1
|
Vu PT, Chahine C, Chatterjee N, MacLean MT, Swago S, Bhattaru A, Thompson EW, Ikhlas A, Oteng E, Davidson L, Tran R, Hazim M, Raghupathy P, Verma A, Duda J, Gee J, Luks V, Gershuni V, Wu G, Rader D, Sagreiya H, Witschey WR. CT imaging-derived phenotypes for abdominal muscle and their association with age and sex in a medical biobank. Sci Rep 2024; 14:14807. [PMID: 38926479 PMCID: PMC11208425 DOI: 10.1038/s41598-024-64603-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Accepted: 06/11/2024] [Indexed: 06/28/2024] Open
Abstract
The study of muscle mass as an imaging-derived phenotype (IDP) may yield new insights into determining the normal and pathologic variations in muscle mass in the population. This can be done by determining 3D abdominal muscle mass from 12 distinct abdominal muscle regions and groups using computed tomography (CT) in a racially diverse medical biobank. To develop a fully automatic technique for assessment of CT abdominal muscle IDPs and preliminarily determine abdominal muscle IDP variations with age and sex in a clinically and racially diverse medical biobank. This retrospective study was conducted using the Penn Medicine BioBank (PMBB), a research protocol that recruits adult participants during outpatient visits at hospitals in the Penn Medicine network. We developed a deep residual U-Net (ResUNet) to segment 12 abdominal muscle groups including the left and right psoas, quadratus lumborum, erector spinae, gluteus medius, rectus abdominis, and lateral abdominals. 110 CT studies were randomly selected for training, validation, and testing. 44 of the 110 CT studies were selected to enrich the dataset with representative cases of intra-abdominal and abdominal wall pathology. The studies were divided into non-overlapping training, validation and testing sets. Model performance was evaluated using the Sørensen-Dice coefficient. Volumes of individual muscle groups were plotted to distribution curves. To investigate associations between muscle IDPs, age, and sex, deep learning model segmentations were performed on a larger abdominal CT dataset from PMBB consisting of 295 studies. Multivariable models were used to determine relationships between muscle mass, age and sex. The model's performance (Dice scores) on the test data was the following: psoas: 0.85 ± 0.12, quadratus lumborum: 0.72 ± 0.14, erector spinae: 0.92 ± 0.07, gluteus medius: 0.90 ± 0.08, rectus abdominis: 0.85 ± 0.08, lateral abdominals: 0.85 ± 0.09. The average Dice score across all muscle groups was 0.86 ± 0.11. Average total muscle mass for females was 2041 ± 560.7 g with a high of 2256 ± 560.1 g (41-50 year old cohort) and a change of - 0.96 g/year, declining to an average mass of 1579 ± 408.8 g (81-100 year old cohort). Average total muscle mass for males was 3086 ± 769.1 g with a high of 3385 ± 819.3 g (51-60 year old cohort) and a change of - 1.73 g/year, declining to an average mass of 2629 ± 536.7 g (81-100 year old cohort). Quadratus lumborum was most highly correlated with age for both sexes (correlation coefficient of - 0.5). Gluteus medius mass in females was positively correlated with age with a coefficient of 0.22. These preliminary findings show that our CNN can automate detailed abdominal muscle volume measurement. Unlike prior efforts, this technique provides 3D muscle segmentations of individual muscles. This technique will dramatically impact sarcopenia diagnosis and research, elucidating its clinical and public health implications. Our results suggest a peak age range for muscle mass and an expected rate of decline, both of which vary between genders. Future goals are to investigate genetic variants for sarcopenia and malnutrition, while describing genotype-phenotype associations of muscle mass in healthy humans using imaging-derived phenotypes. It is feasible to obtain 3D abdominal muscle IDPs with high accuracy from patients in a medical biobank using fully automated machine learning methods. Abdominal muscle IDPs showed significant variations in lean mass by age and sex. In the future, this tool can be leveraged to perform a genome-wide association study across the medical biobank and determine genetic variants associated with early or accelerated muscle wasting.
Collapse
Affiliation(s)
- Phuong T Vu
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA
| | - Chantal Chahine
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Neil Chatterjee
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Matthew T MacLean
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
- Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Sophia Swago
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Abhi Bhattaru
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Elizabeth W Thompson
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Anooshey Ikhlas
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Edith Oteng
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Lauren Davidson
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Richard Tran
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Mohamad Hazim
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Pavan Raghupathy
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Anurag Verma
- Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Jeffrey Duda
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - James Gee
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Valerie Luks
- Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Victoria Gershuni
- Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Gary Wu
- Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Daniel Rader
- Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
- Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Hersh Sagreiya
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA
| | - Walter R Witschey
- Department of Radiology, Perelman School of Medicine, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, Philadelphia, PA, 19104, USA.
| |
Collapse
|
2
|
Takahashi M, Sakamoto K, Kogure Y, Nojiri S, Tsuchiya Y, Honjo K, Kawai M, Ishiyama S, Sugimoto K, Nagakari K, Tomiki Y. Use of 3D-CT-derived psoas major muscle volume in defining sarcopenia in colorectal cancer. BMC Cancer 2024; 24:741. [PMID: 38890682 PMCID: PMC11184714 DOI: 10.1186/s12885-024-12524-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2023] [Accepted: 06/14/2024] [Indexed: 06/20/2024] Open
Abstract
BACKGROUND Sarcopenia is characterized by reduced skeletal muscle volume and is a condition that is prevalent among elderly patients and associated with poor prognosis as a comorbidity in malignancies. Given the aging population over 80 years old in Japan, an understanding of malignancies, including colorectal cancer (CRC), complicated by sarcopenia is increasingly important. Therefore, the focus of this study is on a novel and practical diagnostic approach of assessment of psoas major muscle volume (PV) using 3-dimensional computed tomography (3D-CT) in diagnosis of sarcopenia in patients with CRC. METHODS The subjects were 150 patients aged ≥ 80 years with CRC who underwent primary tumor resection at Juntendo University Hospital between 2004 and 2017. 3D-CT measurement of PV and conventional CT measurement of the psoas major muscle cross-sectional area (PA) were used to identify sarcopenia (group S) and non-sarcopenia (group nS) cases. Clinicopathological characteristics, operative results, postoperative complications, and prognosis were compared between these groups. RESULTS The S:nS ratios were 15:135 for the PV method and 52:98 for the PA method. There was a strong positive correlation (r = 0.66, p < 0.01) between PVI (psoas major muscle volume index) and PAI (psoas major muscle cross-sectional area index), which were calculated by dividing PV or PA by the square of height. Surgical results and postoperative complications did not differ significantly in the S and nS groups defined using each method. Overall survival was worse in group S compared to group nS identified by PV (p < 0.01), but not significantly different in groups S and nS identified by PA (p = 0.77). A Cox proportional hazards model for OS identified group S by PV as an independent predictor of a poor prognosis (p < 0.05), whereas group S by PA was not a predictor of prognosis (p = 0.60). CONCLUSIONS The PV method for identifying sarcopenia in elderly patients with CRC is more practical and sensitive for prediction of a poor prognosis compared to the conventional method.
