Radiomics

Development of a Multi-Modality Imaging Approach to evaluate Lupus Nephritis and initial results.

© Author(s) (or their employer(s)) 2019. Published by BMJ.
Annals of the Rheumatic Diseases. 2019 June;78(2)

Abstract

BACKGROUND:
Lupus nephritis (LN) remains a significant cause of morbidity and mortality in subjects with Systemic Lupus Erythematosus (SLE). The gold standard for evaluation of LN remains the kidney biopsy, whereas renal function is usually evaluated by eGFR and urinary protein:creatinine ratio. More effective and sensitive methodology is needed to assess LN and also the response to treatment. Functional imaging of the kidney using quantitative techniques has great potential, as it can assess kidney function and pathologic changes non-invasively by evaluating perfusion, oxygenation, cellular density and fibrosis.
OBJECTIVE:
To develop a multi-modality imaging approach for the evaluation of the spectrum of pathologic changes in LN.

METHODS:

In this multi-center study, subjects who were having a standard of care renal biopsy for LN were asked to participate in the imaging evaluation. Local Institutional Review Board approval was obtained, and subjects signed an Informed Consent Form. Dynamic contrast enhanced MRI (DCE-MRI) was employed to detect changes in vascularization and perfusion, Diffusion Weighted Imaging (DWI) to assess interstitial diffusion, T2*Map/BOLD – the tissue oxygenation and T1rho to evaluate fibrosis. The imaging scores will be compared to renal biopsy, including ISN/RPS classification of LN, activity index and chronicity index.

RESULTS:
Five patients have been evaluated to date and their imaging data assessed for quality. The initial results have demonstrated the feasibility of acquiring multi-modality imaging data, including dynamic imaging sequences, in the multi-center trial setting. Figure 1 illustrates scans from a representative patient. This study will determine whether multi-modality imaging could become an effective, non-invasive tool to assess renal function and pathology in LN.
CONCLUSION:
The initial assessment of 5 LN subjects has established the feasibility of multi-modality imaging as a tool to evaluate LN in a multi-center study. By assessing functional and structural MRI outcomes and correlating them to clinical data, this study will provide essential preliminary evidence on the value of multi-modality imaging in diagnosis and evaluating the response to treatment of LN patients.

Magnetic Resonance Imaging Tenosynovitis and Osteitis are Independent Predictors of Radiographic and MRI Damage Progression in Rheumatoid Arthritis Patients In Clincial Remission

Copyright © Author(s) (or their employer(s)) 2019. No commercial re-use. See rights and permissions. Published by BMJ
Annals of the Rheumatic Diseases. 2019 June;78(2)_suppl. doi: 10.1136/annrheumdis-2019-eular.2006

Abstract

BACKGROUND:
Progression of structural joint damage occurs in 20-30 % of patients with rheumatoid arthritis (RA) in clinical remission1. Magnetic resonance imaging (MRI)-detected synovitis and in particular osteitis/bone marrow edema (BME) are known predictors of structural progression in both active RA and in remission, but the predictive value of adding MRI tenosynovitis assessment as potential predictor in patients in clinical remission has not been investigated.

OBJECTIVES:
To investigate the predictive value of baseline MRI inflammatory and damage parameters on 2 year MRI and X-ray damage progression in an RA cohort in clinical remission, following MRI and conventional treat-to-target (T2T) strategies.

METHODS:
200 RA patients in clinical remission (DAS28-CRP<3.2 and no swollen joints) on conventional DMARDs, included in the randomized IMAGINE-RA trial2 (conventional DAS28 + MRI-guided T2T strategy targeting absence of BME vs conventional DAS28 guided T2T strategy) had baseline and 2 years contrast-enhanced MRIs of the dominant wrist and 2nd-5th MCP joints and X-rays of hands and feet performed, which were evaluated with known chronology by two experienced readers according to the OMERACT RAMRIS scoring system and Sharp/van der Heijde method, respectively.

