Volumetric texture features from higher-order images for diagnosis of colon lesions via CT colonography

Artificial intelligence and machine learning in colorectal cancer

Colorectal cancer (CRC) is a heterogeneous illness characterized by various epigenetic and microenvironmental changes and is the third-highest cause of cancer-related death in the US. Artificial intelligence (AI) with its ability to allow automatic learning and improvement from experiences using statistical methods and Deep learning has made a distinctive contribution to the diagnosis and treatment of several cancer types. This review discusses the uses and application of AI in CRC screening using automated polyp detection assistance technologies to the development of computer-assisted diagnostic algorithms capable of accurately detecting polyps during colonoscopy and classifying them. Furthermore, we summarize the current research initiatives geared towards building computer-assisted diagnostic algorithms that aim at improving the diagnostic accuracy of benign from premalignant lesions. Considering the evolving transition to more personalized and tailored treatment strategies for CRC, the review also discusses the development of machine learning algorithms to understand responses to therapies and mechanisms of resistance as well as the future roles that AI applications may play in assisting in the treatment of CRC with the aim to improve disease outcomes. We also discuss the constraints and limitations of the use of AI systems. While the medical profession remains enthusiastic about the future of AI and machine learning, large-scale randomized clinical trials are needed to analyze AI algorithms before they can be used.

Vector textures derived from higher order derivative domains for classification of colorectal polyps

Textures have become widely adopted as an essential tool for lesion detection and classification through analysis of the lesion heterogeneities. In this study, higher order derivative images are being employed to combat the challenge of the poor contrast across similar tissue types among certain imaging modalities. To make good use of the derivative information, a novel concept of vector texture is firstly introduced to construct and extract several types of polyp descriptors. Two widely used differential operators, i.e., the gradient operator and Hessian operator, are utilized to generate the first and second order derivative images. These derivative volumetric images are used to produce two angle-based and two vector-based (including both angle and magnitude) textures. Next, a vector-based co-occurrence matrix is proposed to extract texture features which are fed to a random forest classifier to perform polyp classifications. To evaluate the performance of our method, experiments are implemented over a private colorectal polyp dataset obtained from computed tomographic colonography. We compare our method with four existing state-of-the-art methods and find that our method can outperform those competing methods over 4%-13% evaluated by the area under the receiver operating characteristics curves.

Applications of Artificial Intelligence in Screening, Diagnosis, Treatment, and Prognosis of Colorectal Cancer

Colorectal cancer (CRC) is one of the most common cancers worldwide. Accurate early detection and diagnosis, comprehensive assessment of treatment response, and precise prediction of prognosis are essential to improve the patients’ survival rate. In recent years, due to the explosion of clinical and omics data, and groundbreaking research in machine learning, artificial intelligence (AI) has shown a great application potential in clinical field of CRC, providing new auxiliary approaches for clinicians to identify high-risk patients, select precise and personalized treatment plans, as well as to predict prognoses. This review comprehensively analyzes and summarizes the research progress and clinical application value of AI technologies in CRC screening, diagnosis, treatment, and prognosis, demonstrating the current status of the AI in the main clinical stages. The limitations, challenges, and future perspectives in the clinical implementation of AI are also discussed.

Advancements in Oncology with Artificial Intelligence—A Review Article

Simple Summary

With the advancement of artificial intelligence, including machine learning, the field of oncology has seen promising results in cancer detection and classification, epigenetics, drug discovery, and prognostication. In this review, we describe what artificial intelligence is and its function, as well as comprehensively summarize its evolution and role in breast, colorectal, and central nervous system cancers. Understanding the origin and current accomplishments might be essential to improve the quality, accuracy, generalizability, cost-effectiveness, and reliability of artificial intelligence models that can be used in worldwide clinical practice. Students and researchers in the medical field will benefit from a deeper understanding of how to use integrative AI in oncology for innovation and research.

Abstract

Well-trained machine learning (ML) and artificial intelligence (AI) systems can provide clinicians with therapeutic assistance, potentially increasing efficiency and improving efficacy. ML has demonstrated high accuracy in oncology-related diagnostic imaging, including screening mammography interpretation, colon polyp detection, glioma classification, and grading. By utilizing ML techniques, the manual steps of detecting and segmenting lesions are greatly reduced. ML-based tumor imaging analysis is independent of the experience level of evaluating physicians, and the results are expected to be more standardized and accurate. One of the biggest challenges is its generalizability worldwide. The current detection and screening methods for colon polyps and breast cancer have a vast amount of data, so they are ideal areas for studying the global standardization of artificial intelligence. Central nervous system cancers are rare and have poor prognoses based on current management standards. ML offers the prospect of unraveling undiscovered features from routinely acquired neuroimaging for improving treatment planning, prognostication, monitoring, and response assessment of CNS tumors such as gliomas. By studying AI in such rare cancer types, standard management methods may be improved by augmenting personalized/precision medicine. This review aims to provide clinicians and medical researchers with a basic understanding of how ML works and its role in oncology, especially in breast cancer, colorectal cancer, and primary and metastatic brain cancer. Understanding AI basics, current achievements, and future challenges are crucial in advancing the use of AI in oncology.

Deep learning in CT colonography: differentiating premalignant from benign colorectal polyps

Objectives

To investigate the differentiation of premalignant from benign colorectal polyps detected by CT colonography using deep learning.

Methods

In this retrospective analysis of an average risk colorectal cancer screening sample, polyps of all size categories and morphologies were manually segmented on supine and prone CT colonography images and classified as premalignant (adenoma) or benign (hyperplastic polyp or regular mucosa) according to histopathology. Two deep learning models SEG and noSEG were trained on 3D CT colonography image subvolumes to predict polyp class, and model SEG was additionally trained with polyp segmentation masks. Diagnostic performance was validated in an independent external multicentre test sample. Predictions were analysed with the visualisation technique Grad-CAM++.

Results

The training set consisted of 107 colorectal polyps in 63 patients (mean age: 63 ± 8 years, 40 men) comprising 169 polyp segmentations. The external test set included 77 polyps in 59 patients comprising 118 polyp segmentations. Model SEG achieved a ROC-AUC of 0.83 and 80% sensitivity at 69% specificity for differentiating premalignant from benign polyps. Model noSEG yielded a ROC-AUC of 0.75, 80% sensitivity at 44% specificity, and an average Grad-CAM++ heatmap score of ≥ 0.25 in 90% of polyp tissue.

Conclusions

In this proof-of-concept study, deep learning enabled the differentiation of premalignant from benign colorectal polyps detected with CT colonography and the visualisation of image regions important for predictions. The approach did not require polyp segmentation and thus has the potential to facilitate the identification of high-risk polyps as an automated second reader.

Key Points

• Non-invasive deep learning image analysis may differentiate premalignant from benign colorectal polyps found in CT colonography scans.

• Deep learning autonomously learned to focus on polyp tissue for predictions without the need for prior polyp segmentation by experts.

• Deep learning potentially improves the diagnostic accuracy of CT colonography in colorectal cancer screening by allowing for a more precise selection of patients who would benefit from endoscopic polypectomy, especially for patients with polyps of 6–9 mm size.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-08532-2.

An Adaptive Learning Model for Multiscale Texture Features in Polyp Classification via Computed Tomographic Colonography

Objective: As an effective lesion heterogeneity depiction, texture information extracted from computed tomography has become increasingly important in polyp classification. However, variation and redundancy among multiple texture descriptors render a challenging task of integrating them into a general characterization. Considering these two problems, this work proposes an adaptive learning model to integrate multi-scale texture features. Methods: To mitigate feature variation, the whole feature set is geometrically split into several independent subsets that are ranked by a learning evaluation measure after preliminary classifications. To reduce feature redundancy, a bottom-up hierarchical learning framework is proposed to ensure monotonic increase of classification performance while integrating these ranked sets selectively. Two types of classifiers, traditional (random forest + support vector machine)- and convolutional neural network (CNN)-based, are employed to perform the polyp classification under the proposed framework with extended Haralick measures and gray-level co-occurrence matrix (GLCM) as inputs, respectively. Experimental results are based on a retrospective dataset of 63 polyp masses (defined as greater than 3 cm in largest diameter), including 32 adenocarcinomas and 31 benign adenomas, from adult patients undergoing first-time computed tomography colonography and who had corresponding histopathology of the detected masses. Results: We evaluate the performance of the proposed models by the area under the curve (AUC) of the receiver operating characteristic curve. The proposed models show encouraging performances of an AUC score of 0.925 with the traditional classification method and an AUC score of 0.902 with CNN. The proposed adaptive learning framework significantly outperforms nine well-established classification methods, including six traditional methods and three deep learning ones with a large margin. Conclusions: The proposed adaptive learning model can combat the challenges of feature variation through a multiscale grouping of feature inputs, and the feature redundancy through a hierarchal sorting of these feature groups. The improved classification performance against comparative models demonstrated the feasibility and utility of this adaptive learning procedure for feature integration.

