Tumor cell heterogeneity and its transcriptional bases in pancreatic cancer: a tale of two cell types and their many variants.

Pancreatic ductal adenocarcinoma (PDAC), one of the most highly lethal tumors, is characterized by complex histology, with a massive fibrotic stroma in which both pseudo-glandular structures and compact nests of abnormally differentiated tumor cells are embedded, in different proportions and with different mutual relationships in space. This complexity and the heterogeneity of the tumor component have hindered the development of a broadly accepted, clinically actionable classification of PDACs, either on a morphological or a molecular basis. Here, we discuss evidence suggesting that such heterogeneity can to a large extent, albeit not exclusively, be traced back to two main classes of PDAC cells that commonly coexist in the same tumor: cells that maintained their ability to differentiate toward endodermal, mucin-producing epithelia and epithelial cells unable to form glandular structures and instead characterized by various levels of squamous differentiation and the expression of mesenchymal lineage genes. The underlying gene regulatory networks and how they are controlled by distinct transcription factors, as well as the practical implications of these two different populations of tumor cells, are discussed.

One label is all you need: Interpretable AI-enhanced histopathology for oncology.

Artificial Intelligence (AI)-enhanced histopathology presents unprecedented opportunities to benefit oncology through interpretable methods that require only one overall label per hematoxylin and eosin (H&E) slide with no tissue-level annotations. We present a structured review of these methods organized by their degree of verifiability and by commonly recurring application areas in oncological characterization. First, we discuss morphological markers (tumor presence/absence, metastases, subtypes, grades) in which AI-identified regions of interest (ROIs) within whole slide images (WSIs) verifiably overlap with pathologist-identified ROIs. Second, we discuss molecular markers (gene expression, molecular subtyping) that are not verified via H&E but rather based on overlap with positive regions on adjacent tissue. Third, we discuss genetic markers (mutations, mutational burden, microsatellite instability, chromosomal instability) that current technologies cannot verify if AI methods spatially resolve specific genetic alterations. Fourth, we discuss the direct prediction of survival to which AI-identified histopathological features quantitatively correlate but are nonetheless not mechanistically verifiable. Finally, we discuss in detail several opportunities and challenges for these one-label-per-slide methods within oncology. Opportunities include reducing the cost of research and clinical care, reducing the workload of clinicians, personalized medicine, and unlocking the full potential of histopathology through new imaging-based biomarkers. Current challenges include explainability and interpretability, validation via adjacent tissue sections, reproducibility, data availability, computational needs, data requirements, domain adaptability, external validation, dataset imbalances, and finally commercialization and clinical potential. Ultimately, the relative ease and minimum upfront cost with which relevant data can be collected in addition to the plethora of available AI methods for outcome-driven analysis will surmount these current limitations and achieve the innumerable opportunities associated with AI-driven histopathology for the benefit of oncology.

Novel Insights Into the International Association for the Study of Lung Cancer Grading System for Lung Adenocarcinoma.

The new grading system for lung adenocarcinoma proposed by the International Association for the Study of Lung Cancer (IASLC) defines prognostic subgroups on the basis of histologic patterns observed on surgical specimens. This study sought to provide novel insights into the IASLC grading system, with particular focus on recurrence-specific survival (RSS) and lung cancer-specific survival among patients with stage I adenocarcinoma. Under the IASLC grading system, tumors were classified as grade 1 (lepidic predominant with <20% high-grade patterns [micropapillary, solid, and complex glandular]), grade 2 (acinar or papillary predominant with <20% high-grade patterns), or grade 3 (≥20% high-grade patterns). Kaplan-Meier survival estimates, pathologic features, and genomic profiles were investigated for patients whose disease was reclassified into a higher grade under the IASLC grading system on the basis of the hypothesis that they would strongly resemble patients with predominant high-grade tumors. Overall, 423 (29%) of 1443 patients with grade 1 or 2 tumors classified based on the predominant pattern-based grading system had their tumors upgraded to grade 3 based on the IASLC grading system. The RSS curves for patients with upgraded tumors were significantly different from those for patients with grade 1 or 2 tumors (log-rank P < .001) but not from those for patients with predominant high-grade patterns (P = .3). Patients with upgraded tumors had a similar incidence of visceral pleural invasion and spread of tumor through air spaces as patients with predominant high-grade patterns. In multivariable models, the IASLC grading system remained significantly associated with RSS and lung cancer-specific survival after adjustment for aggressive pathologic features such as visceral pleural invasion and spread of tumor through air spaces. The IASLC grading system outperforms the predominant pattern-based grading system and appropriately reclassifies tumors into higher grades with worse prognosis, even after other pathologic features of aggressiveness are considered.