The following potentially predictive baseline variables: MRI BME, synovitis, tenosynovitis, MRI and X-ray erosion and joint space narrowing (JSN) score, CRP, DAS28, smoking status, gender, age and patient group were tested in univariate logistic regression analyses with 2-year progression in MRI combined damage score, Total Sharp Score (TSS), and MRI and X-ray JSN and erosion scores as dependent variables. Variables with p<0.1, age, gender and patient group were included in multivariable logistic regression analyses with backward selection.

RESULTS:
Based on univariate analyses MRI BME, synovitis, tenosynovitis, x-ray erosion and JSN, gender and age were included in subsequent multivariable analyses. Independent MRI predictors of structural progression were BME (MRI progression) and tenosynovitis (MRI and X-ray progression), MRI combined damage score: sum score of MRI erosion and JSN scores.

CONCLUSION:
This trial is the first to report that MRI tenosynovitis independently predicts both X-ray and MRI damage progression in RA patients in clinical remission. Further studies are needed to confirm MRI-determined tenosynovitis as predictor of progressive joint destruction in RA clinical remission.

Richter Transformation of Chronic Lymphocytic Leukemia: A Review of Fluorodeoxyglucose Positron Emission Tomography–Computed Tomography and Molecular Diagnostics

Copyright © 2017 © 2017, Shaikh et al.
Cureus. 2017 Jan;9(1) doi: 10.7759/cureus.968

Abstract

BACKGROUND:
Chronic lymphocytic leukemia (CLL) is a low-grade B-cell proliferative disease with a generally indolent course. In a few cases, it undergoes transformation and becomes a more aggressive malignancy, such as diffuse large B-cell lymphoma (DLBCL). This process, which is called Richter transformation (RT), is often detected too late and is associated with a poor prognosis. There are multiple molecular diagnostic approaches to detect RT in preexisting CLL. Metabolic imaging using 18-fluorine fluorodeoxyglucose positron emission tomography–computed tomography (18F-FDG PET/CT) can be a very useful tool for early detection of RT and which can hence allow for timely intervention, thereby improving the patient’s chances of survival.

Translational Radiomics: Defining the Strategy Pipeline and Considerations for Application-Part II: From Clinical implementation to Enterprise.

Enterprise imaging has channeled various technological innovations to the field of clinical radiology, ranging from advanced imaging equipment and postacquisition iterative reconstruction tools to image analysis and computer-aided detection tools. More recently, the advancements in the field of quantitative image analysis coupled with machine learning-based data analytics, classification, and integration have ushered us into the era of radiomics, which has tremendous potential in clinical decision support as well as drug discovery. There are important issues to consider to incorporate radiomics as a clinically applicable system and a commercially viable solution. In this two-part series, we offer insights into the development of the translational pipeline for radiomics from methodology to clinical implementation (Part 1) and from that to enterprise development (Part 2)

Technical Challenges in the Clinical Application of Radiomics

Radiomics is a quantitative approach to medical image analysis targeted at deciphering the morphologic and functional features of a lesion. Radiomic methods can be applied across various malignant conditions to identify tumor phenotype characteristics in the images that correlate with their likelihood of survival, as well as their association with the underlying biology. Identifying this set of characteristic features, called tumor signature, holds tremendous value in predicting the behavior and progression of cancer, which in turn has the potential to predict its response to various therapeutic options. We discuss the technical challenges encountered in the application of radiomics, in terms of methodology, workflow integration, and user experience, that need to be addressed to harness its true potential.

Translational Radiomics: Defining the Strategy Pipeline and Considerations for Application-Part 1: From Methodology to Clinical Implementation.

Enterprise imaging has channeled various technological innovations to the field of clinical radiology, ranging from advanced imaging equipment and postacquisition iterative reconstruction tools to image analysis and computer-aided detection tools. More recently, the advancements in the field of quantitative image analysis coupled with machine learning-based data analytics, classification, and integration have ushered us into the era of radiomics, which has tremendous potential in clinical decision support as well as drug discovery. There are important issues to consider to incorporate radiomics as a clinically applicable system and a commercially viable solution. In this two-part series, we offer insights into the development of the translational pipeline for radiomics from methodology to clinical implementation (Part 1) and from that to enterprise development (Part 2)