Automated image analysis of digital colposcopy for the detection of cervical neoplasia

Cervical pre-cancerous lesion detection: development of smartphone-based VIA application using artificial intelligence

OBJECTIVE

Visual inspection of cervix after acetic acid application (VIA) has been considered an alternative to Pap smear in resource-limited settings, like Indonesia. However, VIA results mainly depend on examiner's experience and with the lack of comprehensive training of healthcare workers, VIA accuracy keeps declining. We aimed to develop an artificial intelligence (AI)-based Android application that can automatically determine VIA results in real time and may be further developed as a health care support system in cervical cancer screening.

RESULT

A total of 199 women who underwent VIA test was studied. Images of cervix before and after VIA test were taken with smartphone, then evaluated and labelled by experienced oncologist as VIA positive or negative. Our AI model training pipeline consists of 3 steps: image pre-processing, feature extraction, and classifier development. Out of the 199 data, 134 were used as train-validation data and the remaining 65 data were used as test data. The trained AI model generated a sensitivity of 80%, specificity of 96.4%, accuracy of 93.8%, precision of 80%, and ROC/AUC of 0.85 (95% CI 0.66-1.0). The developed AI-based Android application may potentially aid cervical cancer screening, especially in low resource settings.

Diagnosis of Cervical Cancer and Pre-Cancerous Lesions by Artificial Intelligence: A Systematic Review

OBJECTIVE

The likelihood of timely treatment for cervical cancer increases with timely detection of abnormal cervical cells. Automated methods of detecting abnormal cervical cells were established because manual identification requires skilled pathologists and is time consuming and prone to error. The purpose of this systematic review is to evaluate the diagnostic performance of artificial intelligence (AI) technologies for the prediction, screening, and diagnosis of cervical cancer and pre-cancerous lesions.

MATERIALS AND METHODS

Comprehensive searches were performed on three databases: Medline, Web of Science Core Collection (Indexes = SCI-EXPANDED, SSCI, A & HCI Timespan) and Scopus to find papers published until July 2022. Articles that applied any AI technique for the prediction, screening, and diagnosis of cervical cancer were included in the review. No time restriction was applied. Articles were searched, screened, incorporated, and analyzed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines.

RESULTS

The primary search yielded 2538 articles. After screening and evaluation of eligibility, 117 studies were incorporated in the review. AI techniques were found to play a significant role in screening systems for pre-cancerous and cancerous cervical lesions. The accuracy of the algorithms in predicting cervical cancer varied from 70% to 100%. AI techniques make a distinction between cancerous and normal Pap smears with 80-100% accuracy. AI is expected to serve as a practical tool for doctors in making accurate clinical diagnoses. The reported sensitivity and specificity of AI in colposcopy for the detection of CIN2+ were 71.9-98.22% and 51.8-96.2%, respectively.

CONCLUSION

The present review highlights the acceptable performance of AI systems in the prediction, screening, or detection of cervical cancer and pre-cancerous lesions, especially when faced with a paucity of specialized centers or medical resources. In combination with human evaluation, AI could serve as a helpful tool in the interpretation of cervical smears or images.

Earth Mover’s Distance-Based Tool for Rapid Screening of Cervical Cancer Using Cervigrams

Cervical cancer is a major public health challenge that can be cured with early diagnosis and timely treatment. This challenge formed the rationale behind our design and development of an intelligent and robust image analysis and diagnostic tool/scale, namely “OM—The OncoMeter”, for which we used R (version-3.6.3) and Linux (Ubuntu-20.04) to tag and triage patients in order of their disease severity. The socio-demographic profiles and cervigrams of 398 patients evaluated at OPDs of Batra Hospital & Medical Research Centre, New Delhi, India, and Delhi State Cancer Institute (East), New Delhi, India, were acquired during the course of this study. Tested on 398 India-specific women’s cervigrams, the scale yielded significant achievements, with 80.15% accuracy, a sensitivity of 84.79%, and a specificity of 66.66%. The statistical analysis of sociodemographic profiles showed significant associations of age, education, annual income, occupation, and menstrual health with the health of the cervix, where a p-value less than (<) 0.05 was considered statistically significant. The deployment of cervical cancer screening tools such as “OM—The OncoMeter” in live clinical settings of resource-limited healthcare infrastructure will facilitate early diagnosis in a non-invasive manner, leading to a timely clinical intervention for infected patients upon detection even during primary healthcare (PHC).

Advanced Optical Imaging-Guided Nanotheranostics towards Personalized Cancer Drug Delivery

Nanomedicine involves the use of nanotechnology for clinical applications and holds promise to improve treatments. Recent developments offer new hope for cancer detection, prevention and treatment; however, being a heterogenous disorder, cancer calls for a more targeted treatment approach. Personalized Medicine (PM) aims to revolutionize cancer therapy by matching the most effective treatment to individual patients. Nanotheranostics comprise a combination of therapy and diagnostic imaging incorporated in a nanosystem and are developed to fulfill the promise of PM by helping in the selection of treatments, the objective monitoring of response and the planning of follow-up therapy. Although well-established imaging techniques, such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT), Positron Emission Tomography (PET) and Single-Photon Emission Computed Tomography (SPECT), are primarily used in the development of theranostics, Optical Imaging (OI) offers some advantages, such as high sensitivity, spatial and temporal resolution and less invasiveness. Additionally, it allows for multiplexing, using multi-color imaging and DNA barcoding, which further aids in the development of personalized treatments. Recent advances have also given rise to techniques permitting better penetration, opening new doors for OI-guided nanotheranostics. In this review, we describe in detail these recent advances that may be used to design and develop efficient and specific nanotheranostics for personalized cancer drug delivery.