Automatic removal of large blood vasculature for objective assessment of brain tumors using quantitative dynamic contrast-enhanced magnetic resonance imaging.

The presence of a normal large blood vessel (LBV) in a tumor region can impact the evaluation of quantitative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parameters and tumor classification. Hence, there is a need for automatic removal of LBVs from brain tissues including intratumoral regions for achieving an objective assessment of tumors. This retrospective study included 103 histopathologically confirmed brain tumor patients who underwent MRI, including DCE-MRI data acquisition. Quantitative DCE-MRI analysis was performed for computing various parameters such as wash-out slope (Slope-2), relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF), blood plasma volume fraction (Vp), and volume transfer constant (Ktrans). An approach based on data-clustering algorithm, morphological operations, and quantitative DCE-MRI maps was proposed for the segmentation of normal LBVs in brain tissues, including the tumor region. Here, three widely used data-clustering algorithms were evaluated on two types of quantitative maps: (a) Slope-2, and (b) a new proposed combination of rCBV and Slope-2 maps. Fluid-attenuated inversion recovery-MRI hyperintense lesions were also automatically segmented using deep learning-based architecture. The accuracy of LBV segmentation was qualitatively assessed blindly by two experienced observers, and Likert scoring was also obtained from each individual and compared using Cohen's Kappa test, and multiple statistical features from quantitative DCE-MRI parameters were obtained in the segmented tumor. t-test and receiver operating characteristic (ROC) curve analysis were performed for comparing the effect of removal of LBVs on parameters as well as on tumor grading. k-means clustering exhibited better accuracy and computational efficiency. Tumors, in particular high-grade gliomas (HGGs), showed a high contrast compared with normal tissues (relative % difference = 18.5%) on quantitative maps after the removal of LBVs. Statistical features (95th percentile values) of all parameters in the tumor region showed a statistically significant difference (p < 0.05) between with and without LBV maps. Similar results were obtained for the ROC curve analysis for differentiation between low-grade gliomas and HGGs. Moreover, after the removal of LBVs, the rCBV, rCBF, and Vp maps show better visualization of tumor regions.

A hybrid deep CNN model for brain tumor image multi-classification.

The current approach to diagnosing and classifying brain tumors relies on the histological evaluation of biopsy samples, which is invasive, time-consuming, and susceptible to manual errors. These limitations underscore the pressing need for a fully automated, deep-learning-based multi-classification system for brain malignancies. This article aims to leverage a deep convolutional neural network (CNN) to enhance early detection and presents three distinct CNN models designed for different types of classification tasks. The first CNN model achieves an impressive detection accuracy of 99.53% for brain tumors. The second CNN model, with an accuracy of 93.81%, proficiently categorizes brain tumors into five distinct types: normal, glioma, meningioma, pituitary, and metastatic. Furthermore, the third CNN model demonstrates an accuracy of 98.56% in accurately classifying brain tumors into their different grades. To ensure optimal performance, a grid search optimization approach is employed to automatically fine-tune all the relevant hyperparameters of the CNN models. The utilization of large, publicly accessible clinical datasets results in robust and reliable classification outcomes. This article conducts a comprehensive comparison of the proposed models against classical models, such as AlexNet, DenseNet121, ResNet-101, VGG-19, and GoogleNet, reaffirming the superiority of the deep CNN-based approach in advancing the field of brain tumor classification and early detection.

Efficacy of Preoperative Biopsy in Predicting the Newly Proposed Histologic Grade of Resected Lung Adenocarcinoma.

