by on July 31, 2020. For personal use only. jnm.snmjournals.org Downloaded from ABSTRACT Radiomics is a rapidly evolving field of research concerned with the extraction and quantification of patterns -the so-called radiomic features -within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape, and may, alone or in combination with demographic, histological, genomic or proteomic data, be used for clinical problem-solving. The goal of this CE article is to provide an introduction to the field, covering the basic radiomics workflow:feature calculation and selection, dimensionality reduction, and data processing . Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

No abstract

In a Special Report, the T-PLL International Study group presents consensus criteria for the diagnosis, staging, and treatment response assessment of patients with T-cell prolymphocytic leukemia.

We thank the patients and their families for their trust in taking part in this study. The study was academically funded and supported by the Medical University Vienna, the General Hospital Vienna, and the Research Center for Molecular Medicine (CeMM) of the Austrian Academy of Sciences. We gratefully acknowledge funding from the Vienna Science and Technology Fund (LS16-034 to GSF and UJ), the Austrian Science Fund (F4704-B20 to PV, F4711-B20 to GSF, and P27132-B20 to PBS), and the European Molecular Biology Organization Long Term Fellowship (1543-2012 to GIV, 733-2016 to TP). BS acknowledges

PurposeTo determine whether [18F]FDG PET/CT-derived radiomic features alone or in combination with clinical, laboratory and biological parameters are predictive of 2-year progression-free survival (PFS) in patients with mantle cell lymphoma (MCL), and whether they enable outcome prognostication.MethodsIncluded in this retrospective study were 107 treatment-naive MCL patients scheduled to receive CD20 antibody-based immuno(chemo)therapy. Standardized uptake values (SUV), total lesion glycolysis, and 16 co-occurrence matrix radiomic features were extracted from metabolic tumour volumes on pretherapy [18F]FDG PET/CT scans. A multilayer perceptron neural network in combination with logistic regression analyses for feature selection was used for prediction of 2-year PFS. International prognostic indices for MCL (MIPI and MIPI-b) were calculated and combined with the radiomic data. Kaplan–Meier estimates with log-rank tests were used for PFS prognostication.ResultsSUVmean (OR 1.272, P = 0.013) and Entropy (heterogeneity of glucose metabolism; OR 1.131, P = 0.027) were significantly predictive of 2-year PFS: median areas under the curve were 0.72 based on the two radiomic features alone, and 0.82 with the addition of clinical/laboratory/biological data. Higher SUVmean in combination with higher Entropy (SUVmean >3.55 and entropy >3.5), reflecting high “metabolic risk”, was associated with a poorer prognosis (median PFS 20.3 vs. 39.4 months, HR 2.285, P = 0.005). The best PFS prognostication was achieved using the MIPI-bm (MIPI-b and metabolic risk combined): median PFS 43.2, 38.2 and 20.3 months in the low-risk, intermediate-risk and high-risk groups respectively (P = 0.005).ConclusionIn MCL, the [18F]FDG PET/CT-derived radiomic features SUVmean and Entropy may improve prediction of 2-year PFS and PFS prognostication. The best results may be achieved using a combination of metabolic, clinical, laboratory and biological parameters.

Existing quantitative imaging biomarkers (QIBs) are associated with known biological tissue characteristics and follow a well-understood path of technical, biological and clinical validation before incorporation into clinical trials. In radiomics, novel data-driven processes extract numerous visually imperceptible statistical features from the imaging data with no a priori assumptions on their correlation with biological processes. The selection of relevant features (radiomic signature) and incorporation into clinical trials therefore requires additional considerations to ensure meaningful imaging endpoints. Also, the number of radiomic features tested means that power calculations would result in sample sizes impossible to achieve within clinical trials. This article examines how the process of standardising and validating data-driven imaging biomarkers differs from those based on biological associations. Radiomic signatures are best developed initially on datasets that represent diversity of acquisition protocols as well as diversity of disease and of normal findings, rather than within clinical trials with standardised and optimised protocols as this would risk the selection of radiomic features being linked to the imaging process rather than the pathology. Normalisation through discretisation and feature harmonisation are essential pre-processing steps. Biological correlation may be performed after the technical and clinical validity of a radiomic signature is established, but is not mandatory. Feature selection may be part of discovery within a radiomics-specific trial or represent exploratory endpoints within an established trial; a previously validated radiomic signature may even be used as a primary/secondary endpoint, particularly if associations are demonstrated with specific biological processes and pathways being targeted within clinical trials. Key Points • Data-driven processes like radiomics risk false discoveries due to high-dimensionality of the dataset compared to sample size, making adequate diversity of the data, cross-validation and external validation essential to mitigate the risks of spurious associations and overfitting. • Use of radiomic signatures within clinical trials requires multistep standardisation of image acquisition, image analysis and data mining processes. • Biological correlation may be established after clinical validation but is not mandatory.

