Sarcopenia identified by computed tomography imaging using a deep learning–based segmentation approach impacts survival in patients with newly diagnosed multiple myeloma

• Published in: Cancer 2023-02, Vol.129 (3), p.385-392
• Main Authors: Nandakumar, Bharat, Baffour, Francis, Abdallah, Nadine H., Kumar, Shaji K., Dispenzieri, Angela, Buadi, Francis K., Dingli, David, Lacy, Martha Q., Hayman, Suzanne R., Kapoor, Prashant, Leung, Nelson, Fonder, Amie, Hobbs, Miriam, Hwa, Yi Lisa, Muchtar, Eli, Warsame, Rahma, Kourelis, Taxiarchis V., Go, Ronald S., Kyle, Robert A., Gertz, Morie A., Rajkumar, S. Vincent, Klug, Jason, Korfiatis, Panagiotis, Gonsalves, Wilson I.
• Format: Article
• Language: English
• Subjects: Algorithms; artificial intelligence; Artificial neural networks; Clinical trials; Computed tomography; Cytogenetics; Deep Learning; Fluorescence; Fluorescence in situ hybridization; Humans; Image processing; Image segmentation; In Situ Hybridization, Fluorescence; Learning algorithms; Machine learning; Multiple myeloma; Multiple Myeloma - complications; Multiple Myeloma - diagnostic imaging; Multiple Myeloma - pathology; Muscle, Skeletal - diagnostic imaging; Muscles; Musculoskeletal system; Neural networks; Oncology; Patients; Prognosis; prognostic factors in multiple myeloma; Prospective Studies; Retrospective Studies; Sarcopenia; Sarcopenia - complications; Sarcopenia - diagnostic imaging; Skeletal muscle; Survival; survival outcomes in multiple myeloma; Tomography; Tomography, X-Ray Computed - methods; Vertebrae
• ISSN: 0008-543X; 1097-0142
• DOI: 10.1002/cncr.34545

Background Sarcopenia increases with age and is associated with poor survival outcomes in patients with cancer. By using a deep learning–based segmentation approach, clinical computed tomography (CT) images of the abdomen of patients with newly diagnosed multiple myeloma (NDMM) were reviewed to determine whether the presence of sarcopenia had any prognostic value. Methods Sarcopenia was detected by accurate segmentation and measurement of the skeletal muscle components present at the level of the L3 vertebrae. These skeletal muscle measurements were further normalized by the height of the patient to obtain the skeletal muscle index for each patient to classify them as sarcopenic or not. Results The study cohort consisted of 322 patients of which 67 (28%) were categorized as having high risk (HR) fluorescence in situ hybridization (FISH) cytogenetics. A total of 171 (53%) patients were sarcopenic based on their peri‐diagnosis standard‐dose CT scan. The median overall survival (OS) and 2‐year mortality rate for sarcopenic patients was 44 months and 40% compared to 90 months and 18% for those not sarcopenic, respectively (p