Hybrid Transfer Learning for Classification of Uterine Cervix Images for Cervical Cancer Screening

Transfer learning using deep pre-trained convolutional neural networks is increasingly used to solve a large number of problems in the medical field. In spite of being trained using images with entirely different domain, these networks are flexible to adapt to solve a problem in a different domain too. Transfer learning involves fine-tuning a pre-trained network with optimal values of hyperparameters such as learning rate, batch size, and number of training epochs. The process of training the network identifies the relevant features for solving a specific problem. Adapting the pre-trained network to solve a different problem requires fine-tuning until relevant features are obtained. This is facilitated through the use of large number of filters present in the convolutional layers of pre-trained network. A very few features out of these features are useful for solving the problem in a different domain, while others are irrelevant, use of which may only reduce the efficacy of the network. However, by minimizing the number of filters required to solve the problem, the efficiency of the training the network can be improved. In this study, we consider identification of relevant filters using the pre-trained networks namely AlexNet and VGG-16 net to detect cervical cancer from cervix images. This paper presents a novel hybrid transfer learning technique, in which a CNN is built and trained from scratch, with initial weights of only those filters which were identified as relevant using AlexNet and VGG-16 net. This study used 2198 cervix images with 1090 belonging to negative class and 1108 to positive class. Our experiment using hybrid transfer learning achieved an accuracy of 91.46%.

Quantitative Screening of Cervical Cancers for Low-Resource Settings: Pilot Study of Smartphone-Based Endoscopic Visual Inspection After Acetic Acid Using Machine Learning Techniques

BACKGROUND

Approximately 90% of global cervical cancer (CC) is mostly found in low- and middle-income countries. In most cases, CC can be detected early through routine screening programs, including a cytology-based test. However, it is logistically difficult to offer this program in low-resource settings due to limited resources and infrastructure, and few trained experts. A visual inspection following the application of acetic acid (VIA) has been widely promoted and is routinely recommended as a viable form of CC screening in resource-constrained countries. Digital images of the cervix have been acquired during VIA procedure with better quality assurance and visualization, leading to higher diagnostic accuracy and reduction of the variability of detection rate. However, a colposcope is bulky, expensive, electricity-dependent, and needs routine maintenance, and to confirm the grade of abnormality through its images, a specialist must be present. Recently, smartphone-based imaging systems have made a significant impact on the practice of medicine by offering a cost-effective, rapid, and noninvasive method of evaluation. Furthermore, computer-aided analyses, including image processing-based methods and machine learning techniques, have also shown great potential for a high impact on medicinal evaluations.

OBJECTIVE

In this study, we demonstrate a new quantitative CC screening technique and implement a machine learning algorithm for smartphone-based endoscopic VIA. We also evaluated the diagnostic performance and practicability of the approach based on the results compared to the gold standard and from physicians' interpretation.

METHODS

A smartphone-based endoscope system was developed and applied to the VIA screening. A total of 20 patients were recruited for this study to evaluate the system. Overall, five were healthy, and 15 were patients who had shown a low to high grade of cervical intraepithelial neoplasia (CIN) from both colposcopy and cytology tests. Endoscopic VIA images were obtained before a loop electrosurgical excision procedure for patients with abnormal tissues, and their histology tissues were collected. Endoscopic VIA images were assessed by four expert physicians relative to the gold standard of histopathology. Also, VIA features were extracted from multiple steps of image processing techniques to find the differences between abnormal (CIN2+) and normal (≤CIN1). By using the extracted features, the performance of different machine learning classifiers, such as k-nearest neighbors (KNN), support vector machine, and decision tree (DT), were compared to find the best algorithm for VIA. After determining the best performing classifying model, it was used to evaluate the screening performance of VIA.

RESULTS

An average accuracy of 78%, with a Cohen kappa of 0.571, was observed for the evaluation of the system by four physicians. Through image processing, 240 sliced images were obtained from the cervicogram at each clock position, and five features of VIA were extracted. Among the three models, KNN showed the best performance for finding VIA within holdout 10-fold cross-validation, with an accuracy of 78.3%, area under the curve of 0.807, a specificity of 80.3%, and a sensitivity of 75.0%, respectively. The trained model performed using an unprovided data set resulted in an accuracy of 80.8%, specificity of 84.1%, and sensitivity of 71.9%. Predictions were visualized with intuitive color labels, indicating the normal/abnormal tissue using a circular clock-type segmentation. Calculating the overlapped abnormal tissues between the gold standard and predicted value, the KNN model overperformed the average assessments of physicians for finding VIA.

CONCLUSIONS

We explored the potential of the smartphone-based endoscopic VIA as an evaluation technique and used the cervicogram to evaluate normal/abnormal tissue using machine learning techniques. The results of this study demonstrate its potential as a screening tool in low-resource settings.

Andriod Device-Based Cervical Cancer Screening for Resource-Poor Settings

Visual inspection with acetic acid (VIA) is an effective, affordable and simple test for cervical cancer screening in resource-poor settings. But considerable expertise is needed to differentiate cancerous lesions from normal lesions, which is lacking in developing countries. Many studies have attempted automation of cervical cancer detection from cervix images acquired during the VIA process. These studies used images acquired through colposcopy or cervicography. However, colposcopy is expensive and hence is not feasible as a screening tool in resource-poor settings. Cervicography uses a digital camera to acquire cervix images which are subsequently sent to experts for evaluation. Hence, cervicography does not provide a real-time decision of whether the cervix is normal or not, during the VIA examination. In case the cervix is found to be abnormal, the patient may be referred to a hospital for further evaluation using Pap smear and/or biopsy. An android device with an inbuilt app to acquire images and provide instant results would be an obvious choice in resource-poor settings. In this paper, we propose an algorithm for analysis of cervix images acquired using an android device, which can be used for the development of decision support system to provide instant decision during cervical cancer screening. This algorithm offers an accuracy of 97.94%, a sensitivity of 99.05% and specificity of 97.16%.

