“Fruiting body” ofAspergillus species in a routine cervico-vaginal smear (Pap test)

Machine Learning Allows for Distinguishing Precancerous and Cancerous Human Epithelial Cervical Cells Using High-Resolution AFM Imaging of Adhesion Maps

Previously, the analysis of atomic force microscopy (AFM) images allowed us to distinguish normal from cancerous/precancerous human epithelial cervical cells using only the fractal dimension parameter. High-resolution maps of adhesion between the AFM probe and the cell surface were used in that study. However, the separation of cancerous and precancerous cells was rather poor (the area under the curve (AUC) was only 0.79, whereas the accuracy, sensitivity, and specificity were 74%, 58%, and 84%, respectively). At the same time, the separation between premalignant and malignant cells is the most significant from a clinical point of view. Here, we show that the introduction of machine learning methods for the analysis of adhesion maps allows us to distinguish precancerous and cancerous cervical cells with rather good precision (AUC, accuracy, sensitivity, and specificity are 0.93, 83%, 92%, and 78%, respectively). Substantial improvement in sensitivity is significant because of the unmet need in clinical practice to improve the screening of cervical cancer (a relatively low specificity can be compensated by combining this approach with other currently existing screening methods). The random forest decision tree algorithm was utilized in this study. The analysis was carried out using the data of six precancerous primary cell lines and six cancerous primary cell lines, each derived from different humans. The robustness of the classification was verified using K-fold cross-validation (K = 500). The results are statistically significant at p < 0.0001. Statistical significance was determined using the random shuffle method as a control.

SVM classifier of cervical histopathology images based on texture and morphological features

BACKGROUND

Cervical histopathology image classification is a crucial indicator in cervical biopsy results.

OBJECTIVE

The objective of this study is to identify histopathology images of cervical cancer at an early stage by extracting texture and morphological features for the Support Vector Machine (SVM) classifier.

METHODS

We extract three different texture features and one morphological feature of cervical histopathology images: first-order histogram, K-means clustering, Gray Level Co-occurrence Matrix (GLCM) and nucleus feature. The original dataset used in our experiment is obtained from 20 patients diagnosed with cervical cancer, including 135 whole slide images (WSIs). Given an entire WSI, the patches on its tissue region are extracted randomly.

RESULTS

We finally obtain 3,000 patches, including 1,000 normal, 1,000 hysteromyoma and 1,000 cancer images. Among them, 80% of the entire data set is randomly selected as training set and the remaining 20% as test set. The accuracy of SVM classification using first-order histogram, K-means clustering, GLAM and nucleus feature for extracting features are respectively 87.4%, 90.6%, 91.6% and 93.5%.

CONCLUSIONS

The classification accuracy of the SVM combining the four features is 96.8%, and the proposed nucleus feature plays a key role in the SVM classification of cervical histopathology images.

A worm in the cytology laboratory: A root cause analysis case study

In the spring of 2018, nematode-like organisms were first noted at the time of microscopic diagnosis on gynecologic (GYN) and anal pap specimens in our institution's cytopathology department. Due to their morphology and specimen source, we considered a diagnosis of pinworm. However, after identifying at least 30 more cases over 3 months from patients living in variable locations, we started favoring a contaminant. This report studies the steps that were initiated to figure the source of pap smear-preparation contamination and the molecular investigation to identify the nature of the contaminant.

Aspergillus in liquid-based cervicovaginal cytology in a postmenopausal patient: A case report

Aspergillus is an opportunistic fungus present in humid environments, whose natural environment is in soil, hay and compost. It is a frequent contaminant in the clinical laboratory. Because of this, the fungus is often inhaled, affecting those with an underlying pulmonary disease or immune deficiency. Fungal genitourinary tract infections are relatively common. A rare Aspergillus spp cervical infection diagnosed via liquid-based cytology is presented in the current study. The 57-year-old woman attended her annual check-up without any relevant medical history. The result of a gynecological examination by Papanicolaou smear was normal and routine liquid-based cytology was performed. The specimen exhibited fungal organisms characterized by septate hyphae branching at acute angles, most consistent with the Aspergillus species. Subsequent cytology demonstrated the same results. Antifungal treatment was initiated and a second post-treatment smear only exhibited atrophy. The cytomorphological features of Aspergillus spp. are discussed in the current study and a brief review of the few reported cases of a primary cervical infection in the literature is provided. In addition, the liquid-based cytology was established as a tool to diagnose the rare Aspergillus infection.

