Search Results (3,647)

Aim: The aim of the current investigation was to detect serotypes of Aggregatibacter actinomycetemcomitans in a cohort of Western Australians diagnosed with periodontitis. Materials and Methods: A total of 64 subjects were selected. Intra-oral samples were taken from every subject in the present investigation. Periodontal, radiographical, and microbiological analyses were conducted. A polymerase chain reaction was employed to investigate the presence of Aggregatibacter actinomycetemcomitans serotypes. Results: Only twelve (18.75%) patients were tested positive for Aggregatibacter actinomycetemcomitans. The most dominant serotypes of Aggregatibacter actinomycetemcomitans in this group were serotype e (80.55%), followed by serotype c (52.77%). Both serotypes b and d were absent in the present investigation. Serotype e presented in isolation or combined with other serotypes. The other serotypes tend to be present alone, but when they were isolated together, they were always combined with serotype e. It seems that serotype e of Aggregatibacter actinomycetemcomitans is associated with those who live in rural areas (p = 0.003), and those with low education (p = 0.041), and severe forms of periodontitis in this cohort. Conclusions: In patients diagnosed with severe periodontitis, serotype e was dominant in this population. Serotypes b and d did not appear in the present study. Full article

This study introduces a MATrix LABoratory (MATLAB, version R2024b, update 1 (24.2.0.2740171))-based automated system for the detection and measurement of indication areas in coated surfaces, enhancing the accuracy and efficiency of quality control processes in metal, polymeric and thermoplastic coatings. The developed code identifies various indication characteristics in the image and provides numerical results, assesses the size and quantity of indications and evaluates conformity to ISO standards. A comprehensive testing method, involving non-destructive penetrant testing (PT) and radiographic testing (RT), allowed for an in-depth analysis of surface and internal porosity across different coating methods, including aluminum-, copper-, polytetrafluoroethylene (PTFE)- and polyether ether ketone (PEEK)-based materials. Initial findings had a major impact on indicating a non-homogeneous surface of obtained coatings, manufactured using different technologies and materials. Whereas researchers using non-destructive testing (NDT) methods typically rely on visual inspection and manual counting, the system under study automates this process. Each sample image is loaded into MATLAB and analyzed using the Image Processing Tool, Computer Vision Toolbox, Statistics and Machine Learning Toolbox. The custom code performs essential tasks such as image conversion, filtering, boundary detection, layering operations and calculations. These processes are integral to rendering images with developed indications according to NDT method requirements, providing a detailed visual and numerical representation of the analysis. RT also validated the observations made through surface indication detection, revealing either the absence of hidden defects or, conversely, internal porosity correlating with surface conditions. Matrix and graphical representations were used to facilitate the comparison of test results, highlighting more advanced methods and materials as the superior choice for achieving optimal mechanical and structural integrity. This research contributes to addressing challenges in surface quality assurance, advancing digital transformation in inspection processes and exploring more advanced alternatives to traditional coating technologies and materials. Full article

Background and Objectives: Monteggia fracture-dislocations are rare but critical injuries in children. Accurate early diagnosis is essential to avoid long-term complications; however, such injuries are frequently missed. Therefore, this study aimed to assess the diagnostic accuracy of Monteggia fractures among physicians of varying specialties and experience levels and to identify factors influencing diagnostic performance. Materials and Methods: This retrospective study analyzed the radiographic interpretations of pediatric elbow and forearm injuries by six physician groups: orthopedic residents, general orthopedic surgeons, pediatric orthopedic surgeons, general radiologists, and subspecialized musculoskeletal radiologists. The final diagnosis established by pediatric radiology experts served as the reference standard. Influential variables, such as image quality, splint application, and age-related ossification, were evaluated. Results: In total, 120 patients were included, 40 (33.3%) of whom were diagnosed with Monteggia fractures and 80 (66.7%) with other fracture types. The diagnostic accuracy of Monteggia fractures varied significantly according to the physician’s experience. First-year residents and non-subspecialty radiologists had the highest rate of missed diagnoses. While other fracture types were occasionally influenced by technical factors, most missed Monteggia fracture cases stemmed from recognition failure. Subtle imaging features, plastic deformation of the ulna, and the omission of dedicated elbow views contributed to the misdiagnosis. Awareness and training improved performance, and a high index of suspicion was identified as crucial. Early follow-ups and standardized imaging protocols were identified as effective safeguards. Conclusions: Experience level, awareness, and imaging protocol quality were identified as being central to the accurate diagnosis of pediatric Monteggia fractures. Implementing educational strategies, promoting systematic imaging reviews, and reinforcing team-based approaches may reduce the rate of missed diagnoses. Full article