Role of CT colonography in differentiating sigmoid cancer from chronic diverticular disease

PURPOSE

To evaluate the accuracy of computed tomography colonography (CTC) in differentiating chronic diverticular disease from colorectal cancer (CRC), using morphological and textural parameters.

MATERIALS AND METHODS

We included 95 consecutive patients with histologically proven chronic diverticular disease (n = 53) or CRC (n = 42) who underwent CTC. One radiologist, unaware of histological findings, evaluated CTC studies for the presence of potential discriminators including: maximum thickness, involved segment length, shouldering phenomenon, growth pattern, diverticula, fascia thickening, fat tissue edema, loco-regional lymph nodes, mucosal pattern. Another radiologist performed volumetric texture analysis on the involved segment.

RESULTS

Several qualitative imaging parameters resulted to significantly correlated with colorectal cancer, including absence of diverticula in the affected segment, straightened growth pattern and shouldering phenomenon. A maximum wall thickness/involved segment length ratio < 0.1 had 98% specificity and 47% sensitivity in identifying diverticular disease. Regarding first-order texture analysis parameters, kurtosis resulted to be significantly different between the two groups.

CONCLUSIONS

Absence of diverticula, straightened growth pattern and shouldering phenomenon are significantly associated with CRC (71-91% sensitivity; 82-91%).

A Novel Radiomics Nomogram for the Prediction of Secondary Loss of Response to Infliximab in Crohn's Disease

Purpose

The prediction of the loss of response (LOR) to infliximab (IFX) is crucial for optimizing treatment strategies and shifting biologics. However, a secondary LOR is difficult to predict by endoscopy due to the intestinal stricture, perforation, and fistulas. This study aimed to develop and validate a radiomic nomogram for the prediction of secondary LOR to IFX in patients with Crohn’s disease (CD).

Patients and Methods

A total of 186 biologic-naive patients diagnosed with CD between September 2016 and June 2019 were enrolled. Secondary LOR was determined during week 54. Computed tomography enterography (CTE) texture analysis (TA) features were extracted from lesions and analyzed using LIFEx software. Feature selection was performed by least absolute shrinkage and selection operator (LASSO) and ten-fold cross validation. A nomogram was constructed using multivariable logistic regression, and the internal validation was approached by ten-fold cross validation.

Results

Predictors contained in the radiomics nomogram included three first-order and five second-order signatures. The prediction model presented significant discrimination (AUC, 0.880; 95% CI, 0.816–0.944) and high calibration (mean absolute error of = 0.028). Decision curve analysis (DCA) indicated that the nomogram provided clinical net benefit. Ten-fold cross validation assessed the stability of the nomogram with an AUC of 0.817 and an accuracy of 0.819.

Conclusion

This novel radiomics nomogram provides a predictive tool to assess secondary LOR to IFX in patients with Crohn’s disease. This tool will help physicians decide when to switch therapy.

Artificial Intelligence in Colorectal Cancer Screening, Diagnosis and Treatment. A New Era

The development of artificial intelligence (AI) algorithms has permeated the medical field with great success. The widespread use of AI technology in diagnosing and treating several types of cancer, especially colorectal cancer (CRC), is now attracting substantial attention. CRC, which represents the third most commonly diagnosed malignancy in both men and women, is considered a leading cause of cancer-related deaths globally. Our review herein aims to provide in-depth knowledge and analysis of the AI applications in CRC screening, diagnosis, and treatment based on current literature. We also explore the role of recent advances in AI systems regarding medical diagnosis and therapy, with several promising results. CRC is a highly preventable disease, and AI-assisted techniques in routine screening represent a pivotal step in declining incidence rates of this malignancy. So far, computer-aided detection and characterization systems have been developed to increase the detection rate of adenomas. Furthermore, CRC treatment enters a new era with robotic surgery and novel computer-assisted drug delivery techniques. At the same time, healthcare is rapidly moving toward precision or personalized medicine. Machine learning models have the potential to contribute to individual-based cancer care and transform the future of medicine.

A multiparametric MRI-based CAD system for accurate diagnosis of bladder cancer staging

Appropriate treatment of bladder cancer (BC) is widely based on accurate and early BC staging. In this paper, a multiparametric computer-aided diagnostic (MP-CAD) system is developed to differentiate between BC staging, especially T1 and T2 stages, using T2-weighted (T2W) magnetic resonance imaging (MRI) and diffusion-weighted (DW) MRI. Our framework starts with the segmentation of the bladder wall (BW) and localization of the whole BC volume (V_t) and its extent inside the wall (V_w). Our segmentation framework is based on a fully connected convolution neural network (CNN) and utilized an adaptive shape model followed by estimating a set of functional, texture, and morphological features. The functional features are derived from the cumulative distribution function (CDF) of the apparent diffusion coefficient. Texture features are radiomic features estimated from T2W-MRI, and morphological features are used to describe the tumors' geometric. Due to the significant texture difference between the wall and bladder lumen cells, V_t is parcelled into a set of nested equidistance surfaces (i.e., iso-surfaces). Finally, features are estimated for individual iso-surfaces, which are then augmented and used to train and test machine learning (ML) classifier based on neural networks. The system has been evaluated using 42 data sets, and a leave-one-subject-out approach is employed. The overall accuracy, sensitivity, specificity, and area under the receiver operating characteristics (ROC) curve (AUC) are 95.24%, 95.24%, 95.24%, and 0.9864, respectively. The advantage of fusion multiparametric iso-features is highlighted by comparing the diagnostic accuracy of individual MRI modality, which is confirmed by the ROC analysis. Moreover, the accuracy of our pipeline is compared against other statistical ML classifiers (i.e., random forest (RF) and support vector machine (SVM)). Our CAD system is also compared with other techniques (e.g., end-to-end convolution neural networks (i.e., ResNet50).

Machine Learning-based Differentiation of Benign and Premalignant Colorectal Polyps Detected with CT Colonography in an Asymptomatic Screening Population: A Proof-of-Concept Study

Background CT colonography does not enable definite differentiation between benign and premalignant colorectal polyps. Purpose To perform machine learning-based differentiation of benign and premalignant colorectal polyps detected with CT colonography in an average-risk asymptomatic colorectal cancer screening sample with external validation using radiomics. Materials and Methods In this secondary analysis of a prospective trial, colorectal polyps of all size categories and morphologies were manually segmented on CT colonographic images and were classified as benign (hyperplastic polyp or regular mucosa) or premalignant (adenoma) according to the histopathologic reference standard. Quantitative image features characterizing shape (n = 14), gray level histogram statistics (n = 18), and image texture (n = 68) were extracted from segmentations after applying 22 image filters, resulting in 1906 feature-filter combinations. Based on these features, a random forest classification algorithm was trained to predict the individual polyp character. Diagnostic performance was validated in an external test set. Results The random forest model was fitted using a training set consisting of 107 colorectal polyps in 63 patients (mean age, 63 years ± 8 [standard deviation]; 40 men) comprising 169 segmentations on CT colonographic images. The external test set included 77 polyps in 59 patients comprising 118 segmentations. Random forest analysis yielded an area under the receiver operating characteristic curve of 0.91 (95% CI: 0.85, 0.96), a sensitivity of 82% (65 of 79) (95% CI: 74%, 91%), and a specificity of 85% (33 of 39) (95% CI: 72%, 95%) in the external test set. In two subgroup analyses of the external test set, the area under the receiver operating characteristic curve was 0.87 in the size category of 6-9 mm and 0.90 in the size category of 10 mm or larger. The most important image feature for decision making (relative importance of 3.7%) was quantifying first-order gray level histogram statistics. Conclusion In this proof-of-concept study, machine learning-based image analysis enabled noninvasive differentiation of benign and premalignant colorectal polyps with CT colonography. © RSNA, 2021 Online supplemental material is available for this article.