Collapse
Affiliation(s)
- Makoto Takahashi
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan.
| | - Kazuhiro Sakamoto
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Yosuke Kogure
- Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan
| | - Shuko Nojiri
- Medical Technology Innovation Center, Juntendo University, Tokyo, Japan
| | - Yuki Tsuchiya
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Kumpei Honjo
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Masaya Kawai
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Shun Ishiyama
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Kiichi Sugimoto
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Kunihiko Nagakari
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Yuichi Tomiki
- Department of Coloproctological Surgery, Faculty of Medicine, Juntendo University, Tokyo, Japan
| |
Collapse
|
3
|
Praveen AD, Sollmann N, Baum T, Ferguson SJ, Benedikt H. CT image-based biomarkers for opportunistic screening of osteoporotic fractures: a systematic review and meta-analysis. Osteoporos Int 2024; 35:971-996. [PMID: 38353706 PMCID: PMC11136833 DOI: 10.1007/s00198-024-07029-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/17/2023] [Accepted: 01/19/2024] [Indexed: 05/30/2024]
Abstract
The use of opportunistic computed tomography (CT) image-based biomarkers may be a low-cost strategy for screening older individuals at high risk for osteoporotic fractures and populations that are not sufficiently targeted. This review aimed to assess the discriminative ability of image-based biomarkers derived from existing clinical routine CT scans for hip, vertebral, and major osteoporotic fracture prediction. A systematic search in PubMed MEDLINE, Embase, Cochrane, and Web of Science was conducted from the earliest indexing date until July 2023. The evaluation of study quality was carried out using a modified Quality Assessment Tool for Diagnostic Accuracy Studies (QUADAS-2) checklist. The primary outcome of interest was the area under the curve (AUC) and its corresponding 95% confidence intervals (CIs) obtained for four main categories of biomarkers: areal bone mineral density (BMD), image attenuation, volumetric BMD, and finite element (FE)-derived biomarkers. The meta-analyses were performed using random effects models. Sixty-one studies were included in this review, among which 35 were synthesized in a meta-analysis and the remaining articles were qualitatively synthesized. In comparison to the pooled AUC of areal BMD (0.73 [95% CI 0.71-0.75]), the pooled AUC values for predicting osteoporotic fractures for FE-derived parameters (0.77 [95% CI 0.72-0.81]; p < 0.01) and volumetric BMD (0.76 [95% CI 0.71-0.81]; p < 0.01) were significantly higher, but there was no significant difference with the pooled AUC for image attenuation (0.73 [95% CI 0.66-0.79]; p = 0.93). Compared to areal BMD, volumetric BMD and FE-derived parameters may provide a significant improvement in the discrimination of osteoporotic fractures using opportunistic CT assessments.
Collapse
Affiliation(s)
- Anitha D Praveen
- Early Detection of Health Risks and Prevention, Future Health Technologies, Singapore-ETH Centre (SEC), Campus for Research Excellence and Technological Enterprise (CREATE), 1 Create Way, CREATE Tower, #06-01, Singapore, 138602, Singapore.
| | - Nico Sollmann
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Ulm, Germany
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
- TUM-Neuroimaging Center, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Thomas Baum
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Stephen J Ferguson
- Early Detection of Health Risks and Prevention, Future Health Technologies, Singapore-ETH Centre (SEC), Campus for Research Excellence and Technological Enterprise (CREATE), 1 Create Way, CREATE Tower, #06-01, Singapore, 138602, Singapore
- Institute for Biomechanics, ETH-Zurich, Zurich, Switzerland
| | - Helgason Benedikt
- Early Detection of Health Risks and Prevention, Future Health Technologies, Singapore-ETH Centre (SEC), Campus for Research Excellence and Technological Enterprise (CREATE), 1 Create Way, CREATE Tower, #06-01, Singapore, 138602, Singapore
- Institute for Biomechanics, ETH-Zurich, Zurich, Switzerland
| |
Collapse
|
4
|
Lee S, Jung JY, Mahatthanatrakul A, Kim JS. Artificial Intelligence in Spinal Imaging and Patient Care: A Review of Recent Advances. Neurospine 2024; 21:474-486. [PMID: 38955525 PMCID: PMC11224760 DOI: 10.14245/ns.2448388.194] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2024] [Revised: 05/14/2024] [Accepted: 05/23/2024] [Indexed: 07/04/2024] Open
Abstract
Artificial intelligence (AI) is transforming spinal imaging and patient care through automated analysis and enhanced decision-making. This review presents a clinical task-based evaluation, highlighting the specific impact of AI techniques on different aspects of spinal imaging and patient care. We first discuss how AI can potentially improve image quality through techniques like denoising or artifact reduction. We then explore how AI enables efficient quantification of anatomical measurements, spinal curvature parameters, vertebral segmentation, and disc grading. This facilitates objective, accurate interpretation and diagnosis. AI models now reliably detect key spinal pathologies, achieving expert-level performance in tasks like identifying fractures, stenosis, infections, and tumors. Beyond diagnosis, AI also assists surgical planning via synthetic computed tomography generation, augmented reality systems, and robotic guidance. Furthermore, AI image analysis combined with clinical data enables personalized predictions to guide treatment decisions, such as forecasting spine surgery outcomes. However, challenges still need to be addressed in implementing AI clinically, including model interpretability, generalizability, and data limitations. Multicenter collaboration using large, diverse datasets is critical to advance the field further. While adoption barriers persist, AI presents a transformative opportunity to revolutionize spinal imaging workflows, empowering clinicians to translate data into actionable insights for improved patient care.
Collapse
Affiliation(s)
- Sungwon Lee
- Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
- Visual Analysis and Learning for Improved Diagnostics (VALID) Lab, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Joon-Yong Jung
- Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
- Visual Analysis and Learning for Improved Diagnostics (VALID) Lab, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Akaworn Mahatthanatrakul
- Department of Orthopaedics, Faculty of Medicine, Naresuan University Hospital, Phitsanulok, Thailand
| | - Jin-Sung Kim
- Spine Center, Department of Neurosurgery, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
| |
Collapse
|
5
|
Vendrami C, Shevroja E, Gonzalez Rodriguez E, Gatineau G, Elmers J, Reginster J, Harvey NC, Lamy O, Hans D. Muscle parameters in fragility fracture risk prediction in older adults: A scoping review. J Cachexia Sarcopenia Muscle 2024; 15:477-500. [PMID: 38284511 PMCID: PMC10995267 DOI: 10.1002/jcsm.13418] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Revised: 11/01/2023] [Accepted: 11/28/2023] [Indexed: 01/30/2024] Open
Abstract
Half of osteoporotic fractures occur in patients with normal/osteopenic bone density or at intermediate or low estimated risk. Muscle measures have been shown to contribute to fracture risk independently of bone mineral density. The objectives were to review the measurements of muscle health (muscle mass/quantity/quality, strength and function) and their association with incident fragility fractures and to summarize their use in clinical practice. This scoping review follows the PRISMA-ScR guidelines for reporting. Our search strategy covered the three overreaching concepts of 'fragility fractures', 'muscle health assessment' and 'risk'. We retrieved 14 745 references from Medline Ovid SP, EMBASE, Web of Science Core Collection and Google Scholar. We included original and prospective studies on community-dwelling adults aged over 50 years that analysed an association between at least one muscle parameter and incident fragility fractures. We systematically extracted 17 items from each study, including methodology, general characteristics and results. Data were summarized in tables and graphically presented in adjusted forest plots. Sixty-seven articles fulfilled the inclusion criteria. In total, we studied 60 muscle parameters or indexes and 322 fracture risk ratios over 2.8 million person-years (MPY). The median (interquartile range) sample size was 1642 (921-5756), age 69.2 (63.5-73.6) years, follow-up 10.0 (4.4-12.0) years and number of incident fragility fractures 166 (88-277). A lower muscle mass was positively/not/negatively associated with incident fragility fracture in 28 (2.0), 64 (2.5) and 10 (0.2 MPY) analyses. A lower muscle strength was positively/not/negatively associated with fractures in 53 (1.3), 57 (1.7 MPY) and 0 analyses. A lower muscle function was positively/not/negatively associated in 63 (1.9), 45 (1.0 MPY) and 0 analyses. An in-depth analysis shows how each single muscle parameter was associated with each fragility fractures subtype. This review summarizes markers of muscle health and their association with fragility fractures. Measures of muscle strength and function appeared to perform better for fracture risk prediction. Of these, hand grip strength and gait speed are likely to be the most practical measures for inclusion in clinical practice, as in the evaluation of sarcopenia or in further fracture risk assessment scores. Measures of muscle mass did not appear to predict fragility fractures and might benefit from further research, on D3-creatine dilution test, lean mass indexes and artificial intelligence methods.
