Combining radiomic phenotypes of non-small cell lung cancer with liquid biopsy data may improve prediction of response to EGFR inhibitors

Integrating Imaging and Circulating Tumor DNA Features for Predicting Patient Outcomes

Biomarkers for evaluating tumor response to therapy and estimating the risk of disease relapse represent tremendous areas of clinical need. To evaluate treatment efficacy, tumor response is routinely assessed using different imaging modalities like positron emission tomography/computed tomography or magnetic resonance imaging. More recently, the development of circulating tumor DNA detection assays has provided a minimally invasive approach to evaluate tumor response and prognosis through a blood test (liquid biopsy). Integrating imaging- and circulating tumor DNA-based biomarkers may lead to improvements in the prediction of patient outcomes. For this mini-review, we searched the scientific literature to find original articles that combined quantitative imaging and circulating tumor DNA biomarkers to build prediction models. Seven studies reported building prognostic models to predict distant recurrence-free, progression-free, or overall survival. Three discussed building models to predict treatment response using tumor volume, pathologic complete response, or objective response as endpoints. The limited number of articles and the modest cohort sizes reported in these studies attest to the infancy of this field of study. Nonetheless, these studies demonstrate the feasibility of developing multivariable response-predictive and prognostic models using regression and machine learning approaches. Larger studies are warranted to facilitate the building of highly accurate response-predictive and prognostic models that are generalizable to other datasets and clinical settings.

Imaging-based characterization of tumoral heterogeneity for personalized cancer treatment

With personalized tumor therapy, understanding and addressing the heterogeneity of malignant tumors is becoming increasingly important. Heterogeneity can be found within one lesion (intralesional) and between several tumor lesions emerging from one primary tumor (interlesional). The heterogeneous tumor cells may show a different response to treatment due to their biology, which in turn influences the outcome of the affected patients and the choice of therapeutic agents. Therefore, both intra- and interlesional heterogeneity should be addressed at the diagnostic stage. While genetic and biological heterogeneity are important parameters in molecular tumor characterization and in histopathology, they are not yet addressed routinely in medical imaging. This article summarizes the recently established markers for tumor heterogeneity in imaging as well as heterogeneous/mixed response to therapy. Furthermore, a look at emerging markers is given. The ultimate goal of this overview is to provide comprehensive understanding of tumor heterogeneity and its implications for radiology and for communication with interdisciplinary teams in oncology. KEY POINTS::   · Tumor heterogeneity can be described within one lesion (intralesional) or between several lesions (interlesional).. · The heterogeneous biology of tumor cells can lead to a mixed therapeutic response and should be addressed in diagnostics and the therapeutic regime.. · Quantitative image diagnostics can be enhanced using AI, improved histopathological methods, and liquid profiling in the future..

Tumor classification of gastrointestinal liver metastases using CT-based radiomics and deep learning

OBJECTIVES

The goal of this study is to demonstrate the performance of radiomics and CNN-based classifiers in determining the primary origin of gastrointestinal liver metastases for visually indistinguishable lesions.

METHODS

In this retrospective, IRB-approved study, 31 pancreatic cancer patients with 861 lesions (median age [IQR]: 65.39 [56.87, 75.08], 48.4% male) and 47 colorectal cancer patients with 435 lesions (median age [IQR]: 65.79 [56.99, 74.62], 63.8% male) were enrolled. A pretrained nnU-Net performed automated segmentation of 1296 liver lesions. Radiomics features for each lesion were extracted using pyradiomics. The performance of several radiomics-based machine-learning classifiers was investigated for the lesions and compared to an image-based deep-learning approach using a DenseNet-121. The performance was evaluated by AUC/ROC analysis.

RESULTS

The radiomics-based K-nearest neighbor classifier showed the best performance on an independent test set with AUC values of 0.87 and an accuracy of 0.67. In comparison, the image-based DenseNet-121-classifier reached an AUC of 0.80 and an accuracy of 0.83.

CONCLUSIONS

CT-based radiomics and deep learning can distinguish the etiology of liver metastases from gastrointestinal primary tumors. Compared to deep learning, radiomics based models showed a varying generalizability in distinguishing liver metastases from colorectal cancer and pancreatic adenocarcinoma.

Application value of CT radiomic nomogram in predicting T790M mutation of lung adenocarcinoma

BACKGROUND

The purpose of this study was to develop a radiomic nomogram to predict T790M mutation of lung adenocarcinoma base on non-enhanced CT lung images.

METHODS

This retrospective study reviewed demographic data and lung CT images of 215 lung adenocarcinoma patients with T790M gene test results. 215 patients (including 52 positive) were divided into a training set (n = 150, 36 positive) and an independent test set (n = 65, 16 positive). Multivariate logistic regression was used to select demographic data and CT semantic features to build clinical model. We extracted quantitative features from the volume of interest (VOI) of the lesion, and developed the radiomic model with different feature selection algorithms and classifiers. The models were trained by a 5-fold cross validation strategy on the training set and assessed on the test set. ROC was used to estimate the performance of the clinical model, radiomic model, and merged nomogram.