Evaluating treatment response to neoadjuvant chemoradiotherapy in rectal cancer using various MRI-based radiomics models

Background

To validate and compare various MRI-based radiomics models to evaluate treatment response to neoadjuvant chemoradiotherapy (nCRT) of rectal cancer.

Methods

A total of 80 patients with locally advanced rectal cancer (LARC) who underwent surgical resection after nCRT were enrolled retrospectively. Rectal MR images were scanned pre- and post-nCRT. The radiomics features were extracted from T2-weighted images, then reduced separately by least absolute shrinkage and selection operator (LASSO) and principal component analysis (PCA). Four classifiers of Logistic Regression, Random Forest (RF), Decision Tree and K-nearest neighbor (KNN) models were constructed to assess the tumor regression grade (TRG) and pathologic complete response (pCR), respectively. The diagnostic performances of models were determined with leave-one-out cross-validation by generating receiver operating characteristic curves and decision curve analysis.

Results

Three features related to the TRG and 11 features related to the pCR were obtained by LASSO. Top five principal components representing a cumulative contribution of 80% to overall features were selected by PCA. For TRG, the area under the curve (AUC) of RF model was 0.943 for LASSO and 0.930 for PCA, higher than other models (P < 0.05 for both). As for pCR, the AUCs of KNN for LASSO and PCA were 0.945 and 0.712, higher than other models (P < 0.05 for both). The DCA showed that LASSO algorithm was clinically superior to PCA.

Conclusion

MRI-based radiomics models demonstrated good performance for evaluating the treatment response of LARC after nCRT and LASSO algorithm yielded more clinical benefit.

A dynamic lesion model for differentiation of malignant and benign pathologies

Malignant lesions have a high tendency to invade their surrounding environment compared to benign ones. This paper proposes a dynamic lesion model and explores the 2nd order derivatives at each image voxel, which reflect the rate of change of image intensity, as a quantitative measure of the tendency. The 2nd order derivatives at each image voxel are usually represented by the Hessian matrix, but it is difficult to quantify a matrix field (or image) through the lesion space as a measure of the tendency. We conjecture that the three eigenvalues contain important information of the Hessian matrix and are chosen as the surrogate representation of the Hessian matrix. By treating the three eigenvalues as a vector, called Hessian vector, which is defined in a local coordinate formed by three orthogonal Hessian eigenvectors and further adapting the gray level occurrence computing method to extract the vector texture descriptors (or measures) from the Hessian vector, a quantitative presentation for the dynamic lesion model is completed. The vector texture descriptors were applied to differentiate malignant from benign lesions from two pathologically proven datasets: colon polyps and lung nodules. The classification results not only outperform four state-of-the-art methods but also three radiologist experts.

A Systematic Approach of Data Collection and Analysis in Medical Imaging Research

Background:

Obtaining the right image dataset for the medical image research systematically is a tedious task. Anatomy segmentation is the key step before extracting the radiomic features from these images.

Objective:

The purpose of the study was to segment the 3D colon from CT images and to measure the smaller polyps using image processing techniques. This require huge number of samples for statistical analysis. Our objective was to systematically classify and arrange the dataset based on the parameters of interest so that the empirical testing becomes easier in medical image research.

Materials and Methods:

This paper discusses a systematic approach of data collection and analysis before using it for empirical testing. In this research the image were considered from National Cancer Institute (NCI). TCIA from NCI has a vast collection of diagnostic quality images for the research community. These datasets were classified before empirical testing of the research objectives. The images in the TCIA collection were acquired as per the standard protocol defined by the American College of Radiology. Patients in the age group of 50-80 years were involved in various clinical trials (multicenter). The dataset collection has more than 10 billion of DICOM images of various anatomies. In this study, the number of samples considered for empirical testing was 300 (n) acquired from both supine and prone positions. The datasets were classified based on the parameters of interest. The classified dataset makes the dataset selection easier during empirical testing. The images were validated for the data completeness as per the DICOM standard of the 2020b version. A case study of CT Colonography dataset is discussed.

Conclusion:

With this systematic approach of data collection and classification, analysis will be become more easier during empirical testing.

Scope of Artificial Intelligence in Screening and Diagnosis of Colorectal Cancer

Globally, colorectal cancer is the third most diagnosed malignancy. It causes significant mortality and morbidity, which can be reduced by early diagnosis with an effective screening test. Integrating artificial intelligence (AI) and computer-aided detection (CAD) with screening methods has shown promising colorectal cancer screening results. AI could provide a “second look” for endoscopists to decrease the rate of missed polyps during a colonoscopy. It can also improve detection and characterization of polyps by integration with colonoscopy and various advanced endoscopic modalities such as magnifying narrow-band imaging, endocytoscopy, confocal endomicroscopy, laser-induced fluorescence spectroscopy, and magnifying chromoendoscopy. This descriptive review discusses various AI and CAD applications in colorectal cancer screening, polyp detection, and characterization.

Diagnostic advances of artificial intelligence and radiomics in gastroenterology

Traditional medical imaging, including ultrasound, computed tomography, magnetic resonance imaging, or positron emission tomography, remains widely used diagnostic modalities for gastrointestinal diseases at present. These modalities are used to assess changes in morphology, attenuation, signal intensity, and enhancement characteristics. Gastrointestinal tumors, especially malignant tumors, are commonly seen in clinical practice with an increasing number of deaths each year. Because the imaging manifestations of different diseases usually overlap, accurate early diagnosis of tumor lesions, noninvasive and effective evaluation of tumor staging, and prediction of prognosis remain challenging. Fortunately, traditional medical images contain a great deal of important information that cannot be recognized by human eyes but can be extracted by artificial intelligence (AI) technology, which can quantitatively assess the heterogeneity of lesions and provide valuable information, including therapeutic effects and patient prognosis. With the development of computer technology, the combination of medical imaging and AI technology is considered to represent a promising field in medical image analysis. This new emerging field is called “radiomics”, which makes big data mining and extraction from medical imagery possible and can help clinicians make effective decisions and develop personalized treatment plans. Recently, AI and radiomics have been gradually applied to lesion detection, qualitative and quantitative diagnosis, histopathological grading and staging of tumors, therapeutic efficacy assessment, and prognosis evaluation. In this minireview, we briefly introduce the basic principles and technology of radiomics. Then, we review the research and application of AI and radiomics in gastrointestinal diseases, especially diagnostic advancements of radiomics in the differential diagnosis, treatment option, assessment of therapeutic efficacy, and prognosis evaluation of esophageal, gastric, hepatic, pancreatic, and colorectal diseases.

3D-GLCM CNN: A 3-Dimensional Gray-Level Co-Occurrence Matrix-Based CNN Model for Polyp Classification via CT Colonography

Accurately classifying colorectal polyps, or differentiating malignant from benign ones, has a significant clinical impact on early detection and identifying optimal treatment of colorectal cancer. Convolution neural network (CNN) has shown great potential in recognizing different objects (e.g. human faces) from multiple slice (or color) images, a task similar to the polyp differentiation, given a large learning database. This study explores the potential of CNN learning from multiple slice (or feature) images to differentiate malignant from benign polyps from a relatively small database with pathological ground truth, including 32 malignant and 31 benign polyps represented by volumetric computed tomographic (CT) images. The feature image in this investigation is the gray-level co-occurrence matrix (GLCM). For each volumetric polyp, there are 13 GLCMs, computed from each of the 13 directions through the polyp volume. For comparison purpose, the CNN learning is also applied to the multi-slice CT images of the volumetric polyps. The comparison study is further extended to include Random Forest (RF) classification of the Haralick texture features (derived from the GLCMs). From the relatively small database, this study achieved scores of 0.91/0.93 (two-fold/leave-one-out evaluations) AUC (area under curve of the receiver operating characteristics) by using the CNN on the GLCMs, while the RF reached 0.84/0.86 AUC on the Haralick features and the CNN rendered 0.79/0.80 AUC on the multiple-slice CT images. The presented CNN learning from the GLCMs can relieve the challenge associated with relatively small database, improve the classification performance over the CNN on the raw CT images and the RF on the Haralick features, and have the potential to perform the clinical task of differentiating malignant from benign polyps with pathological ground truth.

CT-based radiomic features to predict pathological response in rectal cancer: A retrospective cohort study

INTRODUCTION

Innovative biomarkers to predict treatment response in rectal cancer would be helpful in optimizing personalized treatment approaches. In this study, we aimed to develop and validate a CT-based radiomic imaging biomarker to predict pathological response.

