Search

Aims The aim of this study is to describe the demographic, presenting features and associated risk factors of ocular surface squamous neoplasia (OSSN) at a tertiary eye hospital in Johannesburg, South Africa. Methods An interventional prospective study of patients presenting with conjunctival masses was conducted. An electronic questionnaire was completed to document demographic data, presenting history, and associated risk factors. A slit lamp examination and photos were used to document and describe the clinical features at presentation. Cases (OSSN) and controls (benign lesions) were determined by histology. Results There were 130 cases and 45 controls. Median age was 44 years (IQR: 35–51) with an equal gender distribution in cases. The prevalence of HIV in cases was 74% and was strongly associated with OSSN (p p Conclusion Our study describes a sample of OSSN that is young and has no gender predisposition. The majority of cases presented with CIN lesions, rather than SCC reported in other African countries. HIV was the most significant risk factor in this study population.

Urine cytology offers a rapid and relatively inexpensive method to diagnose urothelial neoplasia. In our setting of a public sector laboratory in South Africa, urothelial neoplasia is rare, compromising pathology training in this specific aspect of cytology. Artificial intelligence-based synthetic image generation-specifically the use of generative adversarial networks (GANs)-offers a solution to this problem.A limited, but morphologically diverse, dataset of 1000 malignant urothelial cytology images was used to train a StyleGAN3 model to create completely novel, synthetic examples of malignant urine cytology using computer resources within reach of most pathology departments worldwide.We have presented the results of our trained GAN model, which was able to generate realistic, morphologically diverse examples of malignant urine cytology images when trained using a modest dataset. Although the trained model is capable of generating realistic images, we have also presented examples for which unrealistic and artifactual images were generated-illustrating the need for manual curation when using this technology in a training context.We have presented a proof-of-concept illustration of creating synthetic malignant urine cytology images using machine learning technology to augment cytology training when real-world examples are sparse. We have shown that despite significant morphologic diversity in terms of staining variations, slide background, variations in the diagnostic malignant cellular elements, the presence of other nondiagnostic cellular elements, and artifacts, visually acceptable and varied results are achievable using limited data and computing resources.

Visual literacy is an essential skill in Anatomical Pathology. However, there appears to be a dearth of literature that engages explicitly with how to teach or learn visual skills with respect to Anatomical Pathology residents. Using a variety of modalities, with a focus on practical arts-based methodologies, three-two hour workshops were designed to explore the complexity of precise observation and structured description. This intervention was based on the hypothesis that cytopathology and analyzing an artwork share a language and set of formal processes. Evaluation of the workshops was both quantitative and qualitative. The former assessed pre- and post-workshop descriptions of cytology images and artworks while the latter was in the form of a focus group. An actual improvement in both cytopathology and artwork description was demonstrated while the focus group discussion revealed the majority of residents considered the workshops as having a positive impact on the observation and description skills required in Anatomical Pathology. Some felt the purpose and approach of these workshops was not made explicit enough. Thematic analysis of the focus group showed robust discussion regarding who should conduct these workshops and when they should be conducted in resident training. Unanticipated benefits of the workshops such as personal creativity and pleasure formed a significant theme that requires serious consideration. Introducing visual literacy workshops into residency training appears to be valuable and improved observation and description skills in cytopathology. The focus group discussion will be used to improve on this first set of workshops.

Ocular surface squamous neoplasia (OSSN) is the most common ocular tumour with an incidence ranging from 0.03 to 1.9 per 100,000 persons/year. The diagnosis is made on clinical suspicion and confirmed with anterior-segment optical coherence tomography (AS-OCT), cytology, or histology. The purpose of this review is to provide an overview of the management options available for OSSN and review their success and recurrence rates. Surgery is the gold standard for the management of small OSSN lesions. With the increased use of less invasive diagnostic modalities such as AS-OCT and cytology, there has been a move to use topical therapies for the management of OSSN. The most commonly used agents are interferon-α2b (IFN), mitomycin-C (MMC) and 5-fluorouracil (5FU). They have been shown to have similar resolution and recurrence rates but differ in cost and side effect profile. IFN has the lowest side effect profile, but is also the most expensive, whereas MMC has the greatest surface toxicity and is priced midway between the three. 5FU is the cheapest of the three topical agents with less surface toxicity than MMC. Radiotherapy is mostly employed as adjuvant therapy. Newer novel therapies are available but have not been widely adopted as mainstream therapy due to cost and lack of clinical evidence. OSSN has the benefit of many management options. No single modality has been shown to superior and some patients will need the use of combination therapy to achieve an optimal clinical outcome.摘要: 眼表鳞状细胞癌 (Ocular surface squamous neoplasia, OSSN) 是最常见的眼部肿瘤, 发病率为0.031.9 / 10万人/年。临床表现疑似的病例, 进一步由前节相干光断层扫描 (anterior-segment optical coherence tomography, AS-OCT) 、细胞学或组织学进行确诊。本综述的目的是针对OSSN可行的治疗策略进行概述, 并阐述它们的成功率和复发率。手术是治疗小病灶OSSN治疗的金标准。随着AS-OCT和细胞学等侵入性较低的诊断方法的使用越来越多, 局部滴用眼药的治疗OSSN已经成为一种趋势。最常用的药物是干扰素-α2b (interferon-α2b, IFN)、丝裂霉素- c (mitomycin-C, MMC)和5-氟尿嘧啶(5-fluorouracil, 5FU)。它们具有相似的治疗率和复发率, 但在成本和副作用方面有所不同。IFN的副作用最低, 但也是最贵的, 而MMC的表面毒性最大, 价格介于三种药物之间。5FU是三种眼药中最便宜的, 表面毒性较MMC小。放射治疗主要用于辅助治疗。新的治疗手段是可行的, 但由于成本及缺乏临床证据, 并没有被广泛采用作为主流疗法。OSSN受益于许多治疗以及管理策略。没有一种单一的治疗方式显示出优越性, 一些患者需要使用联合治疗以达到最佳的临床结局。.