Collapse
Affiliation(s)
- Colin Vendrami
- Interdisciplinary Center of Bone Diseases, Rheumatology Unit, Department of Bone and JointLausanne University Hospital and University of LausanneLausanneSwitzerland
- Internal Medicine Unit, Department of Internal MedicineLausanne University Hospital and University of LausanneLausanneSwitzerland
| | - Enisa Shevroja
- Interdisciplinary Center of Bone Diseases, Rheumatology Unit, Department of Bone and JointLausanne University Hospital and University of LausanneLausanneSwitzerland
| | - Elena Gonzalez Rodriguez
- Interdisciplinary Center of Bone Diseases, Rheumatology Unit, Department of Bone and JointLausanne University Hospital and University of LausanneLausanneSwitzerland
| | - Guillaume Gatineau
- Interdisciplinary Center of Bone Diseases, Rheumatology Unit, Department of Bone and JointLausanne University Hospital and University of LausanneLausanneSwitzerland
| | - Jolanda Elmers
- University Library of Medicine, Faculty of Biology and MedicineLausanne University Hospital and University of LausanneLausanneSwitzerland
| | - Jean‐Yves Reginster
- WHO Collaborating Center for Public Health Aspects of Musculo‐Skeletal Health and Ageing, Division of Public Health, Epidemiology and Health EconomicsUniversity of LiègeLiègeBelgium
| | - Nicholas C. Harvey
- MRC Lifecourse Epidemiology CentreUniversity of SouthamptonSouthamptonUK
| | - Olivier Lamy
- Interdisciplinary Center of Bone Diseases, Rheumatology Unit, Department of Bone and JointLausanne University Hospital and University of LausanneLausanneSwitzerland
- Internal Medicine Unit, Department of Internal MedicineLausanne University Hospital and University of LausanneLausanneSwitzerland
| | - Didier Hans
- Interdisciplinary Center of Bone Diseases, Rheumatology Unit, Department of Bone and JointLausanne University Hospital and University of LausanneLausanneSwitzerland
| |
Collapse
|
6
|
Liu D, Garrett JW, Perez AA, Zea R, Binkley NC, Summers RM, Pickhardt PJ. Fully automated CT imaging biomarkers for opportunistic prediction of future hip fractures. Br J Radiol 2024; 97:770-778. [PMID: 38379423 PMCID: PMC11027263 DOI: 10.1093/bjr/tqae041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Revised: 09/27/2023] [Accepted: 02/19/2024] [Indexed: 02/22/2024] Open
Abstract
OBJECTIVE Assess automated CT imaging biomarkers in patients who went on to hip fracture, compared with controls. METHODS In this retrospective case-control study, 6926 total patients underwent initial abdominal CT over a 20-year interval at one institution. A total of 1308 patients (mean age at initial CT, 70.5 ± 12.0 years; 64.4% female) went on to hip fracture (mean time to fracture, 5.2 years); 5618 were controls (mean age 70.3 ± 12.0 years; 61.2% female; mean follow-up interval 7.6 years). Validated fully automated quantitative CT algorithms for trabecular bone attenuation (at L1), skeletal muscle attenuation (at L3), and subcutaneous adipose tissue area (SAT) (at L3) were applied to all scans. Hazard ratios (HRs) comparing highest to lowest risk quartiles and receiver operating characteristic (ROC) curve analysis including area under the curve (AUC) were derived. RESULTS Hip fracture HRs (95% CI) were 3.18 (2.69-3.76) for low trabecular bone HU, 1.50 (1.28-1.75) for low muscle HU, and 2.18 (1.86-2.56) for low SAT. 10-year ROC AUC values for predicting hip fracture were 0.702, 0.603, and 0.603 for these CT-based biomarkers, respectively. Multivariate combinations of these biomarkers further improved predictive value; the 10-year ROC AUC combining bone/muscle/SAT was 0.733, while combining muscle/SAT was 0.686. CONCLUSION Opportunistic use of automated CT bone, muscle, and fat measures can identify patients at higher risk for future hip fracture, regardless of the indication for CT imaging. ADVANCES IN KNOWLEDGE CT data can be leveraged opportunistically for further patient evaluation, with early intervention as needed. These novel AI tools analyse CT data to determine a patient's future hip fracture risk.
Collapse
Affiliation(s)
- Daniel Liu
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, 53792, United States
| | - John W Garrett
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, 53792, United States
| | - Alberto A Perez
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, 53792, United States
| | - Ryan Zea
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, 53792, United States
| | - Neil C Binkley
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, 53792, United States
| | - Ronald M Summers
- National Institutes of Health Clinical Center, Potomac, MD, 20892, United States
| | - Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, 53792, United States
| |
Collapse
|
7
|
Yao L, Petrosyan A, Chaudhari AJ, Lenchik L, Boutin RD. Clinical, functional, and opportunistic CT metrics of sarcopenia at the point of imaging care: analysis of all-cause mortality. Skeletal Radiol 2024; 53:515-524. [PMID: 37684434 PMCID: PMC10841085 DOI: 10.1007/s00256-023-04438-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/28/2023] [Revised: 08/23/2023] [Accepted: 08/23/2023] [Indexed: 09/10/2023]
Abstract
PURPOSE This study examines clinical, functional, and CT metrics of sarcopenia and all-cause mortality in older adults undergoing outpatient imaging. METHODS The study included outpatients ≥ 65 years of age undergoing CT or PET/CT at a tertiary care institution. Assessments included screening questionnaires for sarcopenia (SARC-F) and frailty (FRAIL scale), and measurements of grip strength and usual gait speed (6 m course). Skeletal muscle area (SMA), index (SMI, area/height2) and density (SMD) were measured on CT at T12 and L3. A modified SMI was also examined (SMI-m, area/height). Mortality risk was studied with Cox proportional hazard analysis. RESULTS The study included 416 patients; mean age 73.8 years [sd 6.2]; mean follow-up 2.9 years (sd 1.34). Abnormal grip, SARC-F, and FRAIL scale assessments were associated with higher mortality risk (HR [95%CI] = 2.0 [1.4-2.9], 1.6 [1.1-2.3], 2.0 [1.4-2.8]). Adjusting for age, higher L3-SMA, T12-SMA, T12-SMI and T12-SMI-m were associated with lower mortality risk (HR [95%CI] = 0.80 [0.65-0.90], 0.76 [0.64-0.90], 0.84 [0.70-1.00], and 0.80 [0.67-0.90], respectively). T12-SMD and L3-SMD were not predictive of mortality. After adjusting for abnormal grip strength and FRAIL scale assessments, T12-SMA and T12-SMI-m remained predictive of mortality risk (HR [95%CI] = 0.83 [0.70-1.00] and 0.80 [0.67-0.97], respectively). CONCLUSION CT areal metrics were weaker predictors of all-cause mortality than clinical and functional metrics of sarcopenia in our older patient cohort; a CT density metric (SMD) was not predictive. Of areal CT metrics, SMI (area/height2) appeared to be less effective than non-normalized SMA or SMA normalized by height1.