Intraoperative multispectral and hyperspectral label-free imaging: A systematic review of in vivo clinical studies

Multispectral and hyperspectral imaging (HSI) are emerging optical imaging techniques with the potential to transform the way surgery is performed but it is not clear whether current systems are capable of delivering real-time tissue characterization and surgical guidance. We conducted a systematic review of surgical in vivo label-free multispectral and HSI systems that have been assessed intraoperatively in adult patients, published over a 10-year period to May 2018. We analysed 14 studies including 8 different HSI systems. Current in-vivo HSI systems generate an intraoperative tissue oxygenation map or enable tumour detection. Intraoperative tissue oxygenation measurements may help to predict those patients at risk of postoperative complications and in-vivo intraoperative tissue characterization may be performed with high specificity and sensitivity. All systems utilized a line-scanning or wavelength-scanning method but the spectral range and number of spectral bands employed varied significantly between studies and according to the system's clinical aim. The time to acquire a hyperspectral cube dataset ranged between 5 and 30 seconds. No safety concerns were reported in any studies. A small number of studies have demonstrated the capabilities of intraoperative in-vivo label-free HSI but further work is needed to fully integrate it into the current surgical workflow.

Development of Algorithms for Automated Detection of Cervical Pre-Cancers With a Low-Cost, Point-of-Care, Pocket Colposcope

GOAL

In this paper, we propose methods for (1) automatic feature extraction and classification for acetic acid and Lugol's iodine cervigrams and (2) methods for combining features/diagnosis of different contrasts in cervigrams for improved performance.

METHODS

We developed algorithms to pre-process pathology-labeled cervigrams and extract simple but powerful color and textural-based features. The features were used to train a support vector machine model to classify cervigrams based on corresponding pathology for visual inspection with acetic acid, visual inspection with Lugol's iodine, and a combination of the two contrasts.

RESULTS

The proposed framework achieved a sensitivity, specificity, and accuracy of 81.3%, 78.6%, and 80.0%, respectively, when used to distinguish cervical intraepithelial neoplasia (CIN+) relative to normal and benign tissues. This is superior to the average values achieved by three expert physicians on the same data set for discriminating normal/benign cases from CIN+ (77% sensitivity, 51% specificity, and 63% accuracy).

CONCLUSION

The results suggest that utilizing simple color- and textural-based features from visual inspection with acetic acid and visual inspection with Lugol's iodine images may provide unbiased automation of cervigrams.

SIGNIFICANCE

This would enable automated, expert-level diagnosis of cervical pre-cancer at the point of care.

Deep Belief Network for the Enhancement of Ultrasound Images with Pelvic Lesions

It is well known that ultrasound images are cost-efficient and exhibit hassle-free usage. However, very few works have focused on exploiting the ultrasound modality for lesion diagnosis. Moreover, there is no reliable contribution reported in the literature for diagnosing pelvic lesions from the pelvic portion of humans, especially females. While few contributions are found for diagnosis of lesions in the pelvic region, no effort has been made on enhancing the images. Inspired from the neural network (NN), our methodology adopts deep belief NN for enhancing the ultrasound image with pelvic lesions. The higher-order statistical characteristics of image textures, such as entropy and autocorrelation, are considered to enhance the image from its noisy environment. The alignment problem is considered using skewness. The proposed method is compared with the existing NN method to demonstrate its enhancement performance.

Optimization of Classification Strategies of Acetowhite Temporal Patterns towards Improving Diagnostic Performance of Colposcopy

Efforts have been being made to improve the diagnostic performance of colposcopy, trying to help better diagnose cervical cancer, particularly in developing countries. However, improvements in a number of areas are still necessary, such as the time it takes to process the full digital image of the cervix, the performance of the computing systems used to identify different kinds of tissues, and biopsy sampling. In this paper, we explore three different, well-known automatic classification methods (k-Nearest Neighbors, Naïve Bayes, and C4.5), in addition to different data models that take full advantage of this information and improve the diagnostic performance of colposcopy based on acetowhite temporal patterns. Based on the ROC and PRC area scores, the k-Nearest Neighbors and discrete PLA representation performed better than other methods. The values of sensitivity, specificity, and accuracy reached using this method were 60% (95% CI 50–70), 79% (95% CI 71–86), and 70% (95% CI 60–80), respectively. The acetowhitening phenomenon is not exclusive to high-grade lesions, and we have found acetowhite temporal patterns of epithelial changes that are not precancerous lesions but that are similar to positive ones. These findings need to be considered when developing more robust computing systems in the future.

Development of a Multimodal Colposcopy for Characterization of Cervical Intraepithelial Neoplasia

To develop and evaluate the clinical application of a multimodal colposcopy combining multispectral reflectance, autofluorescence, and red, green, blue (RGB) imaging for noninvasive characterization of cervical intraepithelial neoplasia (CIN). We developed a multimodal colposcopy system that combined multispectral reflectance, autofluorescence, and RGB imaging for noninvasive characterization of CIN. We studied the optical properties of cervical tissue first; then the imaging system was designed and tested in a clinical trial where comprehensive datasets were acquired and analyzed to differentiate between squamous normal and high grade types of cervical tissue. The custom-designed multimodal colposcopy is capable of acquiring multispectral reflectance images, autofluorescence images, and RGB images of cervical tissue consecutively. The classification algorithm was employed on both normal and abnormal cases for image segmentation. The performance characteristics of this system were comparable to the gold standard histopathologic measurements with statistical significance. Our pilot study demonstrated the clinical potential of this multimodal colposcopic system for noninvasive characterization of CIN. The proposed system was simple, noninvasive, cost-effective, and portable, making it a suitable device for deployment in developing countries or rural regions of limited resources.

Alternative Colposcopy Techniques: A Systematic Review and Meta-analysis

OBJECTIVE

To assess the diagnostic value of alternative (digital) colposcopy techniques for detection of cervical intraepithelial neoplasia (CIN) 2 or worse in a colposcopy population.

DATA SOURCES

MEDLINE, EMBASE, ClinicalTrials.gov, and the Cochrane Library were searched from inception up to January 11, 2016, for studies that evaluated the diagnostic value of alternative (digital) colposcopy techniques.