BACKGROUND: To the authors' knowledge, the impact of the coronavirus disease 2019 (COVID-19) pandemic on cytopathology practices worldwide has not been investigated formally. In the current study, data from 41 respondents from 23 countries were reported. METHODS: Data regarding the activity of each cytopathology laboratory during 4 weeks of COVID-19 lockdown were collected and compared with those obtained during the corresponding period in 2019. The overall number and percentage of exfoliative and fine-needle aspiration cytology samples from each anatomic site were recorded. Differences in the malignancy and suspicious rates between the 2 periods were analyzed using a meta-analytical approach. RESULTS: Overall, the sample volume was lower compared with 2019 (104,319 samples vs 190,225 samples), with an average volume reduction of 45.3% (range, 0.1%-98.0%). The percentage of samples from the cervicovaginal tract, thyroid, and anorectal region was significantly reduced (P < .05). Conversely, the percentage of samples from the urinary tract, serous cavities, breast, lymph nodes, respiratory tract, salivary glands, central nervous system, gastrointestinal tract, pancreas, liver, and biliary tract increased (P < .05). An overall increase of 5.56% (95% CI, 3.77%-7.35%) in the malignancy rate in nongynecological samples during the COVID-19 pandemic was observed. When the suspicious category was included, the overall increase was 6.95% (95% CI, 4.63%-9.27%). CONCLUSIONS: The COVID-19 pandemic resulted in a drastic reduction in the total number of cytology specimens regardless of anatomic site or specimen type. The rate of malignancy increased, reflecting the prioritization of patients with cancer who were considered to be at high risk. Prospective monitoring of the effect of delays in access to health services during the lockdown period is warranted. ispartof: CANCER CYTOPATHOLOGY vol:128 issue:12 pages:885-894 ispartof: location:United States status: published

Background Cytology-based cervical cancer screening followed by confirmation and treatment of biopsy-proven high-grade squamous intraepithelial lesions (bHSIL) is difficult to implement in resource-constrained settings. We hypothesized that high-risk human papillomavirus (hrHPV) testing followed by immediate cryotherapy of women with hrHPV (HPV screen-and-treat) may improve outcomes. Methods Randomized, open-label, phase 2, multinational clinical trial enrolling women with human immunodeficiency virus (HIV) age 18 or older with cervical hrHPV and having no cervical lesions or lesions appropriate for cryotherapy. Women were randomized to immediate cryotherapy (Arm A) or cytology-based screening (Arm B). For Arm A, cervical biopsies were obtained followed by cervical cryotherapy, and in Arm B, women with abnormal cytology underwent colposcopy followed by loop electroexcision procedure (LEEP) if bHSIL was detected. Women were followed through 30 months. The primary outcome was time to bHSIL detected from Month 6 through study completion. Results In total, 288 women (145 in Arm A, 143 in Arm B) were randomized: median age 35 years, 84% on antiretroviral therapy, median CD4 501 cells/mm3. In Arm A, 39 (27%) of women had bHSIL at entry, and in Arm B, 88 (62%) had abnormal cytology, 22 (15%) were diagnosed with bHSIL, 12 (8%) underwent LEEP. In follow-up, 30 (21%) and 31 (22%) developed bHSIL; time to bHSIL was similar between arms (P=.94). The prevalence of hrHPV at Month 6 was similar between arms (61% and 70%, P=.13). Conclusions HPV test-and-treat was not associated with improved bHSIL outcomes as compared to cytology-based screening. More effective treatment options are required to improve outcomes from screen-and-treat programs. Clinical Trials Registration NCT01315363.

Context.— Pathologists may encounter extraneous pieces of tissue (tissue floaters) on glass slides because of specimen cross-contamination. Troubleshooting this problem, including performing molecular tests for tissue identification if available, is time consuming and often does not satisfactorily resolve the problem. Objective.— To demonstrate the feasibility of using an image search tool to resolve the tissue floater conundrum. Design.— A glass slide was produced containing 2 separate hematoxylin and eosin (H&E)-stained tissue floaters. This fabricated slide was digitized along with the 2 slides containing the original tumors used to create these floaters. These slides were then embedded into a dataset of 2325 whole slide images comprising a wide variety of H&E stained diagnostic entities. Digital slides were broken up into patches and the patch features converted into barcodes for indexing and easy retrieval. A deep learning-based image search tool was employed to extract features from patches via barcodes, hence enabling image matching to each tissue floater. Results.— There was a very high likelihood of finding a correct tumor match for the queried tissue floater when searching the digital database. Search results repeatedly yielded a correct match within the top 3 retrieved images. The retrieval accuracy improved when greater proportions of the floater were selected. The time to run a search was completed within several milliseconds. Conclusions.— Using an image search tool offers pathologists an additional method to rapidly resolve the tissue floater conundrum, especially for those laboratories that have transitioned to going fully digital for primary diagnosis.

BackgroundThe mitotic count in breast carcinoma is an important prognostic marker. Unfortunately substantial inter- and intra-laboratory variation exists when pathologists manually count mitotic figures. Artificial intelligence (AI) coupled with whole slide imaging offers a potential solution to this problem. The aim of this study was to accordingly critique an AI tool developed to quantify mitotic figures in whole slide images of invasive breast ductal carcinoma.MethodsA representative H&E slide from 320 breast invasive ductal carcinoma cases was scanned at 40x magnification. Ten expert pathologists from two academic medical centers labeled mitotic figures in whole slide images to train and validate an AI algorithm to detect and count mitoses. Thereafter, 24 readers of varying expertise were asked to count mitotic figures with and without AI support in 140 high-power fields derived from a separate dataset. Their accuracy and efficiency of performing these tasks were calculated and statistical comparisons performed.ResultsFor each experience level the accuracy, precision and sensitivity of counting mitoses by users improved with AI support. There were 21 readers (87.5%) that identified more mitoses using AI support and 13 reviewers (54.2%) that decreased the quantity of falsely flagged mitoses with AI. More time was spent on this task for most participants when not provided with AI support. AI assistance resulted in an overall time savings of 27.8%.ConclusionsThis study demonstrates that pathology end-users were more accurate and efficient at quantifying mitotic figures in digital images of invasive breast carcinoma with the aid of AI. Higher inter-pathologist agreement with AI assistance suggests that such algorithms can also help standardize practice. Not surprisingly, there is much enthusiasm in pathology regarding the prospect of using AI in routine practice to perform mundane tasks such as counting mitoses.