Collapse
Affiliation(s)
- Lawrence Yao
- Radiology and Imaging Sciences/CC/NIH, 10 Center Drive, Bethesda, MD, 20892, USA.
| | | | - Abhijit J Chaudhari
- University of California, Davis 4860 Y Street, Suite 3100, Sacramento, CA, 95817, USA
| | - Leon Lenchik
- Wake Forest School of Medicine, Medical Center Boulevard, Winston-Salem, NC, 27157, USA
| | - Robert D Boutin
- Stanford University School of Medicine, 300 Pasteur Drive, MC-5105, Stanford, CA, 94305, USA
| |
Collapse
|
8
|
Sheng M, Cao J, Hou S, Li M, Wang Y, Fang Q, Miao A, Yang M, Liu S, Hu C, Liu C, Wang S, Zheng J, Xiao J, Zhang X, Liu H, Liu B, Wang B. Computed tomography-determined skeletal muscle density predicts 3-year mortality in initial-dialysis patients in China. J Cachexia Sarcopenia Muscle 2023; 14:2569-2578. [PMID: 37722854 PMCID: PMC10751407 DOI: 10.1002/jcsm.13331] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Revised: 06/21/2023] [Accepted: 08/21/2023] [Indexed: 09/20/2023] Open
Abstract
BACKGROUND Skeletal muscle mass and quality assessed by computed tomography (CT) images of the third lumbar vertebra (L3) level have been established as risk factors for poor clinical outcomes in several illnesses, but the relevance for dialysis patients is unclear. A few studies have suggested a correlation between CT-determined skeletal muscle mass and quality at the first lumbar vertebra (L1) level and adverse outcomes. Generally, chest CT does not reach beyond L1. We aimed to determine whether opportunistic CT scan (chest CT)-determined skeletal muscle mass and quality at L1 are associated with mortality in initial-dialysis patients. METHODS This 3-year multicentric retrospective study included initial-dialysis patients from four centres between 2014 and 2017 in China. Unenhanced CT images of the L1 and L3 levels were obtained to assess skeletal muscle mass [by skeletal muscle index, (SMI), cm2 /m2 ] and quality [by skeletal muscle density (SMD), HU]. Skeletal muscle measures at L1 were compared with those at L3. The sex-specific optimal cutoff values of L1 SMI and L1 SMD were determined in relation to all-cause mortality. The outcomes were all-cause death and cardiac death. Cox regression models were applied to investigate the risk factors for death. RESULTS A total of 485 patients were enrolled, of whom 257 had both L1 and L3 images. Pearson's correlation coefficient between L1 and L3 SMI was 0.84 (P < 0.001), and that between L1 and L3 SMD was 0.90 (P < 0.001). No significant association between L1 SMI and mortality was observed (P > 0.05). Low L1 SMD (n = 280, 57.73%) was diagnosed based on the optimal cutoff value (<39.56 HU for males and <33.06 HU for females). Multivariate regression analysis revealed that the low L1 SMD group had higher risks of all-cause death (hazard ratio 1.80; 95% confidence interval 1.05-3.11, P = 0.034) and cardiac death (hazard ratio 3.74; 95% confidence interval 1.43-9.79, P = 0.007). CONCLUSIONS In initial-dialysis patients, there is high agreement between the L1 and L3 measures for SMI and SMD. Low SMD measured at L1, but not low SMI, is an independent predictor of both all-cause death and cardiac death.
Collapse
Affiliation(s)
- Ming‐jie Sheng
- Department of Nephrology, Zhong Da HospitalSoutheast University School of MedicineNanjingChina
- Department of NephrologyThe Affiliated Kunshan Hospital of Jiangsu UniversityKunshanChina
| | - Jing‐yuan Cao
- Department of Nephrology, Zhong Da HospitalSoutheast University School of MedicineNanjingChina
- Department of NephrologyThe Affiliated Taizhou People's Hospital of Nanjing Medical University, Taizhou School of Clinical Medicine, Nanjing Medical UniversityTaizhouChina
| | - Shi‐mei Hou
- Department of Nephrology, Zhong Da HospitalSoutheast University School of MedicineNanjingChina
| | - Min Li
- Department of NephrologyThe First People's Hospital of ChangzhouChangzhouChina
| | - Yao Wang
- Department of NephrologyThe Affiliated Hospital of Yangzhou University, Yangzhou UniversityYangzhouChina
| | - Qiang Fang
- Department of NephrologyThe Affiliated Taizhou People's Hospital of Nanjing Medical University, Taizhou School of Clinical Medicine, Nanjing Medical UniversityTaizhouChina
| | - A‐feng Miao
- Department of NephrologyThe Affiliated Taizhou People's Hospital of Nanjing Medical University, Taizhou School of Clinical Medicine, Nanjing Medical UniversityTaizhouChina
| | - Min Yang
- Department of NephrologyThe First People's Hospital of ChangzhouChangzhouChina
| | - Shu‐su Liu
- Department of NephrologyThe First People's Hospital of ChangzhouChangzhouChina
| | - Chun‐hong Hu
- Department of NephrologyThe Affiliated Hospital of Yangzhou University, Yangzhou UniversityYangzhouChina
| | - Cui‐lan Liu
- Department of NephrologyThe Affiliated Hospital of Yangzhou University, Yangzhou UniversityYangzhouChina
| | - Shi‐yuan Wang
- Department of Epidemiology and Health StatisticsSoutheast University School of Public HealthNanjingChina
| | - Jing Zheng
- Department of Geriatrics, Zhong Da HospitalSoutheast University School of MedicineNanjingChina
| | | | - Xiao‐liang Zhang
- Department of Nephrology, Zhong Da HospitalSoutheast University School of MedicineNanjingChina
| | - Hong Liu
- Department of Nephrology, Zhong Da HospitalSoutheast University School of MedicineNanjingChina
| | - Bi‐cheng Liu
- Department of Nephrology, Zhong Da HospitalSoutheast University School of MedicineNanjingChina
| | - Bin Wang
- Department of Nephrology, Zhong Da HospitalSoutheast University School of MedicineNanjingChina
| |
Collapse
|
9
|
Hajian S, Ghoreifi A, Cen SY, Varghese B, Lei X, Hwang D, Tran K, Tejura T, Whang G, Djaladat H, Duddalwar V. Sarcopenia and body fat change as risk factors for radiologic incisional hernia following robotic nephrectomy. Skeletal Radiol 2023; 52:2469-2477. [PMID: 37249596 PMCID: PMC10582134 DOI: 10.1007/s00256-023-04371-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/07/2023] [Revised: 05/22/2023] [Accepted: 05/22/2023] [Indexed: 05/31/2023]
Abstract
