Current Issue : July-September Volume : 2026 Issue Number : 3 Articles : 5 Articles
Optical coherence tomography (OCT) is a key biological sensing and imaging tool widely used in biomedical detection, and its images are often degraded by multiplicative speckle noises—especially when micro-electro-mechanical system (MEMS) mirrors are employed in endoscopic OCT imaging, which reduces visual quality and affects the accuracy of subsequent analysis. Traditional denoising algorithms and supervised deep learning approaches have shown some effectiveness, but they are limited by their reliance on paired noisy–clean data and their insufficient modeling of global structural dependencies. To address these issues, this paper proposes a frequency-domain enhanced UNet based on the Neighbor2Neighbor (N2N) framework (FEN2N). The proposed FEN2N integrates waveletguided spectral pooling modules (WSPMs) and frequency-domain enhanced receptive field blocks (FE-RFBs). In this work, OCT images are obtained in a self-constructed MEMSOCT system. Then the FEN2N is applied to the OCT image dataset. Results show that FEN2N achieves a more than 2.3 dB PSNR improvement over the N2N baseline, while the incorporation of FE-RFB contributes to a 0.02 improvement in SSIM. In addition, FEN2N outperforms several state-of-the-art methods, effectively suppressing speckle noise while preserving fine structural details that are important for clinical diagnosis....
Objectives: To clarify the role of cervical ultrasound in the investigation and characterization of thyroid nodules and its predictive value for malignancy or benignity by searching for a correlation between ultrasound findings and histology results. Materials and Methods: We performed a prospective study of 34 patients who underwent surgery for nodular thyroid disease at the Louga Regional Hospital Centre over a ten-month period, from 1 January 2023 to 31 October 2023. Results: There were 33 women and 1 man, giving a sex ratio of 0.03. The average age of patients was 42.35 years. Thyroid nodules were discovered in 94.1% of cases due to anterior cervical swelling. A family history of thyroid goiter was noted in 23.5% of patients, and 20.6% of patients had thyroid hyperfunction. On ultrasound, 52.9% of nodules were solitary and 47.1% were part of a multinodular goiter. The nodules were bilobar in 41.2% of cases, with an average size of 26.2 mm. The nodules were solid in 52.9% of cases, mixed in 41.2% and spongiform in 5.9%. The form was oval for 33 nodules (97.1%) and non-oval for 1 nodule (2.9%); 5.9% of nodules had irregular borders. In terms of echogenicity, 17.6% of nodules were hyperechoic, 50% were isoechoic, 20.6% were mildly hypoechoic, 5.9% were severely hypoechoic and 5.9% were anechoic. Microcalcifications were found in 5.9% of cases. The nodules were classed as EU-TIRADS 2 in 5.88% of cases, EU-TIRADS 3 in 64.71%, EU-TIRADS 4 in 20.59% and EU-TIRADS 5 in 8.82% of cases. On histology, 17.6% of nodules were malignant. The risk of malignancy was 0% for score 2, 4.5% for score 3, 28.6% for score 4 and 100% for score 5. The risk of malignancy was associated with nodule size, non-oval shape, irregular contours, hypoechoic appearance and the presence of microcalcifications. Conclusion: Pertinent ultrasound analysis remains highly useful in the pre-surgical identification of factors predictive of malignancy in thyroid nodules....
This study investigates whether detector materials with an effective atomic number (Zeff), density, and light output higher than cesium iodide (CsI) could provide images of better quality in dual-energy cone beam computed tomography (CBCT) breast examinations. Seven different detector material configurations were applied in a simulated micro-CBCT system using GATE v.9.2.1 (GEANT4 application for tomographic emission). Four breast phantoms, containing microcalcifications of Type I and Type II, were imaged. Planar images and tomographic data were analyzed. Microcalcification CNRs (contrast-to-noise ratios) were calculated for each configuration. CZT (cadmium zinc telluride) and GAGG (gadolinium aluminum gallium garnet) materials show a 3–17% increase in relative HAp (hydroxyapatite)-CNR values towards CsI....
Objectives: The differential diagnosis of ameloblastoma and odontogenic keratocyst is essential for surgical planning and patient counseling. While deep learning (DL)-based methods show promising potential in this domain, their clinical translation remains challenging due to insufficient interpretability. This study aims to introduce segmentationguided preprocessing approaches to provide support for the clinical implementation of computer-aided diagnosis systems. Methods: This study evaluated the performance of an InceptionV3 model on 128 pathologically confirmed CBCT scans (AME: 64; OKC: 64) by 5-fold cross-validation. Four experimental inputs were compared: (1) Original slice; (2) Bounding-box ROI; (3) Precise segmentation ROI; and (4) Moderately expanded ROI. All models were trained under the same settings. Assessment was conducted on both the slice and patient levels, incorporating accuracy, recall, precision, F1-score, and the area under the receiver operating characteristic curve (AUC). Grad-CAM visualization and confidence curve analysis were employed to verify models’ attention patterns and diagnostic confidence. Results: All models based on segmentation-guided ROI significantly outperformed models based on original slice. The moderately expanded ROI achieved optimal performance. The bounding-box ROI provided competitive performance with higher recall. Grad-CAM confirmed improved attention localization, while confidence curve analysis showed more consistent and reliable prediction patterns across slices. Conclusions: Segmentation-guided preprocessing represents an effective and clinically relevant approach for jaw lesion diagnosis and enhances interpretability....
Tuberculosis and sarcoidosis can present with similar clinical and radiological features, especially intrathoracic lymphadenopathy, complicating differential diagnosis. This study explored the potential utility of QuantiFERON-TB Gold (QFT), serum High Mobility Group Box 1 protein (HMGB1), and microRNA-221 (miRNA-221) relative expression as biomarkers to aid in distinguishing tuberculosis-related intrathoracic lymphadenopathy (TBIL) from sarcoidosis-related intrathoracic lymphadenopathy (SAIL). The study included 27 patients with TBIL, 27 patients with SAIL, and 27 healthy controls. QFT results, serum HMGB1 levels, and miRNA-221 relative expression were measured and compared across groups using univariable and exploratory multivariable analyses. Significant differences were observed among the study groups for serum HMGB1 levels, miRNA-221 expression, and QFT results (p < 0.001). Both TBIL and SAIL patients had significantly higher HMGB1 levels compared with healthy controls, consistent with inflammatory activity. In contrast, miRNA-221 expression was significantly elevated in TBIL patients compared with both SAIL patients and controls. Exploratory analyses suggested a potential contribution of miRNA-221 to differentiating TBIL from SAIL, whereas the effects of HMGB1 and QFT were less pronounced after adjustment. The findings suggest that miRNA-221, alongside HMGB1 and QFT, may contribute to the differentiation of TBIL from SAIL, although validation in larger cohorts is necessary....
Loading....