Artificial intelligence (AI) technologies have the potential to transform cytopathology practice, and it is important for cytopathologists to embrace this and place themselves at the forefront of implementing these technologies in cytopathology. This review illustrates an archetypal AI workflow from project conception to implementation in a diagnostic setting and illustrates the cytopathologist's role and level of involvement at each stage of the process. Cytopathologists need to develop and maintain a basic understanding of AI, drive decisions regarding the development and implementation of AI in cytopathology, participate in the generation of datasets used to train and evaluate AI algorithms, understand how the performance of these algorithms is assessed, participate in the validation of these algorithms (either at a regulatory level or in the laboratory setting), and ensure continuous quality assurance of algorithms deployed in a diagnostic setting. In addition, cytopathologists should ensure that these algorithms are developed, trained, tested and deployed in an ethical manner. Cytopathologists need to become informed consumers of these AI algorithms by understanding their workings and limitations, how their performance is assessed and how to validate and verify their output in clinical practice.

Background: In a previous worldwide survey, the authors showed a drastic reduction in the number of cytological specimens processed during the coronavirus disease 2019 “lockdown” period along with an increase in malignancy rates. To assess the continued impact of the pandemic on cytological practices around the world, they undertook a second follow-up worldwide survey collecting data from the post-lockdown period (2020). Methods: Participants were asked to provide data regarding their cytopathology activity during the first 12 weeks of their respective national post-lockdown period (2020), which ranged from April 4 to October 31. Differences between the post-lockdown period and the corresponding 2019 period were evaluated, and the authors specifically focused on rates of malignant diagnoses. Results: A total of 29 respondents from 17 countries worldwide joined the survey. Overall, a lower number of cytological specimens (n = 236,352) were processed in comparison with the same period in 2019 (n = 321,466) for a relative reduction of 26.5%. The overall malignancy rate showed a statistically significant increase (12,442 [5.26%] vs 12,882 [4.01%]; P

Introduction: Dataset creation is one of the first tasks required for training AI algorithms but is underestimated in pathology. High-quality data are essential for training algorithms and data should be labelled accurately and include sufficient morphological diversity. The dynamics and challenges of labelling a urine cytology dataset using The Paris System (TPS) criteria are presented. Methods: 2,454 images were labelled by pathologist consensus via video conferencing over a 14-day period. During the labelling sessions, the dynamics of the labelling process were recorded. Quality assurance images were randomly selected from images labelled in previous sessions within this study and randomly distributed throughout new labelling sessions. To assess the effect of time on the labelling process, the labelled set of images was split into 2 groups according to the median relative label time and the time taken to label images and intersession agreement were assessed. Results: Labelling sessions ranged from 24 m 11 s to 41 m 06 s in length, with a median of 33 m 47 s. The majority of the 2,454 images were labelled as benign urothelial cells, with atypical and malignant urothelial cells more sparsely represented. The time taken to label individual images ranged from 1 s to 42 s with a median of 2.9 s. Labelling times differed significantly among categories, with the median label time for the atypical urothelial category being 7.2 s, followed by the malignant urothelial category at 3.8 s and the benign urothelial category at 2.9 s. The overall intersession agreement for quality assurance images was substantial. The level of agreement differed among classes of urothelial cells – benign and malignant urothelial cell classes showed almost perfect agreement and the atypical urothelial cell class showed moderate agreement. Image labelling times seemed to speed up, and there was no evidence of worsening of intersession agreement with session time. Discussion/Conclusion: Important aspects of pathology dataset creation are presented, illustrating the significant resources required for labelling a large dataset. We present evidence that the time taken to categorise urine cytology images varies by diagnosis/class. The known challenges relating to the reproducibility of the AUC (atypical) category in TPS when compared to the NHGUC (benign) or HGUC (malignant) categories is also confirmed.

BACKGROUND With the advent of combined antiretroviral therapy (cART), HIV positive women are expected to live longer. The effect of chronic HIV infection and cART on cervical epithelial maturation has not been well studied in postmenopausal woman. The objective of this study was to determine whether HIV positive postmenopausal women on cART show expected atrophic changes in cervical Pap tests. METHODS The maturation index (MI) was performed on routine cervical smears from HIV-infected, postmenopausal women attending an HIV clinic in a tertiary hospital in Johannesburg, over a 4-year period from January 2009 to December 2012. RESULTS In Pap smears of 111 patients on cART, 58 (52%) showed an unexpected predominantly mature squamous epithelial pattern whereas 53 (48%) were predominantly immature or atrophic (P = .0001). There was no significant statistical difference in maturation according to cART use. CONCLUSION HIV-infected, postmenopausal women in this study had reduced rates of cervical atrophy than expected, irrespective of cART use and CD4 count. Initiation of cART before menopause was associated with greater cervical epithelium maturation than those women who started cART after menopause. Additional, larger studies are required to confirm this novel finding and to investigate the reason for this phenomenon.