METHODS

We used two independent cohorts of rectal cancer patients to develop and validate a CT-based radiomic imaging biomarker predictive of treatment response. A total of 91 rectal cancer cases treated from 2009 to 2018 were assessed for the tumour regression grade (TRG) (0 = pathological complete response, pCR; 1 = moderate response; 2 = partial response; 3 = poor response). Exploratory analysis was performed by combining pre-treatment non-contrast CT images and patterns of TRG. The models built from the training cohort were further assessed using the independent validation cohort.

RESULTS

The patterns of pathological response in training and validation groups were TRG 0 (n = 14, 23.3%; n = 6, 19.4%), 1 (n = 31, 51.7%; n = 15, 48.4%), 2 (n = 12, 20.0%; n = 7, 22.6%) and 3 (n = 3, 5.0%; n = 3, 9.7%), respectively. Separate predictive models were built and analysed from CT features for pathological response. For pathological response prediction, the model including 8 radiomic features by random forest method resulted in 83.9% accuracy in predicting TRG 0 vs TRG 1-3 in validation.

CONCLUSION

The pre-treatment CT-based radiomic signatures were developed and validated in two independent cohorts. This imaging biomarker provided a promising way to predict pCR and select patients for non-operative management.

The feasibility of differentiating colorectal cancer from normal and inflammatory thickening colon wall using CT texture analysis

To investigate the diagnostic value of texture analysis (TA) for differentiating between colorectal cancer (CRC), colonic lesions caused by inflammatory bowel disease (IBD), and normal thickened colon wall (NTC) on computed tomography (CT) and assess which scanning phase has the highest differential diagnostic value. In all, 107 patients with CRC, 113 IBD patients with colonic lesions, and 96 participants with NTC were retrospectively enrolled. All subjects underwent multiphase CT examination, including pre-contrast phase (PCP), arterial phase (AP), and portal venous phase (PVP) scans. Based on these images, classification by TA and visual classification by radiologists were performed to discriminate among the three tissue types. The performance of TA and visual classification was compared. Precise TA classification results (error, 2.03–12.48%) were acquired by nonlinear discriminant analysis for CRC, IBD and NTC, regardless of phase or feature selection. PVP images showed a better ability to discriminate the three tissues by comprising the three scanning phases. TA showed significantly better performance in discriminating CRC, IBD and NTC than visual classification for residents, but there was no significant difference in classification between TA and experienced radiologists. TA could provide useful quantitative information for the differentiation of CRC, IBD and NTC on CT, particularly in PVP images.

Multilayer feature selection method for polyp classification via computed tomographic colonography

Polyp classification is a feature selection and clustering process. Picking the most effective features from multiple polyp descriptors without redundant information is a great challenge in this procedure. We propose a multilayer feature selection method to construct an optimized descriptor for polyp classification with a feature-grouping strategy in a hierarchical framework. First, the proposed method makes good use of image metrics, such as intensity, gradient, and curvature, to divide their corresponding polyp descriptors into several feature groups, which are the preliminary units of this method. Then each preliminary unit generates two ranked descriptors, i.e., their optimized variable groups (OVGs) and preliminary classification measurements. Next, a feature dividing-merging (FDM) algorithm is designed to perform feature merging operation hierarchically and iteratively. Unlike traditional feature selection methods, the proposed FDM algorithm includes two steps for feature dividing and feature merging. At each layer, feature dividing selects the OVG with the highest area under the receiver operating characteristic curve (AUC) as the baseline while other descriptors are treated as its complements. In the fusion step, the FDM merges some variables with gains into the baseline from the complementary descriptors iteratively on every layer until the final descriptor is obtained. This proposed model (including the forward step algorithm and the FDM algorithm) is a greedy method that guarantees clustering monotonicity of all OVGs from the bottom to the top layer. In our experiments, all the selected results from each layer are reported by both graphical illustration and data analysis. Performance of the proposed method is compared to five existing classification methods by a polyp database of 63 samples with pathological reports. The experimental results show that our proposed method outperforms other methods by 4% to 23% gains in terms of AUC scores.

A quantitative validation of segmented colon in virtual colonoscopy using image moments

Background

Evaluation of segmented colon is one of the challenges in Computed Tomography Colonography (CTC). The objective of the study was to measure the segmented colon accurately using image processing techniques.

Methods

This was a retrospective study, and the Institutional Ethical clearance was obtained for the secondary dataset. The technique was tested on 85 CTC dataset. The CTC dataset of 100–120 kVp, 100 mA, and ST (Slice Thickness) of 1.25 and 2.5 mm were used for empirical testing. The initial results of the work appear in the conference proceedings. Post colon segmentation, three distance measurement techniques, and one volumetric overlap computation were applied in Euclidian space in which the distances were measured on MPR views of the segmented and unsegmented colons and the volumetric overlap calculation between these two volumes.

Results

The key finding was that the measurements on both the segmented and the unsegmented volumes remain same without much difference noticed. This was statistically proved. The results were validated quantitatively on 2D MPR images. An accuracy of 95.265±0.4551% was achieved through volumetric overlap computation. Through pairedt−test, at α=5%, statistical values were p=0.6769, and t=0.4169 which infer that there was no much significant difference.

Conclusion

The combination of different validation techniques was applied to check the robustness of colon segmentation method, and good results were achieved with this approach. Through quantitative validation, the results were accepted at α=5%.

Multi-scale characterizations of colon polyps via computed tomographic colonography

Texture features have played an essential role in the field of medical imaging for computer-aided diagnosis. The gray-level co-occurrence matrix (GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these applications. This study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture descriptor. In this study, we first introduce a new parameter - stride, to explore the definition of GLCM. Then we propose three multi-scaling GLCM models according to its three parameters, (1) learning model by multiple displacements, (2) learning model by multiple strides (LMS), and (3) learning model by multiple angles. These models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick model. To further analyze the three parameters, we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign adenomas. Finally, the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning model. LMS obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

Colorectal cancer: Parametric evaluation of morphological, functional and molecular tomographic imaging

Colorectal cancer (CRC) represents one of the leading causes of tumor-related deaths worldwide. Among the various tools at physicians’ disposal for the diagnostic management of the disease, tomographic imaging (e.g., CT, MRI, and hybrid PET imaging) is considered essential. The qualitative and subjective evaluation of tomographic images is the main approach used to obtain valuable clinical information, although this strategy suffers from both intrinsic and operator-dependent limitations. More recently, advanced imaging techniques have been developed with the aim of overcoming these issues. Such techniques, such as diffusion-weighted MRI and perfusion imaging, were designed for the “in vivo” evaluation of specific biological tissue features in order to describe them in terms of quantitative parameters, which could answer questions difficult to address with conventional imaging alone (e.g., questions related to tissue characterization and prognosis). Furthermore, it has been observed that a large amount of numerical and statistical information is buried inside tomographic images, resulting in their invisibility during conventional assessment. This information can be extracted and represented in terms of quantitative parameters through different processes (e.g., texture analysis). Numerous researchers have focused their work on the significance of these quantitative imaging parameters for the management of CRC patients. In this review, we aimed to focus on evidence reported in the academic literature regarding the application of parametric imaging to the diagnosis, staging and prognosis of CRC while discussing future perspectives and present limitations. While the transition from purely anatomical to quantitative tomographic imaging appears achievable for CRC diagnostics, some essential milestones, such as scanning and analysis standardization and the definition of robust cut-off values, must be achieved before quantitative tomographic imaging can be incorporated into daily clinical practice.

Automatic glioma segmentation based on adaptive superpixel

Background

The automatic glioma segmentation is of great significance for clinical practice. This study aims to propose an automatic method based on superpixel for glioma segmentation from the T2 weighted Magnetic Resonance Imaging.

Methods

The proposed method mainly includes three steps. First, we propose an adaptive superpixel generation algorithm based on simple linear iterative clustering version with 0 parameter (ASLIC0). This algorithm can acquire a superpixel image with fewer superpixels and better fit the boundary of region of interest (ROI) by automatically selecting the optimal number of superpixels. Second, we compose a training set by calculating the statistical, texture, curvature and fractal features for each superpixel. Third, Support Vector Machine (SVM) is used to train classification model based on the features of the second step.

Results

The experimental results on Multimodal Brain Tumor Image Segmentation Benchmark 2017 (BraTS2017) show that the proposed method has good segmentation performance. The average Dice, Hausdorff distance, sensitivity, and specificity for the segmented tumor against the ground truth are 0.8492, 3.4697 pixels, 81.47, and 99.64%, respectively. The proposed method shows good stability on high- and low-grade glioma samples. Comparative experimental results show that the proposed method has superior performance.