Fungal spores and fruiting bodies in cervicovaginal smears: Contaminant or infection?

BACKGROUND

Contaminants from various sources are curious findings in cervicovaginal smears and pose diagnostic challenges especially when they need to be distinguished from pathogens. Candidiasis is the most frequently encountered fungal infection but fungal contaminants are relatively common. Detection of fruiting bodies and spores of Aspergillus species is uncommon and may represent either a true infection or contamination. This study was undertaken to evaluate the presence of fungal spores, hyphae, and fruiting bodies in routine cervical smears and distinguish a true infection from contamination.

METHODS

Conventional cervicovaginal smears collected from women were incidentally found to have fungal fruiting bodies and spores. All smears received in the Cytology Department during that one month were reviewed for the presence of these elements.

RESULTS

Five out of the 120 smears, received from the outpatient department over a period of three consecutive days, showed evidence of fungal organisms. The patients were 28-59 years of age. While four patients were asymptomatic, only one patient complained of minimal vaginal discharge. All were immunocompetent. Cervicovaginal smears were prepared as part of routine screening. Fungal fruiting bodies, branching hyphae and numerous spores were seen in otherwise normal smears. Culture of scrapings from the surface of the wooden spatulas grew Aspergillus niger.

CONCLUSIONS

Contamination of Pap smears by fungus must be distinguished from true infection, the latter being supported by positive clinical findings and the presence of significant inflammation in the smears. Literature review was done to see the range of contaminants detected in Pap smears. Diagn. Cytopathol. 2017;45:191-194. © 2016 Wiley Periodicals, Inc.

Diagnosis of cervical cancer cell taken from scanning electron and atomic force microscope images of the same patients using discrete wavelet entropy energy and Jensen Shannon, Hellinger, Triangle Measure classifier

The aim of this article is to provide early detection of cervical cancer by using both Atomic Force Microscope (AFM) and Scanning Electron Microscope (SEM) images of same patient. When the studies in the literature are examined, it is seen that the AFM and SEM images of the same patient are not used together for early diagnosis of cervical cancer. AFM and SEM images can be limited when using only one of them for the early detection of cervical cancer. Therefore, multi-modality solutions which give more accuracy results than single solutions have been realized in this paper. Optimum feature space has been obtained by Discrete Wavelet Entropy Energy (DWEE) applying to the 3×180 AFM and SEM images. Then, optimum features of these images are classified with Jensen Shannon, Hellinger, and Triangle Measure (JHT) Classifier for early diagnosis of cervical cancer. However, between classifiers which are Jensen Shannon, Hellinger, and triangle distance have been validated the measures via relationships. Afterwards, accuracy diagnosis of normal, benign, and malign cervical cancer cell was found by combining mean success rates of Jensen Shannon, Hellinger, and Triangle Measure which are connected with each other. Averages of accuracy diagnosis for AFM and SEM images by averaging the results obtained from these 3 classifiers are found as 98.29% and 97.10%, respectively. It has been observed that AFM images for early diagnosis of cervical cancer have higher performance than SEM images. Also in this article, surface roughness of malign AFM images in the result of the analysis made for the AFM images, according to the normal and benign AFM images is observed as larger, If the volume of particles has found as smaller.

Conidial heads (Fruiting Bodies) as a hallmark for histopathological diagnosis of angioinvasive aspergillosis

Aspergillosis is a mycosis that afflicts immunocompetent and immunocompromised hosts; among the former it exhibits different clinical pictures, and among the latter the infection renders an invasive form of the disease. The histologic diagnosis of invasive aspergillosis is somewhat challenging mostly because of some morphological similarities between other fungi. However, when present, the conidial heads are pathognomonic of aspergillosis. The authors present the case of a 68-year-old woman who was submitted to autologous hematopoietic stem cell transplantation in the pursuit of multiple myeloma treatment. The post-transplantation period was troublesome with the development of severe neutropenia, human respiratory syncytial virus pneumonia, and disseminated aspergillosis, which was suspected because of a positive serum galactomannan antigen determination, and resulted in a fatal outcome. The autopsy findings showed diffuse alveolar damage associated with angioinvasive pulmonary aspergillosis with numerous hyphae and conidial heads in the lung parenchyma histology. The authors call attention to the aid of autopsy in confirming the diagnosis of this deep mycosis, since only the research of the galactomannan antigen may be insufficient and uncertain due to its specificity and of the possibility of false-positive results.