Background Cervical cancer screening strategies using visual inspection or cytology may have suboptimal diagnostic accuracy for detection of precancer in women living with HIV (WLHIV). The optimal screen and screen–triage strategy, age to initiate, and frequency of screening for WLHIV remain unclear. This study evaluated the sensitivity, specificity, and positive predictive value of different cervical cancer strategies in WLHIV in Africa. Methods and findings WLHIV aged 25–50 years attending HIV treatment centres in Burkina Faso (BF) and South Africa (SA) from 5 December 2011 to 30 October 2012 were enrolled in a prospective evaluation study of visual inspection using acetic acid (VIA) or visual inspection using Lugol’s iodine (VILI), high-risk human papillomavirus DNA test (Hybrid Capture 2 [HC2] or careHPV), and cytology for histology-verified high-grade cervical intraepithelial neoplasia (CIN2+/CIN3+) at baseline and endline, a median 16 months later. Among 1,238 women (BF: 615; SA: 623), median age was 36 and 34 years (p < 0.001), 28.6% and 49.6% ever had prior cervical cancer screening (p < 0.001), and 69.9% and 64.2% were taking ART at enrolment (p = 0.045) in BF and SA, respectively. CIN2+ prevalence was 5.8% and 22.4% in BF and SA (p < 0.001), respectively. VIA had low sensitivity for CIN2+ (44.7%, 95% confidence interval [CI] 36.9%–52.7%) and CIN3+ (56.1%, 95% CI 43.3%–68.3%) in both countries, with specificity for ≤CIN1 of 78.7% (95% CI 76.0%–81.3%). HC2 had sensitivity of 88.8% (95% CI 82.9%–93.2%) for CIN2+ and 86.4% (95% CI 75.7%–93.6%) for CIN3+. Specificity for ≤CIN1 was 55.4% (95% CI 52.2%–58.6%), and screen positivity was 51.3%. Specificity was higher with a restricted genotype (HPV16/18/31/33/35/45/52/58) approach (73.5%, 95% CI 70.6%–76.2%), with lower screen positivity (33.7%), although there was lower sensitivity for CIN3+ (77.3%, 95% CI 65.3%–86.7%). In BF, HC2 was more sensitive for CIN2+/CIN3+ compared to VIA/VILI (relative sensitivity for CIN2+ = 1.72, 95% CI 1.28–2.32; CIN3+: 1.18, 95% CI 0.94–1.49). Triage of HC2-positive women with VIA/VILI reduced the number of colposcopy referrals, but with loss in sensitivity for CIN2+ (58.1%) but not for CIN3+ (84.6%). In SA, cytology high-grade squamous intraepithelial lesion or greater (HSIL+) had best combination of sensitivity (CIN2+: 70.1%, 95% CI 61.3%–77.9%; CIN3+: 80.8%, 95% CI 67.5%–90.4%) and specificity (81.6%, 95% CI 77.6%–85.1%). HC2 had similar sensitivity for CIN3+ (83.0%, 95% CI 70.2%–91.9%) but lower specificity compared to HSIL+ (42.7%, 95% CI 38.4%–47.1%; relative specificity = 0.57, 95% CI 0.52–0.63), resulting in almost twice as many referrals. Compared to HC2, triage of HC2-positive women with HSIL+ resulted in a 40% reduction in colposcopy referrals but was associated with some loss in sensitivity. CIN2+ incidence over a median 16 months was highest among VIA baseline screen-negative women (2.2%, 95% CI 1.3%–3.7%) and women who were baseline double-negative with HC2 and VIA (2.1%, 95% CI 1.3%–3.5%) and lowest among HC2 baseline screen-negative women (0.5%, 95% CI 0.1%–1.8%). Limitations of our study are that WLHIV included in the study may not reflect a contemporary cohort of WLHIV initiating ART in the universal ART era and that we did not evaluate HPV tests available in study settings today. Conclusions In this cohort study among WLHIV in Africa, a human papillomavirus (HPV) test targeting 14 high-risk (HR) types had higher sensitivity to detect CIN2+ compared to visual inspection but had low specificity, although a restricted genotype approach targeting 8 HR types decreased the number of unnecessary colposcopy referrals. Cytology HSIL+ had optimal performance for CIN2+/CIN3+ detection in SA. Triage of HPV-positive women with HSIL+ maintained high specificity but with some loss in sensitivity compared to HC2 alone., In this cohort study, Helen Kelly and colleagues explore cervical cancer screening strategies for women living with HIV., Author summary Why was this study done? Invasive cervical cancer is the second most common cancer among women in low- and middle-income countries and a leading cause of cancer-related death in women in sub-Saharan Africa. Women living with human immunodeficiency virus (WLHIV) have an increased risk of cervical cancer and precancer. The majority of WLHIV live in low- and middle-income countries, where access to cervical cancer screening and treatment of precancerous cervical lesions is limited. Screening approaches most commonly used in sub-Saharan Africa, including visual inspection of the cervix and cervical cytology, which checks for cervical cell abnormalities, have shown variable diagnostic accuracy to detect precancerous lesions. Molecular-based screening approaches, such as human papillomavirus (HPV) DNA testing, which screens for oncogenic HPV infection, have shown high sensitivity for cervical precancer but can result in over-referral to colposcopy, a procedure to determine eligibility for treatment. The optimal screening test, age to begin screening, and frequency of screening for WLHIV remain uncertain. What did the researchers do and find? We evaluated several cervical cancer screening strategies in over 1,200 WLHIV in sub-Saharan Africa. We found that an HPV DNA test identified a greater number of women with precancer compared to visual inspection and cytology methods. However, there was a greater proportion of women without precancer who had a positive HPV DNA test, meaning a triage test using cytology or visual inspection was required to determine treatment eligibility. Simple user-applied modifications to the HPV-DNA-based test resulted in fewer women without precancer testing positive and fewer women needing triage. In settings with adequate infrastructure, cervical cytology was a useful triage test for HPV-positive women. What do these findings mean? Our data contribute to the evidence on choice of screening strategies for detection of cervical precancer among WLHIV in low- and middle-income settings. HPV DNA tests can play an important role in cervical cancer screening, especially in the era of universal antiretroviral therapy and where availability of self-sampling will facilitate screening participation. Prevention of cervical cancer should rank high as a public health priority in sub-Saharan Africa since WLHIV represent a group at very high risk of cervical precancer.

Objectives This study aimed to develop and validate a deep learning algorithm to screen digitized acid fast–stained (AFS) slides for mycobacteria within tissue sections. Methods A total of 441 whole-slide images (WSIs) of AFS tissue material were used to develop a deep learning algorithm. Regions of interest with possible acid-fast bacilli (AFBs) were displayed in a web-based gallery format alongside corresponding WSIs for pathologist review. Artificial intelligence (AI)–assisted analysis of another 138 AFS slides was compared to manual light microscopy and WSI evaluation without AI support. Results Algorithm performance showed an area under the curve of 0.960 at the image patch level. More AI-assisted reviews identified AFBs than manual microscopy or WSI examination (P < .001). Sensitivity, negative predictive value, and accuracy were highest for AI-assisted reviews. AI-assisted reviews also had the highest rate of matching the original sign-out diagnosis, were less time-consuming, and were much easier for pathologists to perform (P < .001). Conclusions This study reports the successful development and clinical validation of an AI-based digital pathology system to screen for AFBs in anatomic pathology material. AI assistance proved to be more sensitive and accurate, took pathologists less time to screen cases, and was easier to use than either manual microscopy or viewing WSIs.