OBJECTIVE To assess the effect of body muscle and fat metrics on the development of radiologic incisional hernia (IH) following robotic nephrectomy. MATERIALS AND METHODS We retrospectively reviewed the records of patients who underwent robotic nephrectomy for kidney tumors between 2011 and 2017. All pre- and postoperative CTs were re-reviewed by experienced radiologists for detection of radiologic IH and calculation of the following metrics using Synapse 3D software: cross-sectional psoas muscle mass at the level of L3 and L4 as well as subcutaneous and visceral fat areas. Sarcopenia was defined as psoas muscle index below the lowest quartile. Cox proportional hazard model was constructed to examine the association between muscle and fat metrics and the risk of developing radiologic IH. RESULTS A total of 236 patients with a median (IQR) age of 64 (54-70) years were included in this study. In a median (IQR) follow-up of 23 (14-38) months, 62 (26%) patients developed radiologic IH. On Cox proportional hazard model, we were unable to detect an association between sarcopenia and risk of IH development. In terms of subcutaneous fat change from pre-op, both lower and higher values were associated with IH development (HR (95% CI) 2.1 (1.2-3.4), p = 0.01 and 2.4 (1.4-4.1), p < 0.01 for < Q1 and ≥ Q3, respectively). Similar trend was found for visceral fat area changes from pre-op with a HR of 2.8 for < Q1 and 1.8 for ≥ Q3. CONCLUSION Both excessive body fat gain and loss are associated with development of radiologic IH in patients undergoing robotic nephrectomy.
Collapse
Affiliation(s)
- Simin Hajian
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Alireza Ghoreifi
- Institute of Urology, Norris Comprehensive Cancer Center, University of Southern California, Los Angeles, CA, USA
| | - Steven Yong Cen
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Bino Varghese
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Xiaomeng Lei
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Darryl Hwang
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Khoa Tran
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Tapas Tejura
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Gilbert Whang
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Hooman Djaladat
- Institute of Urology, Norris Comprehensive Cancer Center, University of Southern California, Los Angeles, CA, USA
| | - Vinay Duddalwar
- Department of Radiology, University of Southern California, Los Angeles, CA, USA.
| |
Collapse
|
10
|
Matsushita Y, Yokoyama T, Noguchi T, Nakagawa T. Assessment of skeletal muscle using deep learning on low-dose CT images. Glob Health Med 2023; 5:278-284. [PMID: 37908512 PMCID: PMC10615034 DOI: 10.35772/ghm.2023.01050] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Revised: 09/08/2023] [Accepted: 09/22/2023] [Indexed: 11/02/2023]
Abstract
The visceral fat area obtained by computed tomography (CT) at the navel level is clinically used as an indicator of visceral fat obesity in Japan. Analysis of skeletal muscle mass using CT images at the navel level may potentially support concurrent assessment of sarcopenia and sarcopenic obesity. The purpose of this study was to assess the performance of deep learning models (DLMs) for skeletal muscle mass measurement using low-dose abdominal CT. The primary dataset used in this study included 11,494 low-dose abdominal CT images at navel level acquired in 7,370 subjects for metabolic syndrome screening. The publicly available Cancer Imaging Archive (TCIA) dataset, including 5,801 abdominal CT images, was used as a complementary dataset. For abdominal CT image segmentation, we used the SegU-net DLM with different filter size and hierarchical depth. The segmentation accuracy was assessed by measuring the dice similarity coefficient (DSC), cross-sectional area (CSA) error, and Bland-Altman plots. The proposed DLM achieved a DSC of 0.992 ± 0.012, a CSA error of 0.41 ± 1.89%, and a Bland-Altman percent difference of -0.1 ± 3.8%. The proposed DLM was able to automatically segment skeletal muscle mass measurements from low-dose abdominal CT with high accuracy.
Collapse
Affiliation(s)
- Yumi Matsushita
- Department of Clinical Research, National Center for Global Health and Medicine, Tokyo, Japan
| | - Tetsuji Yokoyama
- Department of Health Promotion, National Institute of Public Health, Saitama, Japan
| | - Tomoyuki Noguchi
- Department of Radiology, National Hospital Organization Kyushu Medical Center, Fukuoka, Japan
| | - Toru Nakagawa
- Hitachi, Ltd. Hitachi Health Care Center, Ibaraki, Japan
| |
Collapse
|
11
|
Bae JH, Seo JW, Kim DY. Deep-learning model for predicting physical fitness in possible sarcopenia: analysis of the Korean physical fitness award from 2010 to 2023. Front Public Health 2023; 11:1241388. [PMID: 37614451 PMCID: PMC10443707 DOI: 10.3389/fpubh.2023.1241388] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Accepted: 07/24/2023] [Indexed: 08/25/2023] Open
Abstract
Introduction Physical fitness is regarded as a significant indicator of sarcopenia. This study aimed to develop and evaluate a deep-learning model for predicting the decline in physical fitness due to sarcopenia in individuals with potential sarcopenia. Methods This study used the 2010-2023 Korean National Physical Fitness Award data. The data comprised exercise- and health-related measurements in Koreans aged >65 years and included body composition and physical fitness variables. Appendicular muscle mass (ASM) was calculated as ASM/height2 to define normal and possible sarcopenia. The deep-learning model was created with EarlyStopping and ModelCheckpoint to prevent overfitting and was evaluated using stratified k-fold cross-validation (k = 5). The model was trained and tested using training data and validation data from each fold. The model's performance was assessed using a confusion matrix, receiver operating characteristic curve, and area under the curve. The average performance metrics obtained from each cross-validation were determined. For the analysis of feature importance, SHAP, permutation feature importance, and LIME were employed as model-agnostic explanation methods. Results The deep-learning model proved effective in distinguishing from sarcopenia, with an accuracy of 87.55%, precision of 85.57%, recall of 90.34%, and F1 score of 87.89%. Waist circumference (WC, cm), absolute grip strength (kg), and body fat (BF, %) had an influence on the model output. SHAP, LIME, and permutation feature importance analyses revealed that WC and absolute grip strength were the most important variables. WC, figure-of-8 walk, BF, timed up-and-go, and sit-and-reach emerged as key factors for predicting possible sarcopenia. Conclusion The deep-learning model showed high accuracy and recall with respect to possible sarcopenia prediction. Considering the need for the development of a more detailed and accurate sarcopenia prediction model, the study findings hold promise for enhancing sarcopenia prediction using deep learning.
