Automated screening of Papanicolaou tests: A review of the literature

Evolution of Pathological Techniques for the Screening of Cervical Cancer: A Comprehensive Review

The evolutionary journey of cervical cancer screening has been a major medical success story, considering the substantial role it has played in dwindling the disease burden. Through sustained collaborative efforts within the medical community, significant advances have been made from the humble yet path-breaking conventional Pap smear to the current automated screening systems and human papillomavirus (HPV) molecular testing. With the integration of artificial intelligence into screening techniques, we are currently at the precipice of circumventing the pitfalls of manual cytology readings and improving the efficiency of the screening systems by a significant margin. Despite the technological milestones traversed, the high logistics and operational cost, besides the technical know-how of operating the automated systems, can pose a major practical challenge in the widespread adoption of these advanced techniques in cervical cancer screening programs. This would suggest the need to adopt strategies that are tailored to the demands and needs of the different settings keeping their limitations in mind. This review aims to take the reader through the entire evolutionary journey of cervical cancer screening programs, highlight the individual merits and demerits of each technique, and discuss the recommendations from the major global guidelines.

Pros and cons of artificial intelligence implementation in diagnostic pathology

The rapid introduction of digital pathology has greatly facilitated development of artificial intelligence (AI) models in pathology that have shown great promise in assisting morphological diagnostics and quantitation of therapeutic targets. We are now at a tipping point where companies have started to bring algorithms to the market, and questions arise whether the pathology community is ready to implement AI in routine workflow. However, concerns also arise about the use of AI in pathology. This article reviews the pros and cons of introducing AI in diagnostic pathology.

The evolution of cervical cancer screening

There are few medical success stories in history as significant as the reduction in cervical cancer incidence. Through the collaborative efforts of dedicated scientific pioneers, the past century has witnessed remarkable advancement that began with the detection of exfoliated cancer cells through cytologic examination to widespread implementation of cervical cancer screening programs to the discovery of the link between cervical cancer and human papillomavirus (HPV). Current screening methods apply HPV-based testing, and artificial intelligence-based screening systems utilizing digitalized cytology images are being used in a continuous effort to optimize the accuracy and efficiency of the Papanicolaou test. This review summarizes the major milestones in cervical cancer screening history to emphasize its evolution as the World Health Organization aims for the global elimination of cervical cancer.

Artificial intelligence in diagnostic pathology

Digital pathology (DP) is being increasingly employed in cancer diagnostics, providing additional tools for faster, higher-quality, accurate diagnosis. The practice of diagnostic pathology has gone through a staggering transformation wherein new tools such as digital imaging, advanced artificial intelligence (AI) algorithms, and computer-aided diagnostic techniques are being used for assisting, augmenting and empowering the computational histopathology and AI-enabled diagnostics. This is paving the way for advancement in precision medicine in cancer. Automated whole slide imaging (WSI) scanners are now rendering diagnostic quality, high-resolution images of entire glass slides and combining these images with innovative digital pathology tools is making it possible to integrate imaging into all aspects of pathology reporting including anatomical, clinical, and molecular pathology. The recent approvals of WSI scanners for primary diagnosis by the FDA as well as the approval of prostate AI algorithm has paved the way for starting to incorporate this exciting technology for use in primary diagnosis. AI tools can provide a unique platform for innovations and advances in anatomical and clinical pathology workflows. In this review, we describe the milestones and landmark trials in the use of AI in clinical pathology with emphasis on future directions.

Recent developments in cervical cancer diagnosis using deep learning on whole slide images: An Overview of models, techniques, challenges and future directions

Integration of whole slide imaging (WSI) and deep learning technology has led to significant improvements in the screening and diagnosis of cervical cancer. WSI enables the examination of all cells on a slide simultaneously and deep learning algorithms can accurately label them as cancerous or non-cancerous. Although many studies have investigated the application of deep learning for diagnosing various diseases, there is a lack of research focusing on the evolution, limitations, and gaps of intelligent algorithms in conjunction with WSI for cervical cancer. This paper provides a comprehensive overview of the state-of-the-art deep learning algorithms used for the timely and precise analysis of cervical WSI images. A total of 115 relevant papers were reviewed, and 37 were selected after screening with specific inclusion and exclusion criteria. Methodological aspects including deep learning techniques, data sources, architectures, and classification techniques employed by the selected studies were analyzed. The review presents the most popular techniques and current trends in deep learning-based cervical classification systems, and categorizes the evolution of the domain based on deep learning techniques, citing an in-depth analysis of various models developed over time. The paper advocates for the implementation of transfer supervised learning when utilizing deep learning models such as ResNet, VGG19, and EfficientNet, and builds a solid foundation for applying relevant techniques in different fields. Although some progress has been made in developing novel models for the diagnosis of cervical cancer, substantial work remains to be done in creating standardized benchmark databases of WSI images for the research community. This paper serves as a comprehensive guide for understanding the fundamental concepts, benefits, and challenges related to various deep learning models on WSI, including their application for cervical system classification. Additionally, it provides valuable insights into future research directions in this area.

