Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 3 appraisals
Scientific reports
Uncertainty estimation and probabilistic skull shape reconstruction using bayesian neural networks
3D shape reconstruction is an active area of research and a fundamental problem in computer vision, with growing applications in the medical domain, where it enables the recovery of missing or fine anatomical structures. Numerous approaches have been proposed for medical shape reconstruction, emphasizing accurate and anatomically plausible reconstructions. However, 3D shape reconstruction remains an inherently ill-posed problem, meaning (1) both neural network-based methods and conventional shape modeling approaches naturally introduce uncertainty in their predictions, and (2) multiple anatomically plausible reconstructions exist for a given partial or low-resolution input. While the uncertainty aspects have been widely explored in general computer vision, they remain relatively under-explored in the context of medical shape reconstruction. In this paper, we developed a 3D Bayesian U-Net and investigated its use for uncertainty estimation and probabilistic reconstructions across three key tasks: cranial reconstruction, facial reconstruction, and skull shape super-resolution. Our findings show that the Bayesian model is able to produce a range of anatomically plausible skull reconstructions while capturing natural skull variations arising from the learned weight uncertainty. Notably, these variations are primarily expressed through differences in bone thickness, which aligns with anatomical expectations, particularly relevant in real-world applications like cranial implant design. Additionally, we propose a principled framework to study the relationship between weight uncertainty and reconstruction uncertainty by analyzing the learned posterior distribution of the weights, demonstrating that our Bayesian U-Net achieves comparable reconstruction performance to a deterministic U-Net baseline while providing reliable uncertainty estimates. Our study also reveals a clear cross-task uncertainty pattern, where tasks with stronger structural constraints, like super-resolution, yield lower predictive uncertainty, while less constrained tasks, like facial reconstruction, result in higher uncertainty. Refer to the project page for more visual results https://git.zib.de/jli/uncertainty-aware-skull-reconstruction/ .
28 May 2026
Read appraisal →Biomedical physics & engineering express
Oral squamous cell carcinoma diagnosis with time and frequency domain features from optical coherence tomography A-scan signals
Optical coherence tomography (OCT) is extremely useful in the screening and detection of oral cancers. But various challenges, such as its subjectivity, operator dependence in interpretation, and lack of quantitative outcomes, have been delaying its adoption in clinical decision-making. The objective of this research is to quantify various A-scan features embedded in the OCT signal through advanced signal processing techniques and machine learning algorithms.Ex vivoimaging of biopsied oral tissues (normal mucosa, carcinomain situ(CIS), well-differentiated, and poorly differentiated oral squamous cell carcinoma) was performed using a spectral domain OCT system. Our A-scan dataset consisted of representative 1D signals obtained from different regions of the tissue bed. A set of 12 time- and 8 frequency-domain features were computed on each A-scan, and ten machine learning models were evaluated for binary and multi-label classification. LightGBM achieved the highest performance in both binary (accuracy: 0.8847,F1: 0.8878, AUC: 0.9539) and multi-label classification (accuracy: 0.8248,F1: 0.8201, AUC: 0.964). LightGBM was selected as the final model based on its superior and consistent performance across both classification paradigms. Our proof-of-concept feasibility study demonstrates good accuracy for differentiating oral mucosal tissues, highlighting the biomarker signature of A-scans.
19 May 2026
Read appraisal →Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery
Machine learning-powered decoding of facial complexity: a diamond-and-triangle geometry for frontal facial analysis
Facial configuration is far more complicated and variable than the representations offered by a couple of conventionally used mathematic laws, necessitating development of a comprehensive and interracially comparable system for frontal facial analysis. In this study, based on morphological analysis of 33 Caucasian and 33 Asian female faces with high perceived facial attractiveness (i.e. facial esthetic appeal in frontal views), validated by independent layperson ratings, in contrast with 'ordinary' faces of 67 Caucasian and 67 Asian females, a machine learning-powered model, building on a diamond-and-triangle geometric framework, was constructed to decode the esthetic-determining facial traits and quantify the probability of a face conforming to the generally accepted attractiveness. The SVM models demonstrated excellent efficacy in this task, based on the input of 21 facial proportion indices derived from the diamond-and-triangle geometry. By interpreting the contribution of input features to each model's diagnosis, the Asian and Caucasian faces shared prioritization of proportional coordination of facial height with mid-facial width and outer canthal distance in determining facial harmony, and exhibited ethnicity-specific variations in hierarchical importance of other proportion indices. The highly coordinated diamond-and-triangle geometric framework distinguished the attractive faces from the ordinary, with cross-ethnic similarities between Caucasian and Asian females. The machine learning-powered model, integrated with the diamond-and-triangle geometry, provides references for cross-ethnic facial analysis and customized treatment planning.
4 May 2026
Read appraisal →