Collapse
Affiliation(s)
- Jun-Hyun Bae
- Able-Art Sport, Department of Theory, Hyupsung University, Hwaseong, Gyeonggi-do, Republic of Korea
| | - Ji-won Seo
- Department of Physical Education, Seoul National University, Seoul, Republic of Korea
| | - Dae Young Kim
- Senior Exercise Rehabilitation Laboratory, Department of Gerokinesiology, Kyungil University, Gyeongsan, Gyeongsangbuk-do, Republic of Korea
| |
Collapse
|
12
|
Ye Z, Saraf A, Ravipati Y, Hoebers F, Catalano PJ, Zha Y, Zapaishchykova A, Likitlersuang J, Guthier C, Tishler RB, Schoenfeld JD, Margalit DN, Haddad RI, Mak RH, Naser M, Wahid KA, Sahlsten J, Jaskari J, Kaski K, Mäkitie AA, Fuller CD, Aerts HJWL, Kann BH. Development and Validation of an Automated Image-Based Deep Learning Platform for Sarcopenia Assessment in Head and Neck Cancer. JAMA Netw Open 2023; 6:e2328280. [PMID: 37561460 PMCID: PMC10415962 DOI: 10.1001/jamanetworkopen.2023.28280] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Accepted: 06/27/2023] [Indexed: 08/11/2023] Open
Abstract
Importance Sarcopenia is an established prognostic factor in patients with head and neck squamous cell carcinoma (HNSCC); the quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical skeletal muscle segmentation and cross-sectional area. However, manual muscle segmentation is labor intensive, prone to interobserver variability, and impractical for large-scale clinical use. Objective To develop and externally validate a fully automated image-based deep learning platform for cervical vertebral muscle segmentation and SMI calculation and evaluate associations with survival and treatment toxicity outcomes. Design, Setting, and Participants For this prognostic study, a model development data set was curated from publicly available and deidentified data from patients with HNSCC treated at MD Anderson Cancer Center between January 1, 2003, and December 31, 2013. A total of 899 patients undergoing primary radiation for HNSCC with abdominal computed tomography scans and complete clinical information were selected. An external validation data set was retrospectively collected from patients undergoing primary radiation therapy between January 1, 1996, and December 31, 2013, at Brigham and Women's Hospital. The data analysis was performed between May 1, 2022, and March 31, 2023. Exposure C3 vertebral skeletal muscle segmentation during radiation therapy for HNSCC. Main Outcomes and Measures Overall survival and treatment toxicity outcomes of HNSCC. Results The total patient cohort comprised 899 patients with HNSCC (median [range] age, 58 [24-90] years; 140 female [15.6%] and 755 male [84.0%]). Dice similarity coefficients for the validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI, 0.90-0.91) and 0.90 (95% CI, 0.89-0.91), respectively, with a mean 96.2% acceptable rate between 2 reviewers on external clinical testing (n = 377). Estimated cross-sectional area and SMI values were associated with manually annotated values (Pearson r = 0.99; P < .001) across data sets. On multivariable Cox proportional hazards regression, SMI-derived sarcopenia was associated with worse overall survival (hazard ratio, 2.05; 95% CI, 1.04-4.04; P = .04) and longer feeding tube duration (median [range], 162 [6-1477] vs 134 [15-1255] days; hazard ratio, 0.66; 95% CI, 0.48-0.89; P = .006) than no sarcopenia. Conclusions and Relevance This prognostic study's findings show external validation of a fully automated deep learning pipeline to accurately measure sarcopenia in HNSCC and an association with important disease outcomes. The pipeline could enable the integration of sarcopenia assessment into clinical decision making for individuals with HNSCC.
Collapse
Affiliation(s)
- Zezhong Ye
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Anurag Saraf
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Yashwanth Ravipati
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Frank Hoebers
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Center+, Maastricht, the Netherlands
| | - Paul J. Catalano
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts
- Department of Data Science, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts
| | - Yining Zha
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Anna Zapaishchykova
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
- Radiology and Nuclear Medicine, CARIM and GROW, Maastricht University, Maastricht, the Netherlands
| | - Jirapat Likitlersuang
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Christian Guthier
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Roy B. Tishler
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Jonathan D. Schoenfeld
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Danielle N. Margalit
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Robert I. Haddad
- Department of Medical Oncology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts
| | - Raymond H. Mak
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Mohamed Naser
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Kareem A. Wahid
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Jaakko Sahlsten
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Joel Jaskari
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Kimmo Kaski
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Antti A. Mäkitie
- Department Otorhinolaryngology–Head and Neck Surgery, University of Helsinki and Helsinki University Hospital, Research Program in Systems Oncology, Faculty of Medicine, University of Helsinki, Helsinki, Finland
| | - Clifton D. Fuller
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Hugo J. W. L. Aerts
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
- Radiology and Nuclear Medicine, CARIM and GROW, Maastricht University, Maastricht, the Netherlands
- Department of Radiology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts
| | - Benjamin H. Kann
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| |
Collapse
|
13
|
Liu D, Binkley NC, Perez A, Garrett JW, Zea R, Summers RM, Pickhardt PJ. CT image-based biomarkers acquired by AI-based algorithms for the opportunistic prediction of falls. BJR Open 2023; 5:20230014. [PMID: 37953870 PMCID: PMC10636337 DOI: 10.1259/bjro.20230014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2023] [Revised: 03/15/2023] [Accepted: 04/11/2023] [Indexed: 11/14/2023] Open
Abstract
Objective Evaluate whether biomarkers measured by automated artificial intelligence (AI)-based algorithms are suggestive of future fall risk. Methods In this retrospective age- and sex-matched case-control study, 9029 total patients underwent initial abdominal CT for a variety of indications over a 20-year interval at one institution. 3535 case patients (mean age at initial CT, 66.5 ± 9.6 years; 63.4% female) who went on to fall (mean interval to fall, 6.5 years) and 5494 controls (mean age at initial CT, 66.7 ± 9.8 years; 63.4% females; mean follow-up interval, 6.6 years) were included. Falls were identified by electronic health record review. Validated and fully automated quantitative CT algorithms for skeletal muscle, adipose tissue, and trabecular bone attenuation at the level of L1 were applied to all scans. Uni- and multivariate assessment included hazard ratios (HRs) and area under the receiver operating characteristic (AUROC) curve. Results Fall HRs (with 95% CI) for low muscle Hounsfield unit, high total adipose area, and low bone Hounsfield unit were 1.82 (1.65-2.00), 1.31 (1.19-1.44) and 1.91 (1.74-2.11), respectively, and the 10-year AUROC values for predicting falls were 0.619, 0.556, and 0.639, respectively. Combining all these CT biomarkers further improved the predictive value, including 10-year AUROC of 0.657. Conclusion Automated abdominal CT-based opportunistic measures of muscle, fat, and bone offer a novel approach to risk stratification for future falls, potentially by identifying patients with osteosarcopenic obesity. Advances in knowledge There are few well-established clinical tools to predict falls. We use novel AI-based body composition algorithms to leverage incidental CT data to help determine a patient's future fall risk.