METHODS OF STUDY SELECTION

Inclusion criteria were: 1) an alternative (digital) colposcopy technique was used in a colposcopy population; 2) a histologic outcome was reported, classified as CIN, differentiating between mild dysplasia or less (CIN 1 or less), and moderate dysplasia or worse (CIN 2 or greater); 3) the entire cervix was scanned at once or a per-woman analysis was performed; 4) no other topical application than acetic acid and Lugol's solution was used; 5) at least three eligible studies had to be available within a single technique; and 6) studies obtained research ethics approval. Language was restricted to English.

TABULATION, INTEGRATION, AND RESULTS

Two reviewers assessed the eligibility of the identified articles. Disagreements were resolved by a third reviewer. Thirteen studies met the inclusion criteria. We found six studies on fluorescence and reflectance spectroscopy, including 2,530 women, with a pooled sensitivity of 93% (95% confidence interval [CI] 89-95%) and specificity of 62% (95% CI 47-76%). Four studies on dynamic spectral imaging were found including 1,173 women with a pooled sensitivity of 69% (95% CI 48-85%) and specificity of 83% (95% CI 76-88%). We found three studies on optical coherence tomography including 693 women with a pooled sensitivity of 48% (95% CI 32-64%) and specificity of 77% (95% CI 52-91%). Previously published conventional colposcopy results showed a sensitivity of 61% (95% CI 58-63%) and a specificity of 85% (95% CI 83-86%).

CONCLUSION

Alternative (digital) colposcopy techniques may result in increased sensitivity and specificity, but no recommendation for introduction in clinical practice can be made yet.

Optical techniques for cervical neoplasia detection

This paper provides an overview of the current research in the field of optical techniques for cervical neoplasia detection and covers a wide range of the existing and emerging technologies. Using colposcopy, a visual inspection of the uterine cervix with a colposcope (a binocular microscope with 3- to 15-fold magnification), has proven to be an efficient approach for the detection of invasive cancer. Nevertheless, the development of a reliable and cost-effective technique for the identification of precancerous lesions, confined to the epithelium (cervical intraepithelial neoplasia) still remains a challenging problem. It is known that even at early stages the neoplastic transformations of cervical tissue induce complex changes and modify both structural and biochemical properties of tissues. The different methods, including spectroscopic (diffuse reflectance spectroscopy, induced fluorescence and autofluorescence spectroscopy, Raman spectroscopy) and imaging techniques (confocal microscopy, optical coherence tomography, Mueller matrix imaging polarimetry, photoacoustic imaging), probe different tissue properties that may serve as optical biomarkers for diagnosis. Both the advantages and drawbacks of these techniques for the diagnosis of cervical precancerous lesions are discussed and compared.

Enhancement of early cervical cancer diagnosis with epithelial layer analysis of fluorescence lifetime images

This work reports the use of layer analysis to aid the fluorescence lifetime diagnosis of cervical intraepithelial neoplasia (CIN) from H&E stained cervical tissue sections. The mean and standard deviation of lifetimes in single region of interest (ROI) of cervical epithelium were previously shown to correlate to the gold standard histopathological classification of early cervical cancer. These previously defined single ROIs were evenly divided into layers for analysis. A 10-layer model revealed a steady increase in fluorescence lifetime from the inner to the outer epithelial layers of healthy tissue sections, suggesting a close association with cellular maturity. The shorter lifetime and minimal lifetime increase towards the epithelial surface of CIN-affected regions are in good agreement with the absence of cellular maturation in CIN. Mean layer lifetimes in the top-half cervical epithelium were used as feature vectors for extreme learning machine (ELM) classifier discriminations. It was found that the proposed layer analysis technique greatly improves the sensitivity and specificity to 94.6% and 84.3%, respectively, which can better supplement the traditional gold standard cervical histopathological examinations.

Novel advancements in colposcopy: historical perspectives and a systematic review of future developments

OBJECTIVE

To describe novel innovations and techniques for the detection of high-grade dysplasia.

MATERIALS AND METHODS

Studies were identified through the PubMed database, spanning the last 10 years. The key words (["computerized colposcopy" or "digital colposcopy" or "spectroscopy" or "multispectral digital colposcopy" or "dynamic spectral imaging", or "electrical impedance spectroscopy" or "confocal endomicroscopy" or "confocal microscopy"or "optical coherence tomography"] and ["cervical dysplasia" or cervical precancer" or "cervix" or "cervical"]) were used. The inclusion criteria were published articles of original research referring to noncolposcopic evaluation of the cervix for the detection of cervical dysplasia. Only English-language articles from the past 10 years were included, in which the technologies were used in vivo, and sensitivities and specificities could be calculated.

RESULTS

The single author reviewed the articles for inclusion. Primary search of the database yielded 59 articles, and secondary cross-reference yielded 12 articles. Thirty-two articles met the inclusion criteria.

CONCLUSIONS

An instrument that globally assesses the cervix, such as computer-assisted colposcopy, optical spectroscopy, and dynamic spectral imaging, would provided the most comprehensive estimate of disease and is therefore best suited when treatment is preferred. Electrical impedance spectroscopy, confocal microscopy, and optical coherence tomography provide information at the cellular level to estimate histology and are therefore best suited when deferment of treatment is preferred. If a device is to eventually replace the colposcope, it will likely combine technologies to best meet the needs of the target population, and as such, no single instrument may prove to be universally appropriate. Analyses of false-positive rates, additional colposcopies and biopsies, cost, and absolute life-savings will be important when considering these technologies and are limited thus far.

Quantitative diagnosis of cervical neoplasia using fluorescence lifetime imaging on haematoxylin and eosin stained tissue sections

The use of conventional fluorescence microscopy for characterizing tissue pathological states is limited by overlapping spectra and the dependence on excitation power and fluorophore concentration. Fluorescence lifetime imaging microscopy (FLIM) can overcome these limitations due to its insensitivity to fluorophore concentration, excitation power and spectral similarity. This study investigates the diagnosis of early cervical cancer using FLIM and a neural network extreme learning machine classifier. A concurrently high sensitivity and specificity of 92.8% and 80.2%, respectively, were achieved. The results suggest that the proposed technique can be used to supplement the traditional histopathological examination of early cervical cancer.

