Whole-body magnetic resonance imaging plus serological follow-up for early identification of progression in smouldering myeloma patients to prevent development of end-organ damage

Reproducible Radiomics Features from Multi-MRI-Scanner Test-Retest-Study: Influence on Performance and Generalizability of Models

BACKGROUND

Radiomics models trained on data from one center typically show a decline of performance when applied to data from external centers, hindering their introduction into large-scale clinical practice. Current expert recommendations suggest to use only reproducible radiomics features isolated by multiscanner test-retest experiments, which might help to overcome the problem of limited generalizability to external data.

PURPOSE

To evaluate the influence of using only a subset of robust radiomics features, defined in a prior in vivo multi-MRI-scanner test-retest-study, on the performance and generalizability of radiomics models.

STUDY TYPE

Retrospective.

POPULATION

Patients with monoclonal plasma cell disorders. Training set (117 MRIs from center 1); internal test set (42 MRIs from center 1); external test set (143 MRIs from center 2-8).

FIELD STRENGTH/SEQUENCE

1.5T and 3.0T; T1-weighted turbo spin echo.

ASSESSMENT

The task for the radiomics models was to predict plasma cell infiltration, determined by bone marrow biopsy, noninvasively from MRI. Radiomics machine learning models, including linear regressor, support vector regressor (SVR), and random forest regressor (RFR), were trained on data from center 1, using either all radiomics features, or using only reproducible radiomics features. Models were tested on an internal (center 1) and a multicentric external data set (center 2-8).

STATISTICAL TESTS

Pearson correlation coefficient r and mean absolute error (MAE) between predicted and actual plasma cell infiltration. Fisher's z-transformation, Wilcoxon signed-rank test, Wilcoxon rank-sum test; significance level P < 0.05.

RESULTS

When using only reproducible features compared with all features, the performance of the SVR on the external test set significantly improved (r = 0.43 vs. r = 0.18 and MAE = 22.6 vs. MAE = 28.2). For the RFR, the performance on the external test set deteriorated when using only reproducible instead of all radiomics features (r = 0.33 vs. r = 0.44, P = 0.29 and MAE = 21.9 vs. MAE = 20.5, P = 0.10).

CONCLUSION

Using only reproducible radiomics features improves the external performance of some, but not all machine learning models, and did not automatically lead to an improvement of the external performance of the overall best radiomics model.

LEVEL OF EVIDENCE: 3

TECHNICAL EFFICACY

Stage 2.

Diagnosis and management of smouldering myeloma: A British Society for Haematology Good Practice Paper

Multiple myeloma is a bone marrow-based plasma cell tumour that develops from asymptomatic pre-cursor conditions smouldering myeloma and monoclonal gammopathy of uncertain significance and all are characterised by the presence of a monoclonal protein in the blood. Diagnosis and distinction between these conditions is based on blood tests, the bone marrow biopsy and cross sectional imaging. There are various risk stratification models that group patients with smouldering myeloma into risk groups based on risk of progression to symptomatic disease. Management is mainly observational for patients with smouldering myeloma although clinical trials for high-risk disease may be available. Restaging is required if evidence for progression.

Clinician preferences on treatment of smoldering myeloma: a cross-sectional survey

Background

Smoldering myeloma (SMM) is an asymptomatic precursor condition to multiple myeloma (MM) with a variable risk of progression. The management of high-risk SMM (HR-SMM) remains controversial, particularly with changes in diagnostic criteria that led to reclassifying of some patients with SMM to MM. This study aimed to assess clinician preferences for whether to treat patients with HR-SMM and/or patients with MM diagnosed solely by SLiM criteria (free light chain ratio >100, bone marrow plasma cell percentage >60, greater than two focal marrow lesions on MRI) through an electronic survey.

Methods

This was a cross-sectional survey of clinicians, conducted via an anonymous online REDCap survey from May 16th to July 5th, 2023. The survey included questions on demographics, SMM surveillance practices, and management preferences for two clinical scenarios (HR-SMM and MM based solely on the free light chain ratio >100 criterion). Data was analysed descriptively via Microsoft Excel.

