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

Applications of machine learning in time-domain fluorescence lifetime imaging: a review

Many medical imaging modalities have benefited from recent advances in Machine Learning (ML), specifically in deep learning, such as neural networks. Computers can be trained to investigate and enhance medical imaging methods without using valuable human resources. In recent years, Fluorescence Lifetime Imaging (FLIm) has received increasing attention from the ML community. FLIm goes beyond conventional spectral imaging, providing additional lifetime information, and could lead to optical histopathology supporting real-time diagnostics. However, most current studies do not use the full potential of machine/deep learning models. As a developing image modality, FLIm data are not easily obtainable, which, coupled with an absence of standardisation, is pushing back the research to develop models which could advance automated diagnosis and help promote FLIm. In this paper, we describe recent developments that improve FLIm image quality, specifically time-domain systems, and we summarise sensing, signal-to-noise analysis and the advances in registration and low-level tracking. We review the two main applications of ML for FLIm: lifetime estimation and image analysis through classification and segmentation. We suggest a course of action to improve the quality of ML studies applied to FLIm. Our final goal is to promote FLIm and attract more ML practitioners to explore the potential of lifetime imaging.

From Diagnosis to Treatment: Exploring the Latest Management Trends in Cervical Intraepithelial Neoplasia

Cervical intraepithelial neoplasia (CIN) stands as a precancerous condition with the potential to progress to invasive cervical cancer. This comprehensive review explores the intricacies of CIN management, beginning with its definition, classification, and etiology. It emphasizes the significance of early detection and outlines the latest trends in diagnosis, including Pap smears, human papillomavirus (HPV) testing, and colposcopy. Grading and staging, pivotal in treatment selection, are elucidated. Current management approaches, encompassing watchful waiting, surgical interventions, emerging minimally invasive techniques, and immunotherapy, are detailed. The factors influencing treatment decisions, informed consent, and patient education are discussed. Potential complications following treatment, the importance of long-term follow-up, and the role of HPV vaccination in prevention are underscored. Finally, the review looks to the future, discussing advances in detection, novel treatments, and the promise of precision medicine. In conclusion, early detection and management remain the cornerstone of CIN care, offering hope for a future where cervical cancer is a preventable and treatable condition.

Label-free spatially maintained measurements of metabolic phenotypes in cells

Metabolic reprogramming at a cellular level contributes to many diseases including cancer, yet few assays are capable of measuring metabolic pathway usage by individual cells within living samples. Here, autofluorescence lifetime imaging is combined with single-cell segmentation and machine-learning models to predict the metabolic pathway usage of cancer cells. The metabolic activities of MCF7 breast cancer cells and HepG2 liver cancer cells were controlled by growing the cells in culture media with specific substrates and metabolic inhibitors. Fluorescence lifetime images of two endogenous metabolic coenzymes, reduced nicotinamide adenine dinucleotide (NADH) and oxidized flavin adenine dinucleotide (FAD), were acquired by a multi-photon fluorescence lifetime microscope and analyzed at the cellular level. Quantitative changes of NADH and FAD lifetime components were observed for cells using glycolysis, oxidative phosphorylation, and glutaminolysis. Conventional machine learning models trained with the autofluorescence features classified cells as dependent on glycolytic or oxidative metabolism with 90%-92% accuracy. Furthermore, adapting convolutional neural networks to predict cancer cell metabolic perturbations from the autofluorescence lifetime images provided improved performance, 95% accuracy, over traditional models trained via extracted features. Additionally, the model trained with the lifetime features of cancer cells could be transferred to autofluorescence lifetime images of T cells, with a prediction that 80% of activated T cells were glycolytic, and 97% of quiescent T cells were oxidative. In summary, autofluorescence lifetime imaging combined with machine learning models can detect metabolic perturbations between glycolysis and oxidative metabolism of living samples at a cellular level, providing a label-free technology to study cellular metabolism and metabolic heterogeneity.

Early Detection of Cervical Cancer by Fluorescence Lifetime Imaging Microscopy Combined with Unsupervised Machine Learning

Cervical cancer has high morbidity and mortality rates, affecting hundreds of thousands of women worldwide and requiring more accurate screening for early intervention and follow-up treatment. Cytology is the current dominant clinical screening approach, and though it has been used for decades, it has unsatisfactory sensitivity and specificity. In this work, fluorescence lifetime imaging microscopy (FLIM) was used for the imaging of exfoliated cervical cells in which an endogenous coenzyme involved in metabolism, namely, reduced nicotinamide adenine dinucleotide (phosphate) [NAD(P)H], was detected to evaluate the metabolic status of cells. FLIM images from 71 participants were analyzed by the unsupervised machine learning method to build a prediction model for cervical cancer risk. The FLIM method combined with unsupervised machine learning (FLIM-ML) had a sensitivity and specificity of 90.9% and 100%, respectively, significantly higher than those of the cytology approach. One cancer recurrence case was predicted as high-risk several months earlier using this method as compared to using current clinical methods, implying that FLIM-ML may be very helpful for follow-up cancer care. This study illustrates the clinical applicability of FLIM-ML as a detection method for cervical cancer screening and a convenient tool for follow-up cancer care.

