Search Results (145)

Background and Objectives: To assess refractive and visual outcomes following phacoemulsification using a novel algorithm for toric intraocular lens (IOL) surgery. Setting: Private practice, Spain. Design: Prospective observational study. Materials and Methods: The algorithm was designed to control the topographic position of the principal meridians (flat and steep) after cataract surgery in eyes without associated corneal pathology or previous corneal surgery. It is well known that a toric IOL must be positioned along the steep meridian. Therefore, it is crucial to predict both the postoperative position of the steep meridian and its magnitude. Data from patients who were planned for refractive lens exchange or cataract surgery using the Pešić-Barraquer algorithm and implantation of a toric IOL in eyes with different degrees of astigmatism were used to assess the effect of residual astigmatism on 6-month postoperative monocular uncorrected and corrected distance logMAR visual acuity values (UDVA and CDVA). Vector analysis was performed with J0 and J45 evaluations, and centroid errors in postoperative refractive astigmatism prediction error were calculated in the spectacle plane using the “Astigmatism Double-Angle Plot Tool”. Results: Three hundred and six eyes of 250 patients with a mean age of 69.0 years ± 8.6 were enrolled in the study. The mean preoperative corneal astigmatism measured with Pentacam was 1.43 D ± 0.83 (SD). One hundred and eighty-four eyes (60.13%) had “against-the-rule” (ATR) astigmatism, 67 (21.90%) had “with-the-rule” (WTR) astigmatism, and 55 (17.97%) eyes had “oblique” corneal (OBL) astigmatism preoperatively. The mean absolute astigmatic prediction error in residual astigmatism was 0.31 D ± 0.28. Eyes with preoperative ATR corneal astigmatism had lower mean absolute errors compared to the eyes with WTR astigmatism (0.29 D ± 0.26 and 0.34 D ± 0.31, respectively). Centroid error in predicted residual astigmatism was 0.08 D ± 0.41 @4°. All eyes achieved residual refractive astigmatism within the 1.00 D range, and 55.23% had no residual astigmatism in the spectacle plane. Mean postoperative refractive astigmatism at the spectacle plane was 0.24 D ± 0.29. There were no postoperative complications. Additional statistical analysis of 310 eyes confirmed that when the main incision is not placed on one of the three meridians (flat, steep, or 45-degree bisector), the axis of astigmatism induced by the incision is significantly altered. Exploratory subgroup analyses demonstrated comparable prediction accuracy across incision positions, preoperative astigmatism types, and surgeons, further supporting the robustness of the proposed algorithm. Conclusions: In addition to enabling more accurate prediction of postoperative refractive residual astigmatism in patients undergoing toric IOL implantation, our newly proposed algorithm provides surgical pearls to facilitate preoperative and intraoperative management of corneal astigmatism, highlighting the importance of precise incision placement for optimal refractive outcomes. Full article

Background/Objectives: Corneal power has the largest impact on the variability of intraocular lens (IOL) power predictions, and corneal data from different biometers cannot be used interchangeably. We quantified the systematic differences between the Zeiss IOLMaster 700 (IOLM) and the Heidelberg Engineering Anterion and derived strategies for using both devices interchangeably in IOL power calculation. Methods: In this retrospective single-centre study, 837 eyes of 837 cataract patients were measured preoperatively with both biometers. Harmonic mean corneal front and back surface radii were derived from the flat and steep meridians, and corneal power referenced to the front apex plane was expressed as spherocylindrical power vectors (spherical equivalent, SEQ; astigmatic components C0 and C45). Three mapping strategies were compared using Bland–Altman and double-angle plots: linear regression of corneal radii without (MR) and with (MRI) intercept and multivariate linear regression of the power vector components (MMV). Results: Corneal front surface radii agreed well between devices (MR slope 1.000), whereas the IOLM reported systematically flatter posterior radii (MR slope 0.943), giving a systematically higher total corneal power (43.105 D versus 42.760 D). MRI mapping largely removed the systematic offset in the corneal radii but did not fully correct the astigmatic centroids, whereas MMV mapping aligned both the SEQ and the astigmatic centroids at the origin and yielded smaller confidence ellipses. Conclusions: Measurements from the two devices are not directly interchangeable, primarily because of systematic discrepancies in the reported posterior corneal curvature. Where identical IOL calculation concepts and formula constants are used across devices, conversion of corneal data is mandatory, and multivariate power vector mapping provides superior harmonisation compared with radius-based approaches. Full article

