Search Results (6,031)

Background/Objectives: Chronic recurrent multifocal osteomyelitis/chronic nonbacterial osteomyelitis (CRMO/CNO) is an auto-inflammatory bone disease for which optimal treatment and imaging-based monitoring remain incompletely defined. Methods: We conducted a single-center retrospective review of nine pediatric patients with CRMO/CNO treated with tumor necrosis factor inhibitors (TNFis). Clinical improvement was assessed using Visual Analog Scale (VAS) pain scores, erythrocyte sedimentation rate (ESR), and physical examination findings. Radiographic assessment used longitudinal, site-specific magnetic resonance imaging (MRI) scored with a simplified approach adapted from the Chronic Nonbacterial Osteomyelitis Magnetic Resonance Imaging Scoring (CROMRIS) system. Results: Our cohort was composed of six females and three males with a median age of seven years. TNFi monotherapy was initiated as a first-line therapy (n = 4) or step-up (n = 5). During a median follow-up time of 26 months, treatment was tolerated well, except for the emergence of psoriasis in three patients (n = 3), among whom one necessitated treatment change. Eight patients on TNFis achieved clinical remission, including five with complete resolution of MRI lesions. Conclusions: In this small, single-center case series, TNFi monotherapy was associated with sustained disease control, as reflected by clinical improvement and MRI-documented lesion resolution. These findings emphasize the need for validation of our observations in larger multi-center cohorts. Full article

Malignant melanoma demonstrates strikingly varied clinical presentations, on account of which it is often challenging to diagnose. We describe herein a rare case of amelanotic malignant melanoma (AMM) in the buccinator muscle presenting as a solitary mass. A middle-aged woman presented with a non-pigmented swelling under the right buccal mucosa. Magnetic resonance imaging (MRI) revealed a well-circumscribed lesion without local invasion. A needle biopsy did not establish the diagnosis and was instead interpreted as suggestive of a salivary gland tumor, reinforcing an initial impression of myoepithelioma. Histopathological analysis of an excised specimen revealed poorly defined, pleomorphic tumor cells and a scattering of melanin-containing cells. The diagnosis of AMM was established by integrating these histopathological features with the clinico-radiological findings and the immunohistochemical results, which were positive for HMB-45, S-100, and SOX10 and negative for cytokeratin. Whole-body positron-emission tomography-computed tomography found no primary lesion. Because tumor nests suggesting possible residual disease were observed near the resection margin, a wider, secondary excision including the affected portion of the buccal mucosa and overlying skin was performed together with neck dissection. Histopathological examination of the re-resection specimen showed no residual tumor, indicating that no malignant cells were identified in the adjacent oral mucosa or facial skin. The patient has remained disease-free for three years. Full article

Background/Objectives: Meniscal tears frequently occur during athletic activities and are often associated with anterior cruciate ligament injuries. The purpose of this study was to compare the posterior tibial slope (PTS) in young adults undergoing arthroscopic surgery for isolated meniscal tears with that of a control group, and to investigate its association with meniscal tears. Methods: This retrospective, single-centre, controlled study included 190 patients aged 18–30 years who presented with unilateral knee pain and underwent knee magnetic resonance imaging (MRI) between 2015 and 2022. Patients with an isolated medial meniscal tear (Group A, n = 67) or an isolated lateral meniscal tear (Group B, n = 31), confirmed on MRI and directly with arthroscopy, were compared with a symptomatic control group who presented with knee pain but had no meniscal or anterior cruciate ligament (ACL) tear on MRI (Group C, n = 92). Medial and lateral PTS angles were measured on pre-existing standing lateral knee radiographs. Interobserver and intraobserver reliability were quantified using intraclass correlation coefficients (ICCs). Group comparisons, receiver operating characteristic (ROC) analysis with the Youden index, and multivariable binary logistic regression adjusted for age, sex and side were performed. Results: Both medial and lateral PTS angles were significantly higher in Groups A and B than in the control group (p < 0.05). ROC analysis identified a cut-off of 9.2° for the medial PTS in the medial-tear group (AUC: 0.756, 95% CI: 0.68–0.83; sensitivity: 64.18%, specificity: 80.43%) and 9.9° for the lateral PTS in the lateral-tear group (AUC: 0.709, 95% CI: 0.60–0.82; sensitivity: 58.06%, specificity: 81.52%). The association persisted after adjustment for age, sex and side (medial slope in medial tears adjusted OR: 1.36 per 1°, 95% CI: 1.19–1.55, p < 0.001; lateral slope in lateral tears adjusted OR: 1.25 per 1°, 95% CI: 1.08–1.44, p = 0.003). Conclusions: In this retrospective cohort of young adults, an increased posterior tibial slope was associated with isolated meniscal tears. A medial PTS greater than 9.2° and a lateral PTS greater than 9.9° were associated with medial and lateral meniscal tears, respectively. Given the modest sensitivity and the observational design, PTS should be regarded as a supportive morphological marker rather than a stand-alone diagnostic metric, and a causal relationship cannot be inferred based on the results of this study. Because discrimination was only fair (AUC 0.693–0.756) and sensitivity limited (54.8–64.2%), these cut-offs are not clinically applicable decision thresholds and should be used only in conjunction with clinical assessment and MRI. Full article

