Search

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: The incidences of genital human papillomavirus (HPV) infection associated squamous intraepithelial lesions and cervical squamous cell carcinoma are significantly increased in HIV-positive women. The role of other cervicovaginal infections in the acquisition of the HPV infection cervical carcinogenesis and genital HIV infection remains largely speculative. METHODS: A retrospective study was conducted including 1087 HIV-positive women in rural Mpumalanga province South Africa for the period 1 May 2009 to 31 August 2010. For each patient the age at first presentation cervical cytological diagnosis subsequent follow-up cytology and histology and microscopically visible infections (including endemic Bilharzia) were tabulated and statistically analysed. RESULTS: The prevalence of low-grade squamous intraepithelial lesion (LSIL) high-grade squamous intraepithelial lesion (HSIL) squamous cell carcinoma atypical squamous cells of undetermined significance (ASC-US) and atypical squamous cells cannot exclude HSIL (ASC-H) in the study population were 22.1% 30.9% 0.6% 13.5% and 4.0% respectively. LSIL HSIL and squamous cell carcinoma were diagnosed respectively at the average ages of 35.7 37.9 and 37.2 years. Four patients with cervical intraepithelial neoplasia grade 1 (CIN1) 32 with CIN2/CIN3 and two with cervical squamous cell carcinoma were also diagnosed with Bilharzia. Of the other infections only bacterial vaginosis had a positive statistical correlation with HPV-induced cervical abnormalities (LSIL HSIL or squamous cell carcinoma). CONCLUSION: This study confirms the high prevalence of progressive HPV-associated cervical disease in a rural Southern African HIV-positive population which is at least equal to or worse than in other African HIV-positive studies. The high incidence of Bilharzia infection in those cases that underwent cervical cone excision suggests a possible relationship with progressive HPV disease and cervical carcinogenesis. Bacterial vaginosis (perhaps in combination with Bilharzia) may compromise the normal barriers against HPV and HIV infection. (c) 2012 John Wiley & Sons Ltd.

Objective: To determine the spectrum of disease, diagnostic accuracy and adequacy of fine needle aspirates (FNA) in human immunodeficiency virus (HIV) positive children who present with mass lesions. Methods: Between January 1997 and December 2002, 95 FNAs were performed in 91 children aged 15 years and younger who were known to be infected with the human immunodeficiency virus (HIV). Results: Head and neck masses including salivary gland swellings were the most common presentation (58.9%) followed by axillary masses (25.3%). Groin masses were aspirated in six children, flank and abdominal masses in four children, buttock masses in three children, a chest wall mass in one child and a sonar guided FNA of a lung mass in one child. Eight FNAs (8.4%) proved inadequate. Reactive lymphadenopathy was diagnosed in 42 cases, mycobacterial infection in 22, four children were diagnosed with abscess, one child had a fungal infection and five were found to have non-Hodgkin’s lymphoma. There were four cases each of lymphoepithelial lesion and Kaposi sarcoma. There was one case each of nephroblastoma, rhabdomyosarcoma, myeloma, melanotic progonoma and spindle cells, not otherwise specified. Conclusion: Fine needle aspiration in HIV positive children is a worthwhile procedure and in most instances allows a rapid diagnosis obviating the need for surgery and enabling swift treatment to be undertaken where necessary. Ancillary studies form an important diagnostic component. Universal safety precautions must be strictly adhered to.

Objective: Cancer of the cervix is one of the commonest cancers in South Africa. Accurate cytological diagnosis is one of the prerequisites for an effective cervical screening programme and requires the implementation of appropriate quality assurance modalities. This study was undertaken to determine if rapid review of reportedly negative cervical smears is a useful internal quality assurance modality in an unscreened population with very high rates of cervical carcinoma. Method: Approximately 26% of all cervical smears received at the study institution between 1 January 1998 and 31 December 2003, and initially reported as negative or inadequate, underwent rapid review. Results: A total of 62 866 (26%) cervical smears out of 241 796 reportedly negative or inadequate cervical smears underwent rapid review. An amended report was sent out in 373 (0.59%) of these 62 866 cervical smears. This included 101 cases of high-grade squamous intraepithelial lesion (HSIL) and high-grade atypical squamous cells (ASC-H), 143 low-grade squamous intraepithelial lesions, 54 atypical squamous cells of undetermined significance (ASC-US) and 33 atypical glandular cells that were not reported initially. The false-negative proportion for HSIL and ASC-H (combined) in this study was 5.76%. No squamous cell carcinomas were diagnosed on rapid review but one patient with HSIL/ASC-H on review had squamous cell carcinoma on biopsy. Three cytotechnologists had a lower sensitivity of primary screening and required retraining. Conclusions: Rapid review is beneficial as an internal quality assurance modality in an unscreened high-risk population and increases the detection of women with significant cervical lesions requiring treatment. The relatively low cost of rapid review compared with other rescreening modalities makes this an attractive option in low resource settings.