Conclusions

This provides a close match to expert delineation across all grades of glioma, leading to a fast and reproducible method of glioma segmentation.

Colorectal Cancer Diagnostic Algorithm Based on Sub-Patch Weight Color Histogram in Combination of Improved Least Squares Support Vector Machine for Pathological Image

In order to improve the diagnostic accuracy of colon cancer, a novel classification algorithm based on sub-patch weight color histogram and improved SVM is proposed, which has good approximation ability for complex pathological image. Our proposed algorithm combines wavelet kernel SVM with color histogram to classify pathological image. Firstly, the pathological image is divided into non-overlapping sub-patches, and the features of sub-patch histogram are extracted. Then, the global and local features are fused by the sub-patch weighting algorithm. Then, the RelicfF based forward selection algorithm is used to integrate color features and texture features so as to enhance the characterization capabilities of the tumor cell. Finally, Morlet wavelet kernel-based least squares support vector machine method is adopted to enhance the generalization ability of the model for small sample with non-linear and high-dimensional pattern classification problems. Experimental results show that the proposed pathological diagnostic algorithm can gain higher accuracy compared with existing comparison algorithms.

An investigation of CNN models for differentiating malignant from benign lesions using small pathologically proven datasets

Cancer has been one of the most threatening diseases to human health. There have been many efforts devoted to the advancement of radiology and transformative tools (e.g. non-invasive computed tomographic or CT imaging) to detect cancer in early stages. One of the major goals is to identify malignant from benign lesions. In recent years, machine deep learning (DL), e.g. convolutional neural network (CNN), has shown encouraging classification performance on medical images. However, DL algorithms always need large datasets with ground truth. Yet in the medical imaging field, especially for cancer imaging, it is difficult to collect such large volume of images with pathological information. Therefore, strategies are needed to learn effectively from small datasets via CNN models. To forward that goal, this paper explores two CNN models by focusing extensively on expansion of training samples from two small pathologically proven datasets (colorectal polyp dataset and lung nodule dataset) and then differentiating malignant from benign lesions. Experimental outcomes indicate that even in very small datasets of less than 70 subjects, malignance can be successfully differentiated from benign via the proposed CNN models, the average AUCs (area under the receiver operating curve) of differentiating colorectal polyps and pulmonary nodules are 0.86 and 0.71, respectively. Our experiments further demonstrate that for these two small datasets, instead of only studying the original raw CT images, feeding additional image features, such as the local binary pattern of the lesions, into the CNN models can significantly improve classification performance. In addition, we find that our explored voxel level CNN model has better performance when facing the small and unbalanced datasets.

Use of Precision Imaging in the Evaluation of Pancreas Cancer

Pancreas cancer is an aggressive and fatal disease that will become one of the leading causes of cancer mortality by 2030. An all-out effort is underway to better understand the basic biologic mechanisms of this disease ranging from early development to metastatic disease. In order to change the course of this disease, diagnostic radiology imaging may play a vital role in providing a precise, noninvasive method for early diagnosis and assessment of treatment response. Recent progress in combining medical imaging, advanced image analysis and artificial intelligence, termed radiomics, can offer an innovate approach in detecting the earliest changes of tumor development as well as a rapid method for the detection of response. In this chapter, we introduce the principles of radiomics and demonstrate how it can provide additional information into tumor biology, early detection, and response assessments advancing the goals of precision imaging to deliver the right treatment to the right person at the right time.

Radiogenomics: bridging imaging and genomics

From diagnostics to prognosis to response prediction, new applications for radiomics are rapidly being developed. One of the fastest evolving branches involves linking imaging phenotypes to the tumor genetic profile, a field commonly referred to as "radiogenomics." In this review, a general outline of radiogenomic literature concerning prominent mutations across different tumor sites will be provided. The field of radiogenomics originates from image processing techniques developed decades ago; however, many technical and clinical challenges still need to be addressed. Nevertheless, increasingly accurate and robust radiogenomic models are being presented and the future appears to be bright.

Domain-Based Analysis of Colon Polyp in CT Colonography Using Image-Processing Techniques

Background: The purpose of the research was to improve the polyp detection accuracy in CT Colonography (CTC) through effective colon segmentation, removal of tagged fecal matter through Electronic Cleansing (EC), and measuring the smaller polyps. Methods: An improved method of boundary-based semi-automatic colon segmentation with the knowledge of colon distension, an adaptive multistep method for the virtual cleansing of segmented colon based on the knowledge of Hounsfield Units, and an automated method of smaller polyp measurement using skeletonization technique have been implemented. Results: The techniques were evaluated on 40 CTC dataset. The segmentation method was able to delineate the colon wall accurately. The submerged colonic structures were preserved without soft tissue erosion, pseudo enhanced voxels were corrected, and the air-contrast layer was removed without losing the adjacent tissues. The smaller polyp of size less than <10mm was detected correctly. The results were statistically validated qualitatively and quantitatively. Segmented colons were validated through volumetric overlap computation, and accuracy of 95.826±0.6854% was achieved. In polyp measurement, the paired t-test method was applied to compare the difference with ground truth and at α=5%, t=0.9937 and p=0.098 was achieved. The statistical values of TPR=90%, TNR=82.3% and accuracy=88.31% were achieved. Conclusion: An automated system of polyp measurement has been developed starting from colon segmentation to improve the existing CTC solutions. The analysis of domain-based approach of polyp has given good results. A prototype software, which can be used as a low-cost polyp diagnosis tool, has been developed.

Chronic Liver Disease Classification Using Hybrid Whale Optimization with Simulated Annealing and Ensemble Classifier

Chronic liver disease (CLD), which indicates the inflammatory condition of the liver, leads to cirrhosis or even partial or total liver dysfunction when left untreated. A non-invasive approach for evaluating CLD with computed tomography (CT) images is proposed using an ensemble of classifiers. To accurately classify CLD, the hybrid whale optimization algorithm with simulated annealing (WOA-SA) is used in selecting an optimal set of features. The proposed method employs seven sets of features with a total of 73–3D (three-dimensional) texture features. A hybrid ensemble classifier with support vector machine (SVM), k—Nearest Neighbor (k-NN), and random forest (RF) classifiers are used to classify liver diseases. Experimental analysis is performed on clinical CT images datasets, which include normal liver, fatty liver, metastasis, cirrhosis, and cancerous samples. The optimal features selected using the WOA-SA improve the accuracy of CLD classification for the five classes of diseases mentioned above. The accuracy of the liver classification using ensemble classifier yields approximately 98% with a 95% confidence interval (CI) of (0.7789, 1.0000) and an error rate of 1.9%. The performance of the proposed method is compared with two existing algorithms and the sensitivity and specificity yield an overall average of 96% and 93%, with 95% confidence interval of (0.7513, 1.0000) and (0.7126, 1.0000), respectively. Classification of CLD based on ensemble classifier illustrates the effectiveness of the proposed method and the comparison analysis demonstrates the superiority of the methodology.

Volumetric Textural Analysis of Colorectal Masses at CT Colonography: Differentiating Benign versus Malignant Pathology and Comparison with Human Reader Performance

RATIONALE AND OBJECTIVES

To (1) apply a quantitative volumetric textural analysis (VTA) to colorectal masses at CT colonography (CTC) for the differentiation of malignant and benign lesions and to (2) compare VTA with human performance.

MATERIALS AND METHODS

A validated, quantitative VTA method was applied to 63 pathologically proven colorectal masses (mean size, 4.2 cm; range, 3-8 cm) at noncontrast CTC in 59 adults (mean age, 66.5 years; range, 45.9-91.6 years). Fifty-one percent (32/63) of the masses were invasive adenocarcinoma, and the remaining 49% (31/63) were large benign adenomas. Three readers with CTC experience independently assessed the likelihood of malignancy using a 5-point scale (1 = definitely benign, 2 = probably benign, 3 = indeterminate, 4 = probably malignant, 5 = definitely malignant). Areas under the curve (AUCs) and accuracy levels were compared.

RESULTS

VTA achieved optimal sensitivity of 83.6% vs 91.7% for human readers (P = .034), with specificities of 87.5% and 77.4%, respectively (P = .007). No significant difference in overall accuracy was seen between VTA and human readers (85.5% vs 84.7%, P = .753). The AUC for differentiating benign and malignant lesions was 0.936 for VTA and 0.917 for human readers. Intraclass correlation coefficient among the human readers was 0.76, indicating good to excellent agreement.

