Objectives: Endometriosis-associated ovarian cancer (EAOC) patients show different clinical characteristics compared with non-EAOC patients. However, a few studies are focused on the imaging characteristics of EAOC until now. We assessed MRI characteristics in differentiating EAOC and non-EAOC. Methods: We retrospectively analyzed clinical and MRI characteristics from 54 patients with 67 lesions diagnosed with primary epithelial ovarian carcinoma at the Third Affiliated Hospital of Guangzhou Medical University between January 2012 and October 2020. We studied MRI findings such as maximum diameter, morphology, configuration, locularity, features of mural nodules, lymphadenopathy, peritoneal implants, the presence of hyperintensity on T1WI, and hypointensity on T2WI. We also studied the clinical characteristics. Significant MRI variables in univariate analysis were selected for subsequent multivariate regression analysis. This study evaluated the diagnostic performance of the significant MRI variables in univariate analysis. Results: We found that the patients with EAOC, compared with those with non-EAOC, were younger, more unilateral, and had earlier FIGO stage. Univariate analysis revealed that morphology, locularity, growth pattern of mural nodules, and hypointensity on T2WI were factors that significantly differed between EAOC and non-EAOC. In the multivariate logistic regression analysis, locularity and hypointensity on T2WI were independent predictors to distinguish EAOC from non-EAOC. Conclusions: EAOC typically presented as a unilocular mass with hypointensity on T2WI in cystic components. MRI could help distinguish EAOC from non-EAOC. Advances in knowledge: MRI is a promising tool for preoperative diagnosis of EAOC.

Cardiac substructure segmentation is a prerequisite for cardiac diagnosis and treatment, providing a basis for accurate calculation, modeling, and analysis of the entire cardiac structure. CT (computed tomography) imaging can be used for a noninvasive qualitative and quantitative evaluation of the cardiac anatomy and function. Cardiac substructures have diverse grayscales, fuzzy boundaries, irregular shapes, and variable locations. We designed a deep learning-based framework to improve the accuracy of the automatic segmentation of cardiac substructures. This framework integrates cardiac anatomical knowledge; it uses prior knowledge of the location, shape, and scale of cardiac substructures and separately processes the structures of different scales. Through two successive segmentation steps with a coarse-to-fine cascaded network, the more easily segmented substructures were coarsely segmented first; then, the more difficult substructures were finely segmented. The coarse segmentation result was used as prior information and combined with the original image as the input for the model. Anatomical knowledge of the large-scale substructures was embedded into the fine segmentation network to guide and train the small-scale substructures, achieving efficient and accurate segmentation of ten cardiac substructures. Sixty cardiac CT images and ten substructures manually delineated by experienced radiologists were retrospectively collected; the model was evaluated using the DSC (Dice similarity coefficient), Recall, Precision, and the Hausdorff distance. Compared with current mainstream segmentation models, our approach demonstrated significantly higher segmentation accuracy, with accurate segmentation of ten substructures of different shapes and sizes, indicating that the segmentation framework fused with prior anatomical knowledge has superior segmentation performance and can better segment small targets in multi-target segmentation tasks.

INTRODUCTION: Accurate antenatal diagnosis of placenta percreta condition has been employed to optimize delivery management and minimize the risk of associated complication. METHODS: We will report two cases about utilizing 3D printing model of placenta percreta to guide obstetrical operation. We performed magnetic resonance imaging of anatomical structures, digital 3D reconstruction, and fabrication via 3D printing. According to the 3D printing model, a multidisciplinary team planned a cesarean hysterectomy and simulated surgery operation before the operation. RESULTS: We made a precise operation plan and had an adequate preoperative preparation. Our operative time and the blood loss were less than the other studies. The neonatal outcome was well. For the patients, they also more easily to understand what operation was performed on them and the dangerousness of the operation before operations. CONCLUSION: 3D printing model is a useful tool to accurate assay the placenta percreta and plan a complex operation, which is helpful for decreasing complication and improve material and fetal outcome. In the future, it maybe will be a useful tool to preoperative assessment or guiding the obstetric and gynecological complex operation.

The burgeoning clinical demand for patient-specific cardiac modeling encounters significant challenges. The current clinical cardiac models are either difficult to manufacture or lack of detailed geometric structures and hence, often fail to incorporate important patient-specific characteristics. Moreover, most 3D-printable soft materials, such as Thermoplastic Poly-Urethane (TPU) or elastic resins, exhibit insufficient flexibility and biocompatibility to accurately mimic cardiac tissues, therefore limiting their ability to truly replicate patient-specific cardiac conditions. To address these limitations, we propose an innovative method for patient-specific cardiac substructure reconstruction based on the integration of Artificial Intelligence (AI) and embedded 3D printing. First, by combining medical imaging data (CT scan) with AI-driven high-precision 3D reconstruction algorithms, the new method segments the patient-specific cardiac structure into 10 substructures. The average Dice coefficient across the ten substructures is 0.87. Second, it uses an embedded 3D printing technique which utilizes silicone rubber matrix as supporting structure and uses diluted catalyst ink to extrude onto the supporting matrix. Through precise regulation of the matrix composition, material deposition rate and curing time, it can fabricate high-fidelity, complex 3D patient-specific silicone heart models with the average dimensional error less than 0.5 mm. The proposed method can substantially reduce manual intervention and post-processing time. The fabricated models provide valuable morphological insights for cardiovascular diagnosis and treatment planning. It is believed that many clinic applications will follow.