Application Potential of Radiomics based on the Unenhanced CT Image for the Identification of Benign or Malignant Pulmonary Nodules

OBJECTIVE

With the rapid development in computed tomography (CT), the establishment of artificial intelligence (AI) technology and improved awareness of health in folks in the decades, it becomes easier to detect and predict pulmonary nodules with high accuracy. The accurate identification of benign and malignant pulmonary nodules has been challenging for radiologists and clinicians. Therefore, this study applied the unenhanced CT imagesbased radiomics to identify the benign or malignant pulmonary nodules.

METHODS

One hundred and four cases of pulmonary nodules confirmed by clinicopathology were analyzed retrospectively, including 79 cases of malignant nodules and 25 cases of benign nodules. They were randomly divided into a training group (n = 74 cases) and test group (n = 30 cases) according to the ratio of 7:3. Using ITK-SNAP software to manually mark the region of interest (ROI), and using AK software (Analysis kit, Version 3.0.0.R, GE Healthcare, America) to extract image radiomics features, a total of 1316 radiomics features were extracted. Then, the minimum-redundancy-maximum-relevance (mRMR) algorithms were used to preliminarily reduce the dimension, and retain the 30 most meaningful features, and then the least absolute shrinkage and selection operator (LASSO) algorithm was used to select the optimal subset of features, so as to establish the final model. The performance of the model was evaluated by using the receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), accuracy, sensitivity and specificity. Calibration refers to the agreement between observed endpoints and predictions, and the clinical benefit of the model to patients was evaluated by decision curve analysis (DCA).

RESULTS

The accuracy, sensitivity, and specificity of the training and testing groups were 81.0%, 77.7%, 82.1% and 76.6%, 85.7%, 73.9%, respectively, and the corresponding AUCs were of 0.83 in both groups.

CONCLUSION

CT image-based radiomics could differentiate benign from malignant pulmonary nodules, which might provide a new method for clinicians to detect benign and malignant pulmonary nodules.

Fourier ptychographic and deep learning using breast cancer histopathological image classification

Automated, as well as accurate classification with breast cancer histological images, was crucial for medical applications because of detecting malignant tumors via histopathological images. In this work create a Fourier ptychographic (FP) and deep learning using breast cancer histopathological image classification. Here the FP method used in the process begins with such a random guess that builds a high-resolution complex hologram, subsequently uses iterative retrieval using FP constraints to stitch around each other low-resolution multi-view means of production owned from either the hologram's high-resolution hologram's elemental images captured via integral imaging. Next, the feature extraction process includes entropy, geometrical features, and textural features. The entropy-based normalization is used to optimize the features. Finally, it attains the classification process of the proposed ENDNN classifies the breast cancer images into normal or abnormal. The experimental outcomes demonstrate that our presented technique overtakes the traditional techniques.

Classifying Chewing and Rumination in Dairy Cows Using Sound Signals and Machine Learning

This research paper introduces a novel methodology for classifying jaw movements in dairy cattle into four distinct categories: bites, exclusive chews, chew-bite combinations, and exclusive sorting, under conditions of tall and short particle sizes in wheat straw and Alfalfa hay feeding. Sound signals were recorded and transformed into images using a short-time Fourier transform. A total of 31 texture features were extracted using the gray level co-occurrence matrix, spatial gray level dependence method, gray level run length method, and gray level difference method. Genetic Algorithm (GA) was applied to the data to select the most important features. Six distinct classifiers were employed to classify the jaw movements. The total precision found was 91.62%, 94.48%, 95.9%, 92.8%, 94.18%, and 89.62% for Naive Bayes, k-nearest neighbor, support vector machine, decision tree, multi-layer perceptron, and k-means clustering, respectively. The results of this study provide valuable insights into the nutritional behavior and dietary patterns of dairy cattle. The understanding of how cows consume different types of feed and the identification of any potential health issues or deficiencies in their diets are enhanced by the accurate classification of jaw movements. This information can be used to improve feeding practices, reduce waste, and ensure the well-being and productivity of the cows. The methodology introduced in this study can serve as a valuable tool for livestock managers to evaluate the nutrition of their dairy cattle and make informed decisions about their feeding practices.

Textural Analysis of the Hyperdense Artery Sign in Patients with Acute Ischemic Stroke Predicts the Outcome of Thrombectomy

Textural analysis is pivotal in augmenting the diagnosis and outcomes of endovascular procedures for stroke patients. Due to the detection of changes imperceptible to the human eye, this type of analysis can potentially aid in deciding the optimal type of endovascular treatment. We included 40 patients who suffered from acute ischemic stroke caused by large vessel occlusion, and calculated 130 different textural features based on the non-enhanced CT scan using an open-source software (3D Slicer). Using chi-squared and Mann-Whitney tests and receiver operating characteristics analysis, we identified a total of 21 different textural parameters capable of predicting the outcome of thrombectomy (quantified as the mTICI score), with variable sensitivity (50-97.9%) and specificity (64.6-99.4%) rates. In conclusion, CT-based radiomics features are potential factors that can predict the outcome of thrombectomy in patients suffering from acute ischemic stroke, aiding in the decision between aspiration, mechanical, or combined thrombectomy procedure.

Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer

Objective

The purpose of this research was to develop a radiomics model that combines several clinical features for preoperative prediction of the pathological grade of bladder cancer (BCa) using non-enhanced computed tomography (NE-CT) scanning images.

