Prateek Prasanna

Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI

BackgroundIn this study, we evaluated the ability of radiomic textural analysis of intratumoral and peritumoral regions on pretreatment breast cancer dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict pathological complete response (pCR) to neoadjuvant chemotherapy (NAC).MethodsA total of 117 patients who had received NAC were retrospectively analyzed. Within the intratumoral and peritumoral regions of T1-weighted contrast-enhanced MRI scans, a total of 99 radiomic textural features were computed at multiple phases. Feature selection was used to identify a set of top pCR-associated features from within a training set (n = 78), which were then used to train multiple machine learning classifiers to predict the likelihood of pCR for a given patient. Classifiers were then independently tested on 39 patients. Experiments were repeated separately among hormone receptor-positive and human epidermal growth factor receptor 2-negative (HR+, HER2−) and triple-negative or HER2+ (TN/HER2+) tumors via threefold cross-validation to determine whether receptor status-specific analysis could improve classification performance.ResultsAmong all patients, a combined intratumoral and peritumoral radiomic feature set yielded a maximum AUC of 0.78 ± 0.030 within the training set and 0.74 within the independent testing set using a diagonal linear discriminant analysis (DLDA) classifier. Receptor status-specific feature discovery and classification enabled improved prediction of pCR, yielding maximum AUCs of 0.83 ± 0.025 within the HR+, HER2− group using DLDA and 0.93 ± 0.018 within the TN/HER2+ group using a naive Bayes classifier. In HR+, HER2− breast cancers, non-pCR was characterized by elevated peritumoral heterogeneity during initial contrast enhancement. However, TN/HER2+ tumors were best characterized by a speckled enhancement pattern within the peritumoral region of nonresponders. Radiomic features were found to strongly predict pCR independent of choice of classifier, suggesting their robustness as response predictors.ConclusionsThrough a combined intratumoral and peritumoral radiomics approach, we could successfully predict pCR to NAC from pretreatment breast DCE-MRI, both with and without a priori knowledge of receptor status. Further, our findings suggest that the radiomic features most predictive of response vary across different receptor subtypes.

Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study

BACKGROUND AND PURPOSE: Despite availability of advanced imaging, distinguishing radiation necrosis from recurrent brain tumors noninvasively is a big challenge in neuro-oncology. Our aim was to determine the feasibility of radiomic (computer-extracted texture) features in differentiating radiation necrosis from recurrent brain tumors on routine MR imaging (gadolinium T1WI, T2WI, FLAIR). MATERIALS AND METHODS: A retrospective study of brain tumor MR imaging performed 9 months (or later) post-radiochemotherapy was performed from 2 institutions. Fifty-eight patient studies were analyzed, consisting of a training (n = 43) cohort from one institution and an independent test (n = 15) cohort from another, with surgical histologic findings confirmed by an experienced neuropathologist at the respective institutions. Brain lesions on MR imaging were manually annotated by an expert neuroradiologist. A set of radiomic features was extracted for every lesion on each MR imaging sequence: gadolinium T1WI, T2WI, and FLAIR. Feature selection was used to identify the top 5 most discriminating features for every MR imaging sequence on the training cohort. These features were then evaluated on the test cohort by a support vector machine classifier. The classification performance was compared against diagnostic reads by 2 expert neuroradiologists who had access to the same MR imaging sequences (gadolinium T1WI, T2WI, and FLAIR) as the classifier. RESULTS: On the training cohort, the area under the receiver operating characteristic curve was highest for FLAIR with 0.79; 95% CI, 0.77–0.81 for primary (n = 22); and 0.79, 95% CI, 0.75–0.83 for metastatic subgroups (n = 21). Of the 15 studies in the holdout cohort, the support vector machine classifier identified 12 of 15 studies correctly, while neuroradiologist 1 diagnosed 7 of 15 and neuroradiologist 2 diagnosed 8 of 15 studies correctly, respectively. CONCLUSIONS: Our preliminary results suggest that radiomic features may provide complementary diagnostic information on routine MR imaging sequences that may improve the distinction of radiation necrosis from recurrence for both primary and metastatic brain tumors.

Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): A new radiomics descriptor.

In this paper, we introduce a new radiomic descriptor, Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe) for capturing subtle differences between benign and pathologic phenotypes which may be visually indistinguishable on routine anatomic imaging. CoLlAGe seeks to capture and exploit local anisotropic differences in voxel-level gradient orientations to distinguish similar appearing phenotypes. CoLlAGe involves assigning every image voxel an entropy value associated with the co-occurrence matrix of gradient orientations computed around every voxel. The hypothesis behind CoLlAGe is that benign and pathologic phenotypes even though they may appear similar on anatomic imaging, will differ in their local entropy patterns, in turn reflecting subtle local differences in tissue microarchitecture. We demonstrate CoLlAGe’s utility in three clinically challenging classification problems: distinguishing (1) radiation necrosis, a benign yet confounding effect of radiation treatment, from recurrent tumors on T1-w MRI in 42 brain tumor patients, (2) different molecular sub-types of breast cancer on DCE-MRI in 65 studies and (3) non-small cell lung cancer (adenocarcinomas) from benign fungal infection (granulomas) on 120 non-contrast CT studies. For each of these classification problems, CoLlAGE in conjunction with a random forest classifier outperformed state of the art radiomic descriptors (Haralick, Gabor, Histogram of Gradient Orientations).

Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): Distinguishing Tumor Confounders and Molecular Subtypes on MRI

We introduce a novel biologically inspired feature descriptor, Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe), that captures higher order co-occurrence patterns of local gradient tensors at a pixel level to distinguish disease phenotypes that have similar morphologic appearances. A number of pathologies (e.g. subtypes of breast cancer) have different histologic phenotypes but similar radiographic appearances. While texture features have been previously employed for distinguishing subtly different pathologies, they attempt to capture differences in global intensity patterns. In this paper we attempt to model CoLlAGe to identify higher order co-occurrence patterns of gradient tensors at a pixel level. The assumption behind this new feature is that different pathologies, even though they may have very similar overall texture and appearance on imaging, at a local scale, will have different co-occurring patterns with respect to gradient orientations. We demonstrate the utility of CoLIAGe in distinguishing two subtly different types of pathologies on MRI in the context of brain tumors and breast cancer. In the first problem, we look at CoLlAGe for distinguishing radiation effects from recurrent brain tumors over a cohort of 40 studies, and in the second, discriminating different molecular subtypes of breast cancer over a cohort of 73 studies. For both these challenging cohorts, CoLlAGe was found to have significantly improved classification performance, as compared to the traditional texture features such as Haralick, Gabor, local binary patterns, and histogram of gradients.

Radiomics and radiogenomics in lung cancer: A review for the clinician

Lung cancer is responsible for a large proportion of cancer-related deaths across the globe, with delayed detection being perhaps the most significant factor for its high mortality rate. Though the National Lung Screening Trial argues for screening of certain at-risk populations, the practical implementation of these screening efforts has not yet been successful and remains in high demand. Radiomics refers to the computerized extraction of data from radiologic images, and provides unique potential for making lung cancer screening more rapid and accurate using machine learning algorithms. The quantitative features analyzed express subvisual characteristics of images which correlate with pathogenesis of diseases. These features are broadly classified into four categories: intensity, structure, texture/gradient, and wavelet, based on the types of image attributes they capture. Many studies have been done to show correlation between these features and the malignant potential of a nodule on a chest CT. In cancer patients, these nodules also have features that can be correlated with prognosis and mutation status. The major limitations of radiomics are the lack of standardization of acquisition parameters, inconsistent radiomic methods, and lack of reproducibility. Researchers are working on overcoming these limitations, which would make radiomics more acceptable in the medical community.