Dehydrated human-derived amnion–chorion membranes (ACM), known for their bioactive composition of growth factors and cytokines, have demonstrated potential as a bioactive scaffold in regenerative medicine; however, their clinical application in regenerative endodontic procedures (REPs) remains unexplored. This retrospective study aimed to evaluate the clinical and radiographic outcomes of REPs using ACM compared to collagen matrices (CM) in immature necrotic permanent teeth. Forty-one immature necrotic teeth from 38 patients (mean age: 14.68 ± 7.43 years) were treated with REPs using either ACM (n = 21) or CM (n = 20) scaffolds over a mean follow-up period of 23.23 months. Outcomes assessed included survival, success, root development measured by radiographic root area (RRA), and pulp sensibility. Independent t-tests compared outcomes between groups, while Cox regression and generalized linear models identified predictors of treatment outcomes. Overall survival and success rates were 87.8% and 82.9%, respectively. ACM-treated teeth achieved 90.5% survival and 85.7% success rates, while CM-treated teeth demonstrated 85.0% survival and 80.0% success rates, with no statistically significant differences between groups (p > 0.05). Root development occurred in 85.4% of cases overall, with significant RRA increases of 13.89 ± 13.95% for ACM and 11.24 ± 11.21% for CM (p < 0.05 within each group). Pulp sensibility recovery was observed in 51.2% of treated teeth overall, with 42.9% for ACM-treated teeth and 55.0% for CM-treated teeth (p > 0.05). Notably, ACM-treated teeth demonstrated earlier sensibility recovery compared to those of CM-treated teeth. Age was identified as a significant negative predictor of root development outcomes (p < 0.05). This clinical study demonstrates that both ACM and CM are clinically effective scaffolds for REPs, achieving high survival rates and promoting root development in immature necrotic teeth. While overall success rates were comparable, ACM showed faster sensibility recovery, suggesting potential biological advantages for enhanced tissue regeneration and earlier functional recovery. Full article

Background/Objectives: No reliable noninvasive biomarkers are available to predict RT-induced cardiotoxicity. Because the pericardial sac is a fast responder to cardiac injury, we investigated whether RT-induced radiographic pericardial changes might serve as early imaging biomarkers for late cardiotoxicity. Methods: We performed a retrospective study of 476 patients (210 males, 266 females; median age, 69 years; median follow-up, 26.7 months) treated with chemo-RT for small cell and non-small cell lung cancers at one single institution from 2009 to 2020. The heart and its 4 mm outmost layer (representing the pericardial sac) were contoured on standard-of-care baseline CTs. Six-month post-RT follow-up CTs were deformably registered on the baseline CTs. Data were harmonized for the effect of contrast. We labeled voxels as Fat, Fluid, Heme, Fibrous, and Calcification using Hounsfield units (HUs). We studied pericardial HU-change histograms as well as volume change and voxel-based mass change in each tissue composition. Results: Pericardial HU-change histograms had skewed distributions with a mean that was significantly correlated with mean pericardial dose. Voxels within Fluid, Heme, and Fibrous had mass changes consistent with the dose. In Kaplan–Meier curves, Fibrous and Heme volume changes (translating into thickening and effusion), Fat mass change, mean doses to heart and pericardium, history of cardiac disease, and being male were significantly associated with shorter survival, whereas thickening and effusion were significantly associated with shorter time to a post-RT cardiovascular disease diagnosis. Conclusions: Pericardium composition distribution has dose-dependent changes detectable on standard-of-care CTs at around 6 months post-RT and may serve as surrogate markers for clinically relevant cardiotoxicity. The findings should be validated with additional research. Full article