Background and Clinical Significance: Dupuytren’s disease (DD) is characterized by abnormal myofibroblast proliferation and excessive collagen deposition, leading to the formation of pathological fibrous cords. It typically affects the palmar surface of the hand, where these contractile cords cause progressive flexion contractures of the metacarpophalangeal (MCP) and proximal interphalangeal (PIP) joints. Lesions involving the proximal interphalangeal (PIP) joint without significant flexion contracture may be misdiagnosed as soft-tissue tumors or inflammatory lesions based on imaging findings, including magnetic resonance imaging (MRI) and ultrasound; Case Presentation: We present a case of a soft-tissue mass located on the volar aspect of the proximal phalanx of the little finger, associated with a mild PIP joint contracture. The initial MRI findings suggested a giant-cell tumor of the tendon sheath; however, the diagnosis of Dupuytren’s disease was established only after histopathological examination; Conclusions: This case highlights the importance of considering DD in the differential diagnosis of peripheral soft-tissue lesions of the finger, particularly when presenting with only mild PIP joint contracture and atypical imaging features. Full article

Three-dimensional (3D) bioprinting has emerged as a versatile biofabrication strategy that enables the precise, spatiotemporally controlled co-deposition of living cells, biomaterials, and bioactive agents, including growth factors, cytokines, and extracellular matrix (ECM) components, into geometrically defined 3D constructs. By translating digital design models derived from computed tomography (CT), magnetic resonance imaging (MRI), or computational modeling directly into physical tissue architectures, 3D bioprinting facilitates the assembly of hierarchically organized constructs that closely recapitulate the structural, mechanical, and functional characteristics of native tissues. The principal 3D bioprinting strategies are broadly classified into scaffold-based and scaffold-free approaches. Engineered bioinks, whether formulated as cell-laden natural, synthetic, or composite polymer hydrogels, tissue-derived decellularized ECM (dECM) components, or pure cellular spheroids and organoids, constitute the cornerstone of these biofabrication platforms. Scaffold-based 3D bioprinting comprises extrusion-based, droplet-based (inkjet and drop-on-demand), light-based vat photopolymerization (stereolithography and digital light processing), and laser-assisted bioprinting based on laser-induced forward transfer (LIFT). Each of these modalities imposes distinct constraints on bioink rheology, crosslinking mechanisms, spatial resolution, throughput, and post-printing cell viability; consequently, a specific 3D bioprinting strategy is selected according to the specific requirements of the target tissue application. Scaffold-free 3D bioprinting and bioassembly techniques, including the Kenzan method, aspiration-assisted bioprinting, magnetic bioprinting, and other field-directed tissue assembly approaches, enable the fabrication of spheroid- and organoid-based constructs without the necessity for exogenous biomaterial scaffolds. Because native tissues exhibit diversity in cellular composition, ECM architecture, mechanical properties, and physiological function, no individual bioprinting platform or bioink formulation serves as a universal 3D bioprinting solution. The engineering of biomimetic tissue constructs, therefore, requires the selection of application-tailored fabrication approaches. Under this biofabrication paradigm, 3D bioprinting has been applied across a wide range of tissue engineering targets, including skin, bone, cartilage, osteochondral interfaces, cardiac and vascular tissue, neural structures, ocular, dental, and adipose tissue. This review discusses recent advances in scaffold-based and scaffold-free 3D bioprinting applications for tissue engineering and regenerative medicine across diverse tissue systems. Full article

