False-negative results in cervical cytologic studies

The appropriate interval between cervical cytologic screening studies is a matter of considerable controversy, with a major consideration being the problem of false-negative results. To determine the rate of false-negative cervical cytologic results in our laboratory and to determine how these failures occur, tissue-proven cases of carcinoma in situ, invasive squamous-cell carcinoma, endocervical adenocarcinoma and lymphoid malignancy involving the cervix with negative Papanicolaou smears obtained within one year prior to the tissue diagnosis were reviewed. Over the four-year period from 1980 through 1983, 339 patients had tissue-proven cervical malignancies. Of these, 66 had false-negative Papanicolaou smears, representing a 20% overall false-negative rate. These false-negative smears were rescreened. For all types of cervical malignancy, the majority of errors were due to sampling. No malignancy was missed disproportionately by either cytotechnologists or cytopathologists. We plan to utilize these data for quality control purposes and for continued review of future performance.     

Differences between papanicolaou smears with correct and incorrect diagnoses

A case control study of women with carcinoma in situ (CINIII) was undertaken comparing Papanicolaou smears for which false negative reports had been issued with slides for which true positive reports had been made. the number of abnormal cells was the strongest differentiating factor. Where there were less than 50 abnormal cells on the slide, the odds of a false negative report being issued was 23.7 times greater (95% confidence interval 3.7-150) than when there were 200 or more abnormal cells. In false negative slides, the abnormal cells were likely to be not represented throughout the slide, present only as single cells rather than as groups, small in size and with finely granular normochromatic nuclei. We conclude that there are intrinsic differences between true positive and false negative slides. Given these characteristics, rapid rescreening of slides that are considered negative may not be an effective method of reducing the false negative rate.     

Potentially difficult smears of women with squamous cell carcinoma pose fewer problems when PAPNET is used for primary screening

The diagnosis of squamous cell carcinoma (SCC) on a cervical smear is often far from easy. This study reports the analysis of 40 true-positive SCC smears detected in primary PAPNET screening and eight false-negative (FN) conventionally screened smears. All FN cases contained sparse abnormal material (< 10% of the slide). In these potentially difficult cases the diagnosis on the PAPNET images was not hard. Statistical analysis of the quantitative data indicated that the PAPNET images of the FN cases and the true-positive cases differed in some aspects. PAPNET highlighted the importance of background information (old blood, fibrin and necrosis). In addition, all FN smears contained cancer cells in the PAPNET images, allowing a correct diagnosis.     

False-negative Papanicolaou smears from women with cancerous and precancerous lesions of the uterine cervix

The occurrence from 1980 to 1989 of false-negative Papanicolaou smears in women with cancerous and precancerous lesions of the uterine cervix was studied. The 4,781 cases of cancer (2,814 invasive carcinomas and 593 carcinomas in situ) and precancerous lesions (418 severe dysplasias, 748 moderate dysplasias and 208 mild dysplasias) included 70 cases (1.5%) with false-negative smears. These 70 cases included 43 invasive carcinomas (61.4%), 17 carcinomas in situ and adenocarcinomas in situ (24.2%), and 10 dysplasias (14.4%); all were diagnosed histologically. The mean age of women with false-negative smears was 44.1 +/- 13.7 years. Review of the original cytologic samples showed a screening error in 41 cases (58.5%), an interpretation error in 2 cases (2.9%) and a sampling error in 27 cases (38.6%). Methods for eliminating false-negative smears are discussed.     

Cellular Differences Between True Negative and False Negative Papanicolaou Smears

A matched case-control study of 123 false negative Papanicolaou smears and 488 true negative Papanicolaou smears was undertaken to determine the association between the types of cells present on the smear and the correctness of the cytology report. the false negative slides were significantly more likely to include endocervical columnar cells than the true negative slides (odds ratio 1.90, 95% confidence interval (CI) 1.21–3.01). No statistically significant difference in metaplastic cell status was evident (odds ratio 1.48, 95% CI 0.95–2.30). When considered together, metaplastic and/or columnar cells were significantly more likely to be present in false negative smears than in true negative smears (odds ratio 1.87, 95% CI 1.13–3.08). the implications of these findings for improving the accuracy of cervical cytology for the detection of precancerous lesions are discussed.     