Materials and methods

The computed tomography (CT), clinical, and pathological data of 105 BCa patients attending our hospital between January 2017 and August 2022 were retrospectively evaluated. The study cohort comprised 44 low-grade BCa and 61 high-grade BCa patients. The subjects were randomly divided into training (n = 73) and validation (n = 32) cohorts at a ratio of 7:3. Radiomic features were extracted from NE-CT images. A total of 15 representative features were screened using the least absolute shrinkage and selection operator (LASSO) algorithm. Based on these characteristics, six models for predicting BCa pathological grade, including support vector machine (SVM), k-nearest neighbor (KNN), gradient boosting decision tree (GBDT), logical regression (LR), random forest (RF), and extreme gradient boosting (XGBOOST) were constructed. The model combining radiomics score and clinical factors was further constructed. The predictive performance of the models was evaluated based on the area under the receiver operating characteristic (ROC) curve, DeLong test, and decision curve analysis (DCA).

Results

The selected clinical factors for the model included age and tumor size. LASSO regression analysis identified 15 features most linked to BCa grade, which were included in the machine learning model. The SVM analysis revealed that the highest AUC of the model was 0.842. A nomogram combining the radiomics signature and selected clinical variables showed accurate prediction of the pathological grade of BCa preoperatively. The AUC of the training cohort was 0.919, whereas that of the validation cohort was 0.854. The clinical value of the combined radiomics nomogram was validated using calibration curve and DCA.

Conclusion

Machine learning models combining CT semantic features and the selected clinical variables can accurately predict the pathological grade of BCa, offering a non-invasive and accurate approach for predicting the pathological grade of BCa preoperatively.

Lack of repeatability of radiomic features derived from PET scans: Results from a 18 F-DCFPyL test-retest cohort

OBJECTIVES

PET-based radiomic metrics are increasingly utilized as predictive image biomarkers. However, the repeatability of radiomic features on PET has not been assessed in a test-retest setting. The prostate-specific membrane antigen-targeted compound ¹⁸ F-DCFPyL is a high-affinity, high-contrast PET agent that we utilized in a test-retest cohort of men with metastatic prostate cancer (PC).

METHODS

Data of 21 patients enrolled in a prospective clinical trial with histologically proven PC underwent two ¹⁸ F-DCFPyL PET scans within 7 days, using identical acquisition and reconstruction parameters. Sites of disease were segmented and a set of 29 different radiomic parameters were assessed on both scans. We determined repeatability of quantification by using Pearson's correlations, within-subject coefficient of variation (wCOV), and Bland-Altman analysis.

RESULTS

In total, 230 lesions (177 bone, 38 lymph nodes, 15 others) were assessed on both scans. For all investigated radiomic features, a broad range of inter-scan correlation was found (r, 0.07-0.95), with acceptable reproducibility for entropy and homogeneity (wCOV, 16.0% and 12.7%, respectively). On Bland-Altman analysis, no systematic increase or decrease between the scans was observed for either parameter (±1.96 SD: 1.07/-1.30, 0.23/-0.18, respectively). The remaining 27 tested radiomic metrics, however, achieved unacceptable high wCOV (≥21.7%).

CONCLUSION

Many common radiomic features derived from a test-retest PET study had poor repeatability. Only Entropy and homogeneity achieved good repeatability, supporting the notion that those image biomarkers may be incorporated in future clinical trials. Those radiomic features based on high frequency aspects of images appear to lack the repeatability on PET to justify further study.

Radiogenomics Reveals Correlation between Quantitative Texture Radiomic Features of Biparametric MRI and Hypoxia-Related Gene Expression in Men with Localised Prostate Cancer

OBJECTIVES

To perform multiscale correlation analysis between quantitative texture feature phenotypes of pre-biopsy biparametric MRI (bpMRI) and targeted sequence-based RNA expression for hypoxia-related genes.

MATERIALS AND METHODS

Images from pre-biopsy 3T bpMRI scans in clinically localised PCa patients of various risk categories (n = 15) were used to extract textural features. The genomic landscape of hypoxia-related gene expression was obtained using post-radical prostatectomy tissue for targeted RNA expression profiling using the TempO-sequence method. The nonparametric Games Howell test was used to correlate the differential expression of the important hypoxia-related genes with 28 radiomic texture features. Then, cBioportal was accessed, and a gene-specific query was executed to extract the Oncoprint genomic output graph of the selected hypoxia-related genes from The Cancer Genome Atlas (TCGA). Based on each selected gene profile, correlation analysis using Pearson's coefficients and survival analysis using Kaplan-Meier estimators were performed.

RESULTS

The quantitative bpMR imaging textural features, including the histogram and grey level co-occurrence matrix (GLCM), correlated with three hypoxia-related genes (ANGPTL4, VEGFA, and P4HA1) based on RNA sequencing using the TempO-Seq method. Further radiogenomic analysis, including data accessed from the cBioportal genomic database, confirmed that overexpressed hypoxia-related genes significantly correlated with a poor survival outcomes, with a median survival ratio of 81.11:133.00 months in those with and without alterations in genes, respectively.

CONCLUSION

This study found that there is a correlation between the radiomic texture features extracted from bpMRI in localised prostate cancer and the hypoxia-related genes that are differentially expressed. The analysis of expression data based on cBioportal revealed that these hypoxia-related genes, which were the focus of the study, are linked to an unfavourable survival outcomes in prostate cancer patients.

Complete Response Evaluation of Locally Advanced Rectal Cancer to Neoadjuvant Chemoradiotherapy Using Textural Features Obtained from T2 Weighted Imaging and ADC Maps

BACKGROUND

The prediction of pathological responses for locally advanced rectal cancer using magnetic resonance imaging (MRI) after neoadjuvant chemoradiotherapy (CRT) is a challenging task for radiologists, as residual tumor cells can be mistaken for fibrosis. Texture analysis of MR images has been proposed to understand the underlying pathology.