Accurate estimation of Alzheimer’s disease (AD) severity from structural magnetic resonance imaging (MRI) remains difficult, as disease-associated anatomical alterations are often subtle and publicly available datasets are typically too small to support robust deep learning model training. This feasibility study sought to determine how much Alzheimer’s disease spectrum-related information could be extracted from a small structural MRI cohort using a deliberately lightweight two-dimensional convolutional neural network (2D CNN), and whether transfer learning improves model performance. This study was intended as a methodological proof of concept rather than the development of a clinically deployable diagnostic tool. Structural scans and Clinical Dementia Rating (CDR) labels from the OASIS-1 dataset were filtered to 214 subjects: 124 cognitively normal (CN), 65 with mild cognitive impairment (MCI; CDR = 0.5), and 25 with AD-level impairment (CDR ≥ 1). A compact 2D CNN trained from scratch and a transfer learning model (frozen ImageNet MobileNetV2 features) were evaluated on four binary tasks (CN vs. AD, MCI vs. AD, CN vs. MCI, and CN vs. any impairment) under identical pre-processing and subject-level repeated 5-fold cross-validation (10 repeats), with the decision threshold tuned only on an inner split. Discrimination was summarized by ROC-AUC with 95% confidence intervals (CIs), permutation tests against chance, and per-task sensitivity and specificity. The from-scratch CNN recovered only a broad normal-versus-impaired signal (CN vs. any impairment AUC 0.59) and was at chance on adjacent-stage tasks (MCI vs. AD 0.41; CN vs. MCI 0.51). Transfer learning improved every task: CN vs. AD AUC 0.745 (95% CI 0.730–0.763), CN vs. any impairment 0.642, CN vs. MCI 0.601, and MCI vs. AD 0.599. On an independent OASIS-2 cohort, the transfer learning CN vs. AD model retained AUC 0.748. In this small-data regime, transfer learning recovers substantially more Alzheimer-spectrum signals than a from-scratch CNN, but performance remains modest because it is bounded by CDR-based, non-biomarker-confirmed labels, suggesting the model separates CDR-defined cognitive-status groups rather than detecting AD pathology. Full article

Background/Objectives: Prostate needle biopsy often underestimates tumor aggressiveness due to limited tissue sampling, leading to Gleason score upgrading after radical prostatectomy (RP). Phosphatase and Tensin Homolog (PTEN) loss is an established tissue-based marker of adverse prostate cancer biology. This study evaluated whether reduced or absent PTEN immunoreactivity in diagnostic biopsies is associated with subsequent Gleason score and International Society of Urological Pathology (ISUP) Grade Group upgrading in RP specimens. Methods: This retrospective study included 85 prostate cancer patients who underwent multiparametric magnetic resonance imaging (mpMRI)-guided biopsy and subsequent RP. PTEN expression on biopsy samples was assessed via immunohistochemistry. Patients were stratified into PTEN-preserved (PTEN+, n = 75) and PTEN-deficient (PTEN−, n = 10) groups. Results: Upgrading occurred in 70% (7/10) of PTEN-deficient cases compared with 20% (15/75) of PTEN-preserved cases. This difference was statistically significant (two-sided Fisher’s exact p = 0.0024), with PTEN-deficient patients showing a 3.50-fold higher relative risk of upgrading (RR = 3.50, 95% CI: 1.91–6.43). Preoperative PSA levels (p = 0.91) and Prostate Imaging Reporting and Data System (PI-RADS) scores (p = 0.73) did not differ significantly between the groups. Conclusions: Reduced PTEN protein expression, as assessed by immunohistochemistry in prostate needle biopsies, was significantly associated with Gleason score/ISUP Grade Group upgrading at radical prostatectomy. PTEN immunohistochemistry warrants further evaluation as a potentially complementary tissue-based marker of biopsy undergrading. However, the observed unadjusted association does not establish PTEN immunoreactivity as an independent predictor of upgrading. Full article

