Superficial fibromatosis: MRI radiomics and T2 mapping correlate with treatment response

MRI T2 mapping assessment of T2 relaxation time in desmoid tumors as a quantitative imaging biomarker of tumor response: preliminary results

Objectives

Because size-based imaging criteria poorly capture biologic response in desmoid-type fibromatosis (DF), changes in MRI T2 signal intensity are frequently used as a response surrogate, but remain qualitative. We hypothesized that absolute quantification of DF T2 relaxation time derived from parametric T2 maps would be a feasible and effective imaging biomarker of disease activity.

Methods

This IRB-approved retrospective study included 11 patients with DF, managed by observation or systemic therapy, assessed by 3T MRI. Tumor maximum diameter, volume, and T2-weighted signal intensity were derived from manual tumor segmentations. Tumor:muscle T2 signal ratios were recorded. Two readers measured tumor T2 relaxation times using a commercial T2 scanning sequence, manual ROI delineation and commercial calculation software enabling estimation of reader reliability. Objective response rates based on RECIST1.1 and best responses were compared between size-based and signal-based parameters.

Results

Median patient age was 52.6 years; 8 subjects were female (73%). Nine patients with longitudinal assessments were followed for an average of 314 days. Median baseline tumor diameter was 7.2 cm (range 4.4 - 18.2 cm). Median baseline T2 was 65.1 ms (range 40.4 - 94.8 ms, n=11); median at last follow-up was 44.3 ms (-32% from baseline; range 29.3 - 94.7 ms, n=9). T2 relaxation times correlated with tumor:muscle T2 signal ratios, Spearman p=0.78 (p<0.001). T2 mapping showed high inter-reader reliability, ICC=0.84. The best response as a percentage change in T2 values was statistically significant (mean -17.9%, p=0.05, paired t-test) while change in diameter was not (mean -8.9%, p=0.12).

Conclusions

Analysis of T2 relaxation time maps of DF may offer a feasible quantitative biomarker for assessing the extent of response to treatment. This approach may have high inter-reader reliability.

Radiomics for the Detection of Active Sacroiliitis Using MR Imaging

Detecting active inflammatory sacroiliitis at an early stage is vital for prescribing medications that can modulate disease progression and significantly delay or prevent debilitating forms of axial spondyloarthropathy. Conventional radiography and computed tomography offer limited sensitivity in detecting acute inflammatory findings as these methods primarily identify chronic structural lesions. Conversely, Magnetic Resonance Imaging (MRI) is the preferred technique for detecting bone marrow edema, although it is a complex process requiring extensive expertise. Additionally, ascertaining the origin of lesions can be challenging, even for experienced medical professionals. Machine learning (ML) has showcased its proficiency in various fields by uncovering patterns that are not easily perceived from multi-dimensional datasets derived from medical imaging. The aim of this study is to develop a radiomic signature to aid clinicians in diagnosing active sacroiliitis. A total of 354 sacroiliac joints were segmented from axial fluid-sensitive MRI images, and their radiomic features were extracted. After selecting the most informative features, a number of ML algorithms were utilized to identify the optimal method for detecting active sacroiliitis, leading to the selection of an Extreme Gradient Boosting (XGBoost) model that accomplished an Area Under the Receiver-Operating Characteristic curve (AUC-ROC) of 0.71, thus further showcasing the potential of radiomics in the field.

Soft Tissue Masses of the Hand: A Review of Clinical Presentation and Imaging Features

More than 15% of all soft-tissue tumors arise in the hand. Because of the location of these tumors, even small abnormalities may be alarming to patients on presentation. Although the majority of lesions are benign and can be diagnosed solely by history and physical examination, additional imaging workup may be required to confirm a diagnosis or define anatomic extent of involvement. This paper aims to review the basic epidemiology, clinical presentation, imaging findings, and treatment options of the more common soft-tissue tumors of the hand.