Inflammatory atypia and the false-negative smear in cervical intraepithelial neoplasia

The effectiveness of cervical cytologic screening is compromised by the increasingly recognized prevalence of false-negative smears. Our previous studies suggested that some false-negative cytologies can be accounted for by smears showing cervical intraepithelial neoplasia (CIN) reported as inflammatory atypia; we found that at least 4% of 5,752 consecutive smears had been underreported in this manner. In the present study, that data was reanalyzed to derive 95% confidence limits for the number of CIN smears reported as inflammatory atypia. Using several differing estimates of cytologic screening sensitivity, it is speculated that, under certain testable assumptions, colposcopy of patients with cytologic diagnoses of inflammatory atypia may be one cost-effective approach to finding CIN cases missed by screening. If confirmed, these findings imply that laboratory quality assurance efforts, traditionally directed to the most serious cytologic diagnoses, should also focus in part on nondysplastic atypia.     

Classification of cytological smears of the cervix with neuronal methods]

BACKGROUND: Cytological smears obtained from the cervix are routinely examined under the microscope as part of screening programs for the early detection of cervical cancer. The aim of the present study was to investigate whether a simple feature extraction approach using only standard image processing techniques combined with a neural classifier would lead to acceptable results that might serve as a starting point for the development of a fully automated screening system. MATERIALS AND METHODS: Gray-value images of 106 cervical smears (512 x 512 pixels) divided into two groups--inconspicuous (57) and atypical (49)--by an experienced pathologist on the basis of the original smears were employed to evaluate the method. From these images, 31 features quantifying properties of either the cell nucleus or the cytoplasm were extracted. These features were categorized with three different architectures of a neural classifier: learning vector quantization (LVQ), multilayer perceptron (MLP) and a single perceptron. CONCLUSIONS: The results show a reclassification accuracy of about 91% for all three algorithms. Sensitivity was uniform at approximately 78%, and specificity varied between 75% and 91% in the leave-one-out evaluation. These very good results provide strong encouragement for further studies involving PAP scores and colour images.     

A comparative study of three variations of the learning vector quantizer in the discrimination of benign from malignant gastric cells

A prospective study was undertaken to investigate the potential value of morphometry and artificial neural networks (ANN) for the discrimination of benign and malignant gastric lesions. Two thousand five hundred cells from 23 cases of cancer, 19 cases of gastritis and 58 cases of ulcer were selected as a training set, and an additional 8524 cells from an equal number of cases of cancer, gastritis and ulcer were used as a test set. Images of routine processed gastric smears stained by the Papanicolaou technique were processed by a custom image analysis system. The application of the learning vector quantization (LVQ) classifier enabled correct classification of > 97% of benign cells and > 95% of malignant cells, obtaining an overall accuracy of > 97%. This study presents the capabilities of ANN, and also indicates that ANN and image morphometry may offer useful information on the potential of malignancy in gastric cells.     

Performance of monolayered cervical smears in a gynecology outpatient setting in Kuwait