Collapse
Affiliation(s)
- Daniel Liu
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA
| | - Neil C Binkley
- Osteoporosis Clinical Research Program, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA
| | - Alberto Perez
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA
| | - John W Garrett
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA
| | - Ryan Zea
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA
| | - Ronald M Summers
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA
| | - Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA
| |
Collapse
|
14
|
Hong JH, Hong H, Choi YR, Kim DH, Kim JY, Yoon JH, Yoon SH. CT analysis of thoracolumbar body composition for estimating whole-body composition. Insights Imaging 2023; 14:69. [PMID: 37093330 PMCID: PMC10126176 DOI: 10.1186/s13244-023-01402-z] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2022] [Accepted: 03/11/2023] [Indexed: 04/25/2023] Open
Abstract
BACKGROUND To evaluate the correlation between single- and multi-slice cross-sectional thoracolumbar and whole-body compositions. METHODS We retrospectively included patients who underwent whole-body PET-CT scans from January 2016 to December 2019 at multiple institutions. A priori-developed, deep learning-based commercially available 3D U-Net segmentation provided whole-body 3D reference volumes and 2D areas of muscle, visceral fat, and subcutaneous fat at the upper, middle, and lower endplate of the individual T1-L5 vertebrae. In the derivation set, we analyzed the Pearson correlation coefficients of single-slice and multi-slice averaged 2D areas (waist and T12-L1) with the reference values. We then built prediction models using the top three correlated levels and tested the models in the validation set. RESULTS The derivation and validation datasets included 203 (mean age 58.2 years; 101 men) and 239 patients (mean age 57.8 years; 80 men). The coefficients were distributed bimodally, with the first peak at T4 (coefficient, 0.78) and the second peak at L2-3 (coefficient 0.90). The top three correlations in the abdominal scan range were found for multi-slice waist averaging (0.92) and single-slice L3 and L2 (0.90, each), while those in the chest scan range were multi-slice T12-L1 averaging (0.89), single-slice L1 (0.89), and T12 (0.86). The model performance at the top three levels for estimating whole-body composition was similar in the derivation and validation datasets. CONCLUSIONS Single-slice L2-3 (abdominal CT range) and L1 (chest CT range) analysis best correlated with whole-body composition around 0.90 (coefficient). Multi-slice waist averaging provided a slightly higher correlation of 0.92.
Collapse
Affiliation(s)
- Jung Hee Hong
- Department of Radiology, Dongsan Hospital, Keimyung University College of Medicine, Daegu, Korea
| | - Hyunsook Hong
- Medical Research Collaborating Center, Seoul National University Hospital, Seoul, Korea
| | - Ye Ra Choi
- Department of Radiology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Dong Hyun Kim
- Department of Radiology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, Korea
| | - Jin Young Kim
- Department of Radiology, Dongsan Hospital, Keimyung University College of Medicine, Daegu, Korea
| | - Jeong-Hwa Yoon
- Institute of Health Policy and Management, Medical Research Center, Seoul National University, Seoul, Korea
| | - Soon Ho Yoon
- Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, 101 Daehak-ro, Chongno-gu, Seoul, 03080, Republic of Korea.
| |
Collapse
|
15
|
Ye Z, Saraf A, Ravipati Y, Hoebers F, Zha Y, Zapaishchykova A, Likitlersuang J, Tishler RB, Schoenfeld JD, Margalit DN, Haddad RI, Mak RH, Naser M, Wahid KA, Sahlsten J, Jaskari J, Kaski K, Mäkitie AA, Fuller CD, Aerts HJ, Kann BH. Fully-automated sarcopenia assessment in head and neck cancer: development and external validation of a deep learning pipeline. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.03.01.23286638. [PMID: 36945519 PMCID: PMC10029039 DOI: 10.1101/2023.03.01.23286638] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/18/2023]
Abstract
Purpose Sarcopenia is an established prognostic factor in patients diagnosed with head and neck squamous cell carcinoma (HNSCC). The quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical neck skeletal muscle (SM) segmentation and cross-sectional area. However, manual SM segmentation is labor-intensive, prone to inter-observer variability, and impractical for large-scale clinical use. To overcome this challenge, we have developed and externally validated a fully-automated image-based deep learning (DL) platform for cervical vertebral SM segmentation and SMI calculation, and evaluated the relevance of this with survival and toxicity outcomes. Materials and Methods 899 patients diagnosed as having HNSCC with CT scans from multiple institutes were included, with 335 cases utilized for training, 96 for validation, 48 for internal testing and 393 for external testing. Ground truth single-slice segmentations of SM at the C3 vertebra level were manually generated by experienced radiation oncologists. To develop an efficient method of segmenting the SM, a multi-stage DL pipeline was implemented, consisting of a 2D convolutional neural network (CNN) to select the middle slice of C3 section and a 2D U-Net to segment SM areas. The model performance was evaluated using the Dice Similarity Coefficient (DSC) as the primary metric for the internal test set, and for the external test set the quality of automated segmentation was assessed manually by two experienced radiation oncologists. The L3 skeletal muscle area (SMA) and SMI were then calculated from the C3 cross sectional area (CSA) of the auto-segmented SM. Finally, established SMI cut-offs were used to perform further analyses to assess the correlation with survival and toxicity endpoints in the external institution with univariable and multivariable Cox regression. Results DSCs for validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI: 0.90 - 0.91) and 0.90 (95% CI: 0.89 - 0.91), respectively. The predicted CSA is highly correlated with the ground-truth CSA in both validation (r = 0.99, p < 0.0001) and test sets (r = 0.96, p < 0.0001). In the external test set (n = 377), 96.2% of the SM segmentations were deemed acceptable by consensus expert review. Predicted SMA and SMI values were highly correlated with the ground-truth values, with Pearson r β 0.99 (p < 0.0001) for both the female and male patients in all datasets. Sarcopenia was associated with worse OS (HR 2.05 [95% CI 1.04 - 4.04], p = 0.04) and longer PEG tube duration (median 162 days vs. 134 days, HR 1.51 [95% CI 1.12 - 2.08], p = 0.006 in multivariate analysis. Conclusion We developed and externally validated a fully-automated platform that strongly correlates with imaging-assessed sarcopenia in patients with H&N cancer that correlates with survival and toxicity outcomes. This study constitutes a significant stride towards the integration of sarcopenia assessment into decision-making for individuals diagnosed with HNSCC. SUMMARY STATEMENT In this study, we developed and externally validated a deep learning model to investigate the impact of sarcopenia, defined as the loss of skeletal muscle mass, on patients with head and neck squamous cell carcinoma (HNSCC) undergoing radiotherapy. We demonstrated an efficient, fullyautomated deep learning pipeline that can accurately segment C3 skeletal muscle area, calculate cross-sectional area, and derive a skeletal muscle index to diagnose sarcopenia from a standard of care CT scan. In multi-institutional data, we found that pre-treatment sarcopenia was associated with significantly reduced overall survival and an increased risk of adverse events. Given the increased vulnerability of patients with HNSCC, the assessment of sarcopenia prior to radiotherapy may aid in informed treatment decision-making and serve as a predictive marker for the necessity of early supportive measures.