OBJECTIVE

This study aimed to assess the responses of lesions to CRT in patients with locally advanced rectal cancer using the first-order textural features of MRI T2-weighted imaging (T2-WI) and apparent diffusion coefficient (ADC) maps.

METHODS

Forty-four patients with locally advanced rectal cancer (median age: 57 years) who underwent MRI before and after CRT were enrolled in this retrospective study. The first-order textural parameters of tumors on T2-WI and ADC maps were extracted. The textural features of lesions in pathologic complete responders were compared to partial responders using Student's t- or Mann-Whitney U tests. A comparison of textural features before and after CRT for each group was performed using the Wilcoxon rank sum test. Receiver operating characteristic curves were calculated to detect the diagnostic performance of the ADC.

RESULTS

Of the 44 patients evaluated, 22 (50%) were placed in a partial response group and 50% were placed in a complete response group. The ADC changes of the complete responders were statistically more significant than those of the partial responders (P = 0.002). Pathologic total response was predicted with an ADC cut-off of 1310 x 10-6 mm2/s, with a sensitivity of 72%, a specificity of 77%, and an accuracy of 78.1% after neoadjuvant CRT. The skewness of the T2-WI before and after neoadjuvant CRT showed a significant difference in the complete response group compared to the partial response group (P = 0.001 for complete responders vs. P = 0.482 for partial responders). Also, relative T2-WI signal intensity in the complete response group was statistically lower than that of the partial response group after neoadjuvant CRT (P = 0.006).

CONCLUSION

As a result of the conversion of tumor cells to fibrosis, the skewness of the T2-WI before and after neoadjuvant CRT was statistically different in the complete response group compared to the partial response group, and the complete response group showed statistically lower relative T2-WI signal intensity than the partial response group after neoadjuvant CRT. Additionally, the ADC cut-off value of 1310 × 10-6 mm2/s could be used as a marker for complete response along with absolute ADC value changes within this dataset.

Prognostic Value of Metabolic, Volumetric and Textural Parameters of Baseline [18F]FDG PET/CT in Early Triple-Negative Breast Cancer

Simple Summary

The aim of this study was to evaluate PET/CT parameters to determine different prognostic groups in TNBC, in order to select patients with a high risk of relapse, for whom therapeutic escalation can be considered. We have demonstrated that the MTV, TLG and entropy of the primary breast lesion could be of interest to predict the prognostic outcome of TNBC patients.

Abstract

(1) Background: triple-negative breast cancer (TNBC) remains a clinical and therapeutic challenge primarily affecting young women with poor prognosis. TNBC is currently treated as a single entity but presents a very diverse profile in terms of prognosis and response to treatment. Positron emission tomography/computed tomography (PET/CT) with ¹⁸F-fluorodeoxyglucose ([¹⁸F]FDG) is gaining importance for the staging of breast cancers. TNBCs often show high [¹⁸F]FDG uptake and some studies have suggested a prognostic value for metabolic and volumetric parameters, but no study to our knowledge has examined textural features in TNBC. The objective of this study was to evaluate the association between metabolic, volumetric and textural parameters measured at the initial [¹⁸F]FDG PET/CT and disease-free survival (DFS) and overall survival (OS) in patients with nonmetastatic TBNC. (2) Methods: all consecutive nonmetastatic TNBC patients who underwent a [¹⁸F]FDG PET/CT examination upon diagnosis between 2012 and 2018 were retrospectively included. The metabolic and volumetric parameters (SUV_max, SUV_mean, SUV_peak, MTV, and TLG) and the textural features (entropy, homogeneity, SRE, LRE, LGZE, and HGZE) of the primary tumor were collected. (3) Results: 111 patients were enrolled (median follow-up: 53.6 months). In the univariate analysis, high TLG, MTV and entropy values of the primary tumor were associated with lower DFS (p = 0.008, p = 0.006 and p = 0.025, respectively) and lower OS (p = 0.002, p = 0.001 and p = 0.046, respectively). The discriminating thresholds for two-year DFS were calculated as 7.5 for MTV, 55.8 for TLG and 2.6 for entropy. The discriminating thresholds for two-year OS were calculated as 9.3 for MTV, 57.4 for TLG and 2.67 for entropy. In the multivariate analysis, lymph node involvement in PET/CT was associated with lower DFS (p = 0.036), and the high MTV of the primary tumor was correlated with lower OS (p = 0.014). (4) Conclusions: textural features associated with metabolic and volumetric parameters of baseline [¹⁸F]FDG PET/CT have a prognostic value for identifying high-relapse-risk groups in early TNBC patients.

Virtual Biopsy for Diagnosis of Chemotherapy-Associated Liver Injuries and Steatohepatitis: A Combined Radiomic and Clinical Model in Patients with Colorectal Liver Metastases