OBJECTIVE: To compare ThinPrep (TP) Papanicolaou smears (Cytyc Corp., Box-borough, Massachusetts, U.S.A.) with matching conventional Papanicolaou (CP) smears for specimen adequacy, cytologic quality, diagnostic accuracy and screening time. STUDY DESIGN: In this prospective study of 1,024 women a split-sample, matched-pair design in favor of CP slides based on single-blind criteria was followed with a smear on a glass slide for CP and the remaining material collected in Preserv-Cyt solution (Cytyc) for a TP smear. A Cytobrush (Medscand, Hollywood, Florida, U.S.A.) was used for smear preparation for CP. TP smears were processed in ThinPrep 2000 (Cytyc). Smears were stained with Papanicolaou stain and were interpreted according to the Bethesda system. RESULTS: The number of satisfactory but limited (SBL) cases with TP were 77 (7.5%) as compared to 127 (12.4%) with the CP method. This reduction in SBL smears with the TP method and consequent increase in satisfactory smears were highly significant (P < .001) by McNemar's test. As regards unsatisfactory smears in discordant pairs, although the number of unsatisfactory smears was higher with TP (41 cases) as against CP (27 cases), the difference was not statistically significant (P < .05). The split-sample method showed a high correlation between the CP and TP diagnoses. TP smears had a significant advantage over CP smears in the reduction in the number of ASCUS and AGUS cases (14 vs. 29) (P < .05) and increased the pickup rate of LSIL, 6 vs. 1. Time taken to screen the TP smears was half that of CP smears. No cases of LSIL or HSIL were missed on TP smears. CONCLUSION: The liquid-based processor significantly improved the adequacy and quality of smears, resulting in fewer recall cases for SBL smears, leading to more definitive diagnoses in atypical cases, increasing the pickup rate of LSILs and reducing the screening time. A machine handling multiple specimens automatically would decrease cost and be an asset to a cytopathology laboratory.     

Comparison of three different methods for automated classification of cervical cells.

Over 4600 exfoliated squamous cervical cells taken from appropriate Papanicolaou samples were classified as normal, mildly dysplastic, moderately dysplastic and severely dysplastic by an experienced cytopathologist. The slides were de-stained and subsequently re-stained with Feulgen Thionin-SO2 stain. Images of the nuclei were then captured, recorded and processed employing an image cytometry device. Automated classification of the cells was carried out using three different methods--discriminant function analysis, a decision tree classifier and a neutral network classifier. The discriminant function analysis method, which combined all dysplastic cells into an abnormal group, achieved a combined error rate of less than 0.4% for moderate and severe dysplastic cells, and less than 40% for mildly dysplastic cells. All three methods yielded comparable results, which approached those of human performance.     

基于面向对象的QuickBird遥感影像林隙分割与分类

传统的实地调查和人工解译方法已经不能满足区域尺度的林隙获取,高空间分辨率遥感影像的出现为区域尺度的林隙获取提供了可能.本研究采用QuickBird高空间分辨率光学遥感影像,结合面向对象分类技术对福建省三明市将乐县将乐国有林场进行林隙分割与分类.在面向对象分类过程中,采用10种尺度(10~100,步长为10)对QuickBird遥感影像进行分割,应用参考对象相交面积(RA_or)和分割对象相交面积(RA_os)进行分割结果评价.对每个尺度分割结果应用16个光谱特征,采用向量机分类器(SVM)进行林隙、非林隙和其他类型分类.结果表明:通过RA_or和RA_os等值法获得最优分割尺度参数为40.不同尺度参数之间的分类总精度最高相差22%.在最优尺度下,应用SVM分类器对林隙、非林隙和其他类型分类的总精度高达88%(Kappa=0.82).采用高空间分辨率遥感数据并结合面向对象的方法,可以代替传统的实地调查和人工解译对区域尺度的林隙进行识别分类.     

Classification of complete blood count and haemoglobin typing data by a C4.5 decision tree,a naïve Bayes classifier and a multilayer perceptron for thalassaemia screening

