Objective: Breast cancer is a critical public health issue and a leading cause of cancer-related deaths among women worldwide. Its early diagnosis and detection can effectively help in increasing the chances of survival rate. For this reason, the diagnosis and classification of breast cancer using Deep learning algorithms have attracted a lot of attention. Therefore, our study aimed to design a computational approach based on deep convolutional neural networks for an efficient classification of breast cancer histopathological images by using our own created dataset. We collected overall 328 digital slides, from 116 of surgical breast specimens diagnosed with invasive breast carcinoma of non-specific type, and referred to the histopathology department of the National Institute of Oncology in Rabat, Morocco. We used two models of deep neural network architectures in order to accurately classify the images into one of three categories: normal tissue-benign lesions, in situ carcinoma or invasive carcinoma. Results: Both Resnet50 and Xception models achieved comparable results, with a small advantage to Xception extracted features. We reported high degrees of overall correct classification accuracy (88%), and sensitivity (95%) for detection of carcinoma cases, which is important for diagnostic pathology workflow in order to assist pathologists for diagnosing breast cancer with precision. The results of the present study showed that the designed classification model has a good generalization performance in predicting diagnosis of breast cancer, in spite of the limited size of the data. To our knowledge, this approach can be highly compared with other common methods in the automated analysis of breast cancer images reported in literature.
Metastasis of renal clear cell carcinoma (RCC) to the breast is exceptional. Breast metastases of extra-mammary tumors are rare and usually involve melanoma, lymphoma or leukemia. We report the case of a patient with breast metastasis of renal clear cell carcinoma occurring 18 years after nephrectomy. A history of RCC should always raise suspicion about breast metastasis, a situation that remains exceptional and whose diagnosis relies on anatomopathology.
Background: Homologous Recombination Deficiency (HRD) testing guides poly (ADP-ribose) polymerase inhibitor (PARPi) therapy in high-grade serous ovarian carcinoma (HGSOC). Centralized commercial assays pose logistical and financial barriers in low- and middle-income countries (LMICs). This study evaluated the pathological validation, clinical implementation, molecular landscape, and feasibility of a decentralized HRD testing platform in North Africa. Materials and methods: This real-world cohort study enrolled 215 advanced HGSOC patients at the National Institute of Oncology in Rabat, Morocco (March 2024–March 2026). Following strict histopathological selection (tumor cellularity ≥ 20%, necrosis < 30%), local genomic profiling utilized an in-house next-generation sequencing (NGS) pipeline (Oncomine Comprehensive Assay Plus) on formalin-fixed paraffin-embedded (FFPE) tumor tissue. HRD positivity was defined by a genomic instability metric (GIM) score ≥ 16. Objective pre-analytical metrics were defined to categorize testing failures. Results: Pre-analytical quality control failed in 57/215 samples (26.5%). DNA degradation ( n = 40, 70.2% of failures) was driven by real-world pre-analytical variability in decentralized workflows, while low DNA yield ( n = 17, 29.8% of failures) was linked to small core needle biopsies with low tumor cellularity or extensive stromal fibrosis. Among 158 evaluable patients, 87 (55.1%) were HRD-positive; 57.5% (50/87) harbored BRCA1/2 mutations and 42.5% (37/87) were BRCA wild-type. HRD prevalence significantly associated with age ( p = 0.017), peaking at 69.4% (50–59 years) and dropping to 32.1% (≥ 70 years). Confrontation of TP53 NGS data with immunohistochemical (IHC) reflex testing on NGS wild-type cases ( n = 27) identified 19 cases with aberrant p53 staining patterns, raising the total rate of p53 abnormalities to 94.9% (150/158). Average turnaround time was three weeks. One test represented 37.1% of the country’s annual Gross Domestic Product (GDP) per capita and over 400% of the monthly minimum wage. Conclusions: Local, decentralized testing is clinically viable in resource-limited settings. Addressing pre-analytical tissue processing quality and conducting formal health-economic evaluations are essential to ensuring sustainable access to precision oncology across LMICs.
Osteo-lipoma is a very rare benign tumor with a good prognosis. It is composed mainly of mature fatty tissue with a bony component. The diagnosis is based on the histological study, given the clinical and radiological characters that can simulate other benign or malignant pathologies. Osteosarcoma is the main differential diagnosis. The distinction between these two neoplasms is essential as the basis of the treatment is different. We report the case of a patient with a giant ossifying lipoma independent of bone tissue located in the thigh.