Deep Learning Enables Spatial Mapping of the Mosaic Microenvironment of Myeloma Bone Marrow Trephine Biopsies.

Bone marrow trephine biopsy is crucial for the diagnosis of multiple myeloma. However, the complexity of bone marrow cellular, morphologic, and spatial architecture preserved in trephine samples hinders comprehensive evaluation. To dissect the diverse cellular communities and mosaic tissue habitats, we developed a superpixel-inspired deep learning method (MoSaicNet) that adapts to complex tissue architectures and a cell imbalance aware deep learning pipeline (AwareNet) to enable accurate detection and classification of rare cell types in multiplex immunohistochemistry images. MoSaicNet and AwareNet achieved an AUC of >0.98 for tissue and cellular classification on separate test datasets. Application of MoSaicNet and AwareNet enabled investigation of bone heterogeneity and thickness as well as spatial histology analysis of bone marrow trephine samples from monoclonal gammopathies of undetermined significance (MGUS) and from paired newly diagnosed and posttreatment multiple myeloma. The most significant difference between MGUS and newly diagnosed multiple myeloma (NDMM) samples was not related to cell density but to spatial heterogeneity, with reduced spatial proximity of BLIMP1+ tumor cells to CD8+ cells in MGUS compared with NDMM samples. Following treatment of patients with multiple myeloma, there was a reduction in the density of BLIMP1+ tumor cells, effector CD8+ T cells, and regulatory T cells, indicative of an altered immune microenvironment. Finally, bone heterogeneity decreased following treatment of patients with multiple myeloma. In summary, deep learning-based spatial mapping of bone marrow trephine biopsies can provide insights into the cellular topography of the myeloma marrow microenvironment and complement aspirate-based techniques. SIGNIFICANCE: Spatial analysis of bone marrow trephine biopsies using histology, deep learning, and tailored algorithms reveals the bone marrow architectural heterogeneity and evolution during myeloma progression and treatment.

Self-supervised deep learning for highly efficient spatial immunophenotyping.

BACKGROUND: Efficient biomarker discovery and clinical translation depend on the fast and accurate analytical output from crucial technologies such as multiplex imaging. However, reliable cell classification often requires extensive annotations. Label-efficient strategies are urgently needed to reveal diverse cell distribution and spatial interactions in large-scale multiplex datasets. METHODS: This study proposed Self-supervised Learning for Antigen Detection (SANDI) for accurate cell phenotyping while mitigating the annotation burden. The model first learns intrinsic pairwise similarities in unlabelled cell images, followed by a classification step to map learnt features to cell labels using a small set of annotated references. We acquired four multiplex immunohistochemistry datasets and one imaging mass cytometry dataset, comprising 2825 to 15,258 single-cell images to train and test the model. FINDINGS: With 1% annotations (18-114 cells), SANDI achieved weighted F1-scores ranging from 0.82 to 0.98 across the five datasets, which was comparable to the fully supervised classifier trained on 1828-11,459 annotated cells (-0.002 to -0.053 of averaged weighted F1-score, Wilcoxon rank-sum test, P = 0.31). Leveraging the immune checkpoint markers stained in ovarian cancer slides, SANDI-based cell identification reveals spatial expulsion between PD1-expressing T helper cells and T regulatory cells, suggesting an interplay between PD1 expression and T regulatory cell-mediated immunosuppression. INTERPRETATION: By striking a fine balance between minimal expert guidance and the power of deep learning to learn similarity within abundant data, SANDI presents new opportunities for efficient, large-scale learning for histology multiplex imaging data. FUNDING: This study was funded by the Royal Marsden/ICR National Institute of Health Research Biomedical Research Centre.

High patient satisfaction and increased physical activity following a remote multidisciplinary team multiple myeloma clinic.