RESULTS

Three demographic features (gender, smoking, emphysema) and ten radiomic features (Kruskal-Wallis as selection algorithm, LASSO Logistic Regression as classifier) were determined to build the models. The AUC of the clinical model, radiomic model, and nomogram in the test set were 0.742(95%CI, 0.619-0.843), 0.810(95%CI, 0.696-0.907), 0.841(95%CI, 0.743-0.938), respectively. The predictive efficacy of the nomogram was better than the clinical model (p = 0.042). The nomogram predicted T790M mutation with cutoff value was 0.69 and the score was above 130.

CONCLUSION

The nomogram developed in this study is a non-invasive, convenient, and economical method for predicting T790M mutation of lung adenocarcinoma, which has a good prospect for clinical application.

Radiomic and Volumetric Measurements as Clinical Trial Endpoints—A Comprehensive Review

Simple Summary

The extraction of quantitative data from standard-of-care imaging modalities offers opportunities to improve the relevance and salience of imaging biomarkers used in drug development. This review aims to identify the challenges and opportunities for discovering new imaging-based biomarkers based on radiomic and volumetric assessment in the single-site solid tumor sites: breast cancer, rectal cancer, lung cancer and glioblastoma. Developing approaches to harmonize three essential areas: segmentation, validation and data sharing may expedite regulatory approval and adoption of novel cancer imaging biomarkers.

Abstract

Clinical trials for oncology drug development have long relied on surrogate outcome biomarkers that assess changes in tumor burden to accelerate drug registration (i.e., Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST v1.1) criteria). Drug-induced reduction in tumor size represents an imperfect surrogate marker for drug activity and yet a radiologically determined objective response rate is a widely used endpoint for Phase 2 trials. With the addition of therapies targeting complex biological systems such as immune system and DNA damage repair pathways, incorporation of integrative response and outcome biomarkers may add more predictive value. We performed a review of the relevant literature in four representative tumor types (breast cancer, rectal cancer, lung cancer and glioblastoma) to assess the preparedness of volumetric and radiomics metrics as clinical trial endpoints. We identified three key areas—segmentation, validation and data sharing strategies—where concerted efforts are required to enable progress of volumetric- and radiomics-based clinical trial endpoints for wider clinical implementation.

Correlation between PD-L1 expression and radiomic features in early-stage lung adenocarcinomas manifesting as ground-glass nodules

Background

Immunotherapy might be a promising auxiliary or alternative systemic treatment for early-stage lung adenocarcinomas manifesting as ground-glass nodules (GGNs). This study intended to investigate the PD-L1 expression in these patients, and to explore the non-invasive prediction model of PD-L1 expression based on radiomics.

Methods

We retrospectively analyzed the PD-L1 expression of patients with postoperative pathological diagnosis of lung adenocarcinomas and with imaging manifestation of GGNs, and divided patients into positive group and negative group according to whether PD-L1 expression ≥1%. Then, CT-based radiomic features were extracted semi-automatically, and feature dimensions were reduced by univariate analysis and LASSO in the randomly selected training cohort (70%). Finally, we used logistic regression algorithm to establish the radiomic models and the clinical-radiomic combined models for PD-L1 expression prediction, and evaluated the prediction efficiency of the models with the receiver operating characteristic (ROC) curves.

Results

A total of 839 “GGN-like lung adenocarcinoma” patients were included, of which 226 (26.9%) showed positive PD-L1 expression. 779 radiomic features were extracted, and 9 of them were found to be highly corelated with PD-L1 expression. The area under the curve (AUC) values of the radiomic models were 0.653 and 0.583 in the training cohort and test cohort respectively. After adding clinically significant and statistically significant clinical features, the efficacy of the combined model was slightly improved, and the AUC values were 0.693 and 0.598 respectively.

Conclusions

GGN-like lung adenocarcinoma had a fairly high positive PD-L1 expression rate. Radiomics was a hopeful noninvasive method for predicting PD-L1 expression, with better predictive efficacy in combination with clinical features.

Novel biomarkers in NSCLC: Radiomic analysis, kinetic analysis, and circulating tumor DNA

Current radiographic methods of measuring treatment response for patients with nonsmall cell lung cancer have significant limitations. Recently, new modalities using standard of care images or minimally invasive blood-based DNA tests have gained interest as methods of evaluating treatment response. This article highlights three emerging modalities: radiomic analysis, kinetic analysis and serum-based measurement of circulating tumor DNA, with a focus on the clinical evidence supporting these methods. Additionally, we discuss the possibility of combining these modalities to develop a robust biomarker with strong correlation to clinically meaningful outcomes that could impact clinical trial design and patient care. At Last, we focus on how these methods specifically apply to a Veteran population.