A novel histologic grading system for invasive lung adenocarcinomas (LUAD) has been newly proposed and adopted by the World Health Organization (WHO) classification. We aimed to evaluate the concordance of newly established grades between preoperative biopsy and surgically resected LUAD samples. Additionally, factors affecting the concordance rate and its prognostic impact were also analyzed. In this study, surgically resected specimens of 222 patients with invasive LUAD and their preoperative biopsies collected between January 2013 and December 2020 were used. We determined the histologic subtypes of preoperative biopsy and surgically resected specimens and classified them separately according to the novel WHO grading system. The overall concordance rate of the novel WHO grades between preoperative biopsy and surgically resected samples was 81.5%, which was higher than that of the predominant subtype. When stratified by grades, the concordance rate of grades 1 (well-differentiated, 84.2%) and 3 (poorly differentiated, 89.1%) was found to be superior compared to grade 2 (moderately differentiated, 66.2%). Overall, the concordance rate was not significantly different from biopsy characteristics, including the number of biopsy samples, biopsy sample size, and tumor area size. On the other hand, the concordance rate of grades 1 and 2 was significantly higher in tumors with smaller invasive diameters, and that of grade 3 was significantly higher in tumors with larger invasive diameters. Preoperative biopsy specimens can predict the novel WHO grades, especially grades 1 and 3 of surgically resected specimens, more accurately than the former grading system, regardless of preoperative biopsy or clinicopathologic characteristics.

A three-component multi-b-value diffusion-weighted imaging might be a useful biomarker for detecting microstructural features in gliomas with differences in malignancy and IDH-1 mutation status.

OBJECTIVES: The purpose of the study was to explore the performance of a three-component diffusion model in evaluating the degree of malignancy and isocitrate dehydrogenase 1 (IDH-1) gene type of gliomas. METHODS: Overall, 60 patients with gliomas were enrolled. The intermediate and perfusion-related diffusion coefficients (Dint and Dp) and fractions of strictly limited, intermediate, and perfusion-related diffusion (Fvery-slow, Fint, and Fp) were obtained with a three-component diffusion model. Parameters were also obtained from a diffusion kurtosis model and mono- and biexponential models. All parameters were compared between different tumor grades and IDH-1 gene types. Diagnostic performance and logistic regression analyses were performed. RESULTS: High-grade gliomas (HGGs) had significantly higher Fint, Fvery-slow, and Dp values but significantly lower Fp and Dint values than low-grade gliomas (LGGs), and Fint and Fp differed significantly among grade II, III, and IV gliomas (p < 0.05 for all). Fint achieved the highest AUC of 0.872 in differentiating between LGGs and HGGs. Logistic regression analysis revealed that in each model, Fint, diffusion coefficient (D), apparent diffusion coefficient (ADC), mean diffusivity (MD), and mean kurtosis (MK) were associated with glioma grading. After multiple regression analysis, Fint remained the only differentiator. Additionally, Fint and Fp showed significant differences between IDH-1 mutated and IDH-1 wild-type gliomas (p = 0.007 and 0.01, respectively). CONCLUSIONS: The three-component DWI model served as a useful biomarker for detecting microstructural features in gliomas with different grades and IDH-1 mutation statuses. KEY POINTS: • The three-component model enables the estimation of an intermediate diffusion component. • The three-component model performed better than the other models in glioma grading and genotyping. • Fint was useful in evaluating the grade and genotype of gliomas.

Coordinatized lesion location analysis empowering ROI-based radiomics diagnosis on brain gliomas.

OBJECTIVES: To assess the value of coordinatized lesion location analysis (CLLA), in empowering ROI-based imaging diagnosis of gliomas by improving accuracy and generalization performances. METHODS: In this retrospective study, pre-operative contrasted T1-weighted and T2-weighted MR images were obtained from patients with gliomas from three centers: Jinling Hospital, Tiantan Hospital, and the Cancer Genome Atlas Program. Based on CLLA and ROI-based radiomic analyses, a fusion location-radiomics model was constructed to predict tumor grades, isocitrate dehydrogenase (IDH) status, and overall survival (OS). An inter-site cross-validation strategy was used for assessing the performances of the fusion model on accuracy and generalization with the value of area under the curve (AUC) and delta accuracy (ACC) (ACCtesting-ACCtraining). Comparisons of diagnostic performances were performed between the fusion model and the other two models constructed with location and radiomics analysis using DeLong's test and Wilcoxon signed ranks test. RESULTS: A total of 679 patients (mean age, 50 years ± 14 [standard deviation]; 388 men) were enrolled. Based on tumor location probabilistic maps, fusion location-radiomics models (averaged AUC values of grade/IDH/OS: 0.756/0.748/0.768) showed the highest accuracy in contrast to radiomics models (0.731/0.686/0.716) and location models (0.706/0.712/0.740). Notably, fusion models ([median Delta ACC: - 0.125, interquartile range: 0.130]) demonstrated improved generalization than that of radiomics model ([- 0.200, 0.195], p = 0.018). CONCLUSIONS: CLLA could empower ROI-based radiomics diagnosis of gliomas by improving the accuracy and generalization of the models. CLINICAL RELEVANCE STATEMENT: This study proposed a coordinatized lesion location analysis for glioma diagnosis, which could improve the performances of the conventional ROI-based radiomics model in accuracy and generalization. KEY POINTS: • Using coordinatized lesion location analysis, we mapped anatomic distribution patterns of gliomas with specific pathological and clinical features and constructed glioma prediction models. • We integrated coordinatized lesion location analysis into ROI-based analysis of radiomics to propose new fusion location-radiomics models. • Fusion location-radiomics models, with the advantages of being less influenced by variabilities, improved accuracy, and generalization performances of ROI-based radiomics models on predicting the diagnosis of gliomas.