CONCLUSION

VTA demonstrates excellent performance for distinguishing benign from malignant colorectal masses (≥3 cm) at CTC, comparable yet potentially complementary to experienced human performance.

Noninvasive Prediction of IDH1 Mutation and ATRX Expression Loss in Low-Grade Gliomas Using Multiparametric MR Radiomic Features

BACKGROUND

Noninvasive detection of isocitrate dehydrogenase 1 mutation (IDH1(+)) and loss of nuclear alpha thalassemia/mental retardation syndrome X-linked expression ((ATRX(-)) are clinically meaningful for molecular stratification of low-grade gliomas (LGGs).

PURPOSE

To study a radiomic approach based on multiparametric MR for noninvasively determining molecular status of IDH1(+) and ATRX(-) in patients with LGG.

STUDY TYPE

Retrospective, radiomics.

POPULATION

Fifty-seven LGG patients with IDH1(+) (n = 36 with 19 ATRX(-) and 17 ATRX(+) patients) and IDH1(-) (n = 21).

FIELD STRENGTH/SEQUENCE

3.0T MRI / 3D arterial spin labeling (3D-ASL), T₂ /fluid-attenuated inversion recovery (T₂ FLAIR), and diffusion-weighted imaging (DWI).

ASSESSMENT

In all, 265 high-throughput radiomic features were extracted on each tumor volume of interest from T₂ FLAIR and the other three parametric maps of ASL-derived cerebral blood flow (CBF), DWI-derived apparent diffusion coefficient (ADC), and exponential ADC (eADC). Optimal feature subsets were selected as using the support vector machine with a recursive feature elimination algorithm (SVM-RFE). Receiver operating characteristic curve (ROC) analysis was employed to assess the efficiency for identifying the IDH1(+) and ATRX(-) status.

STATISTICAL TESTS

Student's t-test, chi-square test, and Fisher's exact test were applied to confirm whether intergroup significant differences exist between molecular subtypes decided by IDH1 and ATRX.

RESULTS

Optimal SVM predictive models of IDH1(+) and ATRX(-) were established using 28 features from T₂ Flair, ADC, eADC, and CBF and six features from T₂ Flair, ADC, and CBF. The accuracies/AUCs/sensitivity/specifity/PPV/NPV of predicting IDH1(+) in LGG were 94.74%/0.931/100%/85.71%/92.31%/100%, and those of predicting ATRX(-) in LGG with IDH1(+) were 91.67%/0.926/94.74%/88.24%/90.00%/93.75%, respectively.

DATA CONCLUSION

Using the optimal texture features extracted from multiple MR sequences or parametric maps, a promising stratifying strategy was acquired for predicting molecular subtypes of IDH1 and ATRX in LGGs.

LEVEL OF EVIDENCE

3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019;49:808-817.

The Natural History of Colorectal Polyps: Overview of Predictive Static and Dynamic Features

For decades, colorectal screening strategies have been largely driven by static features, particularly polyp size. Although cross-sectional features of polyp size, morphology, and location are important determinants of clinical relevance before histology, they lack any dynamic information on polyp growth rates. Computed tomography colonography allows for in vivo surveillance of colorectal polyps, providing volumetric growth rates that are providing new insights into tumorigenesis. In this article, existing cross-sectional and longitudinal data on colorectal polyps are reviewed, with an emphasis on how these features may affect clinical relevance and patient management.

Advanced Imaging Techniques in Evaluation of Colorectal Cancer

Imaging techniques are clinical decision-making tools in the evaluation of patients with colorectal cancer (CRC). The aim of this article is to discuss the potential of recent advances in imaging for diagnosis, prognosis, therapy planning, and assessment of response to treatment of CRC. Recent developments and new clinical applications of conventional imaging techniques such as virtual colonoscopy, dual-energy spectral computed tomography, elastography, advanced computing techniques (including volumetric rendering techniques and machine learning), magnetic resonance (MR) imaging-based magnetization transfer, and new liver imaging techniques, which may offer additional clinical information in patients with CRC, are summarized. In addition, the clinical value of functional and molecular imaging techniques such as diffusion-weighted MR imaging, dynamic contrast material-enhanced imaging, blood oxygen level-dependent imaging, lymphography with contrast agents, positron emission tomography with different radiotracers, and MR spectroscopy is reviewed, and the advantages and disadvantages of these modalities are evaluated. Finally, the future role of imaging-based analysis of tumor heterogeneity and multiparametric imaging, the development of radiomics and radiogenomics, and future challenges for imaging of patients with CRC are discussed. Online supplemental material is available for this article. ^©RSNA, 2018.

Radiomics strategy for glioma grading using texture features from multiparametric MRI

BACKGROUND

Accurate glioma grading plays an important role in the clinical management of patients and is also the basis of molecular stratification nowadays.

PURPOSE/HYPOTHESIS

To verify the superiority of radiomics features extracted from multiparametric MRI to glioma grading and evaluate the grading potential of different MRI sequences or parametric maps.

STUDY TYPE

Retrospective; radiomics.

POPULATION

A total of 153 patients including 42, 33, and 78 patients with Grades II, III, and IV gliomas, respectively.

FIELD STRENGTH/SEQUENCE

3.0T MRI/T₁ -weighted images before and after contrast-enhanced, T₂ -weighted, multi-b-value diffusion-weighted and 3D arterial spin labeling images.

ASSESSMENT

After multiparametric MRI preprocessing, high-throughput features were derived from patients' volumes of interests (VOIs). The support vector machine-based recursive feature elimination was adopted to find the optimal features for low-grade glioma (LGG) vs. high-grade glioma (HGG), and Grade III vs. IV glioma classification tasks. Then support vector machine (SVM) classifiers were established using the optimal features. The accuracy and area under the curve (AUC) was used to assess the grading efficiency.

STATISTICAL TESTS

Student's t-test or a chi-square test were applied on different clinical characteristics to confirm whether intergroup significant differences exist.

RESULTS

Patients' ages between LGG and HGG groups were significantly different (P < 0.01). For each patient, 420 texture and 90 histogram parameters were derived from 10 VOIs of multiparametric MRI. SVM models were established using 30 and 28 optimal features for classifying LGGs from HGGs and grades III from IV, respectively. The accuracies/AUCs were 96.8%/0.987 for classifying LGGs from HGGs, and 98.1%/0.992 for classifying grades III from IV, which were more promising than using histogram parameters or using the single sequence MRI.

DATA CONCLUSION

Texture features were more effective for noninvasively grading gliomas than histogram parameters. The combined application of multiparametric MRI provided a higher grading efficiency. The proposed radiomic strategy could facilitate clinical decision-making for patients with varied glioma grades.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;48:1518-1528.

Radiomics Strategy for Molecular Subtype Stratification of Lower-Grade Glioma: Detecting IDH and TP53 Mutations Based on Multimodal MRI

BACKGROUND

Noninvasive detection of isocitrate dehydrogenase (IDH) and TP53 mutations are meaningful for molecular stratification of lower-grade gliomas (LrGG).

PURPOSE

To explore potential MRI features reflecting IDH and TP53 mutations of LrGG, and propose a radiomics strategy for detecting them.

STUDY TYPE

Retrospective, radiomics.

POPULATION/SUBJECTS

A total of 103 LrGG patients were separated into development (n = 73) and validation (n = 30) cohorts.

FIELD STRENGTH/SEQUENCE

T₁ -weighted (before and after contrast-enhanced), T₂ -weighted, and fluid-attenuation inversion recovery images from 1.5T (n = 37) or 3T (n = 66) scanners.

ASSESSMENT

After data preprocessing, high-throughput features were derived from patients' volumes of interests of different sequences. The support vector machine-based recursive feature elimination (SVM-RFE) was adopted to find the optimal features for IDH and TP53 mutation detection. SVM models were trained and tested on development and validation cohort. The commonly used metric was used for assessing the efficiency.

STATISTICAL TESTS

One-way analysis of variance (ANOVA), chi-square, or Fisher's exact test were applied on clinical characteristics to confirm whether significant differences exist between three molecular subtypes decided by IDH and TP53 status. Intraclass correlation coefficients were calculated to assess the robustness of the radiomics features.