Background/Objectives: Low back pain (LBP) is highly prevalent among dentists, although the relationship between lumbar magnetic resonance imaging (MRI) findings and symptoms remains unclear. This study aimed to identify lumbar MRI-derived structural profiles in actively practicing dentists and to examine their relationship with LBP, pain-related disability, demographic characteristics, occupational factors, and individual MRI findings. Methods: A cross-sectional observational study was conducted in 57 actively practicing dentists. Demographic, occupational, and clinical data were collected, and lumbar MRI examinations were performed using standardized protocols. MRI findings included disc bulging, disc herniation, annular fissure, Modic changes, osteophytes, facet joint degeneration, and spinal canal stenosis. Cluster analysis was used to identify MRI-derived structural profiles. Associations between profiles, LBP, disability, demographic characteristics, occupational factors, and individual MRI findings were assessed using chi-square tests and correspondence analysis. Results: Two distinct MRI-derived structural profiles were identified: a disc–facet degenerative profile (n = 38) and a non-osseous degeneration profile (n = 19). Disc bulging (100% vs. 52.6%, p < 0.001), facet joint degeneration (94.7% vs. 10.5%, p < 0.001), and osteophytes (23.7% vs. 0%, p = 0.022) significantly contributed to profile differentiation, whereas disc herniation, Modic changes, and annular fissure did not. Neither MRI-derived profile was associated with the presence of LBP or pain-related disability (p > 0.05). Younger dentists were more frequently classified within the disc–facet degenerative profile with LBP, whereas older dentists with similar structural findings were more commonly classified within the same profile without LBP (p = 0.007). No significant associations were observed between MRI-derived profiles and occupational characteristics. Conclusions: Two distinct lumbar MRI-derived structural profiles were identified in dentists, but neither was associated with LBP or pain-related disability. Age appeared to influence the clinical expression of the disc–facet degenerative profile, suggesting that lumbar MRI findings should be interpreted within a broader, age-sensitive clinical context rather than as isolated determinants of symptoms. Full article

Brain tumors exhibit extensive metabolic reprogramming that supports proliferation, invasion, therapeutic resistance, and adaptation to dynamic microenvironmental conditions. These alterations provide opportunities for metabolic imaging approaches that extend beyond conventional anatomical neuroimaging. Hyperpolarized magnetic resonance imaging (hpMRI) has emerged as a novel metabolic imaging platform capable of non-invasively visualizing real-time cellular metabolism through dynamic nuclear polarization of carbon-13-labeled substrates. By dramatically enhancing magnetic resonance signal intensity, hpMRI enables interrogation of enzyme-specific metabolic pathways and provides unique insight into tumor energetics, metabolic heterogeneity, and treatment response. The distinct contribution of this review is an updated, brain tumor-specific, clinically oriented framework that integrates recent human evidence with longitudinal metabolic phenotyping, emerging pathway-specific probes, acquisition standardization, multimodal validation, and the remaining barriers to clinical implementation. Particular emphasis is placed on hyperpolarized [1-¹³C]pyruvate, which has demonstrated feasibility and safety in patients with gliomas and has enabled assessment of glycolytic metabolism, oxidative phosphorylation, tumor recurrence, and longitudinal treatment response. Serial changes in lactate and bicarbonate flux may also reflect evolution toward more glycolytic, heterogeneous, and treatment-resistant tumor phenotypes, supporting the potential prognostic value of hpMRI before conventional radiographic progression becomes evident. We also review emerging applications involving α-ketoglutarate metabolism, redox biology, glutathione cycling, perfusion imaging, and molecular characterization of clinically relevant alterations including IDH1, TERT, and c-MYC-associated metabolic programs. In addition, we discuss recent advances in acquisition methods, image standardization, and multimodal integration with conventional MRI and positron emission tomography. Although several technical and logistical challenges remain, hpMRI is an investigational, radiation-free metabolic imaging modality with potential applications in diagnosis, molecular stratification, and treatment monitoring; however, substantial technical, regulatory, logistical, and economic barriers currently limit routine clinical use, molecular stratification, therapeutic monitoring, and precision medicine approaches in neuro-oncology. Continued clinical translation and development of novel metabolic probes may further expand its role in brain tumors and other neurological diseases. Full article