Objectives: Spinal tumors often require complex surgical treatments, in particular en bloc vertebrectomy, and a pre-operative kinematics and functional assessment of the spine could be advised to improve surgical outcomes and patients’ quality of life. However, established protocols for stereophotogrammetry-based gait analysis are not available. This study aims at evaluating the feasibility of an experimental protocol for multi-segment trunk and spine kinematics in patients scheduled for en bloc vertebrectomy. Methods: Ten patients and ten age- and sex-matched healthy controls underwent full-body gait analysis using an established marker-set able to track the lower limbs, pelvis, thorax, shoulders, and five spine line segments. The participants completed static double leg standing, barefoot level walking, and elementary trunk movements. A preliminary within-session repeatability assessment in two individuals (one representative patient and one healthy participant) was performed (root mean square error smaller than 10% of ROM; intra-class correlation coefficients > 0.8). Results: Compared with controls, patients affected by spinal tumors showed slower gait, shorter stride length, smaller ROM at the pelvis and thorax, and reduced frontal-plane mobility between spine line segments, but physiological lower-limb joint kinematics. During elementary movements, patients exhibited reduced trunk ROM in the anatomical plane of motion, particularly at a central spine segment, and smaller pelvic mobility in axial rotations. Conclusions: The results of this study support the feasibility of the proposed protocol for gait analysis in the rare clinical population of patients affected by spinal tumors and provide descriptive functional information that may complement conventional pre-operative clinical and imaging assessments. Full article

Background: Classical Couinaud’s segmentation assumes the dichotomous division of the right posterior portal vein (RPPV) into P6 and P7. However, increasing imaging evidence suggests substantial anatomical variability, limiting the intraoperative identification of segmental borders and providing guidance for subsegmental resection. Methods: We retrospectively analyzed contrast-enhanced five-phase computed tomography (CT)-based three-dimensional reconstructions from 100 consecutive eligible cases (2020–2025). Third-order RPPV branching patterns were classified into three types: bifurcation (PV-type 1), loops (PV-type 2), and others (PV-type 3). We measured the 3D distances from the posterior portal origin to the first major branch point and performed volumetric analysis of territories supplied by individual third-order branches using Ziostation REVORAS. Hepatic vein anatomy was categorized as HV-type 1 (a fissure plane forming an intersegmental vein), HV-type 2 (a landmark vein without plane formation), or HV-type 3 (neither) and compared between portal types. Results: PV-type 1 was observed in 45 cases (45.0%), while PV-type 2 was seen in 53 cases (53.0%); however, two cases (2.0%) showed other patterns. The distance to the first branch point was shorter in PV-type 1 than in PV-type 2 (8.89 ± 7.87 vs. 17.3 ± 8.36 mm; p < 0.001). In PV-type 1, the first caudal branch territory (corresponding to S6) accounted for 43.8% ± 12.6% of the posterior section, whereas the first-branch cone-unit territory in PV-type 2 accounted for 14.9% ± 8.64% (p < 0.001). The HV-type 1/2/3 ratios differed by portal type (PV-type 1: 29/16/0; PV-type 2: 25/14/14; p < 0.001), and 26.4% of PV-type 2 cases lacked any hepatic venous landmarks. Conclusions: PV-type 2 peripheral RPPV branching was observed in 53% of cases. Although conventional Couinaud-based segmentectomy with the Glissonian approach and vein-guided transection was suitable for PV-type 1, cone-unit-based anatomical resection supported by individualized preoperative simulation and intraoperative navigation may prove useful for PV-type 2 anatomy. Full article

