Robust feature selection to predict tumor treatment outcome

Novel ensemble feature selection techniques applied to high-grade gastroenteropancreatic neuroendocrine neoplasms for the prediction of survival

BACKGROUND AND OBJECTIVE

Determining the most informative features for predicting the overall survival of patients diagnosed with high-grade gastroenteropancreatic neuroendocrine neoplasms is crucial to improve individual treatment plans for patients, as well as the biological understanding of the disease. The main objective of this study is to evaluate the use of modern ensemble feature selection techniques for this purpose with respect to (a) quantitative performance measures such as predictive performance, (b) clinical interpretability, and (c) the effect of integrating prior expert knowledge.

METHODS

The Repeated Elastic Net Technique for Feature Selection (RENT) and the User-Guided Bayesian Framework for Feature Selection (UBayFS) are recently developed ensemble feature selectors investigated in this work. Both allow the user to identify informative features in datasets with low sample sizes and focus on model interpretability. While RENT is purely data-driven, UBayFS can integrate expert knowledge a priori in the feature selection process. In this work, we compare both feature selectors on a dataset comprising 63 patients and 110 features from multiple sources, including baseline patient characteristics, baseline blood values, tumor histology, imaging, and treatment information.

RESULTS

Our experiments involve data-driven and expert-driven setups, as well as combinations of both. In a five-fold cross-validated experiment without expert knowledge, our results demonstrate that both feature selectors allow accurate predictions: A reduction from 110 to approximately 20 features (around 82%) delivers near-optimal predictive performances with minor variations according to the choice of the feature selector, the predictive model, and the fold. Thereafter, we use findings from clinical literature as a source of expert knowledge. In addition, expert knowledge has a stabilizing effect on the feature set (an increase in stability of approximately 40%), while the impact on predictive performance is limited.

CONCLUSIONS

The features WHO Performance Status, Albumin, Platelets, Ki-67, Tumor Morphology, Total MTV, Total TLG, and SUVmax are the most stable and predictive features in our study. Overall, this study demonstrated the practical value of feature selection in medical applications not only to improve quantitative performance but also to deliver potentially new insights to experts.

A review of AI and Data Science support for cancer management

INTRODUCTION

Thanks to improvement of care, cancer has become a chronic condition. But due to the toxicity of treatment, the importance of supporting the quality of life (QoL) of cancer patients increases. Monitoring and managing QoL relies on data collected by the patient in his/her home environment, its integration, and its analysis, which supports personalization of cancer management recommendations. We review the state-of-the-art of computerized systems that employ AI and Data Science methods to monitor the health status and provide support to cancer patients managed at home.

OBJECTIVE

Our main objective is to analyze the literature to identify open research challenges that a novel decision support system for cancer patients and clinicians will need to address, point to potential solutions, and provide a list of established best-practices to adopt.

METHODS

We designed a review study, in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, analyzing studies retrieved from PubMed related to monitoring cancer patients in their home environments via sensors and self-reporting: what data is collected, what are the techniques used to collect data, semantically integrate it, infer the patient's state from it and deliver coaching/behavior change interventions.

RESULTS

Starting from an initial corpus of 819 unique articles, a total of 180 papers were considered in the full-text analysis and 109 were finally included in the review. Our findings are organized and presented in four main sub-topics consisting of data collection, data integration, predictive modeling and patient coaching.

CONCLUSION

Development of modern decision support systems for cancer needs to utilize best practices like the use of validated electronic questionnaires for quality-of-life assessment, adoption of appropriate information modeling standards supplemented by terminologies/ontologies, adherence to FAIR data principles, external validation, stratification of patients in subgroups for better predictive modeling, and adoption of formal behavior change theories. Open research challenges include supporting emotional and social dimensions of well-being, including PROs in predictive modeling, and providing better customization of behavioral interventions for the specific population of cancer patients.