RESULTS

The constituent ratio of histopathologic subtypes was significantly different among three molecular subtypes (P = 0.017). SVM models for detecting IDH and TP53 mutation were established using 12 and 22 optimal features selected by SVM-RFE. The accuracies and area under the curves for IDH and TP53 mutations on the development cohort were 84.9%, 0.830, and 92.0%, 0.949, while on the validation cohort were 80.0%, 0.792, and 85.0%, 0.869, respectively. Furthermore, the stratified accuracies of three subtypes were 72.8%, 71.9%, and 70%, respectively.

DATA CONCLUSION

Using a radiomics approach integrating SVM model and multimodal MRI features, molecular subtype stratification of LGG patients was implemented through detecting IDH and TP53 mutations. The results suggested that the proposed approach has promising detecting efficiency and T₂ -weighted image features are more important than features from other images.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;48:916-926.

CT Texture Analysis: Definitions, Applications, Biologic Correlates, and Challenges

This review discusses potential oncologic and nononcologic applications of CT texture analysis ( CTTA CT texture analysis ), an emerging area of "radiomics" that extracts, analyzes, and interprets quantitative imaging features. CTTA CT texture analysis allows objective assessment of lesion and organ heterogeneity beyond what is possible with subjective visual interpretation and may reflect information about the tissue microenvironment. CTTA CT texture analysis has shown promise in lesion characterization, such as differentiating benign from malignant or more biologically aggressive lesions. Pretreatment CT texture features are associated with histopathologic correlates such as tumor grade, tumor cellular processes such as hypoxia or angiogenesis, and genetic features such as KRAS or epidermal growth factor receptor (EGFR) mutation status. In addition, and likely as a result, these CT texture features have been linked to prognosis and clinical outcomes in some tumor types. CTTA CT texture analysis has also been used to assess response to therapy, with decreases in tumor heterogeneity generally associated with pathologic response and improved outcomes. A variety of nononcologic applications of CTTA CT texture analysis are emerging, particularly quantifying fibrosis in the liver and lung. Although CTTA CT texture analysis seems to be a promising imaging biomarker, there is marked variability in methods, parameters reported, and strength of associations with biologic correlates. Before CTTA CT texture analysis can be considered for widespread clinical implementation, standardization of tumor segmentation and measurement techniques, image filtration and postprocessing techniques, and methods for mathematically handling multiple tumors and time points is needed, in addition to identification of key texture parameters among hundreds of potential candidates, continued investigation and external validation of histopathologic correlates, and structured reporting of findings. ^©RSNA, 2017.

Texture analysis of CT images in predicting malignancy risk of gastrointestinal stromal tumours

AIM

To explore the role of texture analysis of computed tomography (CT) images in predicting the malignancy risk of gastrointestinal stromal tumours (GISTs).

MATERIALS AND METHODS

Seventy-eight patients with histopathologically confirmed GISTs underwent preoperative CT. Texture analysis was performed on unenhanced and contrast-enhanced CT images, respectively. Fourteen CT texture parameters were obtained and compared among GISTs at different malignancy risks with one-way analysis of variance or independent-samples Kruskal-Wallis test. Correlations between CT texture parameters and malignancy risk were analysed with Spearman's correlation test. Diagnostic performance of CT texture parameters in differentiating GISTs at low/very low malignancy risk was tested with receiver operating characteristic (ROC) analysis.

RESULTS

Three parameters on unenhanced images (r=-0.268-0.506), four parameters on arterial phase (r=-0.365-0.508), and six parameters on venous phase (r=-0.343-0.481) imaging correlated significantly with malignancy risk of GISTs, respectively (all p<0.05). For identifying GISTs at low/very low malignancy risk, three parameters on unenhanced images (area under ROC curve [AUC], 0.676-0.802), four parameters on arterial phase (AUC, 0.637-0.811), and six parameters on venous phase (AUC, 0.636-0.791) imaging showed significant diagnostic performance, respectively (all p<0.05), especially maximum frequency on both unenhanced and contrast-enhanced images (AUC, 0.791-0.811).

CONCLUSION

Texture analysis of CT images holds great potential to predict the malignancy risk of GISTs preoperatively.

Relationship between Glioblastoma Heterogeneity and Survival Time: An MR Imaging Texture Analysis

BACKGROUND AND PURPOSE

The heterogeneity of glioblastoma contributes to the poor and variant prognosis. The aim of this retrospective study was to assess the glioblastoma heterogeneity with MR imaging textures and to evaluate its impact on survival time.

MATERIALS AND METHODS

A total of 133 patients with primary glioblastoma who underwent postcontrast T1-weighted imaging (acquired before treatment) and whose data were filed with the survival times were selected from the Cancer Genome Atlas. On the basis of overall survival, the patients were divided into 2 groups: long-term (≥12 months, n = 67) and short-term (<12 months, n = 66) survival. To measure heterogeneity, we extracted 3 types of textures, co-occurrence matrix, run-length matrix, and histogram, reflecting local, regional, and global spatial variations, respectively. Then the support vector machine classification was used to determine how different texture types perform in differentiating the 2 groups, both alone and in combination. Finally, a recursive feature-elimination method was used to find an optimal feature subset with the best differentiation performance.

RESULTS

When used alone, the co-occurrence matrix performed best, while all the features combined obtained the best survival stratification. According to feature selection and ranking, 43 top-ranked features were selected as the optimal subset. Among them, the top 10 features included 7 run-length matrix and 3 co-occurrence matrix features, in which all 6 regional run-length matrix features emphasizing high gray-levels ranked in the top 7.

CONCLUSIONS

The results suggest that local and regional heterogeneity may play an important role in the survival stratification of patients with glioblastoma.

Hippocampus and amygdala radiomic biomarkers for the study of autism spectrum disorder

BACKGROUND

Emerging evidence suggests the presence of neuroanatomical abnormalities in subjects with autism spectrum disorder (ASD). Identifying anatomical correlates could thus prove useful for the automated diagnosis of ASD. Radiomic analyses based on MRI texture features have shown a great potential for characterizing differences occurring from tissue heterogeneity, and for identifying abnormalities related to these differences. However, only a limited number of studies have investigated the link between image texture and ASD. This paper proposes the study of texture features based on grey level co-occurrence matrix (GLCM) as a means for characterizing differences between ASD and development control (DC) subjects. Our study uses 64 T1-weighted MRI scans acquired from two groups of subjects: 28 typical age range subjects 4-15 years old (14 ASD and 14 DC, age-matched), and 36 non-typical age range subjects 10-24 years old (20 ASD and 16 DC). GLCM matrices are computed from manually labeled hippocampus and amygdala regions, and then encoded as texture features by applying 11 standard Haralick quantifier functions. Significance tests are performed to identify texture differences between ASD and DC subjects. An analysis using SVM and random forest classifiers is then carried out to find the most discriminative features, and use these features for classifying ASD from DC subjects.

RESULTS

Preliminary results show that all 11 features derived from the hippocampus (typical and non-typical age) and 4 features extracted from the amygdala (non-typical age) have significantly different distributions in ASD subjects compared to DC subjects, with a significance of p < 0.05 following Holm-Bonferroni correction. Features derived from hippocampal regions also demonstrate high discriminative power for differentiating between ASD and DC subjects, with classifier accuracy of 67.85%, sensitivity of 62.50%, specificity of 71.42%, and the area under the ROC curve (AUC) of 76.80% for age-matched subjects with typical age range.

CONCLUSIONS

Results demonstrate the potential of hippocampal texture features as a biomarker for the diagnosis and characterization of ASD.

Preoperative prediction of muscular invasiveness of bladder cancer with radiomic features on conventional MRI and its high-order derivative maps

PURPOSE

To determine radiomic features which are capable of reflecting muscular invasiveness of bladder cancer (BC) and propose a non-invasive strategy for the differentiation of muscular invasiveness preoperatively.

METHODS

Sixty-eight patients with clinicopathologically confirmed BC were included in this retrospective study. A total of 118 cancerous volumes of interest (VOI) were segmented from patients' T2 weighted MR images (T2WI), including 34 non-muscle invasive bladder carcinomas (NMIBCs, stage <T2) and 84 muscle invasive ones (MIBCs, stage ≥T2). The radiomic features quantifying tumor signal intensity and textures were extracted from each VOI and its high-order derivative maps to characterize heterogeneity of tumor tissues. Statistical analysis was used to build radiomic signatures with significant inter-group differences of NMIBCs and MIBCs. The synthetic minority oversampling technique (SMOTE) and a support vector machine (SVM)-based feature selection and classification strategy were proposed to first rebalance the imbalanced sample size and then further select the most predictive and compact signature subset to verify its differentiation capability.

