Quantitative analysis of abnormalities in gynecologic cytopathology with deep learning

Automated analysis of digital medical images in cervical cancer screening: A systematic review

Background

Cervical cancer screening programs are poorly implemented in LMICs due to a shortage of specialists and expensive diagnostic infrastructure. To address the barriers of implementation researchers have been developing low-cost portable devices and automating image analysis for decision support.However, as the knowledge base is growing rapidly, progress on the implementation status of novel imaging devices and algorithms in cervical cancer screening has become unclear. The aim of this project was to provide a systematic review summarizing the full range of automated technology systems used in cervical cancer screening.

Method

A search on academic databases was conducted and the search results were screened by two independent reviewers. Study selection was based on eligibility in meeting the terms of inclusion and exclusion criteria which were outlined using a Population, Intervention, Comparator and Outcome framework.

Results

17 studies reported algorithms developed with source images from mobile device, viz. Pocket Colposcope, MobileODT EVA Colpo, Smartphone Camera, Smartphone-based Endoscope System, Smartscope, mHRME, and PiHRME. While 56 studies reported algorithms with source images from conventional/commercial acquisition devices. Most interventions were in the feasibility stage of development, undergoing initial clinical validations.

Conclusion

Researchers have proven superior prediction performance of computer aided diagnostics (CAD) in colposcopy (>80% accuracies) versus manual analysis (<70.0% accuracies). Furthermore, this review summarized evidence of the algorithms which are being created utilizing portable devices, to circumvent constraints prohibiting wider implementation in LMICs (such as expensive diagnostic infrastructure). However clinical validation of novel devices with CAD is not yet implemented adequately in LMICs.

Artificial Intelligence Applications in Cytopathology: Current State of the Art

The practice of cytopathology has been significantly refined in recent years, largely through the creation of consensus rule sets for the diagnosis of particular specimens (Bethesda, Milan, Paris, and so forth). In general, these diagnostic systems have focused on reducing intraobserver variance, removing nebulous/redundant categories, reducing the use of "atypical" diagnoses, and promoting the use of quantitative scoring systems while providing a uniform language to communicate these results. Computational pathology is a natural offshoot of this process in that it promises 100% reproducible diagnoses rendered by quantitative processes that are free from many of the biases of human practitioners.

A deep learning framework for predicting endometrial cancer from cytopathologic images with different staining styles

Endometrial cancer screening is crucial for clinical treatment. Currently, cytopathologists analyze cytopathology images is considered a popular screening method, but manual diagnosis is time-consuming and laborious. Deep learning can provide objective guidance efficiency. But endometrial cytopathology images often come from different medical centers with different staining styles. It decreases the generalization ability of deep learning models in cytopathology images analysis, leading to poor performance. This study presents a robust automated screening framework for endometrial cancer that can be applied to cytopathology images with different staining styles, and provide an objective diagnostic reference for cytopathologists, thus contributing to clinical treatment. We collected and built the XJTU-EC dataset, the first cytopathology dataset that includes segmentation and classification labels. And we propose an efficient two-stage framework for adapting different staining style images, and screening endometrial cancer at the cellular level. Specifically, in the first stage, a novel CM-UNet is utilized to segment cell clumps, with a channel attention (CA) module and a multi-level semantic supervision (MSS) module. It can ignore staining variance and focus on extracting semantic information for segmentation. In the second stage, we propose a robust and effective classification algorithm based on contrastive learning, ECRNet. By momentum-based updating and adding labeled memory banks, it can reduce most of the false negative results. On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. Our method robustly predicts endometrial cancer on cytopathologic images with different staining styles, which will further advance research in endometrial cancer screening and provide early diagnosis for patients. The code will be available on GitHub.