This article presents the classification of blood characteristics by a C4.5 decision tree, a naïve Bayes classifier and a multilayer perceptron for thalassaemia screening. The aim is to classify eighteen classes of thalassaemia abnormality, which have a high prevalence in Thailand, and one control class by inspecting data characterised by a complete blood count (CBC) and haemoglobin typing. Two indices namely a haemoglobin concentration (HB) and a mean corpuscular volume (MCV) are the chosen CBC attributes. On the other hand, known types of haemoglobin from six ranges of retention time identified via high performance liquid chromatography (HPLC) are the chosen haemoglobin typing attributes. The stratified 10-fold cross-validation results indicate that the best classification performance with average accuracy of 93.23% (standard deviation = 1.67%) and 92.60% (standard deviation = 1.75%) is achieved when the naïve Bayes classifier and the multilayer perceptron are respectively applied to samples which have been pre-processed by attribute discretisation. The results also suggest that the HB attribute is redundant. Moreover, the achieved classification performance is significantly higher than that obtained using only haemoglobin typing attributes as classifier inputs. Subsequently, the naïve Bayes classifier and the multilayer perceptron are applied to an additional data set in a clinical trial which respectively results in accuracy of 99.39% and 99.71%. These results suggest that a combination of CBC and haemoglobin typing analysis with a naïve Bayes classifier or a multilayer perceptron is highly suitable for automatic thalassaemia screening.     

Rapid cervicovaginal smear screening: method of quality control and assessing individual cytotechnologist performance

AIM: To validate the method of rapid screening (RS) in the detection of cervical lesions and false-negative results as well as in quality control of cytotechnologist performance. MATERIAL AND METHODS: The RS method was validated on Papanicolaou-stained and initially conventionally analysed vaginal, cervical and endocervical (VCE) smears collected in an opportunistic programme for the detection of cervical carcinoma. The study included 3680 VCE smears from the Department of Gynaecologic Cytology, University Department of Gynaecology and Obstetrics, Zagreb University Hospital Center, Zagreb and from the Department of Clinical Cytology, Osijek University Hospital, Osijek. Histologically verified abnormal findings accounted for 10% of the study samples. Thirteen cytotechnologists, with no previous experience in RS, performed the test. Each slide was examined using the 'step' technique for 1.5 minutes, the findings were classified as negative or abnormal, and the abnormal ones were also classified according to differential cytological diagnosis. The results were compared with those obtained on initial screening. Abnormal findings from a group of initially negative findings were reanalysed using conventional methods to make definitive cytological diagnosis. RESULTS: RS yielded a sensitivity of 83.7%, specificity of 93.7%, positive predictive value of 62.4%, negative predictive value of 97.9% and diagnostic accuracy of 92.6%. Relative to the initial abnormal differential cytological diagnosis, the diagnostic value of RS increased with lesion severity [54.8%, 68.0% and 91.3% for cervical intraepithelial neoplasia (CIN) I, CIN II and CIN III respectively]. RS detected 38 additional positive findings; 94.2% of these were atypical squamous cells of undetermined significance (ASCUS)/abnormal glandular cells undetermined significance (AGUS) and CIN I. The rate of additional positive findings was 1.14% (38/3135). The false-negative rate of initial screening was 9.4% (38/406), and individual cytotechnologist sensitivity was 60.0-100.0%. CONCLUSION: RS could be introduced as an efficient method of quality control to improve the sensitivity of cytological screening as well as for quality control of cytotechnologist performance.     

Partial Rescreening of All Negative Smears: an Improved Method of Quality Assurance In Laboratories Undertaking Cervical Screening

Partial rescreening was carried out on 9633 cervical smears reported as negative by standard screening. Each slide was ‘step-screened’ at normal speed for 30 s. Thirteen false negative smears were detected by this method. No false negatives were revealed by conventionally rescreening 10% of the same study group. the sensitivity of the method was assessed by ‘step-screening’ 100 known positive smears. of this group 92 were detected. the results indicate that partial rescreening is a sensitive method of quality assurance and should replace conventional 10% proportional rescreening, which is ineffective.     