Large-scale validation study of an improved semiautonomous urine cytology assessment tool: AutoParis-X

BACKGROUND

Adopting a computational approach for the assessment of urine cytology specimens has the potential to improve the efficiency, accuracy, and reliability of bladder cancer screening, which has heretofore relied on semisubjective manual assessment methods. As rigorous, quantitative criteria and guidelines have been introduced for improving screening practices (e.g., The Paris System for Reporting Urinary Cytology), algorithms to emulate semiautonomous diagnostic decision-making have lagged behind, in part because of the complex and nuanced nature of urine cytology reporting.

METHODS

In this study, the authors report on the development and large-scale validation of a deep-learning tool, AutoParis-X, which can facilitate rapid, semiautonomous examination of urine cytology specimens.

RESULTS

The results of this large-scale, retrospective validation study indicate that AutoParis-X can accurately determine urothelial cell atypia and aggregate a wide variety of cell-related and cluster-related information across a slide to yield an atypia burden score, which correlates closely with overall specimen atypia and is predictive of Paris system diagnostic categories. Importantly, this approach accounts for challenges associated with the assessment of overlapping cell cluster borders, which improve the ability to predict specimen atypia and accurately estimate the nuclear-to-cytoplasm ratio for cells in these clusters.

CONCLUSIONS

The authors developed a publicly available, open-source, interactive web application that features a simple, easy-to-use display for examining urine cytology whole-slide images and determining the level of atypia in specific cells, flagging the most abnormal cells for pathologist review. The accuracy of AutoParis-X (and other semiautomated digital pathology systems) indicates that these technologies are approaching clinical readiness and necessitates full evaluation of these algorithms in head-to-head clinical trials.

Beyond the Microscope: A Technological Overture for Cervical Cancer Detection

Cervical cancer is a common and preventable disease that poses a significant threat to women's health and well-being. It is the fourth most prevalent cancer among women worldwide, with approximately 604,000 new cases and 342,000 deaths in 2020, according to the World Health Organization. Early detection and diagnosis of cervical cancer are crucial for reducing mortality and morbidity rates. The Papanicolaou smear test is a widely used screening method that involves the examination of cervical cells under a microscope to identify any abnormalities. However, this method is time-consuming, labor-intensive, subjective, and prone to human errors. Artificial intelligence techniques have emerged as a promising alternative to improve the accuracy and efficiency of Papanicolaou smear diagnosis. Artificial intelligence techniques can automatically analyze Papanicolaou smear images and classify them into normal or abnormal categories, as well as detect the severity and type of lesions. This paper provides a comprehensive review of the recent advances in artificial intelligence diagnostics of the Papanicolaou smear, focusing on the methods, datasets, performance metrics, and challenges. The paper also discusses the potential applications and future directions of artificial intelligence diagnostics of the Papanicolaou smear.

Comparison of the Hologic Genius Digital Diagnostics System with the ThinPrep Imaging System-A retrospective assessment

BACKGROUND

Digital cytology (DC) with artificial intelligence (AI) is a new approach. The authors compared DC with liquid-based cytology (LBC) using computer assistance (CAS) in a retrospective, noninterventional study.

METHODS

In total, 1994 ThinPrep LBC slides (Hologic), which were previously analyzed in 2020 using an imaging system with CAS in routine cotesting for cytology/human papillomavirus, were reviewed in a blinded mode using the Genius Digital Diagnostics System (Hologic). In 555 cases, a histology result was available. The slides were digitally scanned (volumetric scan) at 14 levels integrated into one. AI algorithms were used to present a gallery of six tiles each (containing objects of interest) in five categories. Six additional tile rows were available, from which the diagnoses were made. All cases with a mismatch between DC and imaging system results were reviewed by an additional cytopathologist.

RESULTS

In 86.56% of cases, a complete match between both systems was observed using the same cytology categories. When also considering the histology results, the match was 90.37%. In addition, when a cytology follow-up and/or a retrospective review was applied, the match reached 97.34%. In only 0.65% of cases was a major discrepancy observed (two grades of cytology or a low-grade squamous intraepithelial lesion/high-grade squamous intraepithelial lesion [LSIL/HSIL] shift), and none were identified by DC. Significantly more cases of higher severity (atypical squamous cells cannot exclude high grade [ASC-H], high-grade squamous intraepithelial lesion [HSIL]) were identified with DC, and its negative predictive value was higher. The screening time was significantly shorter with DC.

CONCLUSIONS

With the Genius system for DC, the sensitivity for HSIL+/ASC-H and the specificity for LSIL and HSIL were superior to LBC and CAS. Screening time was significantly lower.

