Artificial Intelligence in Obstetric Anomaly Scan: Heart and Brain.

BACKGROUND: The ultrasound scan represents the first tool that obstetricians use in fetal evaluation, but sometimes, it can be limited by mobility or fetal position, excessive thickness of the maternal abdominal wall, or the presence of post-surgical scars on the maternal abdominal wall. Artificial intelligence (AI) has already been effectively used to measure biometric parameters, automatically recognize standard planes of fetal ultrasound evaluation, and for disease diagnosis, which helps conventional imaging methods. The usage of information, ultrasound scan images, and a machine learning program create an algorithm capable of assisting healthcare providers by reducing the workload, reducing the duration of the examination, and increasing the correct diagnosis capability. The recent remarkable expansion in the use of electronic medical records and diagnostic imaging coincides with the enormous success of machine learning algorithms in image identification tasks. OBJECTIVES: We aim to review the most relevant studies based on deep learning in ultrasound anomaly scan evaluation of the most complex fetal systems (heart and brain), which enclose the most frequent anomalies.

Pattern Recognition and Anomaly Detection in fetal morphology using Deep Learning and Statistical learning (PARADISE): protocol for the development of an intelligent decision support system using fetal morphology ultrasound scan to detect fetal congenital anomaly detection.

INTRODUCTION: Congenital anomalies are the most encountered cause of fetal death, infant mortality and morbidity. 7.9 million infants are born with congenital anomalies yearly. Early detection of congenital anomalies facilitates life-saving treatments and stops the progression of disabilities. Congenital anomalies can be diagnosed prenatally through morphology scans. A correct interpretation of the morphology scan allows a detailed discussion with the parents regarding the prognosis. The central feature of this project is the development of a specialised intelligent system that uses two-dimensional ultrasound movies obtained during the standard second trimester morphology scan to identify congenital anomalies in fetuses. METHODS AND ANALYSIS: The project focuses on three pillars: committee of deep learning and statistical learning algorithms, statistical analysis, and operational research through learning curves. The cross-sectional study is divided into a training phase where the system learns to detect congenital anomalies using fetal morphology ultrasound scan, and then it is tested on previously unseen scans. In the training phase, the intelligent system will learn to answer the following specific objectives: (a) the system will learn to guide the sonographer's probe for better acquisition; (b) the fetal planes will be automatically detected, measured and stored and (c) unusual findings will be signalled. During the testing phase, the system will automatically perform the above tasks on previously unseen videos.Pregnant patients in their second trimester admitted for their routine scan will be consecutively included in a 32-month study (4 May 2022-31 December 2024). The number of patients is 4000, enrolled by 10 doctors/sonographers. We will develop an intelligent system that uses multiple artificial intelligence algorithms that interact between themselves, in bulk or individual. For each anatomical part, there will be an algorithm in charge of detecting it, followed by another algorithm that will detect whether anomalies are present or not. The sonographers will validate the findings at each intermediate step. ETHICS AND DISSEMINATION: All protocols and the informed consent form comply with the Health Ministry and professional society ethics guidelines. The University of Craiova Ethics Committee has approved this study protocol as well as the Romanian Ministry of Research Innovation and Digitization that funded this research. The study will be implemented and reported in line with the STROBE (STrengthening the Reporting of OBservational studies in Epidemiology) statement. TRIAL REGISTRATION NUMBER: The study is registered under the name 'Pattern recognition and Anomaly Detection in fetal morphology using Deep Learning and Statistical Learning', project number 101PCE/2022, project code PN-III-P4-PCE-2021-0057. TRIAL REGISTRATION: ClinicalTrials.gov, unique identifying number NCT05738954, date of registration: 2 November 2023.

Clinical Characteristics and Local Histopathological Modulators of Endometriosis and Its Progression.

Endometriosis (E) and adenomyosis (A) are associated with a wide spectrum of symptoms and may present various histopathological transformations, such as the presence of hyperplasia, atypia, and malignant transformation occurring under the influence of local inflammatory, vascular and hormonal factors and by the alteration of tumor suppressor proteins and the inhibition of cell apoptosis, with an increased degree of lesion proliferation. MATERIAL AND METHODS: This retrospective study included 243 patients from whom tissue with E/A or normal control uterine tissue was harvested and stained by histochemical and classical immunohistochemical staining. We assessed the symptomatology of the patients, the structure of the ectopic epithelium and the presence of neovascularization, hormone receptors, inflammatory cells and oncoproteins involved in lesion development. Atypical areas were analyzed using multiple immunolabeling techniques. RESULTS: The cytokeratin (CK) CK7+/CK20- expression profile was present in E foci and differentiated them from digestive metastases. The neovascularization marker cluster of differentiation (CD) 34+ was increased, especially in areas with malignant transformation of E or A foci. T:CD3+ lymphocytes, B:CD20+ lymphocytes, CD68+ macrophages and tryptase+ mast cells were abundant, especially in cases associated with malignant transformation, being markers of the proinflammatory microenvironment. In addition, we found a significantly increased cell division index (Ki67+), with transformation and inactivation of tumor suppressor genes p53, B-cell lymphoma 2 (BCL-2) and Phosphatase and tensin homolog (PTEN) in areas with E/A-transformed malignancy. CONCLUSIONS: Proinflammatory/vascular/hormonal changes trigger E/A progression and the onset of cellular atypia and malignant transformation, exacerbating symptoms, especially local pain and vaginal bleeding. These triggers may represent future therapeutic targets.

Specific Local Predictors That Reflect the Tropism of Endometriosis-A Multiple Immunohistochemistry Technique.

Ectopic endometrial epithelium associates a wide spectrum of symptomatology. Their evolution can be influenced by inflammatory and vascular changes, that affect not only the structure and cell proliferation rate, but also symptoms. This prospective study involved tissue samples from surgically treated patients, stained using classical histotechniques and immunohistochemistry. We assessed ectopic endometrial glands (CK7+, CK20-), adjacent blood vessels (CD34+), estrogen/progesterone hormone receptors (ER+, PR+), inflammatory cells (CD3+, CD20+, CD68+, Tryptase+), rate of inflammatory cells (Ki67+) and oncoproteins (BCL2+, PTEN+, p53+) involved in the development of endometriosis/adenomyosis. A CK7+/CK20- expression profile was present in the ectopic epithelium and differentiated it from digestive metastases. ER+/PR+ were present in all cases analyzed. We found an increased vascularity (CD34+) in the areas with abdominal endometriosis and CD3+-:T-lymphocytes, CD20+-:B-lymphocytes, CD68+:macrophages, and Tryptase+: mastocytes were abundant, especially in cases with adenomyosis as a marker of proinflammatory microenvironment. In addition, we found a significantly higher division index-(Ki67+) in the areas with adenomyosis, and inactivation of tumor suppressor genes-p53+ in areas with neoplastic changes. The inflammatory/vascular/hormonal mechanisms trigger endometriosis progression and neoplastic changes increasing local pain. Furthermore, they may represent future therapeutic targets. Simultaneous-multiple immunohistochemical labelling represents a valuable technique for rapidly detecting cellular features that facilitate comparative analysis of the studied predictors.