Evaluation of the AutoCyte SCREEN system in a clinical cytopathology laboratory

OBJECTIVE: To compare the AutoCyte SCREEN (AutoCyte, Burlington, North Carolina, U.S.A.) system with manual screening by experienced cytotechnologists using thin-layer preparations that had been previously extensively studied and their cytologic abnormalities well defined. STUDY DESIGN: AutoCyte PREP (AutoCyte) samples prepared for a previous split-sample study comparing thin-layer preparations to conventional smears were used. These 1,992 AutoCyte PREP samples were in a cohort the abnormal findings of which had been confirmed via independent review by two sets of pathologists. For the current study, these samples were remasked and evaluated by the AutoCyte SCREEN system in a clinical laboratory. The instrument scanned each slide and selected six overview fields and 120 single objects for storage and display. The computer classified each slide in one of the following categories: abnormal, uncertain, normal or unsatisfactory. Independently for each case, a cytotechnologist evaluated the six fields and 120 objects selected by the instrument as abnormal, normal or unsatisfactory. For those cases classified as uncertain by AutoCyte, the technologist then reexamined the cellular displays and entered a consensus classification. These results were then compared to those of an independent review by cytotechnologists of the identical set of slides using routine manual screening. RESULTS: The AutoCyte SCREEN selected 35% of slides for manual review. Technologist and computer rendered equivalent classifications in 79%. Of the total slides screened by the AutoCyte SCREEN, 57% were classified as "uncertain," and 88% of these were subsequently classified as normal by consensus. Using the well-defined abnormal values of the cellular sample as a basis for calculation, the AutoCyte SCREEN-assisted practice had a diagnostic sensitivity of 85% and diagnostic specificity of 97.6%. Comparable values for manual screening of the identical cellular sample were a diagnostic sensitivity of 80% and specificity of 97.4%. CONCLUSION: The AutoCyte SCREEN achieves comparable or greater sensitivity in detecting cervical abnormalities in comparison with manual screening. When combined with the substantial advantage of thin-layer preparations over conventional smears, the AutoCyte SCREEN provides a screening system of superior sensitivity over conventionally prepared and examined cervical smears.     

Computer-aided diagnosis of breast cancer using cytological images: A systematic review

Cytological evaluation by microscopic image-based characterization [imprint cytology (IC) and fine needle aspiration cytology (FNAC)] plays an integral role in primary screening/detection of breast cancer. The sensitivity of IC and FNAC as a screening tool is dependent on the image quality and the pathologist’s level of expertise. Computer-aided diagnosis (CAD) is used to assists the pathologists by developing various machine learning and image processing algorithms. This study reviews the various manual and computer-aided techniques used so far in breast cytology. Diagnostic applications were studied to estimate the role of CAD in breast cancer diagnosis. This paper presents an overview of image processing and pattern recognition techniques that have been used to address several issues in breast cytology-based CAD including slide preparation, staining, microscopic imaging, pre-processing, segmentation, feature extraction and diagnostic classification. This review provides better insights to readers regarding the state of the art the knowledge on CAD-based breast cancer diagnosis to date.     

Rapid screening: a comparative study

Although rapid screening of negative and inadequate cervical smears is a quality assurance requirement for all UK laboratories, there has been little attempt to standardize the method and laboratories make use of a number of different techniques and times. The aim of this study was to assess the sensitivity of these various techniques by measuring their ability to pick out known false-negative smears. Completed questionnaires from 123 laboratories across England revealed that 52% of laboratories use a "step" technique, 19% use "turret", 15% use random paths and 34% attempt to rescreen the whole slide quickly. Twenty-two percent of laboratories use a mixture of techniques. Timings are also variable, with the majority of laboratories allowing screeners to review slides at a pace decided by themselves but usually between 1 and 2 min. The study involved 120 participants who performed a total of 24 000 rapid screens. The results showed that, of the 90 abnormal slides used in the study, 62 cases (69%) were identified as abnormal or needing review by more than 50% of participants. Overall rapid screening picked out 58% of high-grade squamous abnormalities, 59% of low-grade abnormalities and 72% of glandular lesions. Step screening performed best, followed by whole slide/random and then turret. One minute was the optimum time and there was a significant fall in performance once individuals attempted to rescreen large numbers (>50). The most significant finding was the marked variation in the performance of individuals using the same slide sets.     