Intelligent screening systems for cervical cancer

Advent of medical image digitalization leads to image processing and computer-aided diagnosis systems in numerous clinical applications. These technologies could be used to automatically diagnose patient or serve as second opinion to pathologists. This paper briefly reviews cervical screening techniques, advantages, and disadvantages. The digital data of the screening techniques are used as data for the computer screening system as replaced in the expert analysis. Four stages of the computer system are enhancement, features extraction, feature selection, and classification reviewed in detail. The computer system based on cytology data and electromagnetic spectra data achieved better accuracy than other data.

Early detection of high-grade squamous intraepithelial lesions in the cervix with quantitative spectroscopic imaging

Quantitative spectroscopy has recently been extended from a contact-probe to wide-area spectroscopic imaging to enable mapping of optical properties across a wide area of tissue. We train quantitative spectroscopic imaging (QSI) to identify cervical high-grade squamous intraepithelial lesions (HSILs) in 34 subjects undergoing the loop electrosurgical excision procedure (LEEP subjects). QSI's performance is then prospectively evaluated on the clinically suspicious biopsy sites from 47 subjects undergoing colposcopic-directed biopsy. The results show the per-subject normalized reduced scattering coefficient at 700 nm (An) and the total hemoglobin concentration are significantly different (p<0.05) between HSIL and non-HSIL sites in LEEP subjects. An alone retrospectively distinguishes HSIL from non-HSIL with 89% sensitivity and 83% specificity. It alone applied prospectively on the biopsy sites distinguishes HSIL from non-HSIL with 81% sensitivity and 78% specificity. The findings of this study agree with those of an earlier contact-probe study, validating the robustness of QSI, and specifically An, for identifying HSIL. The performance of An suggests an easy to use and an inexpensive to manufacture monochromatic instrument is capable of early cervical cancer detection, which could be used as a screening and diagnostic tool for detecting cervical cancer in low resource countries.

Diagnostic aids for detection of oral precancerous conditions

Oral cancer has a tendency to be detected at late stage which is detrimental to the patients because of its high mortality and morbidity rates. Early detection of oral cancer is therefore important to reduce the burden of this devastating disease. In this review article, the most common oral precancerous lesions are discussed and the importance of early diagnosis is emphasized. In addition, the most common non-invasive oral cancer devices that can aid the general practitioners in early diagnosis are also discussed.

Adjunctive colposcopy technologies for examination of the uterine cervix--DySIS, LuViva Advanced Cervical Scan and Niris Imaging System: a systematic review and economic evaluation

BACKGROUND

Women in England (aged 25-64 years) are invited for cervical screening every 3-5 years to assess for cervical intraepithelial neoplasia (CIN) or cancer. CIN is a term describing abnormal changes in the cells of the cervix, ranging from CIN1 to CIN3, which is precancerous. Colposcopy is used to visualise the cervix. Three adjunctive colposcopy technologies for examination of the cervix have been included in this assessment: Dynamic Spectral Imaging System (DySIS), the LuViva Advanced Cervical Scan and the Niris Imaging System.

OBJECTIVE

To determine the clinical effectiveness and cost-effectiveness of adjunctive colposcopy technologies for examination of the uterine cervix for patients referred for colposcopy through the NHS Cervical Screening Programme.

DATA SOURCES

Sixteen electronic databases [Allied and Complementary Medicine Database (AMED), BIOSIS Previews, Cochrane Database of Systematic Reviews (CDSR), Cochrane Central Register of Controlled Trials (CENTRAL), Cumulative Index to Nursing and Allied Health Literature (CINAHL), Database of Abstracts of Reviews of Effects (DARE), EMBASE, Health Management Information Consortium (HMIC), Health Technology Assessment (HTA) database; Inspec, Inside Conferences, MEDLINE, NHS Economic Evaluation Database (NHS EED), PASCAL, Science Citation Index Expanded (SCIE) and Science Citation Index (SCI) - Conference Proceedings], and two clinical trial registries [ClinicalTrials.gov and Current Controlled Trials (CCT)] were searched to September-October 2011.

REVIEW METHODS

Studies comparing DySIS, LuViva or Niris with conventional colposcopy were sought; a narrative synthesis was undertaken. A decision-analytic model was developed, which measured outcomes in terms of quality-adjusted life-years (QALYs) and costs were evaluated from the perspective of the NHS and Personal Social Services with a time horizon of 50 years.

RESULTS

Six studies were included: two studies of DySIS, one study of LuViva and three studies of Niris. The DySIS studies were well reported and had a low risk of bias; they found higher sensitivity with DySIS (both the DySISmap alone and in combination with colposcopy) than colposcopy alone for identifying CIN2+ disease, although specificity was lower with DySIS. The studies of LuViva and Niris were poorly reported and had limitations, which indicated that their results were subject to a high risk of bias; the results of these studies cannot be considered reliable. The base-case cost-effectiveness analysis suggests that both DySIS treatment options are less costly and more effective than colposcopy alone in the overall weighted population; these results were robust to the ranges tested in the sensitivity analysis. DySISmap alone was more costly and more effective in several of the referral groups but the incremental cost-effectiveness ratio (ICER) was never higher than £1687 per QALY. DySIS plus colposcopy was less costly and more effective in all reasons for referral. Only indicative analyses were carried out on Niris and LuViva and no conclusions could be made on their cost-effectiveness.

LIMITATIONS

The assessment is limited by the available evidence on the new technologies, natural history of the disease area and current treatment patterns.

CONCLUSIONS

DySIS, particularly in combination with colposcopy, has higher sensitivity than colposcopy alone. There is no reliable evidence on the clinical effectiveness of LuViva and Niris. DySIS plus colposcopy appears to be less costly and more effective than both the DySISmap alone and colposcopy alone; these results were robust to the sensitivity analyses undertaken. Given the lack of reliable evidence on LuViva and Niris, no conclusions on their potential cost-effectiveness can be drawn. There is some uncertainty about how generalisable these findings will be to the population of women referred for colposcopy in the future, owing to the introduction of the human papillomavirus (HPV) triage test and uptake of the HPV vaccine.