Dual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging

Automated medical data analysis demonstrated a significant role in modern medicine, and cancer diagnosis/prognosis to achieve highly reliable and generalizable systems. In this study, an automated breast cancer screening method in ultrasound imaging is proposed. A convolutional deep autoencoder model is presented for simultaneous segmentation and radiomic extraction. The model segments the breast lesions while concurrently extracting radiomic features. With our deep model, we perform breast lesion segmentation, which is linked to low-dimensional deep-radiomic extraction (four features). Similarly, we used high dimensional conventional imaging throughputs and applied spectral embedding techniques to reduce its size from 354 to 12 radiomics. A total of 780 ultrasound images—437 benign, 210, malignant, and 133 normal—were used to train and validate the models in this study. To diagnose malignant lesions, we have performed training, hyperparameter tuning, cross-validation, and testing with a random forest model. This resulted in a binary classification accuracy of 78.5% (65.1–84.1%) for the maximal (full multivariate) cross-validated model for a combination of radiomic groups.

Machine-Learning-Based Clinical Biomarker Using Cell-Free DNA for Hepatocellular Carcinoma (HCC)

(1) Background: Hepatocellular carcinoma (HCC) is one of the leading causes of cancer-related death worldwide. Although various serum enzymes have been utilized for the diagnosis and prognosis of HCC, the currently available biomarkers lack the sensitivity needed to detect HCC at early stages and accurately predict treatment responses. (2) Methods: We utilized our highly sensitive cell-free DNA (cfDNA) detection system, in combination with a machine learning algorithm, to provide a platform for improved diagnosis and prognosis of HCC. (3) Results: cfDNA, specifically alpha-fetoprotein (AFP) expression in captured cfDNA, demonstrated the highest accuracy for diagnosing malignancies among the serum/plasma biomarkers used in this study, including AFP, aspartate aminotransferase, alanine aminotransferase, albumin, alkaline phosphatase, and bilirubin. The diagnostic/prognostic capability of cfDNA was further improved by establishing a cfDNA score (cfDHCC), which integrated the total plasma cfDNA levels and cfAFP-DNA expression into a single score using machine learning algorithms. (4) Conclusion: The cfDHCC score demonstrated significantly improved accuracy in determining the pathological features of HCC and predicting patients' survival outcomes compared to the other biomarkers. The results presented herein reveal that our cfDNA capture/analysis platform is a promising approach to effectively utilize cfDNA as a biomarker for the diagnosis and prognosis of HCC.

The value proposition of integrative diagnostics for (early) detection of cancer. On behalf of the EFLM interdisciplinary Task and Finish Group "CNAPS/CTC for early detection of cancer"

Disruptive imaging and laboratory technologies can improve clinical decision processes and outcomes in oncology. However, certain obstacles must be overcome before these technologies can be fully implemented as part of the standard for care. An integrative diagnostic approach represents a unique opportunity to unleash the full diagnostic potential and paves the way towards personalized cancer diagnostics. To meet this demand, an interdisciplinary Task Force of the EFLM was initiated as a consequence of an EFLM/ESR during the CELME 2019 meeting in order to evaluate the clinical value of CNAPS/CTC (circulating nucleic acids in plasma and serum/circulating tumor cells) in early detection of cancer. Here, an overview of current disruptive techniques, their clinical implications and potential value of an integrative diagnostic approach is provided. Furthermore, requirements such as the establishment of diagnostic tumor boards, development of adequate software solutions and a change of mindset towards a new generation of diagnosticians providing actionable health information are presented. This development has the potential to elevate the position and clinical recognition of diagnosticians.

Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Automation of medical data analysis is an important topic in modern cancer diagnostics, aiming at robust and reproducible workflows. Therefore, we used a dataset of breast US images (252 malignant and 253 benign cases) to realize and compare different strategies for CAD support in lesion detection and classification. Eight different datasets (including pre-processed and spatially augmented images) were prepared, and machine learning algorithms (i.e., Viola-Jones; YOLOv3) were trained for lesion detection. The radiomics signature (RS) was derived from detection boxes and compared with RS derived from manually obtained segments. Finally, the classification model was established and evaluated concerning accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic curve. After training on a dataset including logarithmic derivatives of US images, we found that YOLOv3 obtains better results in breast lesion detection (IoU: 0.544 ± 0.081; LE: 0.171 ± 0.009) than the Viola-Jones framework (IoU: 0.399 ± 0.054; LE: 0.096 ± 0.016). Interestingly, our findings show that the classification model trained with RS derived from detection boxes and the model based on the RS derived from a gold standard manual segmentation are comparable (p-value = 0.071). Thus, deriving radiomics signatures from the detection box is a promising technique for building a breast lesion classification model, and may reduce the need for the lesion segmentation step in the future design of CAD systems.