Association of Membranous WNT-1 and Nuclear mTOR with Endometrial Cancer Grade.

Endometrial cancer remains a common cancer affecting the female reproductive system. There is still a need for more efficient ways of determining the degree of malignancy and optimizing treatment. WNT and mTOR are components of signaling pathways within tumor cells, and dysfunction of either protein is associated with the pathogenesis of neoplasms. Therefore, the aim of our study was to assess the impact of subcellular WNT-1 and mTOR levels on the clinical course of endometrial cancer. WNT-1 and mTOR levels in the plasma membrane, nucleus, and cytoplasm were evaluated using immunohistochemical staining in a group of 64 patients with endometrial cancer of grades 1-3 and FIGO stages I-IV. We discovered that the levels of WNT-1 and mTOR expression in the cellular compartments were associated with tumor grade and staging. Membranous WNT-1 was negatively associated, whereas cytoplasmic WNT-1 and nuclear mTOR were positively associated with higher grading of endometrial cancer. Furthermore, nuclear mTOR was positively associated with FIGO stages IB-IV. To conclude, we found that the assessment of WNT-1 in the cell membrane may be useful for exclusion of grade 3 neoplasms, whereas cytoplasmic WNT-1 and nuclear mTOR may be used as indicators for confirmation of grade 3 neoplasms.

[Primary salivary gland tumors from a pathology perspective : Morphomolecular peculiarities and diagnostic and therapeutic challenges]. / Primäre Speicheldrüsentumoren aus Sicht der Pathologie : Morphomolekulare Besonderheiten und diagnostisch-therapeutische Herausforderungen.

Similar to tumors of other organs, salivary gland neoplasms were historically viewed as a single neoplastic entity and mostly treated as such. Accordingly, only the clinical tumor stage, and not the histological subtype, was considered to be of significant prognostic impact. However, over the years, several distinct sub-entities have been characterized based on morphological features, such as adenoid cystic carcinoma, mucoepidermoid carcinoma, acinic cell carcinoma, and salivary duct carcinoma. Most importantly, the nosology of salivary gland carcinomas has undergone a dynamic "splitting" on the basis of morphological, immunophenotypic, and molecular characteristics, so that 21 independent carcinomas are now listed in the current World Health Organization (WHO) classification. Moreover, it has become evident that splitting of these carcinoma subtypes no longer represents a "pathologist's hobby," but carries significant prognostic and therapeutic relevance for optimized cancer surgery and potentially systemic therapy. The current review summarizes the major features of salivary gland tumors, both benign and malignant, and gives an account of their classification systems and genetic profiles.

MRI-Based Computer-Aided Diagnostic Model to Predict Tumor Grading and Clinical Outcomes in Patients With Soft Tissue Sarcoma.