Radiographic axial spondyloarthritis (r-axSpA) is associated with increased cardiovascular disease (CVD) risk. The coronary artery calcification (CAC) score, an atherosclerosis burden indicator that predicts CVD risk, is not well studied in r-axSpA. This study investigates CAC scores in patients with r-axSpA compared to controls without rheumatic disease and factors associated with CAC scores in r-axSpA patients. Fifty-eight r-axSpA patients from southwestern Sweden were assessed cross-sectionally using clinical disease measures, physical function, spinal mobility, lipid profiles, inflammation markers, and long-term time-averaged C-reactive protein (CRP). Four controls per patient were selected from the Swedish CArdioPulmonary bioImage Study (SCAPIS). CAC was scored on cardiac computed tomography (CT) using the Agatston method. The presence of CAC in the right coronary artery (RCA) was higher in patients compared to controls. However, no significant difference in total CAC scores was observed between r-axSpA patients and controls, despite numerically higher total CAC scores in patients. In r-axSpA patients, CAC scores correlated positively with time-averaged CRP, reduced physical function, and impaired spinal mobility. These findings suggest that chronic inflammation may contribute to coronary calcification and CVD risk in r-axSpA, highlighting the need for effective anti-inflammatory treatments. Further research is warranted to explore the association between coronary calcification, spinal immobility, and limitations in physical function. Full article

Introduction: Dental caries remains a public health concern, and early detection prevents its progression and complications. Panoramic radiographs are essential diagnostic tools, yet the interpretation of panoramic X-rays varies among practitioners. Artificial intelligence (AI) presents a promising approach to enhance diagnostic accuracy in detecting dental caries. This scoping review examines the current literature on the use of AI programs to analyze panoramic radiographs for the diagnosis of dental caries. Methods: This scoping review searched PubMed, Scopus, Web of Science, and Dentistry and Oral Sciences Source, adhering to PRISMA guidelines. The review included peer-reviewed, original research published in English that investigated the use of AI to diagnose dental caries. Data were extracted on the AI model characteristics, advantages, disadvantages, and diagnostic performance. Results: Seven studies met the inclusion criteria. The Deep Learning Model achieved the highest performance (specificity 0.9487, accuracy 0.9789, F1 score 0.9245), followed by Diagnocat and Tooth Type Enhanced Transformer. Models such as CranioCatch and CariSeg showed moderate performance, while the Dental Caries Detection Network demonstrated the lowest. Benefits included improved diagnostic support and workflow efficiency, while limitations involved dataset biases, interpretability challenges, and computational demands. Conclusions: Applying AI technologies to panoramic X-rays demonstrates the potential for enhancing caries diagnosis, with some models achieving near-expert performance. However, future research must address the generalizability, transparency, and integration of AI models into clinical practice. Future research should focus on diverse training datasets, explainable AI development, clinical validation, and incorporating AI training into dental education and training. Full article

Background/Objectives: Endoscopic retrograde cholangiopancreatography (ERCP) with stone extraction is the standard treatment for common bile duct (CBD) stones. However, when complete removal is not feasible, the temporary placement of a plastic stent (PS) is commonly used. This study aimed to assess 12-month stent patency in elderly patients with CBD stones. Methods: This prospective study included patients aged 70 years or older who underwent ERCP with PS placement for CBD stones at Daegu Catholic University Medical Center from March to December 2023. Patients were followed every three months with laboratory tests and abdominal radiographs. Stent dysfunction was defined as either cholangitis or cholecystitis due to stent migration or occlusion. Results: Of 12 enrolled patients, 2 were lost to follow-up. The remaining 10 had a median age of 85 years. The median stone diameter and number were 16.5 mm and 3, respectively. Two patients (20%) experienced stent dysfunction at 1.4 and 2.7 months and underwent successful stent exchange. Of the remaining eight, one declined further ERCP, while seven underwent elective ERCP at 12 months. Among them, five achieved successful stone removal and two required stent exchange. Kaplan–Meier analysis showed 90% patency at 1.4 months and 80% at 2.7 months, maintained through 12 months. Conclusions: Plastic stents showed an acceptable 12-month patency in most elderly patients. Early complications suggest the need for close monitoring during the first three months, after which long-term stent maintenance may be feasible in selected cases. Larger studies are needed to validate these findings. Full article