A Machine Learning Tool to Predict the Response to Neoadjuvant Chemotherapy in Patients with Locally Advanced Cervical Cancer

Despite several studies having identified factors associated with successful treatment outcomes in locally advanced cervical cancer, there is the lack of accurate predictive modeling for progression-free survival (PFS) in patients who undergo radical hysterectomy after neoadjuvant chemotherapy (NACT). Here we investigated whether machine learning (ML) may have the potential to provide a tool to predict neoadjuvant treatment response as PFS. In this retrospective observational study, we analyzed patients with locally advanced cervical cancer (FIGO stages IB2, IB3, IIA1, IIA2, IIB, and IIIC1) who were followed in a tertiary center from 2010 to 2018. Demographic and clinical characteristics were collected at either treatment baseline or at 24-month follow-up. Furthermore, we recorded data about magnetic resonance imaging (MRI) examinations and post-surgery histopathology. Proper feature selection was used to determine an attribute core set. Three different machine learning algorithms, namely Logistic Regression (LR), Random Forest (RFF), and K-nearest neighbors (KNN), were then trained and validated with 10-fold cross-validation to predict 24-month PFS. Our analysis included n. 92 patients. The attribute core set used to train machine learning algorithms included the presence/absence of fornix infiltration at pre-treatment MRI as well as of either parametrium invasion and lymph nodes involvement at post-surgery histopathology. RFF showed the best performance (accuracy 82.4%, precision 83.4%, recall 96.2%, area under receiver operating characteristic curve (AUROC) 0.82). We developed an accurate ML model to predict 24-month PFS.

Survival outcome prediction in cervical cancer: Cox models vs deep-learning model

BACKGROUND

Historically, the Cox proportional hazard regression model has been the mainstay for survival analyses in oncologic research. The Cox proportional hazard regression model generally is used based on an assumption of linear association. However, it is likely that, in reality, there are many clinicopathologic features that exhibit a nonlinear association in biomedicine.

OBJECTIVE

The purpose of this study was to compare the deep-learning neural network model and the Cox proportional hazard regression model in the prediction of survival in women with cervical cancer.

STUDY DESIGN

This was a retrospective pilot study of consecutive cases of newly diagnosed stage I-IV cervical cancer from 2000-2014. A total of 40 features that included patient demographics, vital signs, laboratory test results, tumor characteristics, and treatment types were assessed for analysis and grouped into 3 feature sets. The deep-learning neural network model was compared with the Cox proportional hazard regression model and 3 other survival analysis models for progression-free survival and overall survival. Mean absolute error and concordance index were used to assess the performance of these 5 models.

RESULTS

There were 768 women included in the analysis. The median age was 49 years, and the majority were Hispanic (71.7%). The majority of tumors were squamous (75.3%) and stage I (48.7%). The median follow-up time was 40.2 months; there were 241 events for recurrence and progression and 170 deaths during the follow-up period. The deep-learning model showed promising results in the prediction of progression-free survival when compared with the Cox proportional hazard regression model (mean absolute error, 29.3 vs 316.2). The deep-learning model also outperformed all the other models, including the Cox proportional hazard regression model, for overall survival (mean absolute error, Cox proportional hazard regression vs deep-learning, 43.6 vs 30.7). The performance of the deep-learning model further improved when more features were included (concordance index for progression-free survival: 0.695 for 20 features, 0.787 for 36 features, and 0.795 for 40 features). There were 10 features for progression-free survival and 3 features for overall survival that demonstrated significance only in the deep-learning model, but not in the Cox proportional hazard regression model. There were no features for progression-free survival and 3 features for overall survival that demonstrated significance only in the Cox proportional hazard regression model, but not in the deep-learning model.

CONCLUSION

Our study suggests that the deep-learning neural network model may be a useful analytic tool for survival prediction in women with cervical cancer because it exhibited superior performance compared with the Cox proportional hazard regression model. This novel analytic approach may provide clinicians with meaningful survival information that potentially could be integrated into treatment decision-making and planning. Further validation studies are necessary to support this pilot study.