Background/Objectives: Wolfram syndrome is an ultra-rare, progressive multisystem disorder in which endocrine and sensory manifestations coexist with neurological involvement. Quantitative magnetic resonance imaging (MRI) may help characterize central nervous system involvement in this condition; however, evidence derived from small imaging cohorts requires cautious interpretation. This study aimed to examine the relationships between different MRI-derived attributes and neurological symptoms in Wolfram syndrome, with the goal of identifying exploratory imaging patterns that may suggest the involvement of specific neural systems. Methods: We analyzed a Spanish cohort of 45 genetically confirmed patients with Wolfram syndrome. A homogeneous subset of 15 patients with standardized 3-Tesla multimodal MRI and adequate image quality was included in the quantitative imaging analysis. T1-weighted MRI, T2-weighted/fluid-attenuated inversion recovery (FLAIR) imaging, and diffusion tensor imaging (DTI) were processed using a standardized workflow for brain extraction, anatomical segmentation, cortical reconstruction, and quantitative feature extraction. A total of 172 MRI-derived features were examined in relation to neurological phenotypes, including dysphagia, ataxia, gait instability, and cognitive impairment. Analyses included principal component analysis, exploratory factor analysis, correlation analyses, and symptom-specific group comparisons. Given the small MRI sample size and the high feature-to-subject ratio, all analyses were considered exploratory and hypothesis-generating, and the findings should be interpreted cautiously pending validation in larger, independent cohorts. Results: Multimodal MRI-derived features showed distributed associations with neurological manifestations. The most recurrent exploratory imaging correlates involved the thalamus, lateral geniculate nucleus, cerebellum, brainstem, ventricular system, corpus callosum, posterior cortical regions, and white-matter pathways. FLAIR-derived signal heterogeneity in the thalamus and lateral geniculate nucleus appeared repeatedly across several clinical manifestations. Dysphagia was associated with a distributed pattern involving cortical thinning, thalamic and brainstem volume reduction, reduced cerebellar white-matter integrity, increased FLAIR heterogeneity, and ventricular enlargement. Ataxia and gait instability showed overlapping but partially distinct imaging profiles, whereas cognitive impairment was associated with broader cortical, subcortical, callosal, cerebellar, and ventricular alterations. Conclusions: In this exploratory pilot study, multimodal MRI-derived features showed clinically plausible associations with neurological manifestations in Wolfram syndrome. The findings support a distributed model of neurological involvement affecting cerebello-thalamo-cortical circuits, visual relay structures, brainstem pathways, and long-range white-matter connections. These results should be interpreted as exploratory MRI-derived attributes rather than as validated biomarkers, prognostic indicators, or clinically applicable imaging signatures. Confirmation in future longitudinal, multicenter studies with harmonized imaging protocols and external validation will be required. Full article