Towards early detection of cervical cancer: Fractal dimension of AFM images of human cervical epithelial cells at different stages of progression to cancer

We used AFM HarmoniX modality to analyse the surface of individual human cervical epithelial cells at three stages of progression to cancer, normal, immortal (pre-malignant) and carcinoma cells. Primary cells from 6 normal strains, 6 cancer, and 6 immortalized lines (derived by plasmid DNA-HPV-16 transfection of cells from 6 healthy individuals) were tested. This cell model allowed for good control of the cell phenotype down to the single cell level, which is impractical to attain in clinical screening tests (ex-vivo). AFM maps of physical (nonspecific) adhesion are collected on fixed dried cells. We show that a surface parameter called fractal dimension can be used to segregate normal from both immortal pre-malignant and malignant cells with sensitivity and specificity of more than 99%. The reported method of analysis can be directly applied to cells collected in liquid cytology screening tests and identified as abnormal with regular optical methods to increase sensitivity.

FROM THE CLINICAL EDITOR

Despite cervical smear screening, sometimes it is very difficult to differentiate cancers cells from pre-malignant cells. By using AFM to analyze the surface properties of human cervical epithelial cells, the authors were able to accurately identify normal from abnormal cells. This method could augment existing protocols to increase diagnostic accuracy.

Emerging of fractal geometry on surface of human cervical epithelial cells during progression towards cancer

Despite considerable advances in understanding the molecular nature of cancer, many biophysical aspects of malignant development are still unclear. Here we study physical alterations of the surface of human cervical epithelial cells during stepwise in vitro development of cancer (from normal to immortal (premalignant), to malignant). We use atomic force microscopy to demonstrate that development of cancer is associated with emergence of simple fractal geometry on the cell surface. Contrary to the previously expected correlation between cancer and fractals, we find that fractal geometry occurs only at a limited period of development when immortal cells become cancerous; further cancer progression demonstrates deviation from fractal. Because of the connection between fractal behaviour and chaos (or far from equilibrium behaviour), these results suggest that chaotic behaviour coincides with the cancer transformation of the immortalization stage of cancer development, whereas further cancer progression recovers determinism of processes responsible for cell surface formation.

Unusual fungal bodies in conventional cervical smears: report of nine cases

Candida spp have often been reported in cervical cytology, other fungal organisms are very rare in modern literature. We report nine cases of conventional cervical smears showing Penicillium, Aspergillus, and Cladosporium spp in healthy immunocompetent females. Penicillium spp seen in four out of nine smears, Cladosporium spp alone in three out of nine smears, and Cladosporium spp along with Aspergillus spp in two out of nine smears. A detail of these nine cases is presented with discussion on importance of these structures when observed in conventional cervical smears. Awareness of such contaminants is important to differentiate from true infection for relevant therapeutic implications. A systematic step-wise approach to such structures is also suggested.

Detection of cancerous cervical cells using physical adhesion of fluorescent silica particles and centripetal force

Here we describe a non-traditional method to identify cancerous human cervical epithelial cells in a culture dish based on physical adhesion between silica beads and cells. It is a simple optical fluorescence-based technique which detects the relative difference in the amount of fluorescent silica beads physically adherent to surfaces of cancerous and normal cervical cells. The method utilizes the centripetal force gradient that occurs in a rotating culture dish. Due to the variation in the balance between adhesion and centripetal forces, cancerous and normal cells demonstrate clearly distinctive distributions of the fluorescent particles adherent to the cell surface over the culture dish. The method demonstrates higher adhesion of silica particles to normal cells compared to cancerous cells. The difference in adhesion was initially observed by atomic force microscopy (AFM). The AFM data were used to design the parameters of the rotational dish experiment. The optical method that we describe is much faster and technically simpler than AFM. This work provides proof of the concept that physical interactions can be used to accurately discriminate normal and cancer cells.