Artifact Detection and Restoration in Histology Images With Stain-Style and Structural Preservation

The artifacts in histology images may encumber the accurate interpretation of medical information and cause misdiagnosis. Accordingly, prepending manual quality control of artifacts considerably decreases the degree of automation. To close this gap, we propose a methodical pre-processing framework to detect and restore artifacts, which minimizes their impact on downstream AI diagnostic tasks. First, the artifact recognition network AR-Classifier first differentiates common artifacts from normal tissues, e.g., tissue folds, marking dye, tattoo pigment, spot, and out-of-focus, and also catalogs artifact patches by their restorability. Then, the succeeding artifact restoration network AR-CycleGAN performs de-artifact processing where stain styles and tissue structures can be maximally retained. We construct a benchmark for performance evaluation, curated from both clinically collected WSIs and public datasets of colorectal and breast cancer. The functional structures are compared with state-of-the-art methods, and also comprehensively evaluated by multiple metrics across multiple tasks, including artifact classification, artifact restoration, downstream diagnostic tasks of tumor classification and nuclei segmentation. The proposed system allows full automation of deep learning based histology image analysis without human intervention. Moreover, the structure-independent characteristic enables its processing with various artifact subtypes. The source code and data in this research are available at https://github.com/yunboer/AR-classifier-and-AR-CycleGAN.

A survey on recent trends in deep learning for nucleus segmentation from histopathology images

Nucleus segmentation is an imperative step in the qualitative study of imaging datasets, considered as an intricate task in histopathology image analysis. Segmenting a nucleus is an important part of diagnosing, staging, and grading cancer, but overlapping regions make it hard to separate and tell apart independent nuclei. Deep Learning is swiftly paving its way in the arena of nucleus segmentation, attracting quite a few researchers with its numerous published research articles indicating its efficacy in the field. This paper presents a systematic survey on nucleus segmentation using deep learning in the last five years (2017-2021), highlighting various segmentation models (U-Net, SCPP-Net, Sharp U-Net, and LiverNet) and exploring their similarities, strengths, datasets utilized, and unfolding research areas.

Deep learning for computational cytology: A survey

Computational cytology is a critical, rapid-developing, yet challenging topic in medical image computing concerned with analyzing digitized cytology images by computer-aided technologies for cancer screening. Recently, an increasing number of deep learning (DL) approaches have made significant achievements in medical image analysis, leading to boosting publications of cytological studies. In this article, we survey more than 120 publications of DL-based cytology image analysis to investigate the advanced methods and comprehensive applications. We first introduce various deep learning schemes, including fully supervised, weakly supervised, unsupervised, and transfer learning. Then, we systematically summarize public datasets, evaluation metrics, versatile cytology image analysis applications including cell classification, slide-level cancer screening, nuclei or cell detection and segmentation. Finally, we discuss current challenges and potential research directions of computational cytology.

Using deep learning to predict survival outcome in non-surgical cervical cancer patients based on pathological images

PURPOSE

We analyzed clinical features and the representative HE-stained pathologic images to predict 5-year overall survival via the deep-learning approach in cervical cancer patients in order to assist oncologists in designing the optimal treatment strategies.

METHODS

The research retrospectively collected 238 non-surgical cervical cancer patients treated with radiochemotherapy from 2014 to 2017. These patients were randomly divided into the training set (n = 165) and test set (n = 73). Then, we extract deep features after segmenting the HE-stained image into patches of size 224 × 224. A Lasso-Cox model was constructed with clinical data to predict 5-year OS. C-index evaluated this model performance with 95% CI, calibration curve, and ROC.

RESULTS

Based on multivariate analysis, 2 of 11 clinical characteristics (C-index 0.68) and 2 of 2048 pathomic features (C-index 0.74) and clinical-pathomic model (C-index 0.83) of nomograms predict 5-year survival in the training set, respectively. In test set, compared with the pathomic and clinical characteristics used alone, the clinical-pathomic model had an AUC of 0.750 (95% CI 0.540-0.959), the clinical predictor model had an AUC of 0.729 (95% CI 0.551-0.909), and the pathomic model AUC was 0.703 (95% CI 0.487-0.919). Based on appropriate nomogram scores, we divided patients into high-risk and low-risk groups, and Kaplan-Meier survival probability curves for both groups showed statistical differences.

CONCLUSION

We built a clinical-pathomic model to predict 5-year OS in non-surgical cervical cancer patients, which may be a promising method to improve the precision of personalized therapy.