Infrared spectral histopathology (SHP): a novel diagnostic tool for the accurate classification of lung cancer

We report results of a study utilizing a recently developed tissue diagnostic method, based on label-free spectral techniques, for the classification of lung cancer histopathological samples from a tissue microarray. The spectral diagnostic method allows reproducible and objective diagnosis of unstained tissue sections. This is accomplished by acquiring infrared hyperspectral data sets containing thousands of spectra, each collected from tissue pixels about 6 μm on edge; these pixel spectra contain an encoded snapshot of the entire biochemical composition of the pixel area. The hyperspectral data sets are subsequently decoded by methods of multivariate analysis, which reveal changes in the biochemical composition between tissue types, and between various stages and states of disease. In this study, a detailed comparison between classical and spectral histopathology (SHP) is presented, which suggests SHP can achieve levels of diagnostic accuracy that is comparable to that of multi-panel immunohistochemistry.

Advances in molecular imaging: targeted optical contrast agents for cancer diagnostics

Over the last three decades, our understanding of the molecular changes associated with cancer development and progression has advanced greatly. This has led to new cancer therapeutics targeted against specific molecular pathways; such therapies show great promise to reduce mortality, in part by enabling physicians to tailor therapy for patients based on a molecular profile of their tumor. Unfortunately, the tools for definitive cancer diagnosis - light microscopic examination of biopsied tissue stained with nonspecific dyes - remain focused on the analysis of tissue ex vivo. There is an important need for new clinical tools to support the molecular diagnosis of cancer. Optical molecular imaging is emerging as a technique to help meet this need. Targeted, optically active contrast agents can specifically label extra- and intracellular biomarkers of cancer. Optical images can be acquired in real time with high spatial resolution to image-specific molecular targets, while still providing morphologic context. This article reviews recent advances in optical molecular imaging, highlighting the advances in technology required to improve early cancer detection, guide selection of targeted therapy and rapidly evaluate therapeutic efficacy.

Automated analysis of cervix images to grade the severity of cancer

This paper discusses a method to objectively analyze the severity of cancer in images obtained from cervix. We propose a novel method to identify the transformation zone in post Lugol's iodine images and acetic acid images that are obtained from the cervix to grade the severity of cancer. We segment the Lugol's iodine image to identify the abnormal tissues and map them to acetic acid images to accurately identify the abnormal tissues in post acetic acid images as well. This information is further used to obtain an opacity difference score that could be used for grading the cancer.

Accuracy of optical spectroscopy for the detection of cervical intraepithelial neoplasia without colposcopic tissue information; a step toward automation for low resource settings

Optical spectroscopy has been proposed as an accurate and low-cost alternative for detection of cervical intraepithelial neoplasia. We previously published an algorithm using optical spectroscopy as an adjunct to colposcopy and found good accuracy (sensitivity=1.00 [95% confidence interval (CI)=0.92 to 1.00], specificity=0.71 [95% CI=0.62 to 0.79]). Those results used measurements taken by expert colposcopists as well as the colposcopy diagnosis. In this study, we trained and tested an algorithm for the detection of cervical intraepithelial neoplasia (i.e., identifying those patients who had histology reading CIN 2 or worse) that did not include the colposcopic diagnosis. Furthermore, we explored the interaction between spectroscopy and colposcopy, examining the importance of probe placement expertise. The colposcopic diagnosis-independent spectroscopy algorithm had a sensitivity of 0.98 (95% CI=0.89 to 1.00) and a specificity of 0.62 (95% CI=0.52 to 0.71). The difference in the partial area under the ROC curves between spectroscopy with and without the colposcopic diagnosis was statistically significant at the patient level (p=0.05) but not the site level (p=0.13). The results suggest that the device has high accuracy over a wide range of provider accuracy and hence could plausibly be implemented by providers with limited training.

Wide-field spectral imaging of human ovary autofluorescence and oncologic diagnosis via previously collected probe data

With no sufficient screening test for ovarian cancer, a method to evaluate the ovarian disease state quickly and nondestructively is needed. The authors have applied a wide-field spectral imager to freshly resected ovaries of 30 human patients in a study believed to be the first of its magnitude. Endogenous fluorescence was excited with 365-nm light and imaged in eight emission bands collectively covering the 400- to 640-nm range. Linear discriminant analysis was used to classify all image pixels and generate diagnostic maps of the ovaries. Training the classifier with previously collected single-point autofluorescence measurements of a spectroscopic probe enabled this novel classification. The process by which probe-collected spectra were transformed for comparison with imager spectra is described. Sensitivity of 100% and specificity of 51% were obtained in classifying normal and cancerous ovaries using autofluorescence data alone. Specificity increased to 69% when autofluorescence data were divided by green reflectance data to correct for spatial variation in tissue absorption properties. Benign neoplasm ovaries were also found to classify as nonmalignant using the same algorithm. Although applied ex vivo, the method described here appears useful for quick assessment of cancer presence in the human ovary.

Optical technologies and molecular imaging for cervical neoplasia: a program project update

There is an urgent global need for effective and affordable approaches to cervical cancer screening and diagnosis. In developing nations, cervical malignancies remain the leading cause of cancer-related deaths in women. This reality may be difficult to accept given that these deaths are largely preventable; where cervical screening programs have been implemented, cervical cancer-related deaths have decreased dramatically. In developed countries, the challenges of cervical disease stem from high costs and overtreatment. The National Cancer Institute-funded Program Project is evaluating the applicability of optical technologies in cervical cancer. The mandate of the project is to create tools for disease detection and diagnosis that are inexpensive, require minimal expertise, are more accurate than existing modalities, and can be feasibly implemented in a variety of clinical settings. This article presents the status and long-term goals of the project.

