The Critical Role of Imaging in the Management of Multiple Myeloma

Current Status and Future of Artificial Intelligence in MM Imaging: A Systematic Review

Artificial intelligence (AI) has attracted increasing attention as a tool for the detection and management of several medical conditions. Multiple myeloma (MM), a malignancy characterized by uncontrolled proliferation of plasma cells, is one of the most common hematologic malignancies, which relies on imaging for diagnosis and management. We aimed to review the current literature and trends in AI research of MM imaging. This study was performed according to the PRISMA guidelines. Three main concepts were used in the search algorithm, including "artificial intelligence" in "radiologic examinations" of patients with "multiple myeloma". The algorithm was used to search the PubMed, Embase, and Web of Science databases. Articles were screened based on the inclusion and exclusion criteria. In the end, we used the checklist for Artificial Intelligence in Medical Imaging (CLAIM) criteria to evaluate the manuscripts. We provided the percentage of studies that were compliant with each criterion as a measure of the quality of AI research on MM. The initial search yielded 977 results. After reviewing them, 14 final studies were selected. The studies used a wide array of imaging modalities. Radiomics analysis and segmentation tasks were the most popular studies (10/14 studies). The common purposes of radiomics studies included the differentiation of MM bone lesions from other lesions and the prediction of relapse. The goal of the segmentation studies was to develop algorithms for the automatic segmentation of important structures in MM. Dice score was the most common assessment tool in segmentation studies, which ranged from 0.80 to 0.97. These studies show that imaging is a valuable data source for medical AI models and plays an even greater role in the management of MM.

Response-Adapted Therapy for Newly Diagnosed Multiple Myeloma

PURPOSE OF REVIEW

The development of potent novel agents has improved outcomes for patients with multiple myeloma (MM). Heterogeneity of response to therapy, an expanding arsenal of treatment options, and cost are however major challenges for physicians making treatment decisions. Response-adapted therapy is hence an attractive strategy for sequencing of therapy in MM. Despite its successful application in other haematologic malignancies, response-adapted therapy is yet to become a standard of care for MM. We provide our perspective on response-adapted therapeutic strategies evaluated thus far and how they may be implemented and improved on in treatment algorithms of the future.

RECENT FINDINGS

While older studies suggested that early response based on International Myeloma Working Group response criteria could impact long-term outcomes, recent data have contradicted these findings. The advent of minimal residual disease (MRD) as a powerful prognostic factor in MM has raised the promise of MRD-adapted treatment strategies. The development of more sensitive techniques for paraprotein quantification as well as imaging modalities to detect extramedullary disease is likely to change response assessment in MM. These techniques combined with MRD assessment may provide sensitive and holistic response assessments which could be evaluated in clinical trials. Response-adapted treatment algorithms have the potential to allow an individualised treatment strategy, maximising efficacy, while minimising toxicities and cost. Standardisation of MRD methodology, incorporation of imaging into response assessment, and the optimal management of MRD positive patients are key questions to be addressed in future trials.

Comprehensive Updates in the Role of Imaging for Multiple Myeloma Management Based on Recent International Guidelines

The diagnostic and treatment methods of multiple myeloma (MM) have been rapidly evolving owing to advances in imaging techniques and new therapeutic agents. Imaging has begun to play an important role in the management of MM, and international guidelines are frequently updated. Since the publication of 2015 International Myeloma Working Group (IMWG) criteria for the diagnosis of MM, whole-body magnetic resonance imaging (MRI) or low-dose whole-body computed tomography (CT) and ¹⁸F-fluorodeoxyglucose positron emission tomography/CT have entered the mainstream as diagnostic and treatment response assessment tools. The 2019 IMWG guidelines also provide imaging recommendations for various clinical settings. Accordingly, radiologists have become a key component of MM management. In this review, we provide an overview of updates in the MM field with an emphasis on imaging modalities.

Improvement in the Symptoms and VEGF Levels after Resection of an Extrame Dullary Spinal Tumor and Additional Chemotherapy in a Patient with Multiple Myeloma Complicated with POEMS Syndrome

We herein report a case of multiple myeloma and polyneuropathy, organomegaly, endocrinopathy, myeloma protein, and skin changes (POEMS) syndrome. The patient experienced exacerbated gait disturbance due to weakness and numbness in the lower limbs. Thoracic magnetic resonance imaging revealed an extramedullary tumor with spinal compression that required surgical resection. Plasmacytoma was diagnosed based on a biopsy. Radiation, betamethasone, and chemotherapy were therefore administered. Surgical removal of extramedullary tumors improved his symptoms, motor conduction velocity, and amplitude of the muscle action potential in the peroneal and tibial nerves, as shown by the nerve conduction study. Surgery also decreased the serum vascular endothelial growth factor levels. The patient required additional chemotherapy due to multiple myeloma and showed better outcomes nine months after discharge. The benefits of some treatments remain controversial due to the small number of patients. However, our findings reveal that an early diagnosis and comprehensive treatment may result in better outcomes in such patients.