A novel systematic approach for cancer treatment prognosis and its applications in oropharyngeal cancer with microRNA biomarkers

MOTIVATION

Predicting early in treatment whether a tumor is likely to respond to treatment is one of the most difficult yet important tasks in providing personalized cancer care. Most oropharyngeal squamous cell carcinoma (OPSCC) patients receive standard cancer therapy. However, the treatment outcomes vary significantly and are difficult to predict. Multiple studies indicate that microRNAs (miRNAs) are promising cancer biomarkers for the prognosis of oropharyngeal cancer. The reliable and efficient use of miRNAs for patient stratification and treatment outcome prognosis is still a very challenging task, mainly due to the relatively high dimensionality of miRNAs compared to the small number of observation sets; the redundancy, irrelevancy and uncertainty in the large amount of miRNAs; and the imbalanced observation patient samples.

RESULTS

In this study, a new machine learning-based prognosis model was proposed to stratify subsets of OPSCC patients with low and high risks for treatment failure. The model cascaded a two-stage prognostic biomarker selection method and an evidential K-nearest neighbors (EK-NN) classifier to address the challenges and improve the accuracy of patient stratification. The model has been evaluated on miRNA expression profiling of 150 oropharyngeal tumors by use of overall survival and disease-specific survival as the end points of disease treatment outcomes, respectively. The proposed method showed superior performance compared to other advanced machine-learning methods in terms of common performance quantification metrics. The proposed prognosis model can be employed as a supporting tool to identify patients who are likely to fail standard therapy and potentially benefit from alternative targeted treatments.

Comparison and Fusion of Machine Learning Algorithms for Prospective Validation of PET/CT Radiomic Features Prognostic Value in Stage II-III Non-Small Cell Lung Cancer

Machine learning (ML) algorithms for selecting and combining radiomic features into multiparametric prediction models have become popular; however, it has been shown that large variations in performance can be obtained by relying on different approaches. The purpose of this study was to evaluate the potential benefit of combining different algorithms into an improved consensus for the final prediction, as it has been shown in other fields. Methods: The evaluation was carried out in the context of the use of radiomics from ¹⁸F-FDG PET/CT images for predicting outcome in stage II-III Non-Small Cell Lung Cancer. A cohort of 138 patients was exploited for the present analysis. Eighty-seven patients had been previously recruited retrospectively for another study and were used here for training and internal validation. We also used data from prospectively recruited patients (n = 51) for testing. Three different machine learning pipelines relying on embedded feature selection were trained to predict overall survival (OS) as a binary classification: Support Vector machines (SVMs), Random Forests (RFs), and Logistic Regression (LR). Two different clinical endpoints were investigated: median OS or OS shorter than 6 months. The fusion of the three approaches was implemented using two different strategies: majority voting on the binary outputs or averaging of the output probabilities. Results: Our results confirm previous findings, highlighting that different ML pipelines select different sets of features and reach different classification performances (accuracy in the testing set ranging between 63% and 67% for median OS, and between 75% and 80% for OS < 6 months). Generating a consensus improved the performance for both endpoints; with the probabilities averaging strategy outperforming the majority voting (accuracy of 78% vs. 71% for median OS and 89 vs. 84% for OS < 6 months). Overall, the performance of these radiomic-based models outperformed the standard clinical staging in both endpoints (accuracy of 58% and 53% accuracy in the testing set for each endpoint). Conclusion: Although obtained in a small cohort of patients, our results suggest that a consensus of machine learning algorithms can improve performance in the context of radiomics. The resulting prognostic stratification in the prospective testing cohort is higher than when relying on the clinical stage. This could be of interest for clinical practice as it could help to identify patients with higher risk amongst stage II and III patients, who could benefit from intensified treatment and/or more frequent follow-up after treatment.

Artificial intelligence-assisted esophageal cancer management: Now and future

Esophageal cancer poses diagnostic, therapeutic and economic burdens in high-risk regions. Artificial intelligence (AI) has been developed for diagnosis and outcome prediction using various features, including clinicopathologic, radiologic, and genetic variables, which can achieve inspiring results. One of the most recent tasks of AI is to use state-of-the-art deep learning technique to detect both early esophageal squamous cell carcinoma and esophageal adenocarcinoma in Barrett’s esophagus. In this review, we aim to provide a comprehensive overview of the ways in which AI may help physicians diagnose advanced cancer and make clinical decisions based on predicted outcomes, and combine the endoscopic images to detect precancerous lesions or early cancer. Pertinent studies conducted in recent two years have surged in numbers, with large datasets and external validation from multi-centers, and have partly achieved intriguing results of expert’s performance of AI in real time. Improved pre-trained computer-aided diagnosis algorithms in the future studies with larger training and external validation datasets, aiming at real-time video processing, are imperative to produce a diagnostic efficacy similar to or even superior to experienced endoscopists. Meanwhile, supervised randomized controlled trials in real clinical practice are highly essential for a solid conclusion, which meets patient-centered satisfaction. Notably, ethical and legal issues regarding the black-box nature of computer algorithms should be addressed, for both clinicians and regulators.