Objective perspective in colposcopy

Colposcopy is a widely used diagnostic procedure, primarily in the assessment of women with abnormal cervical cytology. It is used by appropriately trained individuals using techniques that allow a full assessment of the abnormality and plan for further investigation or treatment. Certain key features are specifically looked for, and a colposcopic impression formed. Using a systematic approach to the colposcopic assessment can improve the diagnostic accuracy. In this chapter, we review various factors and meta-analyses in relation to the diagnostic performance of colposcopy. Newer technologies are being developed that will assist the clinician in assessing the colposcopic changes. Quality assurance of the training and practise of colposcopy is important to maintain appropriate management for women with cytological abnormalities.

Accuracy of optical spectroscopy for the detection of cervical intraepithelial neoplasia: Testing a device as an adjunct to colposcopy

Testing emerging technologies involves the evaluation of biologic plausibility, technical efficacy, clinical effectiveness, patient satisfaction, and cost-effectiveness. The objective of this study was to select an effective classification algorithm for optical spectroscopy as an adjunct to colposcopy and obtain preliminary estimates of its accuracy for the detection of CIN 2 or worse. We recruited 1,000 patients from screening and prevention clinics and 850 patients from colposcopy clinics at two comprehensive cancer centers and a community hospital. Optical spectroscopy was performed, and 4,864 biopsies were obtained from the sites measured, including abnormal and normal colposcopic areas. The gold standard was the histologic report of biopsies, read 2 to 3 times by histopathologists blinded to the cytologic, histopathologic, and spectroscopic results. We calculated sensitivities, specificities, receiver operating characteristic (ROC) curves, and areas under the ROC curves. We identified a cutpoint for an algorithm based on optical spectroscopy that yielded an estimated sensitivity of 1.00 [95% confidence interval (CI) = 0.92-1.00] and an estimated specificity of 0.71 [95% CI = 0.62-0.79] in a combined screening and diagnostic population. The positive and negative predictive values were 0.58 and 1.00, respectively. The area under the ROC curve was 0.85 (95% CI = 0.81-0.89). The per-patient and per-site performance were similar in the diagnostic and poorer in the screening settings. Like colposcopy, the device performs best in a diagnostic population. Alternative statistical approaches demonstrate that the analysis is robust and that spectroscopy works as well as or slightly better than colposcopy for the detection of CIN 2 to cancer.

Domain-specific image analysis for cervical neoplasia detection based on conditional random fields

This paper presents a domain-specific automated image analysis framework for the detection of pre-cancerous and cancerous lesions of the uterine cervix. Our proposed framework departs from previous methods in that we include domain-specific diagnostic features in a probabilistic manner using conditional random fields. Likewise, we provide a novel window-based performance assessment scheme for 2D image analysis which addresses the intrinsic problem of image misalignment. Image regions corresponding to different tissue types are indentified for the extraction of domain-specific anatomical features. The unique optical properties of each tissue type and the diagnostic relationships between neighboring regions are incorporated in the proposed conditional random field model. The validity of our method is examined using clinical data from 48 patients, and its diagnostic potential is demonstrated by a performance comparison with expert colposcopy annotations, using histopathology as the ground truth. The proposed automated diagnostic approach can support or potentially replace conventional colposcopy, allow tissue specimen sampling to be performed in a more objective manner, and lower the number of cervical cancer cases in developing countries by providing a cost effective screening solution in low-resource settings.

Clinical grading of oral mucosa by curve-fitting of corrected autofluorescence using diffuse reflectance spectra

BACKGROUND

Laser-induced autofluorescence (LIAF) and diffuse reflectance (DR) were collectively used in this clinical study to improve early oral cancer diagnosis and tissue grading.

METHODS

LIAF and DR emission from oral mucosa were recorded on a fiber-optic spectrometer by illumination with a 404-nm diode laser and tungsten halogen lamp in 36 healthy volunteers and 40 lesions of 20 patients.

RESULTS

Absorption dips in LIAF spectra at 545 and 575 nm resulting from changes in oxygenated hemoglobin were corrected using DR spectra of the same site. These corrected spectra were curve-fitted using Gaussian spectral functions to determine constituent emission peaks and their relative contribution. The Gaussian peak intensity and area ratios F500/F635 and F500/F685 were found to be useful indicators of tissue transformation. The diagnostic capability of various ratios in differentiating healthy, hyperplastic, dysplastic, and squamous cell carcinomas (SCCs) were examined using discrimination scatterplots.

CONCLUSIONS

The LIAF/DR technique, in conjunction with curve-fitting, differentiates different grades of dysplasia and SCC in this clinical trial and proves its potential for early detection of oral cavity cancer and tissue grading.

Does acetic acid influence the non-dysplastic Pap smear?

OBJECTIVE

Acetic acid tests are commonly performed for colposcopic evaluation of the cervix. However, it is unclear whether the acetic acid influences normal Papanicolaou (Pap) smear results.

METHODS

Patients were routinely seen in our outpatient department between April and May 2009. Two Pap smears were performed in 50 patients. One smear was done before, the other after the acetic acid test. The smears were evaluated by an experienced cytologist. He did not know whether the smear was done with or without acetic acid.

RESULTS

In a normal smear, there was no influence of acetic acid on the cytologic result. In two patients, a smear of Pap III [Bethesda, atypical squamous cells of undetermined significance (ASCUS)] was seen before acetic acid test. This changed to Pap IIID [Bethesda, low-grade squamous epithelial lesions (LSIL)] after acetic acid test.

CONCLUSIONS

The acetic acid test does not seem to alter the result of the non-dysplastic smear. In contrast to this, a dysplastic smear seems to be influenced by the acetic acid. This should be evaluated in a further investigation.