Effective deep learning for oral exfoliative cytology classification

The use of sharpness aware minimization (SAM) as an optimizer that achieves high performance for convolutional neural networks (CNNs) is attracting attention in various fields of deep learning. We used deep learning to perform classification diagnosis in oral exfoliative cytology and to analyze performance, using SAM as an optimization algorithm to improve classification accuracy. The whole image of the oral exfoliation cytology slide was cut into tiles and labeled by an oral pathologist. CNN was VGG16, and stochastic gradient descent (SGD) and SAM were used as optimizers. Each was analyzed with and without a learning rate scheduler in 300 epochs. The performance metrics used were accuracy, precision, recall, specificity, F1 score, AUC, and statistical and effect size. All optimizers performed better with the rate scheduler. In particular, the SAM effect size had high accuracy (11.2) and AUC (11.0). SAM had the best performance of all models with a learning rate scheduler. (AUC = 0.9328) SAM tended to suppress overfitting compared to SGD. In oral exfoliation cytology classification, CNNs using SAM rate scheduler showed the highest classification performance. These results suggest that SAM can play an important role in primary screening of the oral cytological diagnostic environment.

A Weakly Supervised Deep Learning Method for Guiding Ovarian Cancer Treatment and Identifying an Effective Biomarker

Ovarian cancer is a common malignant gynecological disease. Molecular target therapy, i.e., antiangiogenesis with bevacizumab, was found to be effective in some patients of epithelial ovarian cancer (EOC). Although careful patient selection is essential, there are currently no biomarkers available for routine therapeutic usage. To the authors’ best knowledge, this is the first automated precision oncology framework to effectively identify and select EOC and peritoneal serous papillary carcinoma (PSPC) patients with positive therapeutic effect. From March 2013 to January 2021, we have a database, containing four kinds of immunohistochemical tissue samples, including AIM2, c3, C5 and NLRP3, from patients diagnosed with EOC and PSPC and treated with bevacizumab in a hospital-based retrospective study. We developed a hybrid deep learning framework and weakly supervised deep learning models for each potential biomarker, and the experimental results show that the proposed model in combination with AIM2 achieves high accuracy 0.92, recall 0.97, F-measure 0.93 and AUC 0.97 for the first experiment (66% training and 34%testing) and high accuracy 0.86 ± 0.07, precision 0.9 ± 0.07, recall 0.85 ± 0.06, F-measure 0.87 ± 0.06 and AUC 0.91 ± 0.05 for the second experiment using five-fold cross validation, respectively. Both Kaplan-Meier PFS analysis and Cox proportional hazards model analysis further confirmed that the proposed AIM2-DL model is able to distinguish patients gaining positive therapeutic effects with low cancer recurrence from patients with disease progression after treatment (p < 0.005).

Gynecology Meets Big Data in the Disruptive Innovation Medical Era: State-of-Art and Future Prospects

Tremendous scientific and technological achievements have been revolutionizing the current medical era, changing the way in which physicians practice their profession and deliver healthcare provisions. This is due to the convergence of various advancements related to digitalization and the use of information and communication technologies (ICTs)—ranging from the internet of things (IoT) and the internet of medical things (IoMT) to the fields of robotics, virtual and augmented reality, and massively parallel and cloud computing. Further progress has been made in the fields of addictive manufacturing and three-dimensional (3D) printing, sophisticated statistical tools such as big data visualization and analytics (BDVA) and artificial intelligence (AI), the use of mobile and smartphone applications (apps), remote monitoring and wearable sensors, and e-learning, among others. Within this new conceptual framework, big data represents a massive set of data characterized by different properties and features. These can be categorized both from a quantitative and qualitative standpoint, and include data generated from wet-lab and microarrays (molecular big data), databases and registries (clinical/computational big data), imaging techniques (such as radiomics, imaging big data) and web searches (the so-called infodemiology, digital big data). The present review aims to show how big and smart data can revolutionize gynecology by shedding light on female reproductive health, both in terms of physiology and pathophysiology. More specifically, they appear to have potential uses in the field of gynecology to increase its accuracy and precision, stratify patients, provide opportunities for personalized treatment options rather than delivering a package of “one-size-fits-it-all” healthcare management provisions, and enhance its effectiveness at each stage (health promotion, prevention, diagnosis, prognosis, and therapeutics).