Non-invasive diagnosis of chemotherapy-associated liver injuries (CALI) is still an unmet need. The present study aims to elucidate the contribution of radiomics to the diagnosis of sinusoidal dilatation (SinDil), nodular regenerative hyperplasia (NRH), and non-alcoholic steatohepatitis (NASH). Patients undergoing hepatectomy for colorectal metastases after chemotherapy (January 2018-February 2020) were retrospectively analyzed. Radiomic features were extracted from a standardized volume of non-tumoral liver parenchyma outlined in the portal phase of preoperative post-chemotherapy computed tomography. Seventy-eight patients were analyzed: 25 had grade 2-3 SinDil, 27 NRH, and 14 NASH. Three radiomic fingerprints independently predicted SinDil: GLRLM_f3 (OR = 12.25), NGLDM_f1 (OR = 7.77), and GLZLM_f2 (OR = 0.53). Combining clinical, laboratory, and radiomic data, the predictive model had accuracy = 82%, sensitivity = 64%, and specificity = 91% (AUC = 0.87 vs. AUC = 0.77 of the model without radiomics). Three radiomic parameters predicted NRH: conventional_HUQ2 (OR = 0.76), GLZLM_f2 (OR = 0.05), and GLZLM_f3 (OR = 7.97). The combined clinical/laboratory/radiomic model had accuracy = 85%, sensitivity = 81%, and specificity = 86% (AUC = 0.91 vs. AUC = 0.85 without radiomics). NASH was predicted by conventional_HUQ2 (OR = 0.79) with accuracy = 91%, sensitivity = 86%, and specificity = 92% (AUC = 0.93 vs. AUC = 0.83 without radiomics). In the validation set, accuracy was 72%, 71%, and 91% for SinDil, NRH, and NASH. Radiomic analysis of liver parenchyma may provide a signature that, in combination with clinical and laboratory data, improves the diagnosis of CALI.

Evaluation of FET PET Radiomics Feature Repeatability in Glioma Patients

Simple Summary

Initial studies suggested the additional diagnostic value of amino acid positron emission tomography (PET) radiomics using the tracer O-(2-[¹⁸F]fluoroethyl)-L-tyrosine (FET) in brain tumor patient management. However, to ensure the reliable performance of the generated FET PET radiomics models for clinical diagnostics, repeatability of radiomics features is essential. Hence, we assessed the impact of brain tumor volumes and key molecular alterations such as an isocitrate dehydrogenase (IDH) mutation on the repeatability of FET PET radiomics features in 50 newly diagnosed glioma patients. In a test–retest approach based on routinely acquired FET PET scans, we identified 297 repeatable features. The IDH genotype did not affect feature repeatability. Moreover, these robust features were able to differentiate patients with IDH-wildtype glioma from those with an IDH mutation. Our results suggest that robust radiomics features can be obtained from routinely acquired FET PET scans, which are valuable for further standardization of radiomics analyses in neurooncology.

Abstract

Amino acid PET using the tracer O-(2-[¹⁸F]fluoroethyl)-L-tyrosine (FET) has attracted considerable interest in neurooncology. Furthermore, initial studies suggested the additional diagnostic value of FET PET radiomics in brain tumor patient management. However, the conclusiveness of radiomics models strongly depends on feature generalizability. We here evaluated the repeatability of feature-based FET PET radiomics. A test–retest analysis based on equivalent but statistically independent subsamples of FET PET images was performed in 50 newly diagnosed and histomolecularly characterized glioma patients. A total of 1,302 radiomics features were calculated from semi-automatically segmented tumor volumes-of-interest (VOIs). Furthermore, to investigate the influence of the spatial resolution of PET on repeatability, spherical VOIs of different sizes were positioned in the tumor and healthy brain tissue. Feature repeatability was assessed by calculating the intraclass correlation coefficient (ICC). To further investigate the influence of the isocitrate dehydrogenase (IDH) genotype on feature repeatability, a hierarchical cluster analysis was performed. For tumor VOIs, 73% of first-order features and 71% of features extracted from the gray level co-occurrence matrix showed high repeatability (ICC 95% confidence interval, 0.91–1.00). In the largest spherical tumor VOIs, 67% of features showed high repeatability, significantly decreasing towards smaller VOIs. The IDH genotype did not affect feature repeatability. Based on 297 repeatable features, two clusters were identified separating patients with IDH-wildtype glioma from those with an IDH mutation. Our results suggest that robust features can be obtained from routinely acquired FET PET scans, which are valuable for further standardization of radiomics analyses in neurooncology.

FET PET Radiomics for Differentiating Pseudoprogression from Early Tumor Progression in Glioma Patients Post-Chemoradiation

Simple Summary

Following chemoradiation with alkylating agents in glioma patients, structural magnetic resonance imaging (MRI) may suggest tumor progression which subsequently improves during the course of the disease without any treatment change. This phenomenon has been termed pseudoprogression. Despite advances in medical imaging, a reliable diagnosis of pseudoprogression remains a challenging task. Radiomics is a subdiscipline of artificial intelligence and allows the identification and extraction of imaging features from various routine imaging modalities. These features can be used for the generation of mathematical models to improve diagnostics in patients with brain tumors. The present study highlights the potential of radiomics obtained from amino acid positron emission tomography (PET) for the diagnosis of pseudoprogression. In 34 patients with suspicious MRI early after chemoradiation completion, our radiomics model correctly identified all patients with pseudoprogression.

Abstract

Currently, a reliable diagnostic test for differentiating pseudoprogression from early tumor progression is lacking. We explored the potential of O-(2-[¹⁸F]fluoroethyl)-L-tyrosine (FET) positron emission tomography (PET) radiomics for this clinically important task. Thirty-four patients (isocitrate dehydrogenase (IDH)-wildtype glioblastoma, 94%) with progressive magnetic resonance imaging (MRI) changes according to the Response Assessment in Neuro-Oncology (RANO) criteria within the first 12 weeks after completing temozolomide chemoradiation underwent a dynamic FET PET scan. Static and dynamic FET PET parameters were calculated. For radiomics analysis, the number of datasets was increased to 102 using data augmentation. After randomly assigning patients to a training and test dataset, 944 features were calculated on unfiltered and filtered images. The number of features for model generation was limited to four to avoid data overfitting. Eighteen patients were diagnosed with early tumor progression, and 16 patients had pseudoprogression. The FET PET radiomics model correctly diagnosed pseudoprogression in all test cohort patients (sensitivity, 100%; negative predictive value, 100%). In contrast, the diagnostic performance of the best FET PET parameter (TBR_max) was lower (sensitivity, 81%; negative predictive value, 80%). The results suggest that FET PET radiomics helps diagnose patients with pseudoprogression with a high diagnostic performance. Given the clinical significance, further studies are warranted.

