Fusarium is a large fungal genus that is widely distributed in the environment, mostly known for its plant pathogenicity. Rarely, it is involved in human pathology, where the type of infection caused is highly dependent upon the portal of entry and the immune status of the host. The study at hand aims to summarize routine methods used in diagnosing such infections as well as more advanced molecular diagnostic methods, techniques that can play a huge role in differentiating between colonization and infection when trying to decide the therapeutic outcome. Consequently, to further support our findings, two different strains (one isolated from corneal scrapings and one isolated from purulent discharge) were analyzed in a clinical context and thoroughly tested using classical and modern diagnostic methods: identification by macroscopical and microscopical examinations of the culture and mass spectrometry, completed by molecular methods such as PCR for trichothecene and ERIC-PCR for genetic fingerprinting. Isolation of a clinically relevant Fusarium spp. from a sample still remains a diagnostic challenge for both the clinician and the microbiologist, because differentiating between colonization and infection is very strenuous, but can make a difference in the treatment that is administered to the patient.

Skull base pneumatization is anatomically variable and clinically relevant for temporal bone and transsphenoidal surgical corridors, but manual volumetric segmentation is time-consuming. This retrospective pilot study evaluated a clinician-guided deep learning workflow for computed tomography segmentation of temporal bone/mastoid and sphenoid sinus pneumatization. Bone-window computed tomography (CT) datasets were curated, converted to NIfTI format, and segmented using 3D Slicer, MONAI Label, and a three-dimensional SegResNet-based model. The mastoid workflow used side-specific temporal bone crops, while the sphenoid workflow used full-head CT volumes. The final mastoid development dataset included 122 side-cases, with an independent 28 side-case expert-validation cohort. The sphenoid arm included 117 expert-submitted development labels and a separate 17-case expert-validation cohort. The mastoid model achieved strong expert agreement, with mean Dice 0.9691 and median Dice 0.9794 on the independent validation set. The sphenoid workflow achieved a best internal validation Dice of 0.8750, while expert comparison of saved automatic masks showed mean Dice 0.9426 and median Dice 0.9408. Exploratory mask analysis enabled volumetric, densitometric, and extension-pattern assessment of pneumatized skull base compartments. This research supports clinician-guided deep learning as a feasible approach for reproducible CT-based skull base pneumatization segmentation and radiomic analysis.