Background: This study evaluated the analgesic efficacy of the serratus posterior superior intercostal plane block (SPSIPB) in patients undergoing CIED implantation. Methods: In this study, 60 patients undergoing primary CIED implantation were randomized to receive either ultrasound-guided SPSIPB (n = 30) or a sham-control group procedure (n = 30). The primary outcome was perioperative pain intensity, assessed using the Visual Analog Scale (VAS) intraoperatively and at 3, 6, 12, and 24 h postoperatively. Secondary outcomes included postoperative sleep quality measured by the Sleep Quality Numeric Rating Scale (SQ-NRS), patient and physician satisfaction scores. Results: SPSIPB significantly reduced pain scores at all time points compared with the control group (all p < 0.001). Clinically significant intraoperative pain (VAS ≥ 4) occurred in 83.3% of controls but in none of the SPSIPB patients (p < 0.001). Postoperatively, clinically significant pain dropped from 93.3% in controls to just 3.3% with SPSIPB (p < 0.001), with the block group maintaining significantly lower pain scores at 3, 6, 12, and 24 h (mean reductions vs. control of 4.70, 4.13, 3.97, and 1.90 points, respectively; p < 0.001). SQ-NRS scores were lower in the SPSIPB group than in the control group (median 2 vs. 7, p < 0.001). Poor sleep quality (SQ-NRS ≥ 6) was observed in 80.0% of controls and in none of the SPSIPB patients. Patient and physician satisfaction were significantly higher in the SPSIPB group (median Likert score: 5 vs. 3, p < 0.001). Conclusions: Preoperative SPSIPB was associated with substantially lower perioperative pain scores and reduced rescue analgesic requirements during the first 24 h after CIED implantation. Improvements in postoperative sleep quality and patient–physician satisfaction were also observed; however, these secondary outcomes should be interpreted as exploratory. Larger multicenter trials are warranted to confirm the magnitude and generalizability of these findings. Full article

Background: Abdominal wall endometriosis (AWE) following cesarean section (CS) is an increasingly recognized complication. Intramuscular involvement of the rectus abdominis and the management of associated fascial defects remain underreported. Methods: We retrospectively analyzed 14 consecutive women with histopathologically confirmed AWE following CS. Clinical presentation, imaging, operative technique, and follow-up outcomes were analyzed. Results: Mean age was 35.4 years (range 29–45). Three cases (21.4%) showed intramuscular rectus abdominis invasion; 11 (78.6%) were subcutaneous. Mean nodule size was 24.1 mm (range 9–45 mm). Cross-sectional imaging (MRI or CT) was obtained selectively in four patients with the largest lesions. Wide local excision with free margins was achieved in all cases. Two intramuscular cases required primary fascial repair (defects ~2 cm) without prosthetic mesh. No recurrences were detected at 12–24 months of follow-up. Conclusions: AWE following CS may involve both subcutaneous and intramuscular planes. Wide local excision with primary fascial repair is effective for small defects. Preoperative sonographic evaluation and individualized operative planning are essential for optimal outcomes. Full article

Background: Although chronic venous insufficiency is often treated as a localized problem, it is a systemic condition that can negatively affect cardiac hemodynamics. This study investigates the associated effects of eliminating the pathologic venous reservoir on right ventricular (RV) functions, systolic pulmonary artery pressure (sPAP), and inferior vena cava (IVC) diameter in patients undergoing endovenous radiofrequency ablation (RFA) for severe great saphenous vein (GSV) insufficiency. Methods: This retrospective observational study included 154 patients who presented between September 2023 and May 2025 with GSV insufficiency (CEAP C3-C4b) and underwent endovenous RFA. Patients with major cardiopulmonary diseases were strictly excluded. Preoperative and 6-month postoperative transthoracic echocardiography records were analyzed to evaluate RV diastolic diameter, tricuspid annular plane systolic excursion (TAPSE), sPAP, the TAPSE/sPAP ratio, and IVC diameter. Results: At 6 months post-RFA, compared to preoperative values, a significant decrease was detected in the mean sPAP (14.7 ± 2.5 vs. 11.8 ± 1.8 mmHg, p < 0.001) and IVC diameter (2.1 ± 0.2 vs. 1.9 ± 0.2 cm, p < 0.001). Furthermore, significant improvements were observed in TAPSE (20.0 ± 2.0 vs. 21.5 ± 1.8 mm, p < 0.001) and the TAPSE/sPAP ratio (1.36 ± 0.15 vs. 1.82 ± 0.18 mm/mmHg, p < 0.001). Conclusions: Endovenous RFA is associated with favorable changes in right heart parameters. Eliminating pathologic extremity blood pooling may optimize venous return kinetics and subclinically improve right ventricular–pulmonary arterial coupling. Full article