Objectives Developing accurate supervised machine learning algorithms is hampered by the lack of representative annotated datasets. Most data in anatomic pathology are unlabeled and creating large, annotated datasets is a time consuming and laborious process. Unsupervised learning, which does not require annotated data, possesses the potential to assist with this challenge. This review aims to introduce the concept of unsupervised learning and illustrate how clustering, generative adversarial networks (GANs) and autoencoders have the potential to address the lack of annotated data in anatomic pathology. Methods A review of unsupervised learning with examples from the literature was carried out. Results Clustering can be used as part of semisupervised learning where labels are propagated from a subset of annotated data points to remaining unlabeled data points in a dataset. GANs may assist by generating large amounts of synthetic data and performing color normalization. Autoencoders allow training of a network on a large, unlabeled dataset and transferring learned representations to a classifier using a smaller, labeled subset (unsupervised pretraining). Conclusions Unsupervised machine learning techniques such as clustering, GANs, and autoencoders, used individually or in combination, may help address the lack of annotated data in pathology and improve the process of developing supervised learning models.

Background: Ocular surface squamous neoplasia (OSSN) is the most common ocular tumour. The diagnosis of OSSN is based on clinical suspicion and confirmed by various diagnostic modalities, of which histology is the gold standard. With the move to less invasive management options such as topical chemo- or immunotherapy, less invasive diagnostic options have come to the fore. Aim: The purpose of this article was to review the current staging and diagnostic modalities for OSSN with a focus on less invasive modalities. Method: A literature review was performed for publications on ocular surface neoplasia and diagnostic modalities. Results: Histology is the gold standard for diagnosing OSSN. Cytology has been shown to be a simple, repeatable and minimally invasive diagnostic modality, which also allows for additional testing such as polymerase chain reaction. Anterior segment optical coherence tomography provides a non-contact method of evaluating the ocular surface, with OSSN showing a thickened hyper-reflective epithelium, abrupt transition zone and demarcation line. Vital dyes are used less commonly with high sensitivity, but lower specificity for OSSN. Finally, confocal microscopy provides en-face images of the ocular surface, with OSSN showing a classic ‘starry night’ appearance. Conclusion: Histology remains the gold standard for diagnosis; however, with the increasing use of topical therapy for OSSN, there has been an increase in the uptake of less invasive diagnostic modalities.

Background Women living with human immunodeficiency virus (HIV), especially in sub-Saharan Africa, are at high risk for cervical high-grade squamous intraepithelial lesions (HSIL) and cervical cancer. These women have high HSIL recurrence rates after loop electroexcision procedure (LEEP). Retrospective studies suggest that human papillomavirus (HPV) vaccination improves response to treatment of cervical HSIL. Methods We performed a double-blind, randomized clinical trial enrolling 180 women living with HIV in Johannesburg, South Africa, diagnosed with cervical HSIL by colposcopic biopsy. Women received quadrivalent HPV vaccine or placebo (1:1) at entry, week 4, and week 26. LEEP was performed at week 4. Colposcopic-directed biopsies and cervical cytology were performed at weeks 26 and 52. The primary endpoint, cervical HSIL by histology or cytology at either week 26 or 52, was compared between arms using χ 2 analysis. Results Participant characteristics included median age of 39 years and median CD4 count 489 cells/μL, and 94% had HIV suppression. One hundred seventy-four women completed the vaccine/placebo series and had evaluable results at week 26 or 52. The proportion experiencing the primary endpoint was similar in the vaccine and placebo groups (53% vs 45%; relative risk, 1.18 [95% confidence interval, .87–1.6]; P = .29). HSIL recurrence was associated with a LEEP biopsy result of HSIL and detection of HSIL at the margins of the LEEP sample. Conclusions This study did not support HPV vaccination to prevent recurrent HSIL after LEEP in women living with HIV. Recurrent HSIL was high despite virologic suppression. Improved treatments are needed for HSIL to reduce the burden of cervical cancer among women living with HIV. Clinical Trials Registration NCT01928225.

The application of artificial intelligence technologies to anatomic pathology has the potential to transform the practice of pathology, but, despite this, many pathologists are unfamiliar with how these models are created, trained, and evaluated. In addition, many pathologists may feel that they do not possess the necessary skills to allow them to embark on research into this field. This article aims to act as an introductory tutorial to illustrate how to create, train, and evaluate simple artificial learning models (neural networks) on histopathology data sets in the programming language Python using the popular freely available, open-source libraries Keras, TensorFlow, PyTorch, and Detecto. Furthermore, it aims to introduce pathologists to commonly used terms and concepts used in artificial intelligence.

Background: The incorporation of digital pathology into routine pathology practice is becoming more widespread. Definite advantages exist with respect to the implementation of artificial intelligence (AI) and deep learning in pathology, including cytopathology. However, there are also unique challenges in this regard. Summary: This review discusses cytology-specific challenges, including the need to implement digital cytology prior to AI; the large file sizes and increased acquisition times for whole slide images in cytology; the routine use of multiple stains, such as Papanicolaou and Romanowsky stains; the lack of high-quality annotated datasets on which to train algorithms; and the considerable computer resources required, in terms of both computer infrastructure and skilled personnel, for computing and storage of data. Global concerns regarding AI that are certainly applicable to cytology include the need for model validation and continued quality assurance, ethical issues such as the use of patient data in developing algorithms, the need to develop regulatory frameworks regarding what type of data can be utilized and ensuring cybersecurity during data collection and storage, and algorithm development. Key Messages: While AI will likely play a role in cytology practice in the future, applying this technology to cytology poses a unique set of challenges. A broad understanding of digital pathology and algorithm development is desirable to guide the development of algorithms, as well as the need to be cognizant of potential pitfalls to avoid when incorporating the technology in practice.