Diagnostic utility of ThinPrep Imaging System® for detecting atypical glandular cells in cervical smear samples

INTRODUCTION

The ThinPrep Imaging System® (TIS) is an automated system that has now been used for over 20 years in the primary screening of ThinPrep liquid-based cervical samples. Although there are a lot of publications about the diagnostic utility of this method in squamous cell lesions, which has advantages such as time-saving and standardization, there are only a few publications on this issue in glandular cell lesions in the literature. We aimed in this study to investigate the diagnostic utility of the system in the detection of premalignant and malignant glandular lesions in cervical smears.

MATERIAL AND METHOD

Our study was conducted retrospectively, and a total of 126 cervical smear samples between 2010 and 2022 that have histological confirmation of endometrial adenocarcinoma (EAC), endocervical adenocarcinoma (ECAC), or adenocarcinoma in situ (AİS), were included. These samples were re-evaluated by manual and TIS by two experienced pathologists, and the results were compared in terms of sensitivity.

RESULTS

We found out that 70 of the 126 smear samples have atypical glandular cells. We detect 48 cases (48/70) (sensitivity 68.5%) in manual examination, however TIS successfully determined 66 cases (66/70) (sensitivity 94.3%). In 4 cases (5.7%) TIS could not detect the atypical cells within the 22 areas.

CONCLUSION

TIS is quite an effective method with a high sensitivity for detecting atypical glandular cells in cervical smears, like detecting squamous cell anomalies. Imposing this system in our laboratory and using them appropriately, save us time and help to ensure standardization. Additionally, it may be a good way to adopt artificial intelligence and digital pathology in today's world.

Assessing the quality of cytopathology whole slide imaging for education from archived cases

INTRODUCTION

Many institutions have cytopathology case archives for education. Unfortunately, these slides deteriorate over time and have limited accessibility. Whole slide imaging (WSI) can overcome these limitations. However, suboptimal image quality and scanning effort are barriers.

MATERIALS AND METHODS

We selected 123 slides from cytopathology study sets for WSI scanning at 400x magnification without z-stacking. The Ventana DP 200 scanner and Virtuoso software were used. Slides were scanned in 2 rounds: the first round of slides was prepared for scanning with light cleaning, and the second round was performed only on slides that had unacceptable WSI quality after thorough cleaning. Slides were assessed with a 4-tier grading system created by the authors. Time to scan each slide was recorded.

RESULTS

Within the first round, 96 of 123 (78%) slides scanned were determined to be of acceptable quality. After the second round of scanning, in total, 118 of 123 (95.9%) slides were determined to be of acceptable quality. The average time needed to scan each slide was 213 seconds.

CONCLUSIONS

The majority of slides scanned were of acceptable quality in the first round of scanning. After cleaning and rescanning, nearly every slide investigated was of acceptable quality. The primary objective is to provide other institutions that may be considering a similar project a benchmark so that they know what to expect in terms of slide scan success rate and the amount of time needed to digitize slides for educational archiving. This pilot study demonstrates the feasibility of using WSI for cytology education cases.

DNA Karyometry for Automated Detection of Cancer Cells

Background: Microscopical screening of cytological samples for the presence of cancer cells at high throughput with sufficient diagnostic accuracy requires highly specialized personnel which is not available in most countries. Methods: Using commercially available automated microscope-based screeners (MotiCyte and EasyScan), software was developed which is able to classify Feulgen-stained nuclei into eight diagnostically relevant types, using supervised machine learning. the nuclei belonging to normal cells were used for internal calibration of the nuclear DNA content while nuclei belonging to those suspicious of being malignant were specifically identified. The percentage of morphologically abnormal nuclei was used to identify samples suspected of malignancy, and the proof of DNA-aneuploidy was used to definitely determine the state malignancy. A blinded study was performed using oral smears from 92 patients with Fanconi anemia, revealing oral leukoplakias or erythroplakias. In an earlier study, we compared diagnostic accuracies on 121 serous effusion specimens. In addition, using a blinded study employing 80 patients with prostate cancer who were under active surveillance, we aimed to identify those whose cancers would not advance within 4 years. Results: Applying a threshold of the presence of >4% of morphologically abnormal nuclei from oral squamous cells and DNA single-cell or stemline aneuploidy to identify samples suspected of malignancy, an overall diagnostic accuracy of 91.3% was found as compared with 75.0% accuracy determined by conventional subjective cytological assessment using the same slides. Accuracy of automated screening effusions was 84.3% as compared to 95.9% of conventional cytology. No prostate cancer patients under active surveillance, revealing DNA-grade 1, showed progress of their disease within 4.1 years. Conclusions: An automated microscope-based screener was developed which is able to identify malignant cells in different types of human specimens with a diagnostic accuracy comparable with subjective cytological assessment. Early prostate cancers which do not progress despite applying any therapy could be identified using this automated approach.