Background: Three-level anterior cervical discectomy and fusion (ACDF) is widely used for multilevel cervical degenerative disc disease; however, the relationship between postoperative alignment trajectories, adjacent segment degeneration (ASD), and late patient-reported outcomes remains incompletely defined. This study evaluated plane-specific radiological alignment changes, MRI-based ASD, and late functional outcomes in a homogeneous three-level ACDF cohort. Methods: This single-center observational cohort included 29 patients who underwent three-level ACDF between January 2018 and December 2023 and had complete radiographic follow-up. Radiological data were collected retrospectively from institutional records and imaging archives. Cervical sagittal and coronal alignment were assessed using Cobb angles on radiographs obtained preoperatively and at 6 months, 1 year, and 2 years postoperatively. ASD was evaluated at the superior adjacent segment on 2-year MRI. Late patient-reported clinical outcomes were assessed at a mean follow-up of 42.6 ± 6.8 months using the Visual Analog Scale (VAS), Neck Disability Index (NDI), and Nottingham Health Profile (NHP). Results: Sagittal Cobb angle changed significantly over time (χ²(3) = 12.60, p = 0.006; Kendall’s W = 0.145), whereas coronal Cobb angle showed a statistically significant reduction over time, although the absolute magnitude of change was small (χ²(3) = 28.74, p < 0.001; Kendall’s W = 0.330). Lower sagittal Cobb angle correlated with worse NDI (r = −0.46, p = 0.004), and greater coronal Cobb angle correlated with worse physical activity scores (r = 0.52, p = 0.006). Higher Pfirrmann grade correlated with worse NDI (r = 0.49, p = 0.004) and pain scores (r = 0.44, p = 0.021). In exploratory regression analysis, sagittal Cobb angle and Pfirrmann grade were retained in the model for NDI, but these findings should be interpreted as hypothesis-generating. Conclusions: After three-level ACDF, sagittal and coronal alignment followed different postoperative trajectories. Lower sagittal alignment and greater adjacent disc degeneration were associated with worse late neck-related disability. However, given the modest sample size and exploratory nature of the regression analysis, these findings should be interpreted as hypothesis-generating. Larger prospective studies are needed to confirm whether sagittal alignment and MRI-based adjacent segment degeneration independently contribute to late functional outcomes. Full article

Objectives: This randomized, single-blind study aimed to compare the effects of ultrasound-guided erector spinae plane block (ESPB), thoracic paravertebral block (TPVB) and intravenous (IV) analgesia on postoperative pain, opioid consumption and quality of recovery in patients undergoing laparoscopic cholecystectomy (LC). Methods: A total of 120 adult patients (ASA I-III) scheduled for elective LC were randomized into three groups: ESPB (GI), TPVB (GII) and IV analgesia (GIII). Bilateral ESPB or TPVB was performed preoperatively; then all patients received standardized general anesthesia and postoperative analgesia including paracetamol, tenoxicam and IV tramadol via patient-controlled analgesia. The primary outcome was 24 h tramadol consumption. Secondary outcomes included pain scores, rescue analgesia requirement, patient satisfaction, postoperative nausea and vomiting, time to first ambulation, length of hospital stay and Quality of Recovery-15 (QoR-15) scores. Results: Twenty-four-hour tramadol consumption was significantly higher in GIII (135.78 ± 22.73 mg) compared with GI (101.05 ± 26.99 mg) and GII (95.67 ± 31.49 mg) (p < 0.001), with no difference between GI and GII. Both static and dynamic pain scores were lower in GI and GII compared with GIII at most time points. Rescue analgesia requirement and patient dissatisfaction were significantly higher in GIII. QoR-15 scores were significantly improved in GI and GII compared with GIII (p < 0.001), while no difference was observed between the regional techniques. Block performance time was shorter with ESPB than TPVB (p < 0.001). No complications were reported. Conclusions: ESPB and TPVB provided effective analgesia and improved recovery after LC compared with IV analgesia alone. Both regional techniques may be considered as components of multimodal analgesia after LC. Full article

