Background/Objectives: This study aims to create a strong binary classifier and evaluate the performance of pre-trained convolutional neural networks (CNNs) to effectively distinguish between benign and malignant ovarian tumors from still ultrasound images. Methods: The dataset consisted of 3510 ultrasound images from 585 women with ovarian tumors, 390 benign and 195 malignant, that were classified by experts and verified by histopathology. A 20% to80% split for training and validation was applied within a k-fold cross-validation framework, ensuring comprehensive utilization of the dataset. The final classifier was an aggregate of three pre-trained CNNs (VGG16, ResNet50, and InceptionNet), with experimentation focusing on the aggregation weights and decision threshold probability for the classification of each mass. Results: The aggregate model outperformed all individual models, achieving an average sensitivity of 96.5% and specificity of 88.1% compared to the subjective assessment’s (SA) 95.9% sensitivity and 93.9% specificity. All the above results were calculated at a decision threshold probability of 0.2. Notably, misclassifications made by the model were similar to those made by SA. Conclusions: CNNs and AI-assisted image analysis can enhance the diagnosis and aid ultrasonographers with less experience by minimizing errors. Further research is needed to fine-tune CNNs and validate their performance in diverse clinical settings, potentially leading to even higher sensitivity and overall accuracy.

Metaplastic carcinoma of the breast (MpBC) is a very rare and aggressive type of breast cancer. Data focusing on MpBC are limited. The aim of this study was to describe the clinicopathological features of MpBC and evaluate the prognosis of patients with MpBC. Eligible articles about MpBC were identified by searching CASES SERIES gov and the MEDLINE bibliographic database for the period of 1 January 2010 to 1 June 2021 with the keywords metaplastic breast cancer, mammary gland cancer, neoplasm, tumor, and metaplastic carcinoma. In this study, we also report 46 cases of MpBC stemming from our hospital. Survival rates, clinical behavior, and pathological characteristics were analyzed. Data from 205 patients were included for analysis. The mean age at diagnosis was 55 (14.7) years. The TNM stage at diagnosis was mostly stage II (58.5%) and most tumors were triple negative. The median overall survival was 66 (12–118) months, and the median disease-free survival was 56.8 (11–102) months. Multivariate Cox regression analysis revealed that surgical treatment was associated with decreased risk of death (hazard ratio 0.11, 95% confidence interval 0.02–0.54, p = 0.01) while advanced TNM stage was associated with increased risk of death (hazard ratio 1.5, 95% confidence interval 1.04–2.28, p = 0.03). Our results revealed that surgical treatment and TNM stage were the only independent risk factors related to patients’ overall survival.

Background/Objectives: Extra-gastrointestinal stromal tumors (EGISTs) are rare mesenchymal tumors arising outside the gastrointestinal tract, making up 5/50 HPF) was noted in 63.2%. CD117, DOG-1, and vimentin was expressed in all cases, while CD34 was positive in 97.1%. Adjuvant therapy with tyrosine kinase inhibitors (TKIs) was administered in 57.5%, and neoadjuvant therapy was rare (8.6%). Recurrence occurred in 39.4% over a median follow-up of 40 ± 61.5 months, with a median disease-free survival (DFS) of 48 months. One death occurred 13 months postoperatively. Conclusions: Rectovaginal EGISTs are exceedingly rare and often asymptomatic, complicating preoperative diagnosis. Surgical resection remains the cornerstone of treatment, complemented by stage-specific neoadjuvant or adjuvant TKI therapy. The challenging location predisposes to recurrence, underscoring the need for further studies to optimize management and improve outcomes.

Background/objectives: Metaplastic breast carcinoma (MpBC) is a rare, poorly differentiated breast cancer defined by the presence of ductal carcinoma along with areas of matrix-producing, spindle-cell, sarcomatous, or squamous differentiation. It does not express hormone receptors and has a poor overall prognosis. The Hippo molecular pathway was recently related to cancer progression and adjuvant therapy resistance. The objective of this study was to evaluate the expression of Hippo pathway transducers, YAP/TAZ, CCND1, and CTGF, in MpBC and their relation to the clinicopathological characteristics of the disease. Methods: Specimens from patients with MpBC treated at our department from 2003 to 2021 were analyzed utilizing immunohistochemistry and real-time PCR. Results: Forty-four female patients (62.6 ± 14.7 years old) met inclusion criteria and were included in this study. Strong nuclear YAP/TAZ expression was found in 61.4% of patients, while the expressions of CCND1 and CTGF were 3.9% and 12.5%, respectively. Patients presenting at an advanced stage had a statistically worse prognosis compared to the ones diagnosed with stage IA disease. Adjuvant chemotherapy was associated with better overall survival, while disease recurrence was significantly associated with a worse prognosis. Conclusions: Advanced stage at diagnosis and disease recurrence were significantly associated with worse prognosis in MpBC. However, adjuvant chemotherapy significantly led to better overall survival. The Hippo pathway is frequently deregulated (nuclear YAP/TAZ in 61.4% of patients), suggesting it is a compelling novel therapeutic target for this aggressive disease.