Collapse
Affiliation(s)
- Zezhong Ye
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Anurag Saraf
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Yashwanth Ravipati
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Frank Hoebers
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Center+, Maastricht, the Netherlands
| | - Yining Zha
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Anna Zapaishchykova
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
- Department of Radiology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, United States
| | - Jirapat Likitlersuang
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Roy B. Tishler
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Jonathan D. Schoenfeld
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Danielle N. Margalit
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Robert I. Haddad
- Department of Medical Oncology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, United States
| | - Raymond H. Mak
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Mohamed Naser
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Kareem A. Wahid
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Jaakko Sahlsten
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Joel Jaskari
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Kimmo Kaski
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Antti A. Mäkitie
- Department Otorhinolaryngology – Head and Neck Surgery, University of Helsinki and Helsinki University Hospital, Research Program in Systems Oncology, Faculty of Medicine, University of Helsinki, Helsinki, Finland
| | - Clifton D. Fuller
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Hugo J.W.L. Aerts
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
- Department Otorhinolaryngology – Head and Neck Surgery, University of Helsinki and Helsinki University Hospital, Research Program in Systems Oncology, Faculty of Medicine, University of Helsinki, Helsinki, Finland
- Department of Radiology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, United States
| | - Benjamin H. Kann
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| |
Collapse
|
16
|
Pickhardt PJ, Correale L, Hassan C. AI-based opportunistic CT screening of incidental cardiovascular disease, osteoporosis, and sarcopenia: cost-effectiveness analysis. Abdom Radiol (NY) 2023; 48:1181-1198. [PMID: 36670245 DOI: 10.1007/s00261-023-03800-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2022] [Revised: 01/02/2023] [Accepted: 01/04/2023] [Indexed: 01/22/2023]
Abstract
PURPOSE To assess the cost-effectiveness and clinical efficacy of AI-assisted abdominal CT-based opportunistic screening for atherosclerotic cardiovascular (CV) disease, osteoporosis, and sarcopenia using artificial intelligence (AI) body composition algorithms. METHODS Markov models were constructed and 10-year simulations were performed on hypothetical age- and sex-specific cohorts of 10,000 U.S. adults (base case: 55 year olds) undergoing abdominal CT. Using expected disease prevalence, transition probabilities between health states, associated healthcare costs, and treatment effectiveness related to relevant conditions (CV disease/osteoporosis/sarcopenia) were modified by three mutually exclusive screening models: (1) usual care ("treat none"; no intervention regardless of opportunistic CT findings), (2) universal statin therapy ("treat all" for CV prevention; again, no consideration of CT findings), and (3) AI-assisted abdominal CT-based opportunistic screening for CV disease, osteoporosis, and sarcopenia using automated quantitative algorithms for abdominal aortic calcification, bone mineral density, and skeletal muscle, respectively. Model validity was assessed against published clinical cohorts. RESULTS For the base-case scenarios of 55-year-old men and women modeled over 10 years, AI-assisted CT-based opportunistic screening was a cost-saving and more effective clinical strategy, unlike the "treat none" and "treat all" strategies that ignored incidental CT body composition data. Over a wide range of input assumptions beyond the base case, the CT-based opportunistic strategy was dominant over the other two scenarios, as it was both more clinically efficacious and more cost-effective. Cost savings and clinical improvement for opportunistic CT remained for AI tool costs up to $227/patient in men ($65 in women) from the $10/patient base-case scenario. CONCLUSION AI-assisted CT-based opportunistic screening appears to be a highly cost-effective and clinically efficacious strategy across a broad array of input assumptions, and was cost saving in most scenarios.
Collapse
Affiliation(s)
- Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Heatlh, 600 Highland Ave, Madison, WI, 53792, USA.
| | - Loredana Correale
- Department of Gastroenterology, IRCCS Humanitas Research Hospital, Via Manzoni 56, 20089, Rozzano, Milan, Italy
| | - Cesare Hassan
- Department of Gastroenterology, IRCCS Humanitas Research Hospital, Via Manzoni 56, 20089, Rozzano, Milan, Italy
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20072, Pieve Emanuele, Milan, Italy
| |
Collapse
|
17
|
Fully automated CT-based adiposity assessment: comparison of the L1 and L3 vertebral levels for opportunistic prediction. Abdom Radiol (NY) 2023; 48:787-795. [PMID: 36369528 DOI: 10.1007/s00261-022-03728-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2022] [Revised: 10/23/2022] [Accepted: 10/25/2022] [Indexed: 11/13/2022]
Abstract
PURPOSE The purpose of this study is to compare fully automated CT-based measures of adipose tissue at the L1 level versus the standard L3 level for predicting mortality, which would allow for use at both chest (L1) and abdominal (L3) CT. METHODS This retrospective study of 9066 asymptomatic adults (mean age, 57.1 ± 7.8 [SD] years; 4020 men, 5046 women) undergoing unenhanced low-dose abdominal CT for colorectal cancer screening. A previously validated artificial intelligence (AI) tool was used to assess cross-sectional visceral and subcutaneous adipose tissue areas (SAT and VAT), as well as their ratio (VSR) at the L1 and L3 levels. Post-CT survival prediction was compared using area under the ROC curve (ROC AUC) and hazard ratios (HRs). RESULTS Median clinical follow-up interval after CT was 8.8 years (interquartile range, 5.2-11.6 years), during which 5.9% died (532/9066). No significant difference (p > 0.05) for mortality was observed between L1 and L3 VAT and SAT at 10-year ROC AUC. However, L3 measures were significantly better for VSR at 10-year AUC (p < 0.001). HRs comparing worst-to-best quartiles for mortality at L1 vs. L3 were 2.12 (95% CI, 1.65-2.72) and 2.22 (1.74-2.83) for VAT; 1.20 (0.95-1.52) and 1.16 (0.92-1.46) for SAT; and 2.26 (1.7-2.93) and 3.05 (2.32-4.01) for VSR. In women, the corresponding HRs for VSR were 2.58 (1.80-3.69) (L1) and 4.49 (2.98-6.78) (L3). CONCLUSION Automated CT-based measures of visceral fat (VAT and VSR) at L1 are predictive of survival, although overall measures of adiposity at L1 level are somewhat inferior to the standard L3-level measures. Utilizing predictive L1-level fat measures could expand opportunistic screening to chest CT imaging.
Collapse
|
18
|
Psoas attenuation and cross-sectional area improve performance of traditional sarcopenia measurements in predicting one-year mortality among elderly patients undergoing emergency abdominal surgery: a pilot study of five computed tomography techniques. Abdom Radiol (NY) 2023; 48:796-805. [PMID: 36383241 DOI: 10.1007/s00261-022-03652-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Revised: 08/06/2022] [Accepted: 08/09/2022] [Indexed: 11/17/2022]
Abstract
BACKGROUND Risk stratification is challenging in the growing population of geriatric patients requiring emergency surgery. Sarcopenia, which assesses muscle bulk, is a surrogate for frailty and predicts 1-year mortality, but does not incorporate potentially valuable additional information about muscle quality. OBJECTIVE To describe five different CT methods of measuring sarcopenia and muscle quality and to determine which method has the greatest sensitivity for predicting 1-year mortality following emergency abdominal surgery in elderly patients. METHODS This retrospective study includes 297 patients 70 years and older who underwent "urgent" or "emergent" laparotomy or laparoscopy for acute abdominal disease between 2006 and 2011 at a single quaternary academic medical center. All patients received a CT abdomen and pelvis with intravenous contrast within 1 month of surgery. Five different methods were applied to the