Clinical applications of machine learning in predicting 3D shapes of the human body: a systematic review

Abstract

Background Predicting morphological changes to anatomical structures from 3D shapes such as blood vessels or appearance of the face is a growing interest to clinicians. Machine learning (ML) has had great success driving predictions in 2D, however, methods suitable for 3D shapes are unclear and the use cases unknown. Objective and methods This systematic review aims to identify the clinical implementation of 3D shape prediction and ML workflows. Ovid-MEDLINE, Embase, Scopus and Web of Science were searched until 28th March 2022. Results 13,754 articles were identified, with 12 studies meeting final inclusion criteria. These studies involved prediction of the face, head, aorta, forearm, and breast, with most aiming to visualize shape changes after surgical interventions. ML algorithms identified were regressions (67%), artificial neural networks (25%), and principal component analysis (8%). Meta-analysis was not feasible due to the heterogeneity of the outcomes. Conclusion 3D shape prediction is a nascent but growing area of research in medicine. This review revealed the feasibility of predicting 3D shapes using ML clinically, which could play an important role for clinician-patient visualization and communication. However, all studies were early phase and there were inconsistent language and reporting. Future work could develop guidelines for publication and promote open sharing of source code.

Comparison of three-dimensional imaging of the nose using three different 3D-photography systems: an observational study

“…However, despite the detailed accuracy of the systems, the problem of simulating exact structural post-operative changes remains. The respective artificial intelligence models are still in testing phases and seem to play a central role in the future application [ 34 , 35 ]. When discussing the cost-effectiveness of these 3D-photography systems it is important to analyze not only the initial purchase price but also factors like software maintenance, storage, and potential long-term value in medical or dental applications.…”

Comparison of three-dimensional imaging of the nose using three different 3D- photography systems: an observational study

“…However, despite the detailed accuracy of the systems, the problem of simulating exact structural post-operative changes remains. The respective arti cial intelligence models are still in testing phases and seem to play a central role in the future application (31,32). When discussing the cost-effectiveness of these 3D-photography systems it is important to analyze not only the initial purchase price but also factors like software maintenance, storage, and potential longterm value in medical or dental applications.…”

Deep Learning–Based Facial and Skeletal Transformations for Surgical Planning

“…Craniofacial relationship investigation and facial-skeletal transformations remain a challenging task due to the complexity of geometric structures in the craniomaxillofacial (CMF) region and the significant difference between the geometric topologies of facial and skeletal shapes. It primarily involves 2 tasks: (1) facial prediction representing the estimation of external facial appearance from internal bony structures, which has been applied in VSP for CMF surgery, forensic identification, and anthropological research (Wang et al 2022;Ma et al 2023;Shui et al 2023); (2) skeletal prediction, representing the generation of internal bony structures from the facial shapes, which is of great significance for reference skeletal shape modeling in surgical planning, biomechanical head modeling, facial animation, and rehabilitation (Xiao et al 2021;Nguyen et al 2022). Many automated methods have been developed for facial and skeletal shape reconstruction including the facial soft-tissue thicknesses approach, homologues mesh model approach, and statistical model approach (Navic et al 2023).…”