Radiogenomic analysis of hypoxia pathway is predictive of overall survival in Glioblastoma

Hypoxia, a characteristic trait of Glioblastoma (GBM), is known to cause resistance to chemo-radiation treatment and is linked with poor survival. There is hence an urgent need to non-invasively characterize tumor hypoxia to improve GBM management. We hypothesized that (a) radiomic texture descriptors can capture tumor heterogeneity manifested as a result of molecular variations in tumor hypoxia, on routine treatment naïve MRI, and (b) these imaging based texture surrogate markers of hypoxia can discriminate GBM patients as short-term (STS), mid-term (MTS), and long-term survivors (LTS). 115 studies (33 STS, 41 MTS, 41 LTS) with gadolinium-enhanced T1-weighted MRI (Gd-T1w) and T2-weighted (T2w) and FLAIR MRI protocols and the corresponding RNA sequences were obtained. After expert segmentation of necrotic, enhancing, and edematous/nonenhancing tumor regions for every study, 30 radiomic texture descriptors were extracted from every region across every MRI protocol. Using the expression profile of 21 hypoxia-associated genes, a hypoxia enrichment score (HES) was obtained for the training cohort of 85 cases. Mutual information score was used to identify a subset of radiomic features that were most informative of HES within 3-fold cross-validation to categorize studies as STS, MTS, and LTS. When validated on an additional cohort of 30 studies (11 STS, 9 MTS, 10 LTS), our results revealed that the most discriminative features of HES were also able to distinguish STS from LTS (p = 0.003).

Single cell qPCR reveals that additional HAND2 and microRNA-1 facilitate the early reprogramming progress of seven-factor-induced human myocytes

The direct reprogramming of cardiac fibroblasts into induced cardiomyocyte (CM)-like cells (iCMs) holds great promise in restoring heart function. We previously found that human fibroblasts could be reprogrammed toward CM-like cells by 7 reprogramming factors; however, iCM reprogramming in human fibroblasts is both more difficult and more time-intensive than that in mouse cells. In this study, we investigated if additional reprogramming factors could quantitatively and/or qualitatively improve 7-factor-mediated human iCM reprogramming by single-cell quantitative PCR. We first validated 46 pairs of TaqMan® primers/probes that had sufficient efficiency and sensitivity to detect the significant difference of gene expression between individual H9 human embryonic stem cell (ESC)-differentiated CMs (H9CMs) and human fibroblasts. The expression profile of these 46 genes revealed an improved reprogramming in 12-week iCMs compared to 4-week iCMs reprogrammed by 7 factors, indicating a prolonged stochastic phase during human iCM reprogramming. Although none of additional one reprogramming factor yielded a greater number of iCMs, our single-cell qPCR revealed that additional HAND2 or microRNA-1 could facilitate the silencing of fibroblast genes and yield a better degree of reprogramming in more reprogrammed iCMs. Noticeably, the more HAND2 expressed, the higher-level were cardiac genes activated in 7Fs+HAND2-reprogrammed iCMs. In conclusion, HAND2 and microRNA-1 could help 7 factors to facilitate the early progress of iCM-reprogramming from human fibroblasts. Our study provides valuable information to further optimize a method of direct iCM-reprogramming in human cells.

Feature Driven Local Cell Graph (FeDeG): Predicting Overall Survival in Early Stage Lung Cancer