Findings

A total of 146 clinicians completed the full survey, with 92% recommending against routine treatment for a patient with HR-SMM based on a single time point assessment, instead preferring active surveillance. For patients with MM diagnosed solely on the basis of a free light chain ratio >100, 61% recommended active treatment, while 37% recommended active surveillance. The most common reasons recommending against treatment of HR-SMM were toxicity, lack of demonstrated overall survival benefit, and low MM-defining event rates in clinical trials.

Interpretation

The survey indicates that most clinicians recommend against routine treatment for HR-SMM. Active surveillance is the prevailing standard of care and it is therefore an appropriate control arm in future SMM trials. More randomised trials are needed to determine if early treatment of modern-era SMM offers a net benefit to patients.

Funding

None.

How do we image patients with multiple myeloma and precursor states?

Advances in morphological and functional imaging have led to superior detection of early bone disease, bone marrow infiltration, paramedullary and extramedullary involvement in multiple myeloma. The two functional imaging modalities that are most widely used and standardized are 18F-fluorodeoxyglucose-Positron emission tomography/computed tomography (FDG PET/CT) and whole-body magnetic resonance imaging with diffusion-weighted imaging (WB DW-MRI). Both prospective and retrospective studies have demonstrated that WB DW-MRI is more sensitive than PET/CT in the detection of baseline tumour burden and to assess response after therapy. In patients with smouldering multiple myeloma, WB DW-MRI is now the preferred imaging modality to rule out two or more unequivocal lesions which would be considered a myeloma-defining event by the updated international myeloma working group (IMWG) criteria. In addition to sensitive detection of baseline tumour burden, both PET/CT and WB DW-MRI have been successfully used for monitoring response to therapy and provide information that is complementary to IMWG response assessment and bone marrow minimal residual disease. In this article, we present 3 vignettes illustrating how we approach the use of modern imaging in the management of patients with multiple myeloma and precursor states, with a specific focus on recent data that have emerged since the publication of the IMWG consensus guideline on imaging. We have utilized data from prospective and retrospective studies to provide a rationale for our approach to imaging in these clinical scenarios and highlighted knowledge gaps requiring future investigation.

Identification of focal lesion characteristics in MRI which indicate presence of corresponding osteolytic lesion in CT in patients with multiple myeloma

PURPOSE

The presence of bone marrow focal lesions and osteolytic lesions in patients with multiple myeloma (MM) is of high prognostic significance for their individual outcome. It is not known yet why some focal lesions seen in MRI, reflecting localized bone marrow infiltration of myeloma cells, remain non-lytic, whereas others are associated with destruction of mineralized bone. In this study, we analyzed MRI characteristics of manually segmented focal lesions in MM patients to identify possible features that might discriminate lytic and non-lytic lesions.

METHOD

The initial cohort included a total of 140 patients with different stages of MM who had undergone both whole-body MRI and whole-body low-dose CT within 30 days, and of which 29 satisfied the inclusion criteria for this study. Focal lesions in MRI and corresponding osteolytic areas in CT were segmented manually. Analysis of the lesions included volume, location and first order texture features analysis.

RESULTS

There were significantly more lytic lesions in the axial skeleton than in the appendicular skeleton (p = 0.037). Out of 926 focal lesions in the axial skeleton seen on MRI, 544 (59.3 %) were osteolytic. Analysis of volume and first order texture features showed differences in texture and volume between focal lesions in MRI with and without local bone destruction in CT, but these findings were not statistically significant.

CONCLUSIONS

Neither morphological imaging characteristics like size and location nor first order texture features could predict whether focal lesions seen in MRI would exhibit corresponding bone destruction in CT. Studies performing biopsies of such lesions are ongoing.

Presenting Symptoms in Newly Diagnosed Myeloma, Relation to Organ Damage, and Implications for Symptom-Directed Screening: A Secondary Analysis from the Tackling Early Morbidity and Mortality in Myeloma (TEAMM) Trial