BACKGROUND: MRI acts as a potential resource for exploration and interpretation to identify tumor characterization by advanced computer-aided diagnostic (CAD) methods. PURPOSE: To evaluate and validate the performance of MRI-based CAD models for identifying low-grade and high-grade soft tissue sarcoma (STS) and for investigating survival prognostication. STUDY TYPE: Retrospective. SUBJECTS: A total of 540 patients (295 male/female: 295/245, median age: 42 years) with STSs. FIELD SEQUENCE: 5-T MRI with T1 WI sequence and fat-suppressed T2 -weighted (T2 FS) sequence. ASSESSMENT: Manual regions of interests (ROIs) were delineated for generation of radiomic features. Automatic segmentation and pretrained convolutional neural networks (CNNs) were performed for deep learning (DL) analysis. The last fully connected layer at the top of CNNs was removed, and the global max pooling was added to transform feature maps to numeric values. Tumor grade was determined on histological specimens. STATISTICAL TESTS: The support vector machine was adopted as the classifier for all MRI-based models. The DL signature was derived from the DL-MRI model with the highest area under the curve (AUC). The significant clinical variables, tumor location and size, integrated with radiomics and DL signatures were ready for construction of clinical-MRI nomogram to identify tumor grading. The prognostic value of clinical variables and these MRI-based signatures for overall survival (OS) was evaluated via Cox proportional hazard. RESULTS: The clinical-MRI differentiation nomogram represented an AUC of 0.870 in the training cohort, and an AUC of 0.855, accuracy of 79.01%, sensitivity of 79.03%, and specificity of 78.95% in the validation cohort. The prognostic model showed good performance for OS with 3-year C-index of 0.681 and 0.642 and 5-year C-index of 0.722 and 0.676 in the training and validation cohorts. DATA CONCLUSION: MRI-based CAD nomogram represents effective abilities in classification of low-grade and high-grade STSs. The MRI-based prognostic model yields favorable preoperative capacities to identify long-term survivals for STSs. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 4.

WHO grading system for invasive pulmonary lung adenocarcinoma reveals distinct molecular signature: An analysis from the cancer genome atlas database.

Lung adenocarcinoma grading has gained interest in the past years. Recently a three-tier tumor grading was proposed showing that it is related to patients' prognosis. Nevertheless, the underlying molecular basis of this morphological grading remains partly unknown. The aim of our work is to take advantage of The Cancer Genome Atlas lung adenocarcinoma (TCGA_LUAD) cohort to describe the molecular data associated to tumor grading. We performed a study on publicly available data of the TCGA database first by assessing a tumor grade on downloadable tumor slides. Secondly we analyzed the molecular features of each tumor grade group. Our work was performed on a study group of 449 patients. We show that aneuploidy score was significantly different between grade 2 and grade 3 groups with different chromosomal imbalance (p < 0.001). SCGB1A1 mRNA expression was higher in grade 2 (p = 0.0179) whereas NUP155, CHFR, POLQ and CDC7 have a higher expression in grade 3 (p = 0.0189, 0.0427, 0.0427 and 0.427 respectively). GZMB and KRT80 have a higher methylation of DNA in grade 2 (p = 0.0201 and 0.0359 respectively). MT1G, CLEC12B and NDUFA7 have a higher methylation of DNA in grade 3 (p < 0.001, 0.0246 and 0.0359 respectively). We showed that the number of activated pathways is different between grade 2 and grade 3 patients (p = 0.004). We showed that differentially expressed genes by mRNA analysis and DNA methylation analysis involve several genes implied in chemoresistance. This could suggest that grade 3 lung adenocarcinoma might be more resistant to chemotherapy.

Cytokines in Renal Cell Carcinoma: A Step Towards Earlier Detection and Targeted Therapy.

Symptoms of renal cell carcinoma (RCC) have typically late onset and correlate with its advanced stage. No biomarkers of RCC are currently available. The present study analyzed the immuno-biochemical profile of RCC by measuring the levels of cytokines engaged in RCC pathophysiology. Cytokines were examined by capture sandwich immunoassays in tumor tissue and urine. Specimens of cancer and nearby healthy kidney tissues were obtained during nephrectomy from 60 RCC patients. The urine was obtained from both patients and healthy subjects. The findings in RCC tumor tissue compared to healthy renal tissues were following: (i) increases in interleukin-15 (IL-15), vascular endothelial growth factor (VEGF), interferon gamma-induced protein-10 (IP-10), macrophage inflammatory protein-1ß (MIP-1ß), monocyte chemoattractant protein-1 (MCP-1), and eotaxin, with VEGF, IP-10, and MIP-1ß significantly associated with the histologic tumor nuclear grading (NG); (ii) increases in platelet-derived growth factor (PDGF), IL-15, MIP-1ß, eotaxin, and MCP-1 in urine, with significant associations noticed between cytokines and disease stages for eotaxin and MCP-1; and (iii) decreases in PDGF, IL-15, MCP-1, VEGF, MIP-1ß, and eotaxin in urine from six patients on the third day after nephrectomy. We conclude that cytokines may play a critical role in the local pathogenesis of RCC, which opens the way for potential targeting of these molecules in novel therapies and their use as biomarkers for early noninvasive detection of RCC.

