Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning

Fetal biometry and amniotic fluid volume assessments are two essential yet repetitive tasks in fetal ultrasound screening scans, aiding in the detection of potentially life-threatening conditions. However, these assessment methods can occasionally yield unreliable results. Advances in deep learning have opened up new avenues for automated measurements in fetal ultrasound, demonstrating human-level performance in various fetal ultrasound tasks. Nevertheless, the majority of these studies are retrospective in silico studies, with a limited number including African patients in their datasets. In this study we developed and prospectively assessed the performance of deep learning models for end-to-end automation of fetal biometry and amniotic fluid volume measurements. These models were trained using a newly constructed database of 172,293 de-identified Moroccan fetal ultrasound images, supplemented with publicly available datasets. the models were then tested on prospectively acquired video clips from 172 pregnant people forming a consecutive series gathered at four healthcare centers in Morocco. Our results demonstrate that the 95% limits of agreement between the models and practitioners for the studied measurements were narrower than the reported intra- and inter-observer variability among expert human sonographers for all the parameters under study. This means that these models could be deployed in clinical conditions, to alleviate time-consuming, repetitive tasks, and make fetal ultrasound more accessible in limited-resource environments.

Detection of hypermethylation BRCA1/2 gene promoter in breast tumours among Moroccan women

BACKGROUND

The promoter region is a key element of gene expression regulation. In mammals, most of the genes present, at the level of their promoter, a large number of islands CpG. Age also is seen as another factor for developing breast cell cancer reaching the tumour stage.

AIM

This study aimed to explore the hypermethylation of the BRCA1/2 promoter gene in women breast cancer and correlation with age and tumour stage.

MATERIALS AND METHODS

Fifty biopsies were derived from Moroccan women treated for breast carcinoma, the DNA extracted was treated by bisulphite and the targeted BRCA1/2 Amplicons were amplified by specific methylation primers (MSP).

RESULTS

The result shows that 62% of the samples were BRCA1 methylated in addition and negative result for BRCA2, these positive epigenetic factor were remarkable in women over 47 years and at the stage of malignant tumour.

CONCLUSION

These results show that half of the methylated samples are positive with a majority of over 47 years old, and confirms that age might be an additional factor for breast cancer development.

The Biological Significance of Long noncoding RNAs Dysregulation and their Mechanism of Regulating Signaling Pathways in Cervical Cancer

Despite the remarkable decrease in cervical cancer incidence due to the availability of the HPV vaccine and implementation of screening programs for early detection in developed countries, this cancer remains a major health problem globally, especially in developing countries where most of the cases and mortality occur. Therefore, more understanding of molecular mechanisms of cervical cancer development might lead to the discovery of more effective diagnosis and treatment options. Research on long noncoding RNAs (lncRNAs) demonstrates the important roles of these molecules in many physiological processes and diseases, especially cancer. In the present review, we discussed the significance of lncRNAs altered expression in cervical cancer, highlighting their roles in regulating highly conserved signaling pathways, such as mitogen-activated protein kinase (MAPK), Wnt/β-catenin, Notch, and phosphatidylinositol 3-kinase/protein kinase B (PI3K/AKT) pathways and their association with the progression of cervical cancer in order to bring more insight and understanding of this disease and their potential implications in cancer diagnosis and therapy.

Diagnostic Value of MicroRNA 21 in Endometrial Cancer and Benign Lesions and its Differential Expression in Relation to Clinicopathological Parameters

BACKGROUND

Endometrial cancer is one of the most common malignancies among women worldwide. Although this cancer is often diagnosed at early stages, the need for biomarkers of diagnosis remains a necessity to overcome conventional invasive procedures of diagnosis.

OBJECTIVE

In our study, we aim to investigate the diagnostic value of microRNA-21 in endometrial cancer and its relation to clinicopathological features.

METHODS

We used RT-qPCR to measure the expression of microRNA-21 in 71 tumor tissues, 53 adjacent tissues, and 54 benign lesions.

RESULTS

Our results show that microRNA-21 is a potential biomarker for endometrial cancer with an area under the receiver operating characteristic curve of 0.925 (95% CI = 0.863 - 0.964, P<0.0001). The sensitivity was 84.51% (95% CI = 74.0 - 92.0) and specificity was 86.79% (95% CI = 74.7 - 94.5). For discrimination between benign lesions and controls the AUC was 0,881 with a sensitivity of 100% (95% CI = 93.4 - 100.0) and specificity of 66.04 % (95% CI = 51.7 - 78.5), and for discriminating benign lesions from tumors the AUC was 0,750 with a sensitivity of 54.93% (95% CI = 42.7 - 66.8) and specificity of 90.74% (95% CI = 79.7 - 96.9). We also found that tumors with elevated microRNA-21 expression are of advanced FIGO stage, high histological grades, and have cervical invasion, myometrial invasion and distant metastasis.

CONCLUSION

Our findings support the important role of miR-21 as a biomarker for the diagnosis of endometrial cancer. Further studies on minimally invasive/noninvasive samples such as serum, blood, and urine are necessary to provide a better alternative to current diagnosis methods.

Tuberculosis of the breast: analysis of 17 cases

Tuberculosis constitutes a major public health problem in the world. Certain extra-pulmonary locations of tuberculosis disease are very exceptional. Amongst these, tuberculosis of the breast is rare even in countries where this infection is endemic. This form of tuberculosis is characterized by clinical and radiological polymorphisms and might mimic other diseases, especially breast cancer. This retrospective study is entailing seventeen patients treated in the Onco-Gynecology Department of the Mohammed VI Cancer Treatment Center, in the Ibn Rochd University Hospital of Casablanca, for breast tuberculosis, over a period of three years. We report the epidemiological, clinical and paraclinical aspects and we specify the treatment and evolution of the patients.

Oncogenic Human Papillomavirus involvement in epithelial ovarian carcinoma among women in Morocco

Epithelial Ovarian cancer (EOC) although rare is the most lethal gynecological cancer in women worldwide. Despite its high prevalence few studies have been performed to evaluate the prevalence and determinants of HPV infection worldwide. The aim of the present study was to investigate the presence of HPV-DNA in Moroccan patients with EOC using PCR among women in Casablanca, and to examine the prevalence of some HPV genotypes in Moroccan population. We performed a study of HPV detection on Fresh biopsies of 70 epithelial ovarian cancer patients. PCR was realized using the MY09/11 and GP5+/6+ primers. Genotyping of HPV was performed by PCR typespecific for HPV 6, 11, 16, 18, 31, and 33.Data was statistically analyzed using SPSS software. Hence, the mean age was 48.9 years (range,21-76 years). Serous adeno carcinoma (75.71%) and stage III of the disease represent the majority of cases. eight patients were HPV positive (11.42%).Results of HPV genotyping revealed predominance of two genotypes: HPV 16 (87.5%) and HPV 31(12.5).No co-infection identified. Approximately 75% of positive cases had a serous cystadeno carcinoma and more than 62,5% had FIGO advanced stage (III or IV).Our study showed that high-risk HPV infection could play a major role among patients with EOC in Morocco.