Diffuse reflection spectroscopy: an alternative to autofluorescence spectroscopy in tongue cancer detection

Laser-induced autofluorescence (LIAF) and diffuse reflection spectroscopy (DRS) are two emerging noninvasive optical tools that have shown immense potential to detect oral cavity pre-cancer. In a recent study, we have used spectral ratio reference standards (SRRS) of LIAF intensity ratios F500/F635, F500/F685, and F500/F705 for grading of tissues belonging to sites other than dorsal side of tongue (DST), lateral side of tongue (LST), and vermillion border of lip (VBL) that exhibited similar spectral shape for normal and abnormal tissues. This led to dismal diagnostic accuracies, and for the three LIAF-SRRS, normal tissue values were often misclassified as squamous cell carcinoma (SCC), which means that the true negatives were being wrongly identified as true positives. This study examines the applicability of the site-specific diffuse reflection spectral intensity ratio (R545/R575) of the oxygenated hemoglobin bands to classify different DST lesions and compares the results obtained with those obtained using LIAF-SRRS. DRS-SRRS of R545/R575 differentiated benign hyperplastic DST tissues from normal tissue with a sensitivity of 86% and specificity of 80%, which were indistinguishable using LIAF-SRRS. Further, in distinguishing hyperplastic tissues from premalignant dysplastic lesions, DRS-SRRS gave a sensitivity of 90% and a specificity of 86%, as compared to sensitivity of 89% and specificity of 72% shown by the three LIAF-SRRS together. The diagnostic accuracy and statistical adequacy of the two techniques were assessed by receiver operating characteristic curve (ROC-Curve) analysis. Three LIAF ratios gave a low overall ROC area under curve (ROC-AUCs) of 0.521, whereas the DR ratio (R545/R575) has shown an improved accuracy of 0.970 in differentiating different tissue types. While distinguishing hyperplastic from dysplastic tissues, the DR ratio gave a higher discrimination accuracy of 0.9. Based on these findings, it can be concluded that the DRS-SRRS technique by virtue of its low cost and higher diagnostic accuracies could be a viable alternate to LIAF-SRRS for in vivo screening of tongue pre-cancers and grading of different tissue types.

Clinical study of quantitative diagnosis of early cervical cancer based on the classification of acetowhitening kinetics

A quantitative colposcopic imaging system for the diagnosis of early cervical cancer is evaluated in a clinical study. This imaging technology based on 3-D active stereo vision and motion tracking extracts diagnostic information from the kinetics of acetowhitening process measured from the cervix of human subjects in vivo. Acetowhitening kinetics measured from 137 cervical sites of 57 subjects are analyzed and classified using multivariate statistical algorithms. Cross-validation methods are used to evaluate the performance of the diagnostic algorithms. The results show that an algorithm for screening precancer produced 95% sensitivity (SE) and 96% specificity (SP) for discriminating normal and human papillomavirus (HPV)-infected tissues from cervical intraepithelial neoplasia (CIN) lesions. For a diagnostic algorithm, 91% SE and 90% SP are achieved for discriminating normal tissue, HPV infected tissue, and low-grade CIN lesions from high-grade CIN lesions. The results demonstrate that the quantitative colposcopic imaging system could provide objective screening and diagnostic information for early detection of cervical cancer.

Objective detection and delineation of oral neoplasia using autofluorescence imaging

Although the oral cavity is easily accessible to inspection, patients with oral cancer most often present at a late stage, leading to high morbidity and mortality. Autofluorescence imaging has emerged as a promising technology to aid clinicians in screening for oral neoplasia and as an aid to resection, but current approaches rely on subjective interpretation. We present a new method to objectively delineate neoplastic oral mucosa using autofluorescence imaging. Autofluorescence images were obtained from 56 patients with oral lesions and 11 normal volunteers. From these images, 276 measurements from 159 unique regions of interest (ROI) sites corresponding to normal and confirmed neoplastic areas were identified. Data from ROIs in the first 46 subjects were used to develop a simple classification algorithm based on the ratio of red-to-green fluorescence; performance of this algorithm was then validated using data from the ROIs in the last 21 subjects. This algorithm was applied to patient images to create visual disease probability maps across the field of view. Histologic sections of resected tissue were used to validate the disease probability maps. The best discrimination between neoplastic and nonneoplastic areas was obtained at 405 nm excitation; normal tissue could be discriminated from dysplasia and invasive cancer with a 95.9% sensitivity and 96.2% specificity in the training set, and with a 100% sensitivity and 91.4% specificity in the validation set. Disease probability maps qualitatively agreed with both clinical impression and histology. Autofluorescence imaging coupled with objective image analysis provided a sensitive and noninvasive tool for the detection of oral neoplasia.

Using acetowhite opacity index for detecting cervical intraepithelial neoplasia

Cervical intraepithelial neoplasia (CIN) exhibits certain morphologic features that can be identified during a colposcopic exam. Immature metaplastic and dysplastic cervical squamous epithelia turn white after application of acetic acid during the exam. The whitening process occurs visually over several minutes and subjectively helps to discriminate between dysplastic and normal tissue. Digital imaging technologies enable us to assist the physician in analyzing acetowhite (acetic-acid-induced) lesions in a fully automatic way. We report a study designed to measure multiple parameters of the acetowhitening process from two images captured with a digital colposcope. One image is captured before the acetic acid application, and the other is captured after the acetic acid application. The spatial change of the acetowhitening is extracted using color and texture information in the post-acetic-acid image; the temporal change is extracted from the intensity and color changes between the post-acetic-acid and pre-acetic-acid images with an automatic alignment. In particular, we propose an automatic means to calculate an opacity index that indicates the grades of temporal change. The imaging and data analysis system is evaluated with a total of 99 human subjects. The proposed opacity index demonstrates a sensitivity and specificity of 94 and 87%, respectively, for discriminating high-grade dysplasia (CIN2+) from normal and low-grade subjects, considering histology as the gold standard.

Optical imaging for cervical cancer detection: solutions for a continuing global problem

Cervical cancer is the leading cause of cancer death for women in developing countries. Optical technologies can improve the accuracy and availability of cervical cancer screening. For example, battery-powered digital cameras can obtain multi-spectral images of the entire cervix, highlighting suspicious areas, and high-resolution optical technologies can further interrogate such areas, providing in vivo diagnosis with high sensitivity and specificity. In addition, targeted contrast agents can highlight changes in biomarkers of cervical neoplasia. Such advances should provide a much needed global approach to cervical cancer prevention.