HighlightsChoriocarcinoma is a highly malignant trophoblastic neoplasm. Its association with ectopic pregnancy is very rare and aggressive.Clinical diagnosis of interstitial choriocarcinomas is difficult, since it is rare and manifested by non-specific symptoms.Imaging findings are also not helpful in ectopic location.Monitoring of βhCG level was the most useful marker of diagnosis and follow up.Pathology is the only tool of the diagnosis especially with the trend of treatment of ectopic pregnancy by conservative surgery.

Deep-learning based labeling methods have gained unprecedented popularity in different computer vision and medical image segmentation tasks. However, to the best of our knowledge, these have not been used for cervical tumor segmentation. More importantly, while the majority of innovative deeplearning works using convolutional neural networks (CNNs) focus on developing more sophisticated and robust architectures (e.g., ResNet, U-Net, GANs), there is very limited work on how to aggregate different CNN architectures to improve their relational learning at multiple levels of CNN-to-CNN interactions. To address this gap, we introduce a Dynamic Multi-Scale CNN Forest (C K+1 DMF), which aims to address three major issues in medical image labeling and ensemble CNN learning: (1) heterogeneous distribution of MRI training patches, (2) a bidirectional flow of information between two consecutive CNNs as opposed to cascading CNNs-where information passes in a directional way from current to the next CNN in the cascade, and (3) multiscale anatomical variability across patients. To solve the first issue, we group training samples into clusters, then design a forest with (+ 1) trees: a principal tree of CNNs trained using all data samples and subordinate trees, each trained using a cluster of samples. As for the second and third issues, we design each dynamic multiscale tree (DMT) in the forest such that each node in the tree nests a CNN architecture. Two successive CNN nodes in the tree pass bidirectional contextual maps to progressively improve the learning of their relational non-linear mapping. Besides, as we traverse a path from the root node to a leaf node in the tree, the architecture of each CNN node becomes shallower to take in smaller training patches. Our C K+1 DMF significantly (p<0.05) outperformed several conventional and ensemble CNN architectures, including conventional CNN (improvement by 10.3%) and CNN-based DMT (improvement by 5%).

Choriocarcinoma is a gestational trophoblastic tumor that mainly affects women of childbearing age. Cases of choriocarcinoma in postmenopausal women are exceptional. Through an observation and literature review, we propose to study the specific diagnosis and treatment features of this tumor in menopausal women. We report the observation of a pure uterine choriocarcinoma, which occurred in post-menopause. The diagnosis was made on the analysis of surgical specimens confirmed by measurement of hCG. Chemotherapy was started after a total hysterectomy and bilateral salpingo-oophorectomy first. The improvement was dramatic after 3 courses of chemotherapy and the patient is in complete remission after five years of monitoring. The primitive forms of pure choriocarcinoma in postmenopausal women are exceptional. Their etiology is poorly understood and their treatment based on chemotherapy.

Ewing’s sarcoma/primitive neuroectodermal tumors (EWS/PNET) are rare malignant and aggressive tumors, usually seen in the trunk and lower limbs of children and young adults. They are uncommon in the breast. We report a case of a 43-year-old woman who developed a painless breast mass. An initial core needle biopsy concluded to a fibrocystic dystrophy contrasting with a rapidly growing mass; thus a large lumpectomy was done. Diagnosis of primary PNET of the breast was established, based on both histopathological examination and immunohistochemical findings. Surgical margins were positive, therefore, left modified radical mastectomy with axillary lymph nodes dissection was performed. The patient was given 6 cycles of adjuvant chemotherapy containing cyclophosphamide, adriamycin and vincristine. Twenty months later, she is in life without recurrence or metastasis. EWS/PNET may impose a diagnostic challenge. Indeed, mammography and ultrasonography features are non specific. The histopathological pattern is variable depending on the degree of neuroectodermal differentiation. Immuno-phenotyping is necessary and genetic study is the only confirmatory tool of diagnosis showing a characteristic cytogenetic anomaly; t (11; 22) translocation.