Background/Objectives: Optimal trajectories for S2-alar-iliac (S2AI) screw placement have been widely studied; however, in fluoroscopy-assisted free-hand techniques, exact reproduction is rarely achievable. This study aimed to quantify direction-specific safety margins around patient-specific optimal trajectories and to determine their relationship with pelvic parameters. Methods: We retrospectively analyzed patients who underwent S2AI screw fixation with available preoperative and postoperative CT imaging. Pelvic parameters, including pelvic tilt (PT), sacral slope (SS), and pelvic incidence (PI), were measured. Optimal transverse and sagittal screw angles were determined using CT-based planning. Postoperative CT was used to assess actual screw trajectories and cortical violations. Direction-specific generalized estimating equation models were used to evaluate associations between trajectory deviation and screw malposition. Receiver operating characteristic (ROC) analysis was performed to determine cutoff values for safe deviation. Results: A total of 62 patients (105 screws) were included in axial analysis and 41 patients (76 screws) in sagittal analysis. PT and PI showed significant inverse correlations with both optimal transverse and sagittal angles (all p < 0.001). Greater lateral and medial deviations were significantly associated with corresponding cortical violations (OR 2.33, 95% CI 1.51–3.59; and OR 2.10, 95% CI 1.40–3.15 per degree, respectively; both p < 0.001). Inferior deviation was significantly associated with violation in the sagittal plane (OR 1.39, 95% CI 1.18–1.65 per degree; p < 0.001), whereas superior deviation was not significant. ROC analysis demonstrated asymmetric safety margins: 1.5° lateral (AUC = 0.972), 8.1° medial (AUC = 0.965), and 18.5° inferior (AUC = 0.897). Conclusions: S2AI screw placement may be conceptualized as a tolerance-based process centered on a patient-specific optimal trajectory. Safety margins are direction-dependent and asymmetric, with a narrow tolerance for lateral deviation. These findings provide practical guidance for intraoperative trajectory adjustment in free-hand techniques. Full article

Background and Objectives: Although the anterior mandible is generally considered a safe region for implant placement, injury to the medial lingual foramen (MLF) may result in significant vascular complications. Accurate identification of this structure is challenging due to its small size, low volumetric representation, and anatomical variability. This study aimed to evaluate the anatomical characteristics of the MLF using cone-beam computed tomography (CBCT) and to develop and validate a deep learning-based approach for its automated detection and segmentation. Materials and Methods: A total of 106 CBCT scans were retrospectively analyzed to assess the morphology and position of the MLF. Manual pixel-wise annotations of the complete canal trajectory were performed on sagittal slices and used to train convolutional neural network models based on a U-Net-derived framework. Multiple configurations, including multi-class, binary, two-dimensional, and three-dimensional approaches, were evaluated. Given the extremely limited volumetric representation of the MLF, severe class imbalance represented a major challenge during model training and evaluation. Model performance was assessed using the Dice similarity coefficient, precision, recall, and Hausdorff distance. External validation was performed on an independent dataset of 10 CBCT scans. Results: The MLF was identified in all patients, with a single canal observed in 63% of cases. The sagittal-plane binary segmentation model achieved the best performance, with a test Dice score of 0.79, precision of 0.88, and recall of 0.73. External validation demonstrated a Dice score of 0.81, precision of 0.89, and recall of 0.71. The 95th percentile Hausdorff distance was 2.6 mm, and the mean center-point localization error was 1.2 mm. The model correctly detected the MLF in 90% of external cases. Conclusions: Deep learning-based segmentation of the MLF is feasible and may support automated localization assistance during preoperative CBCT assessment. Performance was influenced by the alignment between the annotation strategy and model input, highlighting an important consideration for small-structure segmentation. Further validation on larger multicenter datasets is required before clinical implementation can be considered. Full article

Background/Objectives: High common carotid artery bifurcation (CCAB) is an anatomic variant relevant to carotid endarterectomy that is associated with an increased risk of cranial nerve injury, particularly hypoglossal nerve injury. This study analyzed CCAB location relative to anterior neck landmarks as a method for categorizing its proximity to critical surgical structures. Methods: Eighty-one formalin-fixed donors were dissected, yielding 159 CCABs. CCAB height was classified relative to six transverse anterior neck planes using superficial anatomic landmarks. Distances from the CCAB to the hypoglossal nerve and angle of the mandible were measured. Superior thyroid (ST) artery origin was also recorded. Results: A majority of CCABs occurred near the hyoid bone, but locations varied between and within donors. CCAB height did not differ significantly by sex or by which side of the neck they were from. Higher CCABs were closer to the hypoglossal nerve and angle of the mandible. When using anterior neck landmarks, there was a strong linear relationship between the height of the CCAB and both the hypoglossal nerve and the angle of the mandible. The hypoglossal nerve looped inferior to the CCAB in 11 cases. ST artery origin varied, with higher CCABs originating from the common carotid artery more often. Conclusions: By using anterior neck landmarks to classify CCAB height, clinicians may establish a more precise definition of high CCAB that incorporates reliable estimates of hypoglossal nerve proximity. This approach may improve preoperative risk assessment, guide surgical selection, and reduce complications. Full article