Prediction of progression in idiopathic pulmonary fibrosis using CT scans at baseline: A quantum particle swarm optimization - Random forest approach

Idiopathic pulmonary fibrosis (IPF) is a fatal lung disease characterized by an unpredictable progressive decline in lung function. Natural history of IPF is unknown and the prediction of disease progression at the time of diagnosis is notoriously difficult. High resolution computed tomography (HRCT) has been used for the diagnosis of IPF, but not generally for monitoring purpose. The objective of this work is to develop a novel predictive model for the radiological progression pattern at voxel-wise level using only baseline HRCT scans. Mainly, there are two challenges: (a) obtaining a data set of features for region of interest (ROI) on baseline HRCT scans and their follow-up status; and (b) simultaneously selecting important features from high-dimensional space, and optimizing the prediction performance. We resolved the first challenge by implementing a study design and having an expert radiologist contour ROIs at baseline scans, depending on its progression status in follow-up visits. For the second challenge, we integrated the feature selection with prediction by developing an algorithm using a wrapper method that combines quantum particle swarm optimization to select a small number of features with random forest to classify early patterns of progression. We applied our proposed algorithm to analyze anonymized HRCT images from 50 IPF subjects from a multi-center clinical trial. We showed that it yields a parsimonious model with 81.8% sensitivity, 82.2% specificity and an overall accuracy rate of 82.1% at the ROI level. These results are superior to other popular feature selections and classification methods, in that our method produces higher accuracy in prediction of progression and more balanced sensitivity and specificity with a smaller number of selected features. Our work is the first approach to show that it is possible to use only baseline HRCT scans to predict progressive ROIs at 6 months to 1year follow-ups using artificial intelligence.

Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography

In the context of cancer delineation using positron emission tomography datasets, we present an innovative approach which purpose is to tackle the real-time, three-dimensional segmentation task in a full, or at least nearly full automatized way. The approach comprises a preliminary initialization phase where the user highlights a region of interest around the cancer on just one slice of the tomographic dataset. The algorithm takes care of identifying an optimal and user-independent region of interest around the anomalous tissue and located on the slice containing the highest standardized uptake value so to start the successive segmentation task. The three-dimensional volume is then reconstructed using a slice-by-slice marching approach until a suitable automatic stop condition is met. On each slice, the segmentation is performed using an enhanced local active contour based on the minimization of a novel energy functional which combines the information provided by a machine learning component, the discriminant analysis in the present study. As a result, the whole algorithm is almost completely automatic and the output segmentation is independent from the input provided by the user. Phantom experiments comprising spheres and zeolites, and clinical cases comprising various body districts (lung, brain, and head and neck), and two different radio-tracers (18 F-fluoro-2-deoxy-d-glucose, and 11C-labeled Methionine) were used to assess the algorithm performances. Phantom experiments with spheres and with zeolites showed a dice similarity coefficient above 90% and 80%, respectively. Clinical cases showed high agreement with the gold standard (R² = 0.98). These results indicate that the proposed method can be efficiently applied in the clinical routine with potential benefit for the treatment response assessment, and targeting in radiotherapy.

Challenges and Promises of PET Radiomics

PURPOSE

Radiomics describes the extraction of multiple, otherwise invisible, features from medical images that, with bioinformatic approaches, can be used to provide additional information that can predict underlying tumor biology and behavior.

METHODS AND MATERIALS

Radiomic signatures can be used alone or with other patient-specific data to improve tumor phenotyping, treatment response prediction, and prognosis, noninvasively. The data describing 18F-fluorodeoxyglucose positron emission tomography radiomics, often using texture or heterogeneity parameters, are increasing rapidly.