Recent Application of Artificial Intelligence in Non-Gynecological Cancer Cytopathology: A Systematic Review

Simple Summary

Artificial intelligence (AI) has attracted significant interest in the healthcare sector due to its promising results. Cytological examination is a critical step in the initial diagnosis of cancer. Here, we conducted a systematic review with quantitative analysis to understand the current status of AI applications in non-gynecological (non-GYN) cancer cytology. In our analysis, we found that most of the studies focused on classification and segmentation tasks. Overall, AI showed promising results for non-GYN cancer cytopathology analysis. However, the lack of well-annotated, large-scale datasets with Z-stacking and external cross-validation was the major limitation across all studies.

Abstract

State-of-the-art artificial intelligence (AI) has recently gained considerable interest in the healthcare sector and has provided solutions to problems through automated diagnosis. Cytological examination is a crucial step in the initial diagnosis of cancer, although it shows limited diagnostic efficacy. Recently, AI applications in the processing of cytopathological images have shown promising results despite the elementary level of the technology. Here, we performed a systematic review with a quantitative analysis of recent AI applications in non-gynecological (non-GYN) cancer cytology to understand the current technical status. We searched the major online databases, including MEDLINE, Cochrane Library, and EMBASE, for relevant English articles published from January 2010 to January 2021. The searched query terms were: “artificial intelligence”, “image processing”, “deep learning”, “cytopathology”, and “fine-needle aspiration cytology.” Out of 17,000 studies, only 26 studies (26 models) were included in the full-text review, whereas 13 studies were included for quantitative analysis. There were eight classes of AI models treated of according to target organs: thyroid (n = 11, 39%), urinary bladder (n = 6, 21%), lung (n = 4, 14%), breast (n = 2, 7%), pleural effusion (n = 2, 7%), ovary (n = 1, 4%), pancreas (n = 1, 4%), and prostate (n = 1, 4). Most of the studies focused on classification and segmentation tasks. Although most of the studies showed impressive results, the sizes of the training and validation datasets were limited. Overall, AI is also promising for non-GYN cancer cytopathology analysis, such as pathology or gynecological cytology. However, the lack of well-annotated, large-scale datasets with Z-stacking and external cross-validation was the major limitation found across all studies. Future studies with larger datasets with high-quality annotations and external validation are required.

Artificial Intelligence in Cervical Cancer Screening and Diagnosis

Cervical cancer remains a leading cause of cancer death in women, seriously threatening their physical and mental health. It is an easily preventable cancer with early screening and diagnosis. Although technical advancements have significantly improved the early diagnosis of cervical cancer, accurate diagnosis remains difficult owing to various factors. In recent years, artificial intelligence (AI)-based medical diagnostic applications have been on the rise and have excellent applicability in the screening and diagnosis of cervical cancer. Their benefits include reduced time consumption, reduced need for professional and technical personnel, and no bias owing to subjective factors. We, thus, aimed to discuss how AI can be used in cervical cancer screening and diagnosis, particularly to improve the accuracy of early diagnosis. The application and challenges of using AI in the diagnosis and treatment of cervical cancer are also discussed.

False-negative Papanicolaou tests in women with biopsy-proven invasive endocervical adenocarcinoma/adenocarcinoma in situ: a retrospective analysis with assessment of interobserver agreement

INTRODUCTION

The objectives of our study were to identify factors contributing to false-negative Papanicolaou (Pap) tests in patients with endocervical adenocarcinoma (EA) or adenocarcinoma in situ (AIS), and to analyze the impact of educational instruction on interobserver agreement in these cases.

MATERIALS AND METHODS

False-negative Pap tests from patients with EA/AIS were reviewed by a consensus group and by 12 individual reviewers in 2 rounds, with an educational session on glandular neoplasia in Pap tests conducted between the 2 rounds.

RESULTS

Of 79 Pap tests from patients with EA/AIS, 57 (72.2%) were diagnosed as abnormal and 22 (27.8%) as negative. Of the 22 false-negative cases, 10 remained negative on consensus review, with false-negative diagnoses attributed to sampling variance. The other 12 cases were upgraded to epithelial abnormalities (including 8 to glandular lesions). The false-negative diagnoses were attributed to screening variance in 2 cases and interpretive variance in 10 cases. On individual review, abnormal cells were misinterpreted as reactive glandular cells or endometrial cells in 7 of 8 and 5 of 8 cases upgraded to glandular abnormalities, respectively. With education, the proportion of individual reviewers demonstrating at least moderate agreement with the consensus diagnosis (Cohen's kappa >0.4) increased from 33% (4 of 12) to 75% (9 of 12).

CONCLUSIONS

Sampling and interpretive variance each accounted for nearly one-half of the false-negative Pap tests, with underclassification as reactive glandular or endometrial cells the main source of the interpretive variances. Educational instruction significantly decreased the interpretive variance and interobserver variability in the diagnosis of glandular abnormalities.