[Tumor budding in colorectal cancer-Information for clinical use and instructions for practical evaluation]. / Tumor Budding beim kolorektalen Karzinom ­ Informationen zur klinischen Anwendung und Anleitung zur praktischen Bestimmung.

BACKGROUND: Some patients with high-risk colorectal cancer show a worse prognosis within the same UICC stage. Therefore, the identification of additional risk factors is necessary to find the best treatment for these patients. OBJECTIVE: In which settings can tumor budding help the clinical decision-making process for treatment planning and how should scoring be performed? MATERIAL AND METHODS: Evaluation of current publications on tumor budding with an emphasis on practical grading and potential problems in the determination of tumor budding. RESULTS: Tumor budding is a significant risk factor for worse clinical outcome of colorectal cancer and can influence clinical decision-making in pT1 and stage II colorectal cancer. A scoring method was standardized by the ITBCC 2016 and is feasible in everyday practice. Challenges in assessment can be addressed by increasing awareness of potential problem cases.

Magnetic Resonance Imaging-Based Radiomics Nomogram for Prediction of the Histopathological Grade of Soft Tissue Sarcomas: A Two-Center Study.

BACKGROUND: Preoperative prediction of soft tissue sarcoma (STS) grade is important for treatment decisions. Therefore, formulation an STS grade model is strongly needed. PURPOSE: To develop and test an magnetic resonance imaging (MRI)-based radiomics nomogram for predicting the grade of STS (low-grade vs. high grade). STUDY TYPE: Retrospective POPULATION: One hundred and eighty patients with STS confirmed by pathologic results at two independent institutions were enrolled (training set, N = 109; external validation set, N = 71). FIELD STRENGTH/SEQUENCE: Unenhanced T1-weighted (T1WI) and fat-suppressed T2-weighted images (FS-T2WI) were acquired at 1.5 T and 3.0 T. ASSESSMENT: Clinical-MRI characteristics included age, gender, tumor-node-metastasis (TNM) stage, American Joint Committee on Cancer (AJCC) stage, progression-free survival (PFS), and MRI morphological features (ie, margin). Radiomics feature extraction were performed on T1WI and FS-T2WI images by minimum redundancy maximum relevance (MRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm. The selected features constructed three radiomics signatures models (RS-T1， RS-FST2, and RS-Combined). Univariate and multivariate logistic regression analysis were applied for screening significant risk factors. Radiomics nomogram was constructed by incorporating the radiomics signature and risk factors. STATISTICAL TESTS: Clinical-MRI characteristics were performed by a univariate analysis. Model performances (discrimination, calibration, and clinical usefulness) were validated in the external validation set. The RS-T1 model, RS-FST2 model, and RS-Combined model had an area under curves (AUCs) of 0.645, 0.641, and 0.829, respectively, in the external validation set. The radiomics nomogram, incorporating significant risk factors and the RS-Combined model had AUCs of 0.916 (95%CI, 0.866-0.966, training set) and 0.879 (95%CI, 0.791-0.967, external validation set), and demonstrated good calibration and good clinical utility. DATA CONCLUSION: The proposed noninvasive MRI-based radiomics models showed good performance in differentiating low-grade from high-grade STSs. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Advanced imaging techniques for neuro-oncologic tumor diagnosis, with an emphasis on PET-MRI imaging of malignant brain tumors.

PURPOSE OF REVIEW: This review will explore the latest in advanced imaging techniques, with a focus on the complementary nature of multiparametric, multimodality imaging using magnetic resonance imaging (MRI) and positron emission tomography (PET). RECENT FINDINGS: Advanced MRI techniques including perfusion-weighted imaging (PWI), MR spectroscopy (MRS), diffusion-weighted imaging (DWI), and MR chemical exchange saturation transfer (CEST) offer significant advantages over conventional MR imaging when evaluating tumor extent, predicting grade, and assessing treatment response. PET performed in addition to advanced MRI provides complementary information regarding tumor metabolic properties, particularly when performed simultaneously. 18F-fluoroethyltyrosine (FET) PET improves the specificity of tumor diagnosis and evaluation of post-treatment changes. Incorporation of radiogenomics and machine learning methods further improve advanced imaging. The complementary nature of combining advanced imaging techniques across modalities for brain tumor imaging and incorporating technologies such as radiogenomics has the potential to reshape the landscape in neuro-oncology.