PURPOSE: Patients with multiple myeloma suffer from disease-related complications such as bone destruction, toxicities from repeated therapies and age-related co-morbidities. With improved treatment options, patients are living longer and have specific survivorship needs such as low exercise levels that need to be addressed. In this study, we designed, implemented and evaluated a multidisciplinary team (MDT) myeloma clinic that provided participants with tailored exercise and lifestyle advice. METHODS: The Promoting Individualised Self-Management and Survivorship (PrISMS) clinic was set up in two UK myeloma centres. This remote MDT clinic comprised of a doctor, a nurse specialist and a physiotherapist. Patients were required to complete blood tests and a questionnaire about their symptoms and concerns before each consultation. Patient-reported outcome measures were captured using validated questionnaires. Patient feedback was collected using a specially designed survey and structured telephone interviews. RESULTS: Sixty-one patients were enrolled in the pilot clinic with 210 consultations held during the study period. Nine patients had disease progression and were referred safely back to face-to-face clinics. There was a significant improvement in patients' exercise score (p = 0.02) after PrISMS clinic. Patient satisfaction was high, with 83% feeling more confident in self-managing myeloma after PrISMS clinic. CONCLUSION: PrISMS clinic is safe and feasible, with high patient compliant and acceptability. It empowers patients to self-manage their condition and encourages physical activity, which is associated with improved quality of life and fatigue level. Future randomised controlled trials will help to confirm its benefits on patient clinical outcomes and cost-effectiveness.

Defining Unmet Need Following Lenalidomide Refractoriness: Real-World Evidence of Outcomes in Patients With Multiple Myeloma.

BACKGROUND: The treatment paradigm for multiple myeloma (MM) continues to evolve with the development of novel therapies and the earlier adoption of continuous treatments into the treatment pathway. Lenalidomide-refractory patients now represent a challenge with inferior progression free survival (PFS) reported to subsequent treatments. We therefore sought to describe the natural history of MM patients following lenalidomide in the real world. METHODS: This was a retrospective cohort review of patients with relapsed MM who received lenalidomide-based treatments in the U.K. Data were collected for demographics, subsequent therapies, treatment responses, survival outcomes and clinical trial enrollment. RESULTS: 198 patients received lenalidomide-based treatments at a median of 2 prior lines of therapy at a median of 41 months (range 0.5-210) from diagnosis. 114 patients (72% of 158 evaluable) became refractory to lenalidomide. The overall survival (OS) after lenalidomide failure was 14.7 months having received between 0-6 subsequent lines of therapy. Few deep responses were observed with subsequent treatments and the PFS to each further line was < 7 months. There was a steep reduction in numbers of patients able to receive further treatment, with an associated increase in number of deaths. The OS of patients progressing on lenalidomide who did not enter a clinical trial incorporating novel agents was very poor (8.8 months versus 30 months, p 0.0002), although the trials group were a biologically fitter group. CONCLUSION: These data demonstrate the poor outcomes of patients failing lenalidomide-based treatments in the real world, the highlight need for more effective treatments.

Multiple myeloma and physical activity.

OBJECTIVE: Physical activity has been shown to improve quality of life in cancer patients with some evidence in multiple myeloma. This study aimed to determine myeloma patients' exercise levels, their perception of physical activity, and to explore correlations with quality of life. Myeloma outpatients were invited to complete a number of questionnaires, including the Godin leisure-time exercise questionnaire (GLTEQ) to determine their exercise levels, the Functional Assessment of Cancer Therapy-General (FACT-G) questionnaire to assess health related quality of life, and the Functional Assessment of Chronic Illness Therapy-Fatigue (FACIT-F) questionnaire to assess fatigue. RESULTS: Of the 65 respondents, 75% would like to increase their exercise level. Weakness, fatigue and pain were the most commonly perceived barriers to physical activity. 59% would like to receive physical activity advice. Only 25% were deemed active based on their GLTEQ scores. Finally, there was a significant positive correlation between the GLTEQ score and the FACT-G score (p < 0.001). Results highlight an unmet exercise need in myeloma patients. Current practice should be reviewed to develop a more holistic care model that incorporates tailored exercise advice or programme.