Study of morphological and textural features for classification of oral squamous cell carcinoma by traditional machine learning techniques

BACKGROUND

Oral squamous cell carcinoma (OSCC) is the most prevalent form of oral cancer. Very few researches have been carried out for the automatic diagnosis of OSCC using artificial intelligence techniques. Though biopsy is the ultimate test for cancer diagnosis, analyzing a biopsy report is a very much challenging task. To develop computer-assisted software that will diagnose cancerous cells automatically is very important and also a major need of the hour.

AIM

To identify OSCC based on morphological and textural features of hand-cropped cell nuclei by traditional machine learning methods.

METHODS

In this study, a structure for semi-automated detection and classification of oral cancer from microscopic biopsy images of OSCC, using clinically significant and biologically interpretable morphological and textural features, are examined and proposed. Forty biopsy slides were used for the study from which a total of 452 hand-cropped cell nuclei has been considered for morphological and textural feature extraction and further analysis. After making a comparative analysis of commonly used methods in the segmentation technique, a combined technique is proposed. Our proposed methodology achieves the best segmentation of the nuclei. Henceforth the features extracted were fed into five classifiers, support vector machine, logistic regression, linear discriminant, k-nearest neighbors and decision tree classifier. Classifiers were also analyzed by training time. Another contribution of the study is a large indigenous cell level dataset of OSCC biopsy images.

RESULTS

We achieved 99.78% accuracy applying decision tree classifier in classifying OSCC using morphological and textural features.

CONCLUSION

It is found that both morphological and textural features play a very important role in OSCC diagnosis. It is hoped that this type of framework will help the clinicians/pathologists in OSCC diagnosis.

Dynamic contrast-enhanced MRI differentiates hepatocellular carcinoma from hepatic metastasis of rectal cancer by extracting pharmacokinetic parameters and radiomic features

The aim of the present study was to explore how dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) may differentiate hepatocellular carcinoma (HCC) from hepatic metastasis of rectal cancer (HMRC) by extracting pharmacokinetic parameters and radiomic features. A total of 75 patients, including 41 cases with HCC and 34 cases with HMRC, underwent DCE-MRI examination. Dual-input two-compartment extended Tofts tracer kinetic model attached to a specialized image post-processing software package from OmniKinetics; GE Healthcare was used to calculate the values of the pharmacokinetic parameters and radiomic features, which were extracted from the lesions at the same region of interest. These values were evaluated using Student's t-test and receiver operating characteristic curves, and discriminant models were built to differentiate between HCC and HRMC. The results identified statistically significant differences in the values of the pharmacokinetic parameters hepatic perfusion index (HPI), endothelial transfer constant (K^trans), initial area under the gadolinium concentration curve during the first 60 sec (IAUC) between the HCC and HRMC groups. In addition, statistically significant differences in 17 radiomic features were observed between the two groups (P<0.05). The areas under the receiver operating characteristic (ROC) curves of the pharmacokinetic parameters K^trans, IAUC and HPI were 0.73, 0.77 and 0.67, respectively. The range of the areas under the ROC curves of the 17 radiomic features with statistical differences was 0.63-0.79. In addition, when pharmacokinetic parameters and radiomic features were incorporated, the area under the ROC curve was 0.86. The accuracy of Fisher's discriminant analysis model based on radiomic features was 89.3%, and the leave-one-out cross-validation accuracy was 80.0%. In conclusion, DCE-MRI was demonstrated to be useful in the differential diagnosis of HCC and HMRC by extracting pharmacokinetic parameters and radiomic features, and incorporation of the two paths improved the diagnostic efficacy. A discriminant model based on radiomic features further enhanced the identification of HCC and HMRC.

Predicting response to radiotherapy in tumors with PET/CT: when and how?

Radiotherapy is one of the main methods for tumor treatment, with the improved radiotherapy delivery technique to combat cancer, there is a growing interest for finding effective and feasible ways to predict tumor radiosensitivity. Based on a series of changes in metabolism, microvessel density, hypoxic microenvironment, and cytokines of tumors after radiotherapy, a variety of radiosensitivity detection methods have been studied. Among the detection methods, positron emission tomography-computed tomography (PET/CT) is a feasible tool for response evaluation following definitive radiotherapy for cancers with a high negative predictive value. The prognostic or predictive value of PET/CT is currently being studied widely. However, there are many unresolved issues, such as the optimal probe of PET/CT for radiosensitivity prediction, the selection of the most useful PET/CT parameters and their optimal cut-offs such as total lesion glycolysis (TLG), metabolic tumor volume (MTV) and standardized uptake value (SUV), and the optimal timing of PET/CT pre-treatment, during or following RT. Different radiosensitivity of tumors, modes of radiotherapy action and fraction scheduling may complicate the appropriate choice. In this study, we will discuss the diverse methods for evaluating radiosensitivity, and will also focus on the selection of the optimal probe, timing, cut-offs and parameters of PET/CT for evaluating the radiotherapy response.

PET/MRI Radiomics in Patients With Brain Metastases

Although a variety of imaging modalities are used or currently being investigated for patients with brain tumors including brain metastases, clinical image interpretation to date uses only a fraction of the underlying complex, high-dimensional digital information from routinely acquired imaging data. The growing availability of high-performance computing allows the extraction of quantitative imaging features from medical images that are usually beyond human perception. Using machine learning techniques and advanced statistical methods, subsets of such imaging features are used to generate mathematical models that represent characteristic signatures related to the underlying tumor biology and might be helpful for the assessment of prognosis or treatment response, or the identification of molecular markers. The identification of appropriate, characteristic image features as well as the generation of predictive or prognostic mathematical models is summarized under the term radiomics. This review summarizes the current status of radiomics in patients with brain metastases.