Background: Lateral tibial hemiepiphysiodesis with tension band plates is an established method for correcting genu varum in skeletally immature patients. However, outcomes may vary depending on underlying pathology and patient characteristics. Methods: This retrospective cohort study evaluated 31 patients (53 knees) treated between 2011 and 2024 at a tertiary pediatric orthopedic center. Patients were categorized as idiopathic or non-idioathic genu varum based on diagnosis. Inclusion criteria required open physes, absence of previous or concomitant knee surgeries for alignment correction, and availability of standardized long-standing radiographs. Radiographic parameters, including mechanical axis deviation (MAD), hip–knee–ankle angle (HKA), and medial proximal tibial angle (MPTA), were assessed pre-operatively and at implant removal. Outcomes were classified as complete correction, partial correction, absent correction, overcorrection, or progression of deformity. Results: Overall, 64.2% of knees achieved complete correction. Success was significantly higher in idiopathic cases (82.1%) than in non-idiopathic deformities (44%). Success was also more frequent in males (p = 0.040). In multivariable analysis, non-idiopathic patients (β = 351.9; p = 0.002), HKA improvement (β = 1.4; p = 0.010) and change in BMI z-score (β = 202.4; p = 0.009) independently predicted surgical success. No major complications (Clavien–Dindo–Sink grade > 2) were observed. Conclusions: Lateral tibial hemiepiphysiodesis is effective for idiopathic genu varum, offering minimally invasive correction with low complication rates. However, outcomes in non-idiopathic deformities are less predictable, emphasizing the need for individualized treatment planning and counseling. Early intervention, careful implant positioning, and rigorous follow-up are essential to optimize results and prevent unintended overcorrection. Full article

Background: This retrospective study aimed to assess the prevalence and distribution of common soft tissue ossifications and calcifications in the head and neck area, such as tonsilloliths, calcified lymph nodes, atherosclerotic plaques, stylohyoid ligament calcifications, and laryngeal cartilage calcifications, using panoramic radiographs (PRs) from a Turkish population. A secondary objective was to analyze these findings based on age and gender, ultimately seeking to enhance clinicians’ awareness of these incidental findings and their potential diagnostic significance. Methods: PRs of 1207 patients applying to the Department of Oral and Maxillofacial Radiology at Necmettin Erbakan University Faculty of Dentistry between 2021 and 2022 were reviewed. Out of these, 1193 images meeting quality criteria and showing distinct anatomical details were included. Patients with prior diagnosed bone metabolic disorders were excluded. Two radiologists independently assessed the images for the presence of soft tissue calcifications and ossifications. Inter-observer reliability was quantified using Cohen’s Kappa coefficient, which was found to be 0.78, indicating substantial agreement (95% CI: [0.72–0.83], p < 0.001). The calcifications and ossifications were categorized according to age, gender, and type. Data were analyzed employing descriptive statistical methods and Chi-square tests, with a significance level set at p < 0.05. Results: Soft tissue calcification or ossification was observed in 122 (10.22%) of the 1193 retrospectively evaluated PRs. The most common findings included stylohyoid ligament ossifications (n = 31), laryngeal cartilage calcifications (n = 28), tonsilloliths (n = 25), calcified atherosclerotic plaques (n = 18), and calcified lymph nodes (n = 18). Two antroliths were also identified. Arteriosclerosis, phleboliths, and sialoliths were not detected in this cohort. Although some types of calcification showed numerical variations across age groups and genders (e.g., higher prevalence of most anomalies in patients aged 31 years and older; more frequent laryngeal cartilage calcification in women and tonsilloliths in men), Chi-square analyses revealed no statistically significant association between the presence of these calcifications or ossifications and either age group (p = 0.284) or gender (p = 0.122). Conclusions: PRs serve as an effective initial screening instrument for identifying soft tissue calcifications within the head and neck region, owing to their widespread availability, cost-effectiveness, and minimal radiation exposure. The detection of such findings is of paramount importance, as they may indicate underlying systemic conditions necessitating further diagnostic evaluation. While clinicians should remain vigilant to these anomalies, definitive diagnosis typically requires supplementary imaging modalities such as cone-beam computed tomography (CBCT), ultrasound, or histopathological analysis. Full article