Predictive value of DNA cytometry in CIN 1 and 2. Image analysis of 193 cases

OBJECTIVE: To investigate DNA image cytometry for predicting the prognosis of cervical intraepithelial neoplasia (CIN). STUDY DESIGN: Smears from 151 women affected by CIN 1 or 2 on cytology with minimal follow-up of three years were included. Sixty-seven showed progression, with histologically confirmed carcinoma in situ or invasive cancer. Eighty-four cases showed regression of the disease, which was cytologically, histologically and colposcopically confirmed. Papanicolaou-stained smears were destained, and the Feulgen reaction was performed with consecutive image DNA cytometry of suspicious cells using an image analysis system (Cires, Zeiss, Germany). The DNA index of the greatest stemline and the number of single aneuploid cells, using 9c exceeding events, were computed. RESULTS: In the group with progression, an aneuploid DNA stemline was found in 25 smears (26.9%). In 64 cases (66.7%) more than one aneuploid event was detected. The total number of aneuploid cases in this group was 76 (81%). In the group without progression, the number of aneuploid stemlines was 2 (2%). Single aneuploid cells could be found in five cases (5%). The overall number of aneuploid cases in that group was five. The sensitivity was 74.3%, positive predictive value 85.2% and negative predictive value 77%. CONCLUSION: Aneuploidy is a marker for prospective malignancy in cervical Papanicolaou smears. DNA image cytometry, as an additional method, can be used to predict outcome in patients with CIN 1 and 2 of the cervix. DNA cytometry is not a screening method but can add further information for a treatment decision in doubtful cases.     

Neural network-based segmentation and classification system for automated grading of histologic sections of bladder carcinoma

OBJECTIVE: To develop an image analysis system for automated nuclear segmentation and classification of histologic bladder sections employing quantitative nuclear features. STUDY DESIGN: Ninety-two cases were classified into three classes by experienced pathologists according to the WHO grading system: 18 cases as grade 1, 45 as grade 2, and 29 as grade 3. Nuclear segmentation was performed by means of an artificial neural network (ANN)-based pixel classification algorithm, and each case was represented by 36 nuclei features. Automated grading of bladder tumor histologic sections was performed by an ANN classifier implemented in a two-stage hierarchic tree. RESULTS: On average, 95% of the nuclei were correctly detected. At the first stage of the hierarchic tree, classifier performance in discriminating between cases of grade 1 and 2 and cases of grade 3 was 89%. At the second stage, 79% of grade 1 cases were correctly distinguished from grade 2 cases. CONCLUSION: The proposed image analysis system provides the means to reduce subjectivity in grading bladder tumors and may contribute to more accurate diagnosis and prognosis since it relies on nuclear features, the value of which has been confirmed.     

Evaluation of 100% rapid rescreening of negative cervical smears as a quality assurance measure

OBJECTIVE: The objective of this study was to compare the performance of 100% rapid rescreening, 10% random rescreening and the review of smears selected on the basis of clinical criteria, as a method of internal quality control of cervical smears classified as negative during routine screening. METHODS: A total of 3149 smears were analysed, 173 of which were classified as positive and 2887 as negative, while 89 smears were considered unsatisfactory. The smears classified as negative were submitted to 100% rapid rescreening, 10% random rescreening, and rescreening based on clinical criteria. The rescreening stages were blinded and results were classified according to the Bethesda 2001 terminology. Six cytologists participated in this study, two of whom were responsible for routine screening while the other four alternated in carrying out rescreening so that no individual reviewed the same slide more than once. RESULTS: The 100% rapid rescreening method identified 92 suspect smears, of which 42 were considered positive at final diagnosis. Of the 289 smears submitted to the 10% rescreening method, four were considered abnormal but only one was confirmed positive in the final diagnosis. Of the 690 smears rescreened on the basis of clinical criteria, 10 were considered abnormal and eight received a positive final diagnosis. CONCLUSIONS: The 100% rapid rescreening method is more efficient at detecting false-negative results than 10% random rescreening or rescreening on the basis of clinical criteria, and is recommended as an internal quality control method.