Multiple myeloma (MM) patients risk diagnostic delays and irreversible organ damage. In those with newly diagnosed myeloma, we explored the presenting symptoms to identify early signals of MM and their relationships to organ damage. The symptoms were recorded in patients' own words at diagnosis and included diagnostic time intervals. Those seen by a haematologist >6 months prior to MM diagnosis were classified as precursor disease (PD). Most (962/977) patients provided data. Back pain (38%), other pain (31%) and systemic symptoms (28%) predominated. Patients rarely complain of 'bone pain', simply 'pain'. Vertebral fractures are under-recognised as pathological and are the predominant irreversible organ damage (27% of patients), impacting the performance status (PS) and associated with back pain (odds ratio (OR) 6.14 [CI 4.47-8.44]), bone disease (OR 3.71 [CI 1.88-7.32]) and age >65 years (OR 1.58 [CI 1.15-2.17]). Renal failure is less frequent and associated with gastrointestinal symptoms (OR 2.23 [CI1.28-3.91]), age >65 years (OR 2.14 [CI1.28-3.91]) and absence of back pain (OR 0.44 [CI 0.29-0.67]). Patients with known PD (n = 149) had fewer vertebral fractures (p = 0.001), fewer adverse features (p = 0.001), less decline in PS (p = 0.001) and a lower stage (p = 0.04) than 813 with de novo MM. Our data suggest subgroups suitable for trials of 'symptom-directed' screening: those with back pain, unexplained pain, a general decline in health or low-impact vertebral compression fractures.

Deep Learning for Automatic Bone Marrow Apparent Diffusion Coefficient Measurements From Whole-Body Magnetic Resonance Imaging in Patients With Multiple Myeloma: A Retrospective Multicenter Study

OBJECTIVES

Diffusion-weighted magnetic resonance imaging (MRI) is increasingly important in patients with multiple myeloma (MM). The objective of this study was to train and test an algorithm for automatic pelvic bone marrow analysis from whole-body apparent diffusion coefficient (ADC) maps in patients with MM, which automatically segments pelvic bones and subsequently extracts objective, representative ADC measurements from each bone.

MATERIALS AND METHODS

In this retrospective multicentric study, 180 MRIs from 54 patients were annotated (semi)manually and used to train an nnU-Net for automatic, individual segmentation of the right hip bone, the left hip bone, and the sacral bone. The quality of the automatic segmentation was evaluated on 15 manually segmented whole-body MRIs from 3 centers using the dice score. In 3 independent test sets from 3 centers, which comprised a total of 312 whole-body MRIs, agreement between automatically extracted mean ADC values from the nnU-Net segmentation and manual ADC measurements from 2 independent radiologists was evaluated. Bland-Altman plots were constructed, and absolute bias, relative bias to mean, limits of agreement, and coefficients of variation were calculated. In 56 patients with newly diagnosed MM who had undergone bone marrow biopsy, ADC measurements were correlated with biopsy results using Spearman correlation.

RESULTS

The ADC-nnU-Net achieved automatic segmentations with mean dice scores of 0.92, 0.93, and 0.85 for the right pelvis, the left pelvis, and the sacral bone, whereas the interrater experiment gave mean dice scores of 0.86, 0.86, and 0.77, respectively. The agreement between radiologists' manual ADC measurements and automatic ADC measurements was as follows: the bias between the first reader and the automatic approach was 49 × 10 -6 mm 2 /s, 7 × 10 -6 mm 2 /s, and -58 × 10 -6 mm 2 /s, and the bias between the second reader and the automatic approach was 12 × 10 -6 mm 2 /s, 2 × 10 -6 mm 2 /s, and -66 × 10 -6 mm 2 /s for the right pelvis, the left pelvis, and the sacral bone, respectively. The bias between reader 1 and reader 2 was 40 × 10 -6 mm 2 /s, 8 × 10 -6 mm 2 /s, and 7 × 10 -6 mm 2 /s, and the mean absolute difference between manual readers was 84 × 10 -6 mm 2 /s, 65 × 10 -6 mm 2 /s, and 75 × 10 -6 mm 2 /s. Automatically extracted ADC values significantly correlated with bone marrow plasma cell infiltration ( R = 0.36, P = 0.007).

CONCLUSIONS

In this study, a nnU-Net was trained that can automatically segment pelvic bone marrow from whole-body ADC maps in multicentric data sets with a quality comparable to manual segmentations. This approach allows automatic, objective bone marrow ADC measurements, which agree well with manual ADC measurements and can help to overcome interrater variability or nonrepresentative measurements. Automatically extracted ADC values significantly correlate with bone marrow plasma cell infiltration and might be of value for automatic staging, risk stratification, or therapy response assessment.