Impact of Interobserver Variability in Manual Segmentation of Non-Small Cell Lung Cancer (NSCLC) Applying Low-Rank Radiomic Representation on Computed Tomography

Simple Summary

Discovery of predictive and prognostic radiomic features in cancer is currently of great interest to the radiologic and oncologic community. Tumor phenotypic and prognostic information can be obtained by extracting features on tumor segmentations, and it is typically imaging analysts, physician trainees, and attending physicians who provide these labeled datasets for analysis. The potential impact of level and type of specialty training on interobserver variability in manual segmentation of NSCLC was examined. Although there was some variability in segmentation between readers, the subsequently extracted radiomic features were overall well correlated. High fidelity radiomic feature extraction relies on accurate feature extraction from imaging that produce robust prognostic and predictive radiomic NSCLC biomarkers. This study concludes that this goal can be obtained using segmenters of different levels of training and clinical experience.

Abstract

This study tackles interobserver variability with respect to specialty training in manual segmentation of non-small cell lung cancer (NSCLC). Four readers included for segmentation are: a data scientist (BY), a medical student (LS), a radiology trainee (MH), and a specialty-trained radiologist (SK) for a total of 293 patients from two publicly available databases. Sørensen–Dice (SD) coefficients and low rank Pearson correlation coefficients (CC) of 429 radiomics were calculated to assess interobserver variability. Cox proportional hazard (CPH) models and Kaplan-Meier (KM) curves of overall survival (OS) prediction for each dataset were also generated. SD and CC for segmentations demonstrated high similarities, yielding, SD: 0.79 and CC: 0.92 (BY-SK), SD: 0.81 and CC: 0.83 (LS-SK), and SD: 0.84 and CC: 0.91 (MH-SK) in average for both databases, respectively. OS through the maximal CPH model for the two datasets yielded c-statistics of 0.7 (95% CI) and 0.69 (95% CI), while adding radiomic and clinical variables (sex, stage/morphological status, and histology) together. KM curves also showed significant discrimination between high- and low-risk patients (p-value < 0.005). This supports that readers’ level of training and clinical experience may not significantly influence the ability to extract accurate radiomic features for NSCLC on CT. This potentially allows flexibility in the training required to produce robust prognostic imaging biomarkers for potential clinical translation.

Machine Learning Based on Morphological Features Enables Classification of Primary Intestinal T-Cell Lymphomas

The aim of this study was to investigate the feasibility of using machine learning techniques based on morphological features in classifying two subtypes of primary intestinal T-cell lymphomas (PITLs) defined according to the WHO criteria: monomorphic epitheliotropic intestinal T-cell lymphoma (MEITL) versus intestinal T-cell lymphoma, not otherwise specified (ITCL-NOS), which is considered a major challenge for pathological diagnosis. A total of 40 histopathological whole-slide images (WSIs) from 40 surgically resected PITL cases were used as the dataset for model training and testing. A deep neural network was trained to detect and segment the nuclei of lymphocytes. Quantitative nuclear morphometrics were further computed from these predicted contours. A decision-tree-based machine learning algorithm, XGBoost, was then trained to classify PITL cases into two disease subtypes using these nuclear morphometric features. The deep neural network achieved an average precision of 0.881 in the cell segmentation work. In terms of classifying MEITL versus ITCL-NOS, the XGBoost model achieved an area under receiver operating characteristic curve (AUC) of 0.966. Our research demonstrated an accurate, human-interpretable approach to using machine learning algorithms for reducing the high dimensionality of image features and classifying T cell lymphomas that present challenges in morphologic diagnosis. The quantitative nuclear morphometric features may lead to further discoveries concerning the relationship between cellular phenotype and disease status.

Current Advances and Challenges in Radiomics of Brain Tumors

Imaging diagnosis is crucial for early detection and monitoring of brain tumors. Radiomics enable the extraction of a large mass of quantitative features from complex clinical imaging arrays, and then transform them into high-dimensional data which can subsequently be mined to find their relevance with the tumor's histological features, which reflect underlying genetic mutations and malignancy, along with grade, progression, therapeutic effect, or even overall survival (OS). Compared to traditional brain imaging, radiomics provides quantitative information linked to meaningful biologic characteristics and application of deep learning which sheds light on the full automation of imaging diagnosis. Recent studies have shown that radiomics' application is broad in identifying primary tumor, differential diagnosis, grading, evaluation of mutation status and aggression, prediction of treatment response and recurrence in pituitary tumors, gliomas, and brain metastases. In this descriptive review, besides establishing a general understanding among protocols, results, and clinical significance of these studies, we further discuss the current limitations along with future development of radiomics.