Background and Objectives: Circulating microRNAs (miRNAs) are emerging as accessible biomarkers for multiple sclerosis (MS). In experimental models, miR-221 and miR-222 have been linked to immune and Th17-related pathways, while interleukin-23 (IL-23) is a cytokine driving autoimmune inflammation. This observational study evaluated the expression of circulating miR-221/222 and serum IL-23 concentrations in treatment-naive adult patients with MS. Materials and Methods: This prospective, cross-sectional case–control study included 43 untreated adult patients with MS (36 with relapsing–remitting MS and 7 with primary progressive MS) and 37 healthy controls. Demographic features, Expanded Disability Status Scale (EDSS) scores, magnetic resonance imaging involvement, initial symptoms, serum IL-23 concentration, and miR-221/222 expression were recorded. Total RNA, including small RNAs, was isolated; complementary DNA was synthesized by reverse transcription from RNA templates; and reverse transcription–quantitative real-time PCR (RT-qPCR) was performed using RNU6-2 as the endogenous small RNA reference. Individual ΔΔCt values were specified as the primary inferential scale, while 2^−ΔΔCt fold-change was retained only for descriptive reporting. Results: The relative expression (2^−ΔΔCt) of miR-221 and miR-222 was higher in patients than in controls. Within the patient group, miR-221 and miR-222 relative expression did not differ by age, sex, EDSS, time since MS diagnosis, MRI involvement area, or initial symptoms. No statistically significant difference in IL-23 levels was observed between the patient and control groups. Conclusions: The presence of unaltered IL-23 levels alongside significantly elevated miR-221 and miR-222 expressions in treatment-naive MS patients during the remission phase suggests their potential utility as biomarkers for immune regulation. Given the cross-sectional design of this study, no causal or regulatory relationship between miR-221/222 and IL-23 can be inferred. Full article

Background and Clinical Significance: Spina bifida occulta may be associated with occult spinal dysraphism, including a low-lying conus medullaris or tethered cord, which can increase the risk of neurological injury during neuraxial anesthesia. We report a case in which preoperative magnetic resonance imaging (MRI) and lumbar ultrasonography supported individualized planning for spinal anesthesia for cesarean delivery. Case Presentation: A 31-year-old woman at 37 weeks of gestation was scheduled for elective cesarean delivery because of marginal placenta previa. She had chronic low back pain, and previous lumbar radiography and computed tomography had demonstrated radiographic spina bifida occulta. Preoperative lumbar MRI confirmed that the conus medullaris terminated normally at L1 and showed no evidence of tethered cord, filum terminale thickening, spinal lipoma, or abnormalities at the planned L3/4 puncture site. Based on these findings and discussion with the patient, spinal anesthesia was selected. Immediately before the procedure, lumbar ultrasonography was used to identify the L3/4 interspace, visualize the posterior complex, and estimate needle depth. Spinal anesthesia was successfully achieved with a 27-gauge pencil-point needle and intrathecal hyperbaric bupivacaine, morphine, and fentanyl. Cesarean delivery was completed without new neurological deficits or major anesthetic complications. Conclusions: Preprocedural MRI and lumbar ultrasonography supported individualized anatomical assessment and anesthetic planning in this patient. Full article

Objectives: While longitudinal studies have linked parietal lobe structure and muscle mass, no resistance exercise studies have evaluated whether interventions can have a positive impact on parietal lobe structure. Therefore, we investigated the effects of high-intensity resistance training (HIRT) and blood-flow restriction training (BFRT) on cortical thickness and white matter integrity in the parietal region, as well as in other regions, in an exploratory manner. Methods: A total of 63 older men were assigned to BFRT, HIRT or control groups for 12 weeks of intervention. A total of 48 participants completed brain and thigh magnetic resonance imaging before and after intervention. Cortical thickness was assessed using FreeSurfer, fractional anisotropy (FA) values were calculated using ExploreDTI, thigh muscle anatomical cross-sectional area was measured from MRI. Results: A significant difference in cortical thickness was observed only in HIRT group in the left parietal cortex—inferior parietal, supramarginal and posterior cingulate. Exploratory analyses revealed cortical thickness changes in other left-hemisphere regions, including the temporal (bankssts, inferior temporal), frontal (medial orbitofrontal, precentral, rostral middle frontal), and occipital (lateral occipital) cortices. In contrast, the BFRT group showed significant FA value change in parietal region – in left inferior parietal, left precuneus and right superior parietal. Exploratory analyses showed FA value change in additional regions in the BFRT group, including the left frontal (caudal middle frontal and superior frontal), left temporal (fusiform), right occipital (lateral occipital), and in the HIRT group, in the left frontal region (pars opercularis). Conclusions: HIRT and BFRT were associated with beneficial brain structural changes, although through distinct neurobiological mechanisms, with HIRT primarily influencing cortical thickness and BFRT predominantly affecting white matter microstructure. Full article

