The following narrative review discusses the use of deep learning and 3D modeling in facial reconstruction from skeletal remains, focusing on accuracy, algorithmic bias, and evidential reliability. Forensic facial reconstruction (FFR) is a multidisciplinary field combining anthropology, medicine, and visual sciences to approximate the facial appearance of unidentified individuals from skeletal remains. Traditional manual methods, based on anatomical knowledge and facial soft tissue thickness (FSTT) measurements, are limited by subjectivity, labor intensity, and inter-expert variability. This narrative review summarizes contemporary AI-assisted approaches, with emphasis on convolutional neural networks (CNNs), generative adversarial networks (GANs), variational autoencoders (VAEs), and diffusion models, which enable probabilistic prediction of facial morphology while accounting for demographic variables such as sex, age, and population ancestry. Key challenges affecting reconstruction accuracy—including dataset limitations, population-specific variability, and algorithmic bias—are discussed, alongside quantitative validation methods and concerns regarding model transparency. Legal and ethical considerations, such as privacy, biometric data protection, and the need for explainable AI (XAI) frameworks, are highlighted. Future perspectives include hybrid expert–AI workflows, the development of globally representative datasets, and the integration of multimodal data sources, including DNA phenotyping, 3D morphometrics, and biomechanical modeling. These advances aim to create standardized, interpretable, and biologically informed frameworks that enable AI to support expert judgment and enhance the reliability of forensic facial reconstructions.

The introduction of immune checkpoint inhibitors (ICIs) into the treatment of melanoma has significantly reduced mortality over the past decade. However, therapeutic benefit is not observed in all patients, and treatment may be associated with severe adverse events. Therefore, identifying patients who are most likely to benefit from immunotherapy remains of critical importance. Currently used biomarkers, such as programmed death-ligand 1 (PD-L1) expression and manual assessment of tumour-infiltrating lymphocytes (TILs), have limited predictive value. This narrative review provides a critical appraisal of studies employing digital pathology tools, multiplex and spatial techniques (including multiplex immunofluorescence, imaging mass cytometry, and digital spatial profiling), as well as machine learning algorithms for predicting response to ICIs in patients with melanoma. Available evidence suggests that the highest predictive value may be achieved by approaches integrating quantitative assessment of immune infiltration with information on its spatial distribution, functional state, and interactions within the tumour microenvironment. Particular relevance may be attributed to features associated with the “immune-inflamed”, “immune-excluded”, and “immune-desert” phenotypes, the presence of tertiary lymphoid structures, and the organisation of local immune niches. In addition, this review highlights key limitations in the interpretation of current data, including lack of methodological standardisation, data heterogeneity, and insufficient validation. Directions for future research necessary for the implementation of these approaches into routine clinical practice are also discussed.