Comparison of amide proton transfer imaging and magnetization transfer imaging in revealing glioma grades and proliferative activities: a histogram analysis.

PURPOSE: Comprehensive understanding glioma metabolic characters is of great help for patient management. We aimed to compare amide proton transfer imaging (APTw) and magnetization transfer imaging (MT) in predicting glioma malignancy and reflecting tumor proliferation. METHODS: Thirty low-grade gliomas (LGGs) and 39 high-grade gliomas (HGGs) were prospectively included, of which 58 samples Ki-67 levels were quantified. Anatomical MRI, APTw, and MT were scanned, and magnetization transfer ratio (MTR) and asymmetric magnetic transfer ratio at 3.5 ppm (MTRasym(3.5ppm)) were calculated. ROIs were semi-automatically drawn with ImageJ, from which histogram features, including 5th, 25th, 50th, mean, 70th, 90th, and 95th percentiles were extracted. The independent t test was used to test differences in LGGs and HGGs, and correlations between histogram features and tumor grades, Ki-67 were revealed by Spearman's rank or Pearson's correlation analysis. RESULTS: The maximum correlation coefficient (R) values of APTw were 0.526 (p < 0.001) with tumor grades and 0.397 (p < 0.001) with Ki-67 at 90th percentiles, while only 5th and 25th percentiles of MT significantly correlated with tumor grades. Moreover, APTw features were significantly different in LGGs and HGGs, except 5th percentile. The most significantly different feature was 95th percentile, providing the excellent AUC of 0.808. However, the best feature in MTR was 5th percentiles with AUC of 0.703. Combing 5th and 95th of APTw achieved highest AUC Of 0.837. CONCLUSIONS: Both APTw and MT provide quantitative information for tumor metabolite imaging. However, APTw supplys more specific information in reflecting glioma biological behaviors than MT, and well differentiates glioma malignancy.

The relationship between amount of extra-prostatic extension and length of capsular contact: performances from MR images and radical prostatectomy specimens

Backround/aim: In prostate cancer, extraprostatic extension (EPE) is an unfavorable prognostic factor, and the grade of EPE is correlated with the prognosis. This study aims to evaluate the utility of length of capsular contact (LCC ) in predicting the grade of EPE by correlating the measurements from MRI images and the measurements performed from radical prostatectomy specimens. Materials and methods: MR images and specimens of 110 tumors are analyzed retrospectively. The specimens are used as reference to validate the presence of EPE and to measure the ground truth LCC. MR images are evaluated by two radiologists to identify the presence of EPE and to predict the LCC indirectly. Reliability, accuracy, sensitivity, and specificity of the evaluations are analyzed in comparison with the findings obtained from the specimens. Results: In detection of EPE existence, the radiologists achieve almost the same performance (all AUCs = 0.73) with optimal cut-off values lead to moderate sensitivity and specificity pairs (For cut-off = 15.8 mm; Se = 0.69, Sp = 0.68 and for cut-off of 14.5 mm: Se = 0.77, Sp = 0.62). In distinguishing high-grade EPE from low-grade EPE, the radiologists accomplish very similar performances (AUCs = 0.73 and 0.72) Optimal thresholds of 20.0 mm and 18.5 mm for the readers retrospectively reveal medium sensitivity and specificity pairs (Se = 0.64, Sp = 0.67; Se = 0.64, Sp = 0.67). Conclusion: Consistent LCC estimates can be obtained from MR images providing a beneficial metric for detecting the existence of EPE and for discriminating the grades of EPE.

Analysis of postprocessing steps for residue function dependent dynamic susceptibility contrast (DSC)-MRI biomarkers and their clinical impact on glioma grading for both 1.5 and 3T.