There is high demand to develop computer-assisted diagnostic tools to evaluate prostate core needle biopsies (CNBs), but little clinical validation and a lack of clinical deployment of such tools. We report here on a blinded clinical validation study and deployment of an artificial intelligence (AI)-based algorithm in a pathology laboratory for routine clinical use to aid prostate diagnosis.An AI-based algorithm was developed using haematoxylin and eosin (HE)-stained slides of prostate CNBs digitised with a Philips scanner, which were divided into training (1 357 480 image patches from 549 HE-stained slides) and internal test (2501 HE-stained slides) datasets. The algorithm provided slide-level scores for probability of cancer, Gleason score 7-10 (vs Gleason score 6 or atypical small acinar proliferation [ASAP]), Gleason pattern 5, and perineural invasion and calculation of cancer percentage present in CNB material. The algorithm was subsequently validated on an external dataset of 100 consecutive cases (1627 HE-stained slides) digitised on an Aperio AT2 scanner. In addition, the AI tool was implemented in a pathology laboratory within routine clinical workflow as a second read system to review all prostate CNBs. Algorithm performance was assessed with area under the receiver operating characteristic curve (AUC), specificity, and sensitivity, as well as Pearson's correlation coefficient (Pearson's r) for cancer percentage.The algorithm achieved an AUC of 0·997 (95% CI 0·995 to 0·998) for cancer detection in the internal test set and 0·991 (0·979 to 1·00) in the external validation set. The AUC for distinguishing between a low-grade (Gleason score 6 or ASAP) and high-grade (Gleason score 7-10) cancer diagnosis was 0·941 (0·905 to 0·977) and the AUC for detecting Gleason pattern 5 was 0·971 (0·943 to 0·998) in the external validation set. Cancer percentage calculated by pathologists and the algorithm showed good agreement (r=0·882, 95% CI 0·834 to 0·915; p0·0001) with a mean bias of -4·14% (-6·36 to -1·91). The algorithm achieved an AUC of 0·957 (0·930 to 0·985) for perineural invasion. In routine practice, the algorithm was used to assess 11 429 HE-stained slides pertaining to 941 cases leading to 90 Gleason score 7-10 alerts and 560 cancer alerts. 51 (9%) cancer alerts led to additional cuts or stains being ordered, two (4%) of which led to a third opinion request. We report on the first case of missed cancer that was detected by the algorithm.This study reports the successful development, external clinical validation, and deployment in clinical practice of an AI-based algorithm to accurately detect, grade, and evaluate clinically relevant findings in digitised slides of prostate CNBs.Ibex Medical Analytics.

The International Academy of Cytology (IAC) Yokohama System for Reporting Breast Fine Needle Aspiration Biopsy (FNAB) Cytology reporting system is an initiative of the IAC that seeks to provide a comprehensive, standardized approach to breast FNAB reporting to facilitate reproducible cytopathology reporting and to establish best practice guidelines. The system is evidence-based, supports a structured reporting format and will aid in maximizing the usefulness of the FNAB technique and optimizing communication with the clinical team and the patient.

Objectives To assess whether women with HIV who had low-grade squamous intraepithelial lesions (LSIL) on cytology had cervical disease. Methods The present retrospective cross-sectional study included data from women with LSIL who attended a tertiary hospital in South Africa between April 1, 2003, and December 31, 2013. Patient information was extracted from a colposcopy database. Results The study included 652 patients. The median age was 36 years (interquartile range [IQR] 31-42 years; range 18-66 years) and the median parity was three (IQR 2-5; range 0-10). In all, 266 (40.8%) women had a histology result of HPV or cervical intraepithelial neoplasia 1 (CIN1); 386 (59.2%) had a histology result of CIN2 or higher. The median cluster of differentiation 4 (CD4) count was 275.00 cells/mm3 (IQR 173.50-434.00 cells/mm3 ; range 2-1211 cells/mm3 ). A total of 312 (47.9%) women were using antiretroviral therapy. Use of antiretroviral therapy (unadjusted odds ratio 0.57; P=0.001) and a CD4 count of at least 200 cells/mm3 (unadjusted odds ratio 0.81; P=0.002) were associated with a histology result of HPV or CIN1. Conclusion Most of the women with a cytology report of LSIL had CIN2 or higher, suggesting that the practice of referral for colposcopy should continue.

Objectives This study investigated anal high-risk HPV (HR-HPV) prevalence in HIV-infected women using the Cepheid Xpert HPV assay and compares its performance with that of Hybrid Capture-2 (hc2). Methods A total of 199 HIV-infected women were recruited from Helen Joseph Hospital, Johannesburg. Stored ThinPrep anal swabs that had previously been tested using hc2 were tested for HPV using Xpert. Results The HR-HPV prevalence by Xpert was 40.8% and similar to hc2 (41.8%) with overall agreement of 86.7%; Cohen's kappa 0.73 (95% CI 0.63-0.82). High grade squamous intraepithelial lesions (HSIL) was associated with increasing number of multiple HPV infection (P < .001). Xpert and hc2 were similarly sensitive (77.4% and 77.4%, respectively) and specific (66.1% and 64.8% respectively) for HSIL detection. HPV16 (OR: 14.0, 95% CI: 3.9-48.0, P < .0001), HPV39/68/56/66 (OR: 4.1, 95% CI: 1.4-12, P = .01) and HPV51/59 (OR: 2.8, 95% CI: 1.1-7.6, P = .04) were independently associated with anal HSIL. Conclusions Xpert HPV typing is a promising anal screening test in HIV-infected women that performs similarly to hc2.

Background Persistent high-risk human papillomavirus (HR-HPV) infection is associated with the development of anogenital cancers, particularly in men living with HIV (MLWH). We describe the prevalence of anogenital HPV infection, abnormal anal cytology and anogenital warts (AGWs) in MLWH in Johannesburg, and explore whether HPV infection and receipt of antiretroviral treatment is associated with detection of abnormal anal cytology and AGWs. Methods We enrolled a cohort of 304 sexually-active MLWH ≥18 years, who completed a questionnaire and physical examination. Genital swabs were collected from all men and intra-anal swabs from 250 (82%). Swabs were tested for HPV DNA and genotypes, and anal smears graded using the Bethesda classification. Factors associated with anogenital disease were assessed by logistic regression models. Results Two thirds were receiving antiretroviral treatment, for a median 33 months (IQR = 15–58) and 54% were HIV-virologically suppressed. Only 5% reported ever having sex with men. Among 283 genital swabs with valid results, 79% had any HPV, 52% had HR-HPV and 27% had >1 HR-HPV infection. By comparison, 39% of the 227 valid intra-anal swabs had detectable HPV, 25% had any HR-HPV and 7% >1 HR infection. While most anal smears were normal (51%), 20% had ASCUS and 29% were LSIL. No cases had HSIL or cancer. Infection with >1 HR type (adjusted OR [aOR] = 2.39; 95%CI = 1.02–5.58) and alpha-9 types (aOR = 3.98; 95%CI = 1.42–11.16) were associated with having abnormal cytology. Prevalence of AGWs was 12%. Infection with any LR type (aOR = 41.28; 95%CI = 13.57–125.62), >1 LR type (aOR = 4.14; 95%CI = 1.60–10.69), being