Background/Objectives: Pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) is an important prognostic marker in HER2-positive breast cancer (BC). However, reliable pre-treatment predictors based on routinely available clinical data remain limited. This study evaluated whether clinicopathologic and baseline magnetic resonance imaging (MRI) variables could predict NAC response using classical machine learning (ML) approaches. Methods: A retrospective cohort of 112 patients with HER2-positive BC treated with NAC was analysed, including 57 patients who achieved pCR and 55 who did not. Fourteen pre-treatment variables were evaluated, including hormone receptor (HR) status, tumour grade, ER and PR expression, Ki67, nodal status, age, and baseline MRI characteristics. Seventy ML classifiers were compared using a fully nested leave-one-out cross-validation (LOOCV) framework. Performance was assessed using accuracy, area under the receiver operating characteristic curve (AUROC), Cohen’s kappa, sensitivity, specificity, and F1-score. Results: A support vector machine (SVM) with a radial basis function (RBF) kernel achieved the highest observed accuracy (82.1%) among the 70 evaluated classifiers. The corresponding AUROC was 83.3%, Cohen’s kappa was 64.2%, and sensitivity, specificity, and F1-score were 87.7%, 76.4%, and 83.3%, respectively. HR-related variables, particularly PR and ER expression, together with Ki67 and baseline MRI features, ranked among the most influential predictors. Despite relying exclusively on routinely available pre-treatment variables, the model demonstrated meaningful predictive performance. Conclusions: ML applied to routinely available clinicopathologic and baseline MRI variables showed promising ability to predict pCR before treatment initiation in HER2-positive BC. The proposed approach may support pre-treatment clinical risk assessment using information already generated during routine clinical assessment. Nevertheless, prospective multicentre external validation, calibration assessment, and evaluation of clinical utility are required before implementation in routine clinical practice. Full article

Background and Objectives: We aimed to examine the demographic characteristics, prenatal imaging findings, genetic evaluation results, and postnatal outcomes of fetuses with posterior fossa anomalies (PFAs), and also to evaluate the diagnostic concordance between prenatal ultrasonography (USG) and fetal magnetic resonance imaging (MRI). Materials and Methods: This descriptive study analyzed singleton pregnancies referred to Izmir City Hospital and Tepecik Training and Research Hospital for suspected fetal PFA between 2016 and 2024. Data including USG findings, fetal MRI reports, genetic results, and perinatal outcomes were extracted from institutional records. Diagnostic concordance between USG and MRI was statistically assessed using the kappa coefficient. Results: Out of 152 fetuses with suspected PFA on USG, 116 underwent fetal MRI. Following the exclusion of normal MRI findings (n = 23), the final cohort comprised 93 fetuses with confirmed PFA. Mega cisterna magna (MCM) was the most prevalent diagnosis (54.8%), followed by cerebellar hypoplasia (CH) (15.1%) and Dandy–Walker malformation (DWM) (10.8%). A moderate-to-good diagnostic concordance was observed between USG and MRI (kappa = 0.640, p < 0.001). Significant differences were noted across MRI groups regarding gestational age at diagnosis (p < 0.001) and birth weight, which was notably lower in CH compared to MCM (p = 0.004). Clinical outcomes varied significantly by diagnosis (p < 0.001); while 74.5% of MCM cases showed normal development, adverse outcomes predominated in CH and Walker–Warburg syndrome. Conclusions: Fetal PFAs are a heterogeneous group of anomalies with different diagnostic and variable prognostic profiles. Fetal MRI improves anatomical classification and provides clinically significant contributions to prenatal counseling and perinatal management. Full article