BACKGROUND: Dynamic susceptibility contrast (DSC)-MRI analysis pipelines differ across studies and sites, potentially confounding the clinical value and use of the derived biomarkers. PURPOSE/HYPOTHESIS: To investigate how postprocessing steps for computation of cerebral blood volume (CBV) and residue function dependent parameters (cerebral blood flow [CBF], mean transit time [MTT], capillary transit heterogeneity [CTH]) impact glioma grading. STUDY TYPE: Retrospective study from The Cancer Imaging Archive (TCIA). POPULATION: Forty-nine subjects with low- and high-grade gliomas. FIELD STRENGTH/SEQUENCE: 1.5 and 3.0T clinical systems using a single-echo echo planar imaging (EPI) acquisition. ASSESSMENT: Manual regions of interest (ROIs) were provided by TCIA and automatically segmented ROIs were generated by k-means clustering. CBV was calculated based on conventional equations. Residue function dependent biomarkers (CBF, MTT, CTH) were found by two deconvolution methods: circular discretization followed by a signal-to-noise ratio (SNR)-adapted eigenvalue thresholding (Method 1) and Volterra discretization with L-curve-based Tikhonov regularization (Method 2). STATISTICAL TESTS: Analysis of variance, receiver operating characteristics (ROC), and logistic regression tests. RESULTS: MTT alone was unable to statistically differentiate glioma grade (P > 0.139). When normalized, tumor CBF, CTH, and CBV did not differ across field strengths (P > 0.141). Biomarkers normalized to automatically segmented regions performed equally (rCTH AUROC is 0.73 compared with 0.74) or better (rCBF AUROC increases from 0.74-0.84; rCBV AUROC increases 0.78-0.86) than manually drawn ROIs. By updating the current deconvolution steps (Method 2), rCTH can act as a classifier for glioma grade (P < 0.007), but not if processed by current conventional DSC methods (Method 1) (P > 0.577). Lastly, higher-order biomarkers (eg, rCBF and rCTH) along with rCBV increases AUROC to 0.92 for differentiating tumor grade as compared with 0.78 and 0.86 (manual and automatic reference regions, respectively) for rCBV alone. DATA CONCLUSION: With optimized analysis pipelines, higher-order perfusion biomarkers (rCBF and rCTH) improve glioma grading as compared with CBV alone. Additionally, postprocessing steps impact thresholds needed for glioma grading. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:547-553.

Predicting the ISUP grade of clear cell renal cell carcinoma with multiparametric MR and multiphase CT radiomics.

OBJECTIVE: To investigate externally validated magnetic resonance (MR)-based and computed tomography (CT)-based machine learning (ML) models for grading clear cell renal cell carcinoma (ccRCC). MATERIALS AND METHODS: Patients with pathologically proven ccRCC in 2009-2018 were retrospectively included for model development and internal validation; patients from another independent institution and The Cancer Imaging Archive dataset were included for external validation. Features were extracted from T1-weighted, T2-weighted, corticomedullary-phase (CMP), and nephrographic-phase (NP) MR as well as precontrast-phase (PCP), CMP, and NP CT. CatBoost was used for ML-model investigation. The reproducibility of texture features was assessed using intraclass correlation coefficient (ICC). Accuracy (ACC) was used for ML-model performance evaluation. RESULTS: Twenty external and 440 internal cases were included. Among 368 and 276 texture features from MR and CT, 322 and 250 features with good to excellent reproducibility (ICC ≥ 0.75) were included for ML-model development. The best MR- and CT-based ML models satisfactorily distinguished high- from low-grade ccRCCs in internal (MR-ACC = 73% and CT-ACC = 79%) and external (MR-ACC = 74% and CT-ACC = 69%) validation. Compared to single-sequence or single-phase images, the classifiers based on all-sequence MR (71% to 73% in internal and 64% to 74% in external validation) and all-phase CT (77% to 79% in internal and 61% to 69% in external validation) images had significant increases in ACC. CONCLUSIONS: MR- and CT-based ML models are valuable noninvasive techniques for discriminating high- from low-grade ccRCCs, and multiparameter MR- and multiphase CT-based classifiers are potentially superior to those based on single-sequence or single-phase imaging. KEY POINTS: • Both the MR- and CT-based machine learning models are reliable predictors for differentiating high- from low-grade ccRCCs. • ML models based on multiparameter MR sequences and multiphase CT images potentially outperform those based on single-sequence or single-phase images in ccRCC grading.