RESULTS

In relation to radiation therapy practice, early data have reported the use of radiomic approaches to better define tumor volumes and predict radiation toxicity and treatment response.

CONCLUSIONS

Although at an early stage of development, with many technical challenges remaining and a need for standardization, promise nevertheless exists that PET radiomics will contribute to personalized medicine, especially with the availability of increased computing power and the development of machine-learning approaches for imaging.

Treatment Outcome Prediction for Cancer Patients based on Radiomics and Belief Function Theory

In this study, we proposed a new radiomics-based treatment outcome prediction model for cancer patients. The prediction model is developed based on belief function theory (BFT) and sparsity learning to address the challenges of redundancy, heterogeneity, and uncertainty of radiomic features, and relatively small-sized and unbalanced training samples. The model first selects the most predictive feature subsets from relatively large amounts of radiomic features extracted from pre- and/or in-treatment positron emission tomography (PET) images and available clinical and demographic features. Then an evidential k-nearest neighbor (EK-NN) classifier is proposed to utilize the selected features for treatment outcome prediction. Twenty-five stage II-III lung, 36 esophagus, 63 stage II-III cervix, and 45 lymphoma cancer patient cases were included in this retrospective study. Performance and robustness of the proposed model were assessed with measures of feature selection stability, outcome prediction accuracy, and receiver operating characteristics (ROC) analysis. Comparison with other methods were conducted to demonstrate the feasibility and superior performance of the proposed model.

Role of artificial intelligence in the care of patients with nonsmall cell lung cancer

BACKGROUND

Lung cancer is the leading cause of cancer death worldwide. In up to 57% of patients, it is diagnosed at an advanced stage and the 5-year survival rate ranges between 10%-16%. There has been a significant amount of research using machine learning to generate tools using patient data to improve outcomes.

METHODS

This narrative review is based on research material obtained from PubMed up to Nov 2017. The search terms include "artificial intelligence," "machine learning," "lung cancer," "Nonsmall Cell Lung Cancer (NSCLC)," "diagnosis" and "treatment."

RESULTS

Recent studies support the use of computer-aided systems and the use of radiomic features to help diagnose lung cancer earlier. Other studies have looked at machine learning (ML) methods that offer prognostic tools to doctors and help them in choosing personalized treatment options for their patients based on molecular, genetics and histological features. Combining artificial intelligence approaches into health care may serve as a beneficial tool for patients with NSCLC, and this review outlines these benefits and current shortcomings throughout the continuum of care.

CONCLUSION

We present a review of the various applications of ML methods in NSCLC as it relates to improving diagnosis, treatment and outcomes.

Matched computed tomography segmentation and demographic data for oropharyngeal cancer radiomics challenges

Cancers arising from the oropharynx have become increasingly more studied in the past few years, as they are now epidemic domestically. These tumors are treated with definitive (chemo)radiotherapy, and have local recurrence as a primary mode of clinical failure. Recent data suggest that ‘radiomics’, or extraction of image texture analysis to generate mineable quantitative data from medical images, can reflect phenotypes for various cancers. Several groups have shown that developed radiomic signatures, in head and neck cancers, can be correlated with survival outcomes. This data descriptor defines a repository for head and neck radiomic challenges, executed via a Kaggle in Class platform, in partnership with the MICCAI society 2016 annual meeting.These public challenges were designed to leverage radiomics and/or machine learning workflows to discriminate HPV phenotype in one challenge (HPV status challenge) and to identify patients who will develop a local recurrence in the primary tumor volume in the second one (Local recurrence prediction challenge) in a segmented, clinically curated anonymized oropharyngeal cancer (OPC) data set.