Automatic A-line coronary plaque classification using combined deep learning and textural features in intravascular OCT images

We developed a fully automated method for classifying A-line coronary plaques in intravascular optical coherence tomography images using combined deep learning and textural features. The proposed method was trained on 4,292 images from 48 pullbacks giving 80 manually labeled, volumes of interest. Preprocessing steps including guidewire/shadow removal, lumen boundary detection, pixel shifting, and noise reduction were employed. We built a convolutional neural network to extract the deep learning features from the preprocessed image. Traditional textural features were also extracted and combined with deep learning features. Feature selection was performed using the minimum redundancy maximum relevance method. Combined features were utilized as inputs for a random forest classifier. After classification, conditional random field (CRF) method was used for classification noise cleaning. We determined a sub-feature set with the most predictive power. With CRF noise cleaning, sensitivities/specificities were 82.2%/90.8% and 82.4%/89.2% for fibrolipidic and fibrocalcific classes, respectively, with good Dice coefficients. The classification noise cleaning step improved performance metrics by nearly 10-15%. The predicted en face classification maps of entire pullbacks agreed favorably to the manually labeled counterparts. Both assessments suggested that our automated measurements gave clinically relevant results. The proposed method is very promising with regards to both clinical treatment planning and research applications.

Reproducibility with repeat CT in radiomics study for rectal cancer

Purpose

To evaluate the reproducibility of radiomics features by repeating computed tomographic (CT) scans in rectal cancer. To choose stable radiomics features for rectal cancer.

Results

Volume normalized features are much more reproducible than unnormalized features. The average value of all slices is the most reproducible feature type in rectal cancer. Different filters have little effect for the reproducibility of radiomics features. For the average type features, 496 out of 775 features showed high reproducibility (ICC ≥ 0.8), 225 out of 775 features showed medium reproducibility (0.8 > ICC ≥ 0.5) and 54 out of 775 features showed low reproducibility (ICC < 0.5).

Methods

40 rectal cancer patients with stage II were enrolled in this study, each of whom underwent two CT scans within average 8.7 days. 775 radiomics features were defined in this study. For each features, five different values (value from the largest slice, maximum value, minimum value, average value of all slices and value from superposed intermediate matrix) were extracted. Meanwhile a LOG filter with different parameters was applied to these images to find stable filter value. Concordance correlation coefficients (CCC) and inter-class correlation coefficients (ICC) of two CT scans were calculated to assess the reproducibility, based on original features and volume normalized features.

Conclusions

Features are recommended to be normalized to volume in radiomics analysis. The average type radiomics features are the most stable features in rectal cancer. Further analysis of these features of rectal cancer can be warranted for treatment monitoring and prognosis prediction.

Low-cost oblique illumination: an image quality assessment

We study the effectiveness of several low-cost oblique illumination filters to improve overall image quality, in comparison with standard bright field imaging. For this purpose, a dataset composed of 3360 diatom images belonging to 21 taxa was acquired. Subjective and objective image quality assessments were done. The subjective evaluation was performed by a group of diatom experts by psychophysical test where resolution, focus, and contrast were assessed. Moreover, some objective nonreference image quality metrics were applied to the same image dataset to complete the study, together with the calculation of several texture features to analyze the effect of these filters in terms of textural properties. Both image quality evaluation methods, subjective and objective, showed better results for images acquired using these illumination filters in comparison with the no filtered image. These promising results confirm that this kind of illumination filters can be a practical way to improve the image quality, thanks to the simple and low cost of the design and manufacturing process.

Determining Image Processing Features Describing the Appearance of Challenging Mitotic Figures and Miscounted Nonmitotic Objects

Context:

Previous studies showed that the agreement among pathologists in recognition of mitoses in breast slides is fairly modest.

Aims:

Determining the significantly different quantitative features among easily identifiable mitoses, challenging mitoses, and miscounted nonmitoses within breast slides and identifying which color spaces capture the difference among groups better than others.

Materials and Methods:

The dataset contained 453 mitoses and 265 miscounted objects in breast slides. The mitoses were grouped into three categories based on the confidence degree of three pathologists who annotated them. The mitoses annotated as “probably a mitosis” by the majority of pathologists were considered as the challenging category. The miscounted objects were recognized as a mitosis or probably a mitosis by only one of the pathologists. The mitoses were segmented using k-means clustering, followed by morphological operations. Morphological, intensity-based, and textural features were extracted from the segmented area and also the image patch of 63 × 63 pixels in different channels of eight color spaces. Holistic features describing the mitoses' surrounding cells of each image were also extracted.

Statistical Analysis Used:

The Kruskal–Wallis H-test followed by the Tukey-Kramer test was used to identify significantly different features.

Results:

The results indicated that challenging mitoses were smaller and rounder compared to other mitoses. Among different features, the Gabor textural features differed more than others between challenging mitoses and the easily identifiable ones. Sizes of the non-mitoses were similar to easily identifiable mitoses, but nonmitoses were rounder. The intensity-based features from chromatin channels were the most discriminative features between the easily identifiable mitoses and the miscounted objects.

Conclusions:

Quantitative features can be used to describe the characteristics of challenging mitoses and miscounted nonmitotic objects.