Objective: To determine whether there are significant differences between fibroadenomas and phyllodes tumours with regard to selected cytomorphological features. Study Design: A 10-year retrospective review was performed of patients who underwent excision of a fibroadenoma or phyllodes tumour and in whom a preoperative fine-needle aspiration was performed. The following cytological criteria were assessed: number of stromal and epithelial fragments, stromal-to-epithelial ratio, stromal cellularity, stromal borders, stromal atypia, and proportion of background wavy spindled cells. Patient age, tumour laterality, and tumour size were recorded. Results: Fifty fibroadenomas and 17 phyllodes tumours were included. Compared to phyllodes tumours, fibroadenomas had a larger number of epithelial fragments, a smaller number of stromal fragments, and a lower stromal-to-epithelial ratio. The stroma tended to be less cellular and less atypical compared to phyllodes tumours and the background cellular population contained fewer spindled cells. Conclusion: Fibroadenomas and phyllodes tumours differ with regard to various cytological features, aiding in their distinction on fine-needle aspiration biopsy.

Background: In South Africa, cervical cancer remains among the most common cancers and a leading cause of cancer death. Co-infection with HIV increases the risk of developing cervical pre-cancer and cancer. We analysed National Health Laboratory Service cervical cytology data to investigate geographic variations of Pap smear coverage, quality, and high grade lesions. Methods: Facility-level data were extracted from the NHLS for April 2013–March 2014. We present results and choropleth maps detailing coverage, adequacy and high-grade Pap smear cytology abnormalities defined as Pap smears suspicious for invasive carcinoma, high-grade squamous intraepithelial lesions (HSIL) or atypical squamous cells: cannot exclude HSIL (ASC-H). Results: 4,562 facilities submitted 791,067 cytology slides. The interquartile range (IQR) for Pap smear coverage among HIV-infected women was 26–41%; similar to coverage in women aged 30 and older (IQR: 26–42%). 6/52 districts had adequacy rates above the national standard (70%) and 2/52 districts had adequacy rates below 35%. We observed marked variation in Pap smear abnormalities across the country, with the proportion of high-grade cytology abnormalities ≥0.3% in 17/52 districts.Conclusion: Using district-level choropleth maps, we are able to display variations in Pap smear coverage, quality, and results across South Africa. This approach may be used to improve resource allocation, achieving better equity in cervical cancer prevention.

ObjectiveTo estimate the prevalence, incidence and persistence of anal HPV infection and squamous intra-epithelial lesions (SILs) among men living with HIV (MLHIV), and determine their risk factors.MethodsWe enrolled MLHIV ≥18 years, who attended 6-monthly visits for 18 months. Socio-behavioural data were collected by questionnaire. Clinicians collected blood sample (CD4+ count and HIV plasma viral load), anal swabs (HPV DNA testing) and anal smears (Bethesda classification) at each visit. HPV DNA testing and classification of smears were done at enrolment and last follow-up visit (two time points). Factors associated with persistent anal HPV infection and SILs were evaluated with generalized estimating equations logistic regression and standard logistic regression respectively.ResultsMean age of 304 participants was 38 (Standard Deviation, 8) years; 25% reported >1 sexual partner in the past 3 months. Only 5% reported ever having sex with other men. Most (65%) participants were taking antiretroviral treatment (ART), with a median CD4+ count of 445 cells/μL (IQR, 328-567). Prevalence of any-HPV infection at enrolment was 39% (88/227). In total, 226 men had anal HPV DNA results at both enrolment and final visits. Persistence of any-anal HPV infection among 80 men who had infection at enrolment was 26% (21/80). Any persistent anal HPV infection was more frequent among MLHIV with low CD4+ count (500 cells/μL; aOR = 6.58; 95%CI: 2.41-17.94). Prevalence of anal SILs at enrolment was 49% (118/242) while incidence of SILs among MLHIV who had no anal dysplasia at enrolment was 27% (34/124). Of the 118 men who had anal dysplasia at enrolment, 15% had regressed and 38% persisted by month 18. Persistent anal HPV infection was associated with persistent SILs (aOR = 2.95; 95%CI: 1.08-10.89). ART status or duration at enrolment were not associated with persistent anal HPV infection or persistent SILs during follow-up.ConclusionIn spite of a high prevalence of anal HPV, HIV-positive heterosexual men have a low burden of anal HPV related disease. HPV vaccine and effective ART with immunological reconstitution could reduce this burden of infection.

A variety of primary breast and metastatic lesions to the breast can present with spindle cell cytomorphology. These lesions may range from benign reactive or inflammatory lesions to high-grade malignancies. Spindle cell lesions of the breast are not often seen on fine-needle aspiration biopsy (FNAB) but need to be correctly managed when they are encountered. While mesenchymal lesions of the breast have a spindle morphology, lesions derived from the epithelium and myoepithelium can be spindled as well. By assessing if the lesion comprises spindle cells only or if other components such as epithelial cells are apparent and then determining whether the spindle cells appear bland or pleomorphic, together with close clinicoradiologic correlation and prudent use of ancillary tests, a variety of lesions can be diagnosed on FNAB. However, core needle biopsy or excision biopsy may be required in some patients. The cytomorphology, ancillary studies, and clinicoradiologic findings of a range of spindle cell lesions of the breast are further discussed.