Spatial Evidential Clustering With Adaptive Distance Metric for Tumor Segmentation in FDG-PET Images

While the accurate delineation of tumor volumes in FDG-positron emission tomography (PET) is a vital task for diverse objectives in clinical oncology, noise and blur due to the imaging system make it a challenging work. In this paper, we propose to address the imprecision and noise inherent in PET using Dempster-Shafer theory, a powerful tool for modeling and reasoning with uncertain and/or imprecise information. Based on Dempster-Shafer theory, a novel evidential clustering algorithm is proposed and tailored for the tumor segmentation task in three-dimensional. For accurate clustering of PET voxels, each voxel is described not only by the single intensity value but also complementarily by textural features extracted from a patch surrounding the voxel. Considering that there are a large amount of textures without consensus regarding the most informative ones, and some of the extracted features are even unreliable due to the low-quality PET images, a specific procedure is included in the proposed clustering algorithm to adapt distance metric for properly representing the clustering distortions and the similarities between neighboring voxels. This integrated metric adaptation procedure will realize a low-dimensional transformation from the original space, and will limit the influence of unreliable inputs via feature selection. A Dempster-Shafer-theory-based spatial regularization is also proposed and included in the clustering algorithm, so as to effectively quantify the local homogeneity. The proposed method has been compared with other methods on the real-patient FDG-PET images, showing good performance.

Predictive value of initial FDG-PET features for treatment response and survival in esophageal cancer patients treated with chemo-radiation therapy using a random forest classifier

Purpose

In oncology, texture features extracted from positron emission tomography with 18-fluorodeoxyglucose images (FDG-PET) are of increasing interest for predictive and prognostic studies, leading to several tens of features per tumor. To select the best features, the use of a random forest (RF) classifier was investigated.

Methods

Sixty-five patients with an esophageal cancer treated with a combined chemo-radiation therapy were retrospectively included. All patients underwent a pretreatment whole-body FDG-PET. The patients were followed for 3 years after the end of the treatment. The response assessment was performed 1 month after the end of the therapy. Patients were classified as complete responders and non-complete responders. Sixty-one features were extracted from medical records and PET images. First, Spearman’s analysis was performed to eliminate correlated features. Then, the best predictive and prognostic subsets of features were selected using a RF algorithm. These results were compared to those obtained by a Mann-Whitney U test (predictive study) and a univariate Kaplan-Meier analysis (prognostic study).

Results

Among the 61 initial features, 28 were not correlated. From these 28 features, the best subset of complementary features found using the RF classifier to predict response was composed of 2 features: metabolic tumor volume (MTV) and homogeneity from the co-occurrence matrix. The corresponding predictive value (AUC = 0.836 ± 0.105, Se = 82 ± 9%, Sp = 91 ± 12%) was higher than the best predictive results found using the Mann-Whitney test: busyness from the gray level difference matrix (P < 0.0001, AUC = 0.810, Se = 66%, Sp = 88%). The best prognostic subset found using RF was composed of 3 features: MTV and 2 clinical features (WHO status and nutritional risk index) (AUC = 0.822 ± 0.059, Se = 79 ± 9%, Sp = 95 ± 6%), while no feature was significantly prognostic according to the Kaplan-Meier analysis.

Conclusions

The RF classifier can improve predictive and prognostic values compared to the Mann-Whitney U test and the univariate Kaplan-Meier survival analysis when applied to several tens of features in a limited patient database.

Characterization of PET/CT images using texture analysis: the past, the present… any future?

After seminal papers over the period 2009 - 2011, the use of texture analysis of PET/CT images for quantification of intratumour uptake heterogeneity has received increasing attention in the last 4 years. Results are difficult to compare due to the heterogeneity of studies and lack of standardization. There are also numerous challenges to address. In this review we provide critical insights into the recent development of texture analysis for quantifying the heterogeneity in PET/CT images, identify issues and challenges, and offer recommendations for the use of texture analysis in clinical research. Numerous potentially confounding issues have been identified, related to the complex workflow for the calculation of textural features, and the dependency of features on various factors such as acquisition, image reconstruction, preprocessing, functional volume segmentation, and methods of establishing and quantifying correspondences with genomic and clinical metrics of interest. A lack of understanding of what the features may represent in terms of the underlying pathophysiological processes and the variability of technical implementation practices makes comparing results in the literature challenging, if not impossible. Since progress as a field requires pooling results, there is an urgent need for standardization and recommendations/guidelines to enable the field to move forward. We provide a list of correct formulae for usual features and recommendations regarding implementation. Studies on larger cohorts with robust statistical analysis and machine learning approaches are promising directions to evaluate the potential of this approach.