Tao brush endometrial cytology is a sensitive diagnostic tool for cancer and hyperplasia among women presenting to clinic with abnormal uterine bleeding

Background

Abnormal uterine bleeding requires the investigation of the endometrium. Histology is typically used but there remains room for the improvement and use of cytology.

Methods

Women presenting for clinically indicated office endometrial biopsy were prospectively enrolled. Tao endometrial brushing and office endometrial biopsy were performed, and surgical procedure if clinically indicated. Tao brush cytology specimens were blindly reviewed by up to three pathologists, consensus obtained, and scored as: benign, atypical (favor benign), suspicious, positive for malignancy, or non‐diagnostic. Cytology and histology were compared to surgical pathology to determine sensitivity, specificity, positive, and negative predictive values to detect AH (atypical hyperplasia) or EC (endometrial cancer).

Results

Clinical indications of 197 enrolled patients included postmenopausal bleeding (90, 45.7%), abnormal uterine bleeding (94, 47.7%), and abnormal endometrium on ultrasound without bleeding (13, 6.6%). Of the 197 patients, 185 (93.9%) had cytology score consensus and a total of 196 (99.5%) had consensus regarding cytology positivity.

Surgical pathology diagnoses (N = 85) were 13 (15.3%) FIGO grade 1 or 2 EC, 3 (3.5%) AH, and 69 (81.2%) benign endometrium. Sensitivity and specificity to detect EC or AH were 93.7% and 100%, respectively, via endometrial biopsy; 87.5% and 63.8%, respectively, via endometrial cytology when scores of malignancy, suspicious, or atypical were considered positive.

Conclusions

In a high‐risk population, Tao brush endometrial cytology showed high sensitivity to detect AH and EC comparable to biopsy histology when considering scores of malignancy, suspicious, atypical, and non‐diagnostic. Revisiting the potential value of endometrial cytology in the contemporary era of endometrial diagnostic workup is warranted.

Detection of Cervical Cancer Cells in Whole Slide Images Using Deformable and Global Context Aware Faster RCNN-FPN

Cervical cancer is a worldwide public health problem with a high rate of illness and mortality among women. In this study, we proposed a novel framework based on Faster RCNN-FPN architecture for the detection of abnormal cervical cells in cytology images from a cancer screening test. We extended the Faster RCNN-FPN model by infusing deformable convolution layers into the feature pyramid network (FPN) to improve scalability. Furthermore, we introduced a global contextual aware module alongside the Region Proposal Network (RPN) to enhance the spatial correlation between the background and the foreground. Extensive experimentations with the proposed deformable and global context aware (DGCA) RCNN were carried out using the cervical image dataset of "Digital Human Body" Vision Challenge from the Alibaba Cloud TianChi Company. Performance evaluation based on the mean average precision (mAP) and receiver operating characteristic (ROC) curve has demonstrated considerable advantages of the proposed framework. Particularly, when combined with tagging of the negative image samples using traditional computer-vision techniques, 6-9% increase in mAP has been achieved. The proposed DGCA-RCNN model has potential to become a clinically useful AI tool for automated detection of cervical cancer cells in whole slide images of Pap smear.

Artificial intelligence-assisted fast screening cervical high grade squamous intraepithelial lesion and squamous cell carcinoma diagnosis and treatment planning

Every year cervical cancer affects more than 300,000 people, and on average one woman is diagnosed with cervical cancer every minute. Early diagnosis and classification of cervical lesions greatly boosts up the chance of successful treatments of patients, and automated diagnosis and classification of cervical lesions from Papanicolaou (Pap) smear images have become highly demanded. To the authors' best knowledge, this is the first study of fully automated cervical lesions analysis on whole slide images (WSIs) of conventional Pap smear samples. The presented deep learning-based cervical lesions diagnosis system is demonstrated to be able to detect high grade squamous intraepithelial lesions (HSILs) or higher (squamous cell carcinoma; SQCC), which usually immediately indicate patients must be referred to colposcopy, but also to rapidly process WSIs in seconds for practical clinical usage. We evaluate this framework at scale on a dataset of 143 whole slide images, and the proposed method achieves a high precision 0.93, recall 0.90, F-measure 0.88, and Jaccard index 0.84, showing that the proposed system is capable of segmenting HSILs or higher (SQCC) with high precision and reaches sensitivity comparable to the referenced standard produced by pathologists. Based on Fisher's Least Significant Difference (LSD) test (P < 0.0001), the proposed method performs significantly better than the two state-of-the-art benchmark methods (U-Net and SegNet) in precision, F-Measure, Jaccard index. For the run time analysis, the proposed method takes only 210 seconds to process a WSI and is 20 times faster than U-Net and 19 times faster than SegNet, respectively. In summary, the proposed method is demonstrated to be able to both detect HSILs or higher (SQCC), which indicate patients for further treatments, including colposcopy and surgery to remove the lesion, and rapidly processing WSIs in seconds for practical clinical usages.