Background. The endocervical component of a Pap smear is an important indicator of sample quality – or ‘adequacy’. However, only 6 of 52 districts in South Africa (SA) meet the Department of Health (DoH) performance benchmark: a 70% adequacy rate. We implemented a quality-improvement (QI) intervention to address suboptimal Pap smear quality in Tshwane District, Gauteng Province, SA. Objectives. To determine whether training with the wooden Ayre spatula (step 1) or introduction of the cytobroom (step 2) resulted in greater improvements in Pap smear adequacy rates. Methods. Two Tshwane District health facilities participated in our QI project between May 2016 and February 2017. In step 1, staff received training on the Ayre spatula. In step 2, the spatula was replaced with the cytobroom. Pap smear volumes, adequacy rates and results are reported for the pre-intervention period and after each QI step. We compared adequacy rates using Fisher’s exact test, with a significance level of p =0.05. Results. In the pre-intervention period, 304 of 965 Pap smears were deemed adequate (32%; 95% confidence interval (CI) 29 - 35%). After step 1, the proportion increased to 109 of 191 (57%; 95% CI 50 - 64%; p

Cervical cancer is one of the most common causes of cancer-related deaths in Southern Africa. Human papillomavirus vaccination offers a chance to markedly reduce this burden of disease although challenges with vaccine delivery need to be overcome.

Mycobacterial infection, tuberculosis (TB) in particular, remains one of the world's deadliest communicable diseases in adults and particularly in children, in low and middle income countries. The combination of human immunodeficiency virus (HIV) and TB is often lethal with TB accounting for 25% of deaths in the HIV population. One of the cornerstones for reducing the TB epidemic is early case detection using high quality diagnostic techniques. Cytology, especially fine needle aspiration biopsy (FNAB) is able to diagnose mycobacterial infection in a rapid and cost-effective manner without requiring surgery, thus allowing appropriate management to be quickly instituted. Confirmatory ancillary tests can effectively be performed on cytologic material. In this review, the pertinent cytomorphology of mycobacterial infection in various exfoliative and FNAB specimens is presented, in both immunocompetent and immunosuppressed patients. In the immunosuppressed, the typical cytomorphology of caseating granulomatous inflammation may not be seen but suppurative necrotic inflammation, mycobacterial spindle pseudotumour or a specimen comprised entirely of necrosis may be seen instead. This review includes discussion of currently available ancillary tests that can be performed on cytologic specimens.

Background Ocular surface squamous neoplasia (OSSN) is the most common ocular surface tumour. Diagnosis and management have traditionally been by excision biopsy. Recently there has been success with the use of topical chemo or immunotherapy, which has resulted in a move from invasive diagnosis by histology to an array of non-invasive diagnostic tests. Methods This observational study aims to describe the characteristics of patients with OSSN at St John Eye Hospital in Johannesburg, South Africa. Non-invasive diagnostic tests (impression cytology, anterior segment-OCT, methylene blue staining) will be compared to the gold standard, histology. Treatment success, recurrence and adverse events will be documented between three treatment options that include: surgical excision, topical 5-Fluorouracil (5FU) chemotherapy, and topical 5FU with retinoic acid therapy. Discussion There is a trend to the use of less invasive diagnosis and management for OSSN. Minimally invasive diagnostic tests include cytology, anterior-segment OCT and methylene blue staining. The study will compare these to the gold standard histology, thereby providing evidence for their use in clinical practice. Interferon alpha 2b is commonly used as immunotherapy for OSSN. The cost of this medication is prohibitive to its adoption in a developing country. We therefore decided to use 5FU as the chemotherapeutic agent of choice in this study. The success, adverse events and recurrence rates with this agent may provide additional evidence for its use in the management of OSSN. Overall, if diagnosis and management can be implemented with good success in the outpatient environment, care can be improved for this condition in a developing country.

Background. Cervical cancer remains the second most common cancer among women worldwide, with much of the global burden occurring in low- and middle-income countries. HIV-infected women are at increased risk of human papillomavirus infection, preinvasive cervical disease and invasive cervical cancer (ICC). Funded through the United States President’s Emergency Plan for AIDS Relief (PEPFAR) and working in collaboration with the South African (SA) Department of Health, our team supports cervical screening integrated within public sector HIV clinics in SA. Objectives. To estimate the burden of cervical disease among HIV-infected women accessing screening services supported through our programme. Methods. We constructed conditional probability models to estimate the burden of grade 1 and grades 2/3 cervical intraepithelial lesions (CIN1 and CIN2/3) and ICC among two cohorts: one consisting of 3 190 HIV-infected women for whom only cytology results were available for analysis, and another consisting of 75 358 HIV-infected women for whom neither cytology nor histology results were available. Parameter estimates for the models were derived from routinely collected programmatic data and published clinical trials. Results. Between January 2009 and November 2015, 75 358 HIV-infected women underwent Pap smear screening in public sector clinics supported by our cervical cancer prevention programme. Based on modelling analysis, we estimate that 46 123 cases of CIN1 (range 45 500 - 49 608), 13 598 cases of CIN2/3 (range 12 749 - 14 828), and 104 cases of ICC (range 61 - 186) occurred in this population. Conclusions. Our findings highlight the magnitude of cervical disease among HIV-infected women in SA.

Data on invasive cervical cancer (ICC) incidence in HIV-positive women and the effect of cervical cancer screening in sub-Saharan Africa are scarce. We estimated i) ICC incidence rates in women (≥18 years) who initiated antiretroviral therapy (ART) at the Themba Lethu Clinic (TLC) in Johannesburg, South Africa, between 2004 and 2011 and ii) the effect of a Pap-based screening program. We included 10,640 women; median age at ART initiation: 35 years [interquartile range (IQR) 30-42], median CD4 count at ART initiation: 113 cells/µL (IQR 46-184). During 27,257 person-years (pys), 138 women were diagnosed with ICC; overall incidence rate: 506/100,000 pys [95% confidence interval (CI) 428-598]. The ICC incidence rate was highest (615/100,000 pys) in women who initiated ART before cervical cancer screening became available in 04/2005 and was lowest (260/100,000 pys) in women who initiated ART from 01/2009 onward when the cervical cancer screening program and access to treatment of cervical lesions was expanded [adjusted hazard ratio (aHR) 0.42, 95% CI 0.20-0.87]. Advanced HIV/AIDS stage (4 versus 1, aHR 1.95, 95% CI 1.17-3.24) and middle age at ART initiation (36-45 versus 18-25 years, aHR 2.51, 95% CI 1.07-5.88) were risk factors for ICC. The ICC incidence rate substantially decreased with the implementation of a Pap-based screening program and improved access to treatment of cervical lesions. However, the risk of developing ICC after ART initiation remained high. To inform and improve ICC prevention and care for HIV-positive women in sub-Saharan Africa, implementation and monitoring of cervical cancer screening programs are essential.