What is the state of the art of computer vision-assisted cytology? A Systematic Literature Review.

Cytology is a low-cost and non-invasive diagnostic procedure employed to support the diagnosis of a broad range of pathologies. Cells are harvested from tissues by aspiration or scraping, and it is still predominantly performed manually by medical or laboratory professionals extensively trained for this purpose. It is a time-consuming and repetitive process where many diagnostic criteria are subjective and vulnerable to human interpretation. Computer Vision technologies, by automatically generating quantitative and objective descriptions of examinations' contents, can help minimize the chances of misdiagnoses and shorten the time required for analysis. To identify the state-of-art of computer vision techniques currently applied to cytology, we conducted a Systematic Literature Review, searching for approaches for the segmentation, detection, quantification, and classification of cells and organelles using computer vision on cytology slides. We analyzed papers published in the last 4 years. The initial search was executed in September 2020 and resulted in 431 articles. After applying the inclusion/exclusion criteria, 157 papers remained, which we analyzed to build a picture of the tendencies and problems present in this research area, highlighting the computer vision methods, staining techniques, evaluation metrics, and the availability of the used datasets and computer code. As a result, we identified that the most used methods in the analyzed works are deep learning-based (70 papers), while fewer works employ classic computer vision only (101 papers). The most recurrent metric used for classification and object detection was the accuracy (33 papers and 5 papers), while for segmentation it was the Dice Similarity Coefficient (38 papers). Regarding staining techniques, Papanicolaou was the most employed one (130 papers), followed by H&E (20 papers) and Feulgen (5 papers). Twelve of the datasets used in the papers are publicly available, with the DTU/Herlev dataset being the most used one. We conclude that there still is a lack of high-quality datasets for many types of stains and most of the works are not mature enough to be applied in a daily clinical diagnostic routine. We also identified a growing tendency towards adopting deep learning-based approaches as the methods of choice.

DNA damage analysis in newborns and their mothers related to pregnancy and delivery characteristics.

INTRODUCTION: Increased DNA damage is associated with early events in carcinogenesis. The foetus may be more susceptible to effects of environment by transplacental exposure. We aimed to evaluate DNA damage in cells from umbilical cord (arteries and vein) and maternal blood from pregnant women. METHODS: Fifty eight pregnant women and their offspring were included in this study. They were submitted to an interview to obtain information about personal history, clinical history, and lifestyle habits. Other Information was obtained from medical records. The samples were prepared for Single Cell Gel/Comet assay and Cytokinesis-block Micronucleus Cytome (CBMN-Cyt) assay. RESULTS: Correlation between DNA damage frequency by Comet assay from newborns and their mothers was statistically significant and was significantly associated with nulliparity and more than 1 h of second stage of labour (umbilical vein and maternal blood). A positive MNi relationship was noticed for age (mother's blood) and inappropriate birth weight for gestational age (maternal blood). When multivariate statistical analyses were applied to measure the degree of association between variables that influenced DNA damage markers in the first evaluation, inadequate birth weight and pregnant weight gain were associated with MNi frequency in maternal and newborns blood, respectively. DISCUSSION: Significant associations between DNA damage in newborns and pregnant women, and birth and pregnancy events suggest molecular evidence of transplacental genotoxic effects. However, a potentially increased risk of degenerative diseases, such as cancers, in this population should be carefully investigated by further prospective cohort studies.

Immunocytochemical typing of primary tumors on fine-needle aspiration cytologies of lymph nodes.

The aim of this study was to analyze the role of immunocytochemistry as an ancillary method on routine FNACs of enlarged lymph nodes, using different markers. In a validating cohort study all patients had confirmatory histological and/or clinical follow-up. 10 FNACs were analyzed for the differentiation of Non-Hodgkin Lymphoma (NHL) from metastatic carcinoma (MC), 30 cases to identify the sites of metastatic unknown primary tumors and 16 cases were checked to confirm clinical suspicion of a specific MC. Accuracy to differentiate NHL from MC was 100%, 92.3% to identify a primary tumor site of MC, and 100% to confirm a clinical suspicion of a specific MC. In 7 cases, the site of the primary tumor remained clinically unknown. Application of immunocytochemical markers on the same slide used for microscopic diagnosis is a useful tool in the routine assessment of FNACs of lymph nodes.