Background: The management of irreparable posterosuperior rotator cuff tears with an isolated loss of external rotation presents significant challenges. Latissimus dorsi tendon transfer in conjunction with medialized reverse total shoulder arthroplasty has been employed to rectify external rotation deficits; however, lateralized RTSA designs may yield similar outcomes with a reduced incidence of complications. The objective of this study was to compare the clinical outcomes of lateralized reverse total shoulder arthroplasty without latissimus dorsi tendon transfer against medialized RTSA with LDT in patients with ILER and a positive external rotation lag sign. Methods: This retrospective cohort study involved 34 patients diagnosed with CTA and severe external rotation deficiency, characterized by a positive ER lag sign and 0° active ER. The patients were treated with either lateralized reverse total shoulder arthroplasty (n = 21) or medialized RTSA with LDT (n = 13). Outcomes evaluated preoperatively and at the 24-month follow-up comprised range of motion, ER lag sign, Constant–Murley Score, SPADI, and radiographic offset parameters. Statistical analyses were adjusted for age, sex, and baseline values. Results: At follow-up, 70% of patients undergoing lateralized RTSA exhibited resolution of ER lag, compared to 23% in the LDT group (p < 0.05). Active external rotation improvement was more significant in the LDT group (34.6° compared to 18.5°, p < 0.05). However, both groups exhibited comparable final external rotation and functional scores (CMS: 63 ± 9 vs. 63 ± 16; SPADI: 73 ± 20 vs. 74 ± 22). Lateralized RTSA demonstrated superior preservation of internal rotation, as evidenced by a higher percentage of patients achieving a negative Apley scratch test (67% compared to 23%, p < 0.05). A greater glenoidal offset correlated with improved postoperative external rotation and resolution of external rotation lag. The influence of teres minor integrity was more significant in the LDT group. Conclusions: Lateralized reverse total shoulder arthroplasty without latissimus dorsi tendon transfer provides similar functional restoration of external rotation in irreparable posterosuperior rotator cuff tear patients, accompanied by reduced complications, shorter surgical durations, and improved preservation of internal rotation. LDT has the potential to provide enhanced ER gains from a low baseline; however, it is characterized by increased invasiveness and technical complexity. Prosthetic lateralization is a biomechanically effective method for restoring external rotation in patients with rotator cuff arthropathy and external rotation deficits. Full article

Background/Objectives: Diabetes mellitus (DM) can adversely affect oral health by compromising immune function and promoting chronic inflammation. This effect can significantly impact the outcomes of fixed dental prostheses (FDPs). This study aimed to evaluate the rates of complications in FDPs in diabetes patients. Methods: The study investigated various clinical factors, including technical complications and biological complications. The investigation included diabetic patients (test group) and non-diabetic patients (control group), who were evaluated during their follow-up visits. Clinical and radiographic assessments were performed to determine the cumulative survival rate, and life table survival analyses of FDPs in the presence of complications were performed. Results: This study evaluated 1125 FDPs (66.1% in women), with 27.1% in diabetics, over a mean of 9.3 ± 7.7 years. The overall complication rates analysis, using the Mann–Whitney U test, showed a significant difference between diabetic and non-diabetic patients (p = 0.002). Diabetic patients had higher biological complications (58.4% vs. 51.1%, p = 0.03) and more technical complications (7.5% vs. 6.1%, p = 0.382). Poor oral hygiene strongly correlated with failure (72.1% vs. 12.9%, p < 0.001). Survival analysis revealed a decline in FDP survival probability to 0.23 for diabetics and 0.33 for non-diabetics at 15 years (p = 0.012). Conclusions: DM may reduce the durability of fixed dental prostheses, with diabetic patients showing noticeably higher rates of technical and biological complications compared to non-diabetics. Full article

This study aims to evaluate the morpho-functional changes in the patellar ligament in dogs undergoing tibial plateau leveling osteotomy (TPLO) during the first six months of the postoperative follow-up and correlate the radiographic and conventional ultrasonography changes in the patellar ligament with its elastic properties. Dogs with a unilateral cranial cruciate ligament (CCL) rupture who underwent TPLO were enrolled. The patients were subjected to radiographic, ultrasonographic and elastosonographic evaluations of the patellar ligament before surgery (T0) and 1 month (T1), 2 months (T2) and 6 months (T3) after surgery. The radiographic and ultrasound thicknesses of the patellar ligament were recorded at three points: proximal, central and distal. A color map of strain elastosonography with superimposed B-mode images was used to evaluate the elasticity (hardness and softness) of the ligament. Twenty-two dogs completed the trial. At T0, the patellar ligament showed statistically reduced radiographic and ultrasonographic thicknesses compared to those at T1, T2 and T3. Additionally, the patellar ligament in the distal portion was statistically thicker in comparison to the proximal and central points at T2 and T3. At T1, T2 and T3, there was an increase in hardness and a reduction in softness of the patellar ligament compared to that at T0. The elastosonographic analysis and the radiographic and ultrasonographic thicknesses of the patellar ligament showed no correlation. The patellar ligament showed structural and mechanical alterations in the dogs undergoing TPLO, even six months after surgery. Full article