Mycosis fungoides (MF) is the most common primary cutaneous T-cell lymphoma. While initially restricted to the skin, malignant cells can appear in blood, bone marrow and secondary lymphoid organs in later disease stages. However, only little is known about phenotypic and functional properties of malignant T cells in relationship to tissue environments over the course of disease progression. We thus profiled the tumor micromilieu in skin, blood and lymph node in a patient with advanced MF using single-cell RNA sequencing combined with V-D-J T-cell receptor sequencing. In skin, we identified clonally expanded T-cells with characteristic features of tissue-resident memory T-cells (TRM, CD69+CD27-NR4A1+RGS1+AHR+). In blood and lymph node, the malignant clones displayed a transcriptional program reminiscent of a more central memory-like phenotype (KLF2+TCF7+S1PR1+SELL+CCR7+), while retaining tissue-homing receptors (CLA, CCR10). The skin tumor microenvironment contained potentially tumor-permissive myeloid cells producing regulatory (IDO1) and Th2-associated mediators (CCL13, CCL17, CCL22). Given their expression of PVR, TNFRSF14 and CD80/CD86, they might be under direct control by TIGIT+CTLA4+CSF2+TNFSF14+ tumor cells. In sum, this study highlights the adaptive phenotypic and functional plasticity of MF tumor cell clones. Thus, the TRM-like phenotype enables long-term skin residence of MF cells. Their switch to a TCM-like phenotype with persistent skin homing molecule expression in the circulation might explain the multi-focal nature of MF.

MALT lymphomas express the chemokine receptor CXCR4 on a regular basis, and [68Ga]Ga-Pentixafor-PET has been shown to quantify CXCR4 expression non-invasively. We, therefore, aimed to evaluate [68Ga]Ga-Pentixafor-PET/MRI for the non-invasive assessment of MALT lymphomas. Methods: We included 36 MALT lymphoma patients, who had not undergone previous systemic or radiation therapy, in our prospective, IRB-approved, proof-of-concept study. Involved anatomic regions were the orbit (n=14), stomach (n=10), lungs (n=5), and other sites (soft-tissues n=3; adrenal gland, tonsils, parotid gland, and urinary bladder n=1, respectively). MRI sequences included an axial 2-point Dixon T1 VIBE SPAIR 3D sequence for PET attenuation correction; a coronal T2 HASTE sequence; and an axial echo-planar imaging SPAIR-based diffusion-weighted sequence (DWI) obtained during free-breathing (b-values, 50 and 800), with corresponding ADC (apparent diffusion coefficient) maps. Results: In 33/36 patients, there were MALT lymphomas with an increased uptake of [68Ga]Ga-Pentixafor; all current lymphoma manifestations showed an increased uptake and, accordingly, were positive on the PET/MRI. The remaining three patients had undergone surgery for their orbital MALT lymphomas prior to PET/MRI. Mean SUVmax was 8.6 ± 4.7, mean SUVmean was 4.7 ± 1.8, and mean SUVpeak was 8.0 ± 4.2. The mean SUVmax of the liver was 1.8, and the mean tumor-to-liver ratio was 2.9 ± 2.0. There were no significant differences in SUVmax (P=0.22), SUVmean (P=0.53), SUVpeak (P=0.29), or SUVt/l (P=0.92) between the four anatomic regions (orbit, stomach, lungs, other). The mean tumor volume was 146 ± 499. Conclusions: Our results thus indicate that [68Ga]Ga-Pentixafor-PET is feasible for the assessment of MALT lymphomas, with a good tumor-to-background ratio in terms of radiotracer uptake.