Unicompartmental knee arthroplasty (UKA) is an effective treatment for anteromedial osteoarthritis in carefully selected patients. Increasing attention has recently been directed toward restoration of pre-arthritic coronal alignment, supported by the use of the arithmetic hip–knee–ankle angle (aHKA) to estimate constitutional lower limb alignment. In medial UKA, kinematic alignment principles derived from the original technique described by Cartier et al. may help to reproduce native joint-line orientation while preserving physiological soft-tissue balance. This technical note details the indications, preoperative assessment, planning strategy, and operative steps of the procedure. Preoperative long-leg weight-bearing radiographs are used to estimate constitutional alignment through the aHKA and to plan the coronal inclination of the tibial cut. Intraoperatively, the distal position of the extramedullary guide is reproduced according to the preoperative planning in order to restore the native inclination of the medial tibial plateau. The sagittal tibial cut, posterior tibial slope, distal femoral cut, component sizing, gap assessment, and cementation technique are described, with emphasis on anatomical landmarks and technical pearls to improve reproducibility. The described technique provides a practical method for approximating constitutional coronal alignment in medial UKA without the use of robotic or navigated systems. The key feature of the procedure is accurate planning and execution of the tibial cut in both the coronal and sagittal planes in order to reproduce native joint-line orientation and preserve appropriate ligament balance. Full article

Background: Traditional intraoperative sizing for sutureless aortic valves, such as the Corcym Perceval Plus (CPP), often relies on subjective tactile feedback, which can lead to excessive over-sizing. Significant over-sizing is associated with complications like increased trans-prosthetic gradients, valve thrombosis, and conduction disturbances requiring permanent pacemakers. This study aims to develop an AI-driven predictive recommendation system using Multidetector Computed Tomography (MDCT) data to optimize valve sizing and improve patient outcomes. Methods: Data were collected from 380 consecutive patients who underwent aortic valve replacement with a CPP prosthesis between 2011 and 2026. Two machine learning models were trained using preoperative MDCT features, including annular area, perimeter, and diameters. The first model predicted “normal” clinical labels, while the second used “penalized” labels adjusted for postoperative hemodynamic performance to discourage over-sizing. The dataset was split into training (80%) and testing (20%) subsets. Results: The mean patient age was 77.6 years. The model using normal labels achieved an overall accuracy of 91.84% (68.75% on the test set). The penalized label model showed improved performance with an overall accuracy of 92.89% (72.16% on the test set). MDCT provided highly reproducible objective metrics superior to echocardiography for calculating optimal sizing. Conclusions: The AI-driven recommendation system proves to be a reliable and reproducible tool for preoperative planning. By transitioning from subjective tactile assessment to predictive modeling, surgeons can better select valve sizes that minimize complications, particularly in minimally invasive approaches. Full article

Although breast cancer has been associated with subclinical left ventricular dysfunction in humans, the cardiac effects of CMTs remain poorly defined. This pilot, exploratory (communication) study compared clinical and echocardiographic parameters between dogs with CMTs and healthy controls and assessed the feasibility of combining myocardial deformation imaging with exploratory data-driven analysis for preoperative cardiac assessment. All dogs underwent a standardized clinical and echocardiographic assessment, including two-dimensional speckle-tracking echocardiography (2D-STE). Given the limited sample size, analyses were designed to generate hypotheses rather than to provide definitive predictive conclusions. Exploratory machine learning modeling (XGBoost), receiver operating characteristic (ROC) analysis, calibration, and decision curve analysis were performed as proof-of-concept approaches without external validation. Despite normal conventional systolic indices, dogs with CMTs exhibited reduced global longitudinal strain (GLS) and mitral annular plane systolic excursion (MAPSE) (p < 0.01), suggesting subclinical systolic dysfunction. Deformation-derived parameters appeared more sensitive for detecting subtle myocardial alterations within this cohort. The exploratory machine learning model demonstrated moderate discrimination (AUC-ROC = 0.75); however, these findings are preliminary and should not be interpreted as evidence of clinical predictive performance. Overall, these results suggest that conventional systolic indices may underestimate early myocardial changes in dogs with CMTs. This communication highlights the feasibility of integrating deformation imaging with exploratory analytical approaches and provides a basis for future large-scale, validated studies in veterinary cardio-oncology. Full article