Cric searchable image database as a public platform for conventional pap smear cytology data

Amidst the current health crisis and social distancing, telemedicine has become an important part of mainstream of healthcare, and building and deploying computational tools to support screening more efficiently is an increasing medical priority. The early identification of cervical cancer precursor lesions by Pap smear test can identify candidates for subsequent treatment. However, one of the main challenges is the accuracy of the conventional method, often subject to high rates of false negative. While machine learning has been highlighted to reduce the limitations of the test, the absence of high-quality curated datasets has prevented strategies development to improve cervical cancer screening. The Center for Recognition and Inspection of Cells (CRIC) platform enables the creation of CRIC Cervix collection, currently with 400 images (1,376 × 1,020 pixels) curated from conventional Pap smears, with manual classification of 11,534 cells. This collection has the potential to advance current efforts in training and testing machine learning algorithms for the automation of tasks as part of the cytopathological analysis in the routine work of laboratories.

Point-of-Care Digital Cytology With Artificial Intelligence for Cervical Cancer Screening in a Resource-Limited Setting

IMPORTANCE

Cervical cancer is highly preventable but remains a common and deadly cancer in areas without screening programs. The creation of a diagnostic system to digitize Papanicolaou test samples and analyze them using a cloud-based deep learning system (DLS) may provide needed cervical cancer screening to resource-limited areas.

OBJECTIVE

To determine whether artificial intelligence-supported digital microscopy diagnostics can be implemented in a resource-limited setting and used for analysis of Papanicolaou tests.

DESIGN, SETTING, AND PARTICIPANTS

In this diagnostic study, cervical smears from 740 HIV-positive women aged between 18 and 64 years were collected between September 1, 2018, and September 30, 2019. The smears were digitized with a portable slide scanner, uploaded to a cloud server using mobile networks, and used to train and validate a DLS for the detection of atypical cervical cells. This single-center study was conducted at a local health care center in rural Kenya.

EXPOSURES

Detection of squamous cell atypia in the digital samples by analysis with the DLS.

MAIN OUTCOMES AND MEASURES

The accuracy of the DLS in the detection of low- and high-grade squamous intraepithelial lesions in Papanicolaou test whole-slide images.

RESULTS

Papanicolaou test results from 740 HIV-positive women (mean [SD] age, 41.8 [10.3] years) were collected. The DLS was trained using 350 whole-slide images and validated on 361 whole-slide images (average size, 100 387 × 47 560 pixels). For detection of cervical cellular atypia, sensitivities were 95.7% (95% CI, 85.5%-99.5%) and 100% (95% CI, 82.4%-100%), and specificities were 84.7% (95% CI, 80.2%-88.5%) and 78.4% (95% CI, 73.6%-82.4%), compared with the pathologist assessment of digital and physical slides, respectively. Areas under the receiver operating characteristic curve were 0.94 and 0.96, respectively. Negative predictive values were high (99%-100%), and accuracy was high, particularly for the detection of high-grade lesions. Interrater agreement was substantial compared with the pathologist assessment of digital slides (κ = 0.72) and fair compared with the assessment of glass slides (κ = 0.36). No samples that were classified as high grade by manual sample analysis had false-negative assessments by the DLS.

CONCLUSIONS AND RELEVANCE

In this study, digital microscopy with artificial intelligence was implemented at a rural clinic and used to detect atypical cervical smears with a high sensitivity compared with visual sample analysis.

Cervical cancer: Automation of Pap test screening

BACKGROUND

Cervical cancer progresses slowly, increasing the chance of early detection of pre-neoplastic lesions via Pap exam test and subsequently preventing deaths. However, the exam presents both false-negatives and false-positives results. Therefore, automatic methods (AMs) of reading the Pap test have been used to improve the quality control of the exam. We performed a literature review to evaluate the feasibility of implementing AMs in laboratories.

METHODS

This work reviewed scientific publications regarding automated cytology from the last 15 years. The terms used were "Papanicolaou test" and "Automated cytology screening" in Portuguese, English, and Spanish, in the three scientific databases (SCIELO, PUBMED, MEDLINE).

RESULTS

Of the resulting 787 articles, 34 were selected for a complete review, including three AMs: ThinPrep Imaging System, FocalPoint GS Imaging System and CytoProcessor. In total, 1 317 148 cytopathological slides were evaluated automatically, with 1 308 028 (99.3%) liquid-based cytology slides and 9120 (0.7%) conventional cytology smears. The AM diagnostic performances were statistically equal to or better than those of the manual method. AM use increased the detection of cellular abnormalities and reduced false-negatives. The average sample rejection rate was ≤3.5%.

CONCLUSION

AMs are relevant in quality control during the analytical phase of cervical cancer screening. This technology eliminates slide-handling steps and reduces the sample space, allowing professionals to focus on diagnostic interpretation while maintaining high-level care, which can reduce false-negatives. Further studies with conventional cytology are needed. The use of AM is still not so widespread in cytopathology laboratories.