Correlation of MicroRNA 17-92 Cluster Host Gene (MIR17HG) Polymorphisms With Susceptibility and Prognosis for Multiple Myeloma

PURPOSE

To explore the correlation of MIR17HG polymorphism with susceptibility and prognosis of multiple myeloma (MM).

PATIENTS AND METHODS

A total of 217 MM patients treated with high-dose melphalan combined with autologous peripheral blood stem-cell transplantation at our hospital were enrolled as the case group, and 220 healthy people were included as the control group. Sequenom MassARRAY iPLEX Gold single nucleotide polymorphism genotyping was used to detect polymorphisms of MIR17HG, including rs7336610, rs17735387, rs4284505, and rs1428.

RESULTS

An increased risk of MM was found in patients who carried the rs7336610 T allele and rs4284505 G allele, and the higher the Durie-Salmon and International Staging System stages were, the more MM patients carrying rs7336610 CT + TT genotype and rs4284505 AG + GG genotype (all P < .05). Haplotype AC (rs4284505-rs1428) and CA (rs7336610-rs4284505) evidently reduce MM risk, whereas haplotype GC (rs4284505-rs1428) significantly elevated MM risk (all P < .05). Kaplan-Meier curve analysis demonstrated that rs7336610 CC genotype carriers had higher 5-year survival rate than CT + TT genotype carriers (P = .034), and the AA genotype carriers of rs4284505 had higher 5-year survival rate than AG + GG genotype carriers (P < .001).

CONCLUSION

Polymorphisms of MIR17HG rs7336610 and rs1428 were correlated with MM risk and prognosis.

Copper 64-labeled daratumumab as a PET/CT imaging tracer for multiple myeloma

As a growing number of patients with multiple myeloma (MM) respond to upfront therapies while eventually relapsing in a time frame that is often unpredictable, attention has increasingly focused on developing novel diagnostic criteria to also account for disease dissemination. Positron emission tomography/computed tomography (PET/CT) is often used as a noninvasive monitoring strategy to assess cancer cell dissemination, but because the uptake of the currently used radiotracer 18fluorodeoxyglucose (¹⁸F-FDG) is a function of the metabolic activity of both malignant and nonmalignant cells, the results frequently lack sufficient specificity. Radiolabeled antibodies targeting MM tissue may detect disease irrespective of cell metabolism. Hence, we conjugated the clinically significant CD38-directed human antibody daratumumab (Darzalex [Dara]) to the DOTA chelator and labeled it with the positron-emitting radionuclide copper 64 (⁶⁴Cu; ⁶⁴Cu-DOTA-Dara). Here, we show that ⁶⁴Cu-DOTA-Dara can efficiently bind CD38 on the surface of MM cells and was mainly detected in the bones associated with tumor in a MM murine model. We also show that PET/CT based on ⁶⁴Cu-DOTA-Dara displays a higher resolution and specificity to detect MM cell dissemination than does ¹⁸F-FDG PET/CT and was even more sensitive than were bioluminescence signals. We therefore have supporting evidence for using ⁶⁴Cu-DOTA-Dara as a novel imaging agent for MM.

Impact of Synchronous Multiple Primary Malignant Tumors on Newly Diagnosed Hematological Malignancies

BACKGROUND

Hematological malignancies are occasionally observed with synchronous multiple primary malignant tumors (sMPMTs) at diagnosis. We aimed to clarify the impact of sMPMTs on newly diagnosed hematological malignancies and determine the optimal treatment strategies.

PATIENTS AND METHODS

We analyzed the outcomes of 649 patients with hematological malignancies, including 19 patients with sMPMTs (2.9%), and compared the outcomes between patients with and without sMPMTs.

RESULTS

The overall survival (OS) and disease-free survival (DFS) rates for patients with sMPMTs were 77% and 70%, respectively, at 2 years; these rates were not statistically different from those for patients without sMPMTs (P = .17 and P = .64, respectively). Multivariate analysis showed that the presence of sMPMTs was not a significant prognostic factor for OS, DFS, or relapse (hazard ratio [HR] 1.48, 95% confidence interval [CI] 0.65-3.38, P = .35; HR 0.97, 95% CI 0.46-2.10, P = .97; and HR 0.79, 95% CI 0.29-2.14, P = .65). In patients with sMPMTs, the order of treatment was not a significant prognostic factor. However, discontinuation of treatment was a marginally favorable factor and might reflect a selection bias.

CONCLUSION

The presence of sMPMTs was not a significant risk factor for patients with newly diagnosed hematological malignancies. It is important to provide adequate treatment for both hematological malignancies and solid tumors at the physician's discretion.