Improving Diagnosis of Cervical Pre-Cancer: Combination of PCA and SVM Applied on Fluorescence Lifetime Images

We report a significant improvement in the diagnosis of cervical cancer through a combined application of principal component analysis (PCA) and support vector machine (SVM) on the average fluorescence decay profile of Fluorescence Lifetime Images (FLI) of epithelial hyperplasia (EH) and CIN-I cervical tissue samples, obtained ex-vivo. The fast and slow components of double exponential fitted fluorescence lifetimes were found to be higher for EH compared to the lifetimes of CIN-I samples. Application of PCA to the average time-resolved fluorescence decay profiles showed that the 2nd PC, in combination with 1st PC, enhanced the discrimination between EH and CIN-I tissues. Fluorescence lifetime and PC scores were then classified separately by using SVM support vector machine to identify the two. On applying SVM to a combination of fluorescence lifetime and PC scores, diagnostic capability improved significantly.

Fluorescence microscopy of H&E stained cervical biopsies to assist the diagnosis and grading of CIN

BACKGROUND

Prevention of cervical cancer is based upon the accurate diagnosis and grading of cervical lesions identified during screening. The pathological classification of cervical intraepithelial neoplasia (CIN) is problematic, as it relies on subjective criteria and is known to have high interobserver variability and low reproducibility. These limitations can result in either over or under treatment of patients. Biomarkers to improve CIN diagnosis have not overcome all these challenges.

MAIN BODY

Here we review the use of a promising optical imaging method using eosin-based fluorescence spectroscopy. This technique is able to perform fluorescent analysis of cervical biopsies directly from hematoxylin and eosin (H&E) stained tissues. Eosin is a brominated derivative of fluorescein. Fluorescence characteristics of protein-eosin complexes can demonstrate tissue changes associated with dysplasia and cancer. In this article we review the progress made towards developing eosin-based fluorescence spectroscopy. We describe the various morphologies seen among the CIN grades with this optical method and highlight the progress made to quantitate the spectral image characteristics.

CONCLUSION

Eosin-based fluorescence spectroscopy can be used to directly examine H&E stained tissue slides. Relevant areas can be imaged and spectral analysis done to obtain objective data to identify and grade cervical lesions.

Fluorescence lifetime based bioassays

Fluorescence lifetime (FLT) is a robust intrinsic property and material constant of fluorescent matter. Measuring this important physical indicator has evolved from a laboratory curiosity to a powerful and established technique for a variety of applications in drug discovery, medical diagnostics and basic biological research. This distinct trend was mainly driven by improved and meanwhile affordable laser and detection instrumentation on the one hand, and the development of suitable FLT probes and biological assays on the other. In this process two essential working approaches emerged. The first one is primarily focused on high throughput applications employing biochemical in vitro assays with no requirement for high spatial resolution. The second even more dynamic trend is the significant expansion of assay methods combining highly time and spatially resolved fluorescence data by fluorescence lifetime imaging. The latter approach is currently pursued to enable not only the investigation of immortal tumor cell lines, but also specific tissues or even organs in living animals. This review tries to give an actual overview about the current status of FLT based bioassays and the wide range of application opportunities in biomedical and life science areas. In addition, future trends of FLT technologies will be discussed.

Feasibility of clinical detection of cervical dysplasia using angle-resolved low coherence interferometry measurements of depth-resolved nuclear morphology

This study sought to establish the feasibility of using in situ depth-resolved nuclear morphology measurements for detection of cervical dysplasia. Forty enrolled patients received routine cervical colposcopy with angle-resolved low coherence interferometry (a/LCI) measurements of nuclear morphology. a/LCI scans from 63 tissue sites were compared to histopathological analysis of co-registered biopsy specimens which were classified as benign, low-grade squamous intraepithelial lesion (LSIL), or high-grade squamous intraepithelial lesion (HSIL). Results were dichotomized as dysplastic (LSIL/HSIL) versus non-dysplastic and HSIL versus LSIL/benign to determine both accuracy and potential clinical utility of a/LCI nuclear morphology measurements. Analysis of a/LCI data was conducted using both traditional Mie theory based processing and a new hybrid algorithm that provides improved processing speed to ascertain the feasibility of real-time measurements. Analysis of depth-resolved nuclear morphology data revealed a/LCI was able to detect a significant increase in the nuclear diameter at the depth bin containing the basal layer of the epithelium for dysplastic versus non-dysplastic and HSIL versus LSIL/Benign biopsy sites (both p < 0.001). Both processing techniques resulted in high sensitivity and specificity (>0.80) in identifying dysplastic biopsies and HSIL. The hybrid algorithm demonstrated a threefold decrease in processing time at a slight cost in classification accuracy. The results demonstrate the feasibility of using a/LCI as an adjunctive clinical tool for detecting cervical dysplasia and guiding the identification of optimal biopsy sites. The faster speed from the hybrid algorithm offers a promising approach for real-time clinical analysis.