Pretreatment 18F-FDG PET Textural Features in Locally Advanced Non-Small Cell Lung Cancer: Secondary Analysis of ACRIN 6668/RTOG 0235

In a secondary analysis of American College of Radiology Imaging Network (ACRIN) 6668/RTOG 0235, high pretreatment metabolic tumor volume (MTV) on (18)F-FDG PET was found to be a poor prognostic factor for patients treated with chemoradiotherapy for locally advanced non-small cell lung cancer (NSCLC). Here we utilize the same dataset to explore whether heterogeneity metrics based on PET textural features can provide additional prognostic information.

METHODS

Patients with locally advanced NSCLC underwent (18)F-FDG PET prior to treatment. A gradient-based segmentation tool was used to contour each patient's primary tumor. MTV, maximum SUV, and 43 textural features were extracted for each tumor. To address overfitting and high collinearity among PET features, the least absolute shrinkage and selection operator (LASSO) method was applied to identify features that were independent predictors of overall survival (OS) after adjusting for MTV. Recursive binary partitioning in a conditional inference framework was utilized to identify optimal thresholds. Kaplan-Meier curves and log-rank testing were used to compare outcomes among patient groups.

RESULTS

Two hundred one patients met inclusion criteria. The LASSO procedure identified 1 textural feature (SumMean) as an independent predictor of OS. The optimal cutpoint for MTV was 93.3 cm(3), and the optimal SumMean cutpoint for tumors above 93.3 cm(3) was 0.018. This grouped patients into three categories: low tumor MTV (n = 155; median OS, 22.6 mo), high tumor MTV and high SumMean (n = 23; median OS, 20.0 mo), and high tumor MTV and low SumMean (n = 23; median OS, 6.2 mo; log-rank P < 0.001).

CONCLUSION

We have described an appropriate methodology to evaluate the prognostic value of textural PET features in the context of established prognostic factors. We have also identified a promising feature that may have prognostic value in locally advanced NSCLC patients with large tumors who are treated with chemoradiotherapy. Validation studies are warranted.

Quantitative radiomics: impact of stochastic effects on textural feature analysis implies the need for standards

Image heterogeneity metrics such as textural features are an active area of research for evaluating clinical outcomes with positron emission tomography (PET) imaging and other modalities. However, the effects of stochastic image acquisition noise on these metrics are poorly understood. We performed a simulation study by generating 50 statistically independent PET images of the NEMA IQ phantom with realistic noise and resolution properties. Heterogeneity metrics based on gray-level intensity histograms, co-occurrence matrices, neighborhood difference matrices, and zone size matrices were evaluated within regions of interest surrounding the lesions. The impact of stochastic variability was evaluated with percent difference from the mean of the 50 realizations, coefficient of variation and estimated sample size for clinical trials. Additionally, sensitivity studies were performed to simulate the effects of patient size and image reconstruction method on the quantitative performance of these metrics. Complex trends in variability were revealed as a function of textural feature, lesion size, patient size, and reconstruction parameters. In conclusion, the sensitivity of PET textural features to normal stochastic image variation and imaging parameters can be large and is feature-dependent. Standards are needed to ensure that prospective studies that incorporate textural features are properly designed to measure true effects that may impact clinical outcomes.

18F-FDG PET uptake characterization through texture analysis: investigating the complementary nature of heterogeneity and functional tumor volume in a multi-cancer site patient cohort

Intratumoral uptake heterogeneity in (18)F-FDG PET has been associated with patient treatment outcomes in several cancer types. Textural feature analysis is a promising method for its quantification. An open issue associated with textural features for the quantification of intratumoral heterogeneity concerns its added contribution and dependence on the metabolically active tumor volume (MATV), which has already been shown to be a significant predictive and prognostic parameter. Our objective was to address this question using a larger cohort of patients covering different cancer types.

METHODS

A single database of 555 pretreatment (18)F-FDG PET images (breast, cervix, esophageal, head and neck, and lung cancer tumors) was assembled. Four robust and reproducible textural feature-derived parameters were considered. The issues associated with the calculation of textural features using co-occurrence matrices (such as the quantization and spatial directionality relationships) were also investigated. The relationship between these features and MATV, as well as among the features themselves, was investigated using Spearman rank coefficients for different volume ranges. The complementary prognostic value of MATV and textural features was assessed through multivariate Cox analysis in the esophageal and non-small cell lung cancer (NSCLC) cohorts.

RESULTS

A large range of MATVs was included in the population considered (3-415 cm(3); mean, 35; median, 19; SD, 50). The correlation between MATV and textural features varied greatly depending on the MATVs, with reduced correlation for increasing volumes. These findings were reproducible across the different cancer types. The quantization and calculation methods both had an impact on the correlation. Volume and heterogeneity were independent prognostic factors (P = 0.0053 and 0.0093, respectively) along with stage (P = 0.002) in non-small cell lung cancer, but in the esophageal tumors, volume and heterogeneity had less complementary value because of smaller overall volumes.

CONCLUSION

Our results suggest that heterogeneity quantification and volume may provide valuable complementary information for volumes above 10 cm(3), although the complementary information increases substantially with larger volumes.

Visual versus quantitative assessment of intratumor 18F-FDG PET uptake heterogeneity: prognostic value in non-small cell lung cancer

The goal of this study was to compare visual assessment of intratumor (18)F-FDG PET uptake distribution with a textural-features (TF) automated quantification and to establish their respective prognostic value in non-small cell lung cancer (NSCLC).

METHODS

The study retrospectively included 102 consecutive patients. Only primary tumors were considered. Intratumor heterogeneity was visually scored (3-level scale [Hvisu]) by 2 nuclear medicine physicians. Tumor volumes were automatically delineated, and heterogeneity was quantified with TF. Mean and maximum standardized uptake value were also included. Visual interobserver agreement and correlations with quantitative assessment were evaluated using the κ test and Spearman rank (ρ) coefficient, respectively. Association with overall survival and recurrence-free survival was investigated using the Kaplan-Meier method and Cox regression models.