Challenges Developing Deep Learning Algorithms in Cytology

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.

Artificial intelligence-assisted cytology for detection of cervical intraepithelial neoplasia or invasive cancer: A multicenter, clinical-based, observational study

OBJECTIVE

Artificial intelligence (AI) could automatedly detect abnormalities in digital cytological images, however, the effect in cervical cancer screening is inconclusive. We aim to evaluate the performance of AI-assisted cytology for the detection of histologically cervical intraepithelial lesions (CIN) or cancer.

METHODS

We trained a supervised deep learning algorithm based on 188,542 digital cytological images. Between Mar 13, 2017, and Oct 20, 2018, 2145 referral women from organized screening were enrolled in a multicenter, clinical-based, observational study. Cervical specimen was sampled to generate two liquid-based slides: one random slide was allocated to AI-assisted reading, and the other to manual reading conducted by skilled cytologists from senior hospital and cytology doctors from primary hospitals. HPV testing and colposcopy-directed biopsy was performed, and histological result was regarded as reference. We calculated the relative sensitivity and relative specificity of AI-assisted reading compared to manual reading for CIN2+. This trial was registered, number ChiCTR2000034131.

RESULTS

In the referral population, AI-assisted reading detected 92.6% of CIN 2 and 96.1% of CIN 3+, significantly higher than or similar to manual reading. AI-assisted reading had equivalent sensitivity (relative sensitivity 1.01, 95%CI, 0.97-1.05) and higher specificity (relative specificity 1.26, 1.20-1.32) compared to skilled cytologists; whereas higher sensitivity (1.12, 1.05-1.20) and specificity (1.36, 1.25-1.48) compared to cytology doctors. In HPV-positive women, AI-assisted reading improved specificity for CIN1 or less at no expense of reduction of sensitivity compared to manual reading.

CONCLUSIONS

AI-assisted cytology may contribute to the primary cytology screening or triage. Further studies are needed in general population.

Artificial Intelligence in Neuroradiology: Current Status and Future Directions

Fueled by new techniques, computational tools, and broader availability of imaging data, artificial intelligence has the potential to transform the practice of neuroradiology. The recent exponential increase in publications related to artificial intelligence and the central focus on artificial intelligence at recent professional and scientific radiology meetings underscores the importance. There is growing momentum behind leveraging artificial intelligence techniques to improve workflow and diagnosis and treatment and to enhance the value of quantitative imaging techniques. This article explores the reasons why neuroradiologists should care about the investments in new artificial intelligence applications, highlights current activities and the roles neuroradiologists are playing, and renders a few predictions regarding the near future of artificial intelligence in neuroradiology.

The artificial intelligence-assisted cytology diagnostic system in large-scale cervical cancer screening: A population-based cohort study of 0.7 million women

Background

Adequate cytology is limited by insufficient cytologists in a large‐scale cervical cancer screening. We aimed to develop an artificial intelligence (AI)‐assisted cytology system in cervical cancer screening program.

Methods

We conducted a perspective cohort study within a population‐based cervical cancer screening program for 0.7 million women, using a validated AI‐assisted cytology system. For comparison, cytologists examined all slides classified by AI as abnormal and a randomly selected 10% of normal slides. Each woman with slides classified as abnormal by either AI‐assisted or manual reading was diagnosed by colposcopy and biopsy. The outcomes were histologically confirmed cervical intraepithelial neoplasia grade 2 or worse (CIN2+).

Results

Finally, we recruited 703 103 women, of whom 98 549 were independently screened by AI and manual reading. The overall agreement rate between AI and manual reading was 94.7% (95% confidential interval [CI], 94.5%‐94.8%), and kappa was 0.92 (0.91‐0.92). The detection rates of CIN2+ increased with the severity of cytology abnormality performed by both AI and manual reading (P_trend < 0.001). General estimated equations showed that detection of CIN2+ among women with ASC‐H or HSIL by AI were significantly higher than corresponding groups classified by cytologists (for ASC‐H: odds ratio [OR] = 1.22, 95%CI 1.11‐1.34, P < .001; for HSIL: OR = 1.41, 1.28‐1.55, P < .001). AI‐assisted cytology was 5.8% (3.0%‐8.6%) more sensitive for detection of CIN2+ than manual reading with a slight reduction in specificity.

Conclusions

AI‐assisted cytology system could exclude most of normal cytology, and improve sensitivity with clinically equivalent specificity for detection of CIN2+ compared with manual cytology reading. Overall, the results support AI‐based cytology system for the primary cervical cancer screening in large‐scale population.