The local spatial arrangement of nuclei in histopathology image has been shown to have prognostic value in the context of different cancers. In order to capture the nuclear architectural information locally, local cell cluster graph based measurements have been proposed. However, conventional ways of cell graph construction only utilize nuclear spatial proximity, and do not differentiate different cell types while constructing a cell graph. In this paper, we present feature driven local cell graph (FeDeG), a new approach to constructing local cell graphs by simultaneously considering spatial proximity and attributes of the individual nuclei (e.g. shape, size, texture). In addition, we designed a new set of quantitative graph derived metrics to be extracted from FeDeGs, in turn capturing the interplay between different local cell clusters. We evaluated the efficacy of FeDeG features in a digitized H&E stained tissue micro-array (TMA) images cohort consists of 434 early stage non-small cell lung cancer for predicting short-term ( 5 years) survival. Across a 100 runs of 10-fold cross-validation, a linear discriminant classifier in conjunction with the 15 most predictive FeDeG features identified via the Wilcoxon Rank Sum Test (WRST) yielded an average of AUC = 0.68. By comparison, four state-of-the-art pathomic and a deep learning based classifier had a corresponding AUC of 0.56, 0.54, 0.61, 0.62, and 0.55 respectively.

Vascular Network Organization via Hough Transform (VaNgOGH): A Novel Radiomic Biomarker for Diagnosis and Treatment Response

As a “hallmark of cancer”, tumor-induced angiogenesis is one of the most important mechanisms of a tumor’s adaptation to changes in nutrient requirement. The angiogenic activity of certain tumors has been found to be predictive of a patient’s ultimate response to therapeutic intervention. This then begs the question if there are differences in vessel arrangement and corresponding convolutedness, between tumors that appear phenotypically similar, but respond differently to treatment. Even though textural radiomics and deep learning-based approaches have been shown to distinguish disease aggressiveness and assess therapeutic response, these descriptors do not specifically interpret differences in vessel characteristics. Moreover, most existing approaches have attempted to model disease characteristics just within tumor confines, or right outside, but do not consider explicit parenchymal vessel morphology. In this work, we introduce VaNgOGH (Vascular Network Organization via Hough transform), a new descriptor of architectural disorder of the tumor’s vascular network. We demonstrate the efficacy of VaNgOGH in two clinically challenging problems: (a) Predicting pathologically complete response (pCR) in breast cancer prior to treatment (BCa, N = 76) and (b) distinguishing benign nodules from malignant non-small cell lung cancer (LCa, N = 81). For both tasks, VaNgOGH had test area under the receiver operating characteristic curve (\(AUC_{BCa}\) = 0.75, \(AUC_{LCa}\) = 0.68) higher than, or comparable to, state of the art radiomic approaches (\(AUC_{BCa}\) = 0.75, \(AUC_{LCa}\) = 0.62) and convolutional neural networks (\(AUC_{BCa}\) = 0.67, \(AUC_{LCa}\) = 0.66). Interestingly, when a known radiomic signature was used in conjunction with VaNgOGH, \(AUC_{BCa}\) increased to 0.79.

Quantitative vessel tortuosity: A potential CT imaging biomarker for distinguishing lung granulomas from adenocarcinomas

Adenocarcinomas and active granulomas can both have a spiculated appearance on computed tomography (CT) and both are often fluorodeoxyglucose (FDG) avid on positron emission tomography (PET) scan, making them difficult to distinguish. Consequently, patients with benign granulomas are often subjected to invasive surgical biopsies or resections. In this study, quantitative vessel tortuosity (QVT), a novel CT imaging biomarker to distinguish between benign granulomas and adenocarcinomas on routine non-contrast lung CT scans is introduced. Our study comprised of CT scans of 290 patients from two different institutions, one cohort for training (N = 145) and the other (N = 145) for independent validation. In conjunction with a machine learning classifier, the top informative and stable QVT features yielded an area under receiver operating characteristic curve (ROC AUC) of 0.85 in the independent validation set. On the same cohort, the corresponding AUCs for two human experts including a radiologist and a pulmonologist were found to be 0.61 and 0.60, respectively. QVT features also outperformed well known shape and textural radiomic features which had a maximum AUC of 0.73 (p-value = 0.002), as well as features learned using a convolutional neural network AUC = 0.76 (p-value = 0.028). Our results suggest that QVT features could potentially serve as a non-invasive imaging biomarker to distinguish granulomas from adenocarcinomas on non-contrast CT scans.