RESULTS

Moderate correlations (0.4 < ρ < 0.6) between TF parameters and Hvisu were observed. Interobserver agreement for Hvisu was moderate (κ = 0.64, discrepancies in 27% of the cases). High standardized uptake value, large metabolic volumes, and high heterogeneity according to TF were associated with poorer overall survival and recurrence-free survival and remained an independent prognostic factor of overall survival with respect to clinical variables.

CONCLUSION

Quantification of (18)F-FDG uptake heterogeneity in NSCLC through TF was correlated with visual assessment by experts. However, TF also constitutes an objective heterogeneity quantification, with reduced interobserver variability, and independent prognostic value potentially useful for patient stratification and management.

Automated classification of immunostaining patterns in breast tissue from the human protein atlas

BACKGROUND

The Human Protein Atlas (HPA) is an effort to map the location of all human proteins (http://www.proteinatlas.org/). It contains a large number of histological images of sections from human tissue. Tissue micro arrays (TMA) are imaged by a slide scanning microscope, and each image represents a thin slice of a tissue core with a dark brown antibody specific stain and a blue counter stain. When generating antibodies for protein profiling of the human proteome, an important step in the quality control is to compare staining patterns of different antibodies directed towards the same protein. This comparison is an ultimate control that the antibody recognizes the right protein. In this paper, we propose and evaluate different approaches for classifying sub-cellular antibody staining patterns in breast tissue samples.

MATERIALS AND METHODS

The proposed methods include the computation of various features including gray level co-occurrence matrix (GLCM) features, complex wavelet co-occurrence matrix (CWCM) features, and weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHARM)-inspired features. The extracted features are used into two different multivariate classifiers (support vector machine (SVM) and linear discriminant analysis (LDA) classifier). Before extracting features, we use color deconvolution to separate different tissue components, such as the brownly stained positive regions and the blue cellular regions, in the immuno-stained TMA images of breast tissue.

RESULTS

We present classification results based on combinations of feature measurements. The proposed complex wavelet features and the WND-CHARM features have accuracy similar to that of a human expert.

CONCLUSIONS

Both human experts and the proposed automated methods have difficulties discriminating between nuclear and cytoplasmic staining patterns. This is to a large extent due to mixed staining of nucleus and cytoplasm. Methods for quantification of staining patterns in histopathology have many applications, ranging from antibody quality control to tumor grading.

A comparison study of image features between FFDM and film mammogram images

PURPOSE

This work is to provide a direct, quantitative comparison of image features measured by film and full-field digital mammography (FFDM). The purpose is to investigate whether there is any systematic difference between film and FFDM in terms of quantitative image features and their influence on the performance of a computer-aided diagnosis (CAD) system.

METHODS

The authors make use of a set of matched film-FFDM image pairs acquired from cadaver breast specimens with simulated microcalcifications consisting of bone and teeth fragments using both a GE digital mammography system and a screen-film system. To quantify the image features, the authors consider a set of 12 textural features of lesion regions and six image features of individual microcalcifications (MCs). The authors first conduct a direct comparison on these quantitative features extracted from film and FFDM images. The authors then study the performance of a CAD classifier for discriminating between MCs and false positives (FPs) when the classifier is trained on images of different types (film, FFDM, or both).

RESULTS

For all the features considered, the quantitative results show a high degree of correlation between features extracted from film and FFDM, with the correlation coefficients ranging from 0.7326 to 0.9602 for the different features. Based on a Fisher sign rank test, there was no significant difference observed between the features extracted from film and those from FFDM. For both MC detection and discrimination of FPs from MCs, FFDM had a slight but statistically significant advantage in performance; however, when the classifiers were trained on different types of images (acquired with FFDM or SFM) for discriminating MCs from FPs, there was little difference.

CONCLUSIONS

The results indicate good agreement between film and FFDM in quantitative image features. While FFDM images provide better detection performance in MCs, FFDM and film images may be interchangeable for the purposes of training CAD algorithms, and a single CAD algorithm may be applied to either type of images.

Diagnosis and prognosis of neuroendocrine tumours of the lung by means of high resolution image analysis

Neuroendocrine tumours (NET) of the lung are divided in subtypes with different malignant potential. The first is the benign or low-grade malignant tumours, well-differentiated, called typical carcinoids (TC) and the second is the high-grade malignant tumours, poorly differentiated of small (SCLC) or large cell type (LCLC). Between these tumour types lies the well-differentiated carcinoma with a lower grade of malignancy (WDNEC). In clinical routine it is very important with regard to prognosis to distinguish patients with low malignant potential from those with higher ones. In this study 32 cases of SCLC, 13 of WDNEC and 14 of TC with a follow-up time up to 7 years were collected. Sections 4 microm thick from paraffin embedded tissue were Feulgen stained. By means of high resolution image analysis 100 nuclei per case were randomly gathered to extract morphometric, densitometric and textural quantitative features. To investigate the ploidy status of the tumour the corrected DNA distribution was calculated. Stepwise linear discriminant analysis to differentiate the classes and Cox regression analysis for the survival time analysis were applied. Using chromatin textural and morphometric features in two two-class discriminations, 11 of the 14 TC cases and 8 of the 13 WDNEC cases were correctly classified and 11/13 WDNEC cases and 28/32 SCLC cases, respectively. The WDNEC cases are more similar in chromatin structure to TC than to SCLC. For the survival analysis, only chromatin features were selected to differentiate patients with better and worse prognosis independent of staging and tumour type.