Explainable AI (xAI) for Anatomic Pathology

Pathologists are adopting whole slide images (WSIs) for diagnosis, thanks to recent FDA approval of WSI systems as class II medical devices. In response to new market forces and recent technology advances outside of pathology, a new field of computational pathology has emerged that applies artificial intelligence (AI) and machine learning algorithms to WSIs. Computational pathology has great potential for augmenting pathologists' accuracy and efficiency, but there are important concerns regarding trust of AI due to the opaque, black-box nature of most AI algorithms. In addition, there is a lack of consensus on how pathologists should incorporate computational pathology systems into their workflow. To address these concerns, building computational pathology systems with explainable AI (xAI) mechanisms is a powerful and transparent alternative to black-box AI models. xAI can reveal underlying causes for its decisions; this is intended to promote safety and reliability of AI for critical tasks such as pathology diagnosis. This article outlines xAI enabled applications in anatomic pathology workflow that improves efficiency and accuracy of the practice. In addition, we describe HistoMapr-Breast, an initial xAI enabled software application for breast core biopsies. HistoMapr-Breast automatically previews breast core WSIs and recognizes the regions of interest to rapidly present the key diagnostic areas in an interactive and explainable manner. We anticipate xAI will ultimately serve pathologists as an interactive computational guide for computer-assisted primary diagnosis.

Impact of image analysis and artificial intelligence in thyroid pathology, with particular reference to cytological aspects

OBJECTIVE

Thyroid pathology has great potential for automated/artificial intelligence algorithm application as the incidence of thyroid nodules is increasing and the indeterminate interpretation rate of fine-needle aspiration remains relatively high. The aim of the study is to review the published literature on automated image analysis and artificial intelligence applications to thyroid pathology with whole-slide imaging.

METHODS

Systematic search was carried out in electronic databases. Studies dealing with thyroid pathology and use of automated algorithms applied to whole-slide imaging were included. Quality of studies was assessed with a modified QUADAS-2 tool.

RESULTS

Of 919 retrieved articles, 19 were included. The main themes addressed were the comparison of automated assessment of immunohistochemical staining with manual pathologist's assessment, quantification of differences in cellular and nuclear parameters among tumour entities, and discrimination between benign and malignant nodules. Correlation coefficients with manual assessment were higher than 0.76 and diagnostic performance of automated models was comparable with an expert pathologist diagnosis. Computational difficulties were related to the large size of whole-slide images.

CONCLUSIONS

Overall, the results are promising and it is likely that, with the resolution of technical issues, the application of automated algorithms in thyroid pathology will increase and be adopted following suitable validation studies.

Artificial intelligence in cytopathology: a review of the literature and overview of commercial landscape

Artificial intelligence (AI) has made impressive strides recently in interpreting complex images, thanks to improvements in deep learning techniques and increasing computational power. Researchers have started applying these advanced techniques to pathology images, although most efforts have been focused on histopathology. Cytopathology, however, remains the original field of pathology for which AI models for clinical use were successfully commercialized, to assist with automating Papanicolaou test screening. Recent AI efforts have focused on whole slide images of both gynecologic and non-gynecologic cytopathology. This review summarizes the literature and commercial landscape of AI as applied to cytopathology.

CytoProcessorTM: A New Cervical Cancer Screening System for Remote Diagnosis

BACKGROUND

Current automated cervical cytology screening systems still heavily depend on manipulation of glass slides. We developed a new system called CytoProcessorTM (DATEXIM, Caen, France), which increases sensitivity and takes advantage of virtual slide technology to simplify the workflow and save worker time. We used an approach based on artificial intelligence to identify abnormal cells among the tens of thousands in a cervical preparation.

OBJECTIVES

We set out to compare the diagnostic sensitivity and specificity of CytoProcessorTM and the ThinPrep Imaging System (HOLOGIC, Marlborough, MA, USA).

METHODS

A representative population of 1,352 cases was selected from the routine workflow in a private laboratory. Diagnoses were established using the ThinPrep Imaging System and CytoProcessorTM. All discordances were resolved by a consensus committee.

RESULTS

Compared to the ThinPrep Imaging System, CytoProcessorTM significantly improves diagnostic sensitivity without compromising specificity. The sensitivity of detection of "atypical squamous cells of undetermined significance (ASC-US) and more severe" and "low-grade squamous intraepithelial lesion and more severe" was significantly higher using CytoProcessorTM. Considering that cases with a truth diagnosis of ASC-US or more severe required clinical follow-up, 1.5% of the cases (21/1,360) would have been missed if the CytoProcessorTM diagnosis had been used for clinical decision-making. In contrast, 4% of the cases (54/1,360) were missed when the ThinPrep Imaging System diagnosis was used for clinical decision-making. There were 2.6 times fewer false negatives using CytoProcessorTM. The CytoProcessorTM workflow was 1.5 times faster in terms of worker time.

CONCLUSIONS

CytoProcessorTM is the first of a new generation of automated screening systems, demonstrating improved sensitivity and yielding significant gains in processing time. In addition, the fully digital nature of slide presentation in CytoProcessorTM allows the remote diagnosis of Papanicolaou tests for the first time.