RESULTS

From each tumor VOI, a total of 63 radiomic features were derived and 30 of them showed significant inter-group differences (P ≤ 0.01). By using the SVM-based feature selection algorithm with rebalanced samples, an optimal subset including 13 radiomic signatures was determined. The area under receiver operating characteristic curve and Youden index were improved to 0.8610 and 0.7192, respectively.

CONCLUSION

3D radiomic signatures derived from T2WI and its high-order derivative maps could reflect muscular invasiveness of bladder cancer, and the proposed strategy can be used to facilitate the preoperative prediction of muscular invasiveness in patients with bladder cancer.

Measurement of smaller colon polyp in CT colonography images using morphological image processing

PURPOSE

Automated measurement of the size and shape of colon polyps is one of the challenges in Computed tomography colonography (CTC). The objective of this retrospective study was to improve the sensitivity and specificity of smaller polyp measurement in CTC using image processing techniques.

METHODS

A domain knowledge-based method has been implemented with hybrid method of colon segmentation, morphological image processing operators for detecting the colonic structures, and the decision-making system for delineating the smaller polyp-based on a priori knowledge.

RESULTS

The method was applied on 45 CTC dataset. The key finding was that the smaller polyps were accurately measured. In addition to 6-9 mm range, polyps of even <5 mm were also detected. The results were validated qualitatively and quantitatively using both 2D MPR and 3D view. Implementation was done on a high-performance computer with parallel processing. It takes [Formula: see text] min for measuring the smaller polyp in a dataset of 500 CTC images. With this method, [Formula: see text] and [Formula: see text] were achieved.

CONCLUSIONS

The domain-based approach with morphological image processing has given good results. The smaller polyps were measured accurately which helps in making right clinical decisions. Qualitatively and quantitatively the results were acceptable when compared to the ground truth at [Formula: see text].

Three-dimensional texture features from intensity and high-order derivative maps for the discrimination between bladder tumors and wall tissues via MRI

PURPOSE

This study aims to determine the three-dimensional (3D) texture features extracted from intensity and high-order derivative maps that could reflect textural differences between bladder tumors and wall tissues, and propose a noninvasive, image-based strategy for bladder tumor differentiation preoperatively.

METHODS

A total of 62 cancerous and 62 wall volumes of interest (VOI) were extracted from T2-weighted MRI datasets of 62 patients with pathologically confirmed bladder cancer. To better reflect heterogeneous distribution of tumor tissues, 3D high-order derivative maps (the gradient and curvature maps) were calculated from each VOI. Then 3D Haralick features based on intensity and high-order derivative maps and Tamura features based on intensity maps were extracted from each VOI. Statistical analysis and recursive feature elimination-based support vector machine classifier (RFE-SVM) was proposed to first select the features with significant differences and then obtain a more predictive and compact feature subset to verify its differentiation performance.

RESULTS

From each VOI, a total of 58 texture features were derived. Among them, 37 features showed significant inter-class differences ([Formula: see text]). With 29 optimal features selected by RFE-SVM, the classification results namely the sensitivity, specificity, accuracy and area under the curve (AUC) of the receiver operating characteristics were 0.9032, 0.8548, 0.8790 and 0.9045, respectively. By using synthetic minority oversampling technique to augment the sample number of each group to 200, the sensitivity, specificity, accuracy an AUC value of the feature selection-based classification were improved to 0.8967, 0.8780, 0.8874 and 0.9416, respectively.

CONCLUSIONS

Our results suggest that 3D texture features derived from intensity and high-order derivative maps can better reflect heterogeneous distribution of cancerous tissues. Texture features optimally selected together with sample augmentation could improve the performance on differentiating bladder carcinomas from wall tissues, suggesting a potential way for tumor noninvasive staging of bladder cancer preoperatively.

Texture Analysis of Abnormal Cell Images for Predicting the Continuum of Colorectal Cancer

Abnormal cell (ABC) is a markedly heterogeneous tissue area and can be categorized into three main types: benign hyperplasia (BH), carcinoma (Ca), and intraepithelial neoplasia (IN) or precursor cancerous lesion. In this study, the goal is to determine and characterize the continuum of colorectal cancer by using a 3D-texture approach. ABC was segmented in preprocessing step using an active contour segmentation technique. Cell types were analyzed based on textural features extracted from the gray level cooccurrence matrices (GLCMs). Significant texture features were selected using an analysis of variance (ANOVA) of ABC with a p value cutoff of p < 0.01. Features selected were reduced with a principal component analysis (PCA), which accounted for 97% of the cumulative variance from significant features. The simulation results identified 158 significant features based on ANOVA from a total of 624 texture features extracted from GLCMs. Performance metrics of ABC discrimination based on significant texture features showed 92.59% classification accuracy, 100% sensitivity, and 94.44% specificity. These findings suggest that texture features extracted from GLCMs are sensitive enough to discriminate between the ABC types and offer the opportunity to predict cell characteristics of colorectal cancer.

Texture Feature Extraction and Analysis for Polyp Differentiation via Computed Tomography Colonography

Image textures in computed tomography colonography (CTC) have great potential for differentiating non-neoplastic from neoplastic polyps and thus can advance the current CTC detection-only paradigm to a new level with diagnostic capability. However, image textures are frequently compromised, particularly in low-dose CT imaging. Furthermore, texture feature extraction may vary, depending on the polyp spatial orientation variation, resulting in variable results. To address these issues, this study proposes an adaptive approach to extract and analyze the texture features for polyp differentiation. Firstly, derivative (e.g. gradient and curvature) operations are performed on the CT intensity image to amplify the textures with adequate noise control. Then Haralick co-occurrence matrix (CM) is used to calculate texture measures along each of the 13 directions (defined by the first and second order image voxel neighbors) through the polyp volume in the intensity, gradient and curvature images. Instead of taking the mean and range of each CM measure over the 13 directions as the so-called Haralick texture features, Karhunen-Loeve transform is performed to map the 13 directions into an orthogonal coordinate system so that the resulted texture features are less dependent on the polyp orientation variation. These simple ideas for amplifying textures and stabilizing spatial variation demonstrated a significant impact for the differentiating task by experiments using 384 polyp datasets, of which 52 are non-neoplastic polyps and the rest are neoplastic polyps. By the merit of area under the curve of receiver operating characteristic, the innovative ideas achieved differentiation capability of 0.8016, indicating the CTC diagnostic feasibility.

Progress in Fully Automated Abdominal CT Interpretation

OBJECTIVE

Automated analysis of abdominal CT has advanced markedly over just the last few years. Fully automated assessment of organs, lymph nodes, adipose tissue, muscle, bowel, spine, and tumors are some examples where tremendous progress has been made. Computer-aided detection of lesions has also improved dramatically.

CONCLUSION

This article reviews the progress and provides insights into what is in store in the near future for automated analysis for abdominal CT, ultimately leading to fully automated interpretation.

An adaptive paradigm for computer-aided detection of colonic polyps

Most previous efforts in developing computer-aided detection (CADe) of colonic polyps apply similar measures or parameters to detect polyps regardless of their locations under an implicit assumption that all the polyps reside in a similar local environment, e.g. on a relatively flat colon wall. In reality, this implicit assumption is frequently invalid, because the haustral folds can have a very different local environment from that of the relatively flat colon wall. We conjecture that this assumption may be a major cause of missing the detection of polyps, especially small polyps (<10 mm linear size) located on the haustral folds. In this paper, we take the concept of adaptiveness and present an adaptive paradigm for CADe of colonic polyps. Firstly, we decompose the complicated colon structure into two simplified sub-structures, each of which has similar properties, of (1) relatively flat colon wall and (2) ridge-shaped haustral folds. Then we develop local environment descriptions to adaptively reflect each of these two simplified sub-structures. To show the impact of the adaptiveness of the local environment descriptions upon the polyp detection task, we focus on the local geometrical measures of the volume data for both the detection of initial polyp candidates (IPCs) and the reduction of false positives (FPs) in the IPC pool. The experimental outcome using the local geometrical measures is very impressive such that not only the previously-missed small polyps on the folds are detected, but also the previously miss-removed small polyps on the folds during FP reduction are retained. It is expected that this adaptive paradigm will have a great impact on detecting the small polyps, measuring their volumes and volume changes over time, and optimizing their management plan.