These tools may thus be helpful in
[40]
assessing facial palsy and the success of postoperative outcomes . Moreover, corrective procedures, the use of neurotoxins, or soft tissue fillers could utilize
ML as an assessment tool for photographic or recorded data [39,40] .