Background and Objectives: Ankle fractures represent one of the most common injuries to the lower limb, particularly impacting women and the elderly. The coronavirus disease 2019 (COVID-19) pandemic greatly disrupted both the incidence of these fractures and their treatment patterns globally. This retrospective epidemiological study analyzed 1010 cases of ankle fractures treated at the Orthopedics Department of Policlinico University Hospital in Catania from 2018 to 2023. The study aimed to evaluate trends in incidence, patient demographics, fracture types, treatment modalities, and hospital stay across the pre-COVID-19, COVID-19, and post-COVID-19 periods. Materials and Methods: A retrospective observational study was conducted including all patients diagnosed with ankle fractures from 1 January 2018 to 31 December 2023. Data were collected from hospital medical records using ICD-9-CM codes and radiographic classification systems (Danis–Weber, Lauge-Hansen, and AO/OTA). Variables analyzed included demographics, fracture type and side, treatment modality, and hospitalization details. Statistical analyses were performed using t-tests, chi-square tests, and linear regression, with significance set at p < 0.05. Results: In 2020, there was a 31.7% decrease in fracture incidence. Although overall fracture rates rebounded after COVID-19, they did not reach pre-pandemic levels. During the pandemic, trimalleolar fractures increased significantly, occurring more frequently in older women, likely due to bone fragility. The rate of surgical treatments rose during and after the pandemic, with a distinct shift from ORIF to external fixation. Hospital stays were longer, especially for patients with cardiovascular risk factors. Conclusions: The pandemic significantly altered the epidemiology, treatment strategies, and outcomes of ankle fractures. These findings highlight the necessity for adaptable care models and preventive strategies, particularly for vulnerable populations such as older women. Full article

Background/Objectives: Clinicians routinely rely on periapical radiographs to identify root-end disease, but interpretation errors and inconsistent readings compromise diagnostic accuracy. We, therefore, developed an explainable, multimodal AI framework that (i) fuses two data modalities, deep CNN embeddings and radiomic texture descriptors that are extracted only from lesion-relevant pixels selected by Grad-CAM, and (ii) makes every prediction transparent through dual-layer explainability (pixel-level Grad-CAM heatmaps + feature-level SHAP values). Methods: A dataset of 2285 periapical radiographs was processed using six CNN architectures (EfficientNet-B1/B4/V2M/V2S, ResNet-50, Xception). For each image, a Grad-CAM heatmap generated from the penultimate layer of the CNN was thresholded to create a binary mask that delineated the region most responsible for the network’s decision. Radiomic features (first-order, GLCM, GLRLM, GLDM, NGTDM, and shape2D) were then computed only within that mask, ensuring that handcrafted descriptors and learned embeddings referred to the same anatomic focus. The two feature streams were concatenated, optionally reduced by principal component analysis or SelectKBest, and fed to random forest or XGBoost classifiers; five-view test-time augmentation (TTA) was applied at inference. Pixel-level interpretability was provided by the original Grad-CAM, while SHAP quantified the contribution of each radiomic and deep feature to the final vote. Results: Raw CNNs achieved a ca. 52% accuracy and AUC values near 0.60. The multimodal fusion raised performance dramatically; the Xception + radiomics + random forest model achieved a 95.4% accuracy and an AUC of 0.9867, and adding TTA increased these to 96.3% and 0.9917, respectively. The top ensemble, Xception and EfficientNet-V2S fusion vectors classified with XGBoost under five-view TTA, reached a 97.16% accuracy and an AUC of 0.9914, with false-positive and false-negative rates of 4.6% and 0.9%, respectively. Grad-CAM heatmaps consistently highlighted periapical regions, while SHAP plots revealed that radiomic texture heterogeneity and high-level CNN features jointly contributed to correct classifications. Conclusions: By tightly integrating CNN embeddings, mask-targeted radiomics, and a two-tiered explainability stack (Grad-CAM + SHAP), the proposed system delivers state-of-the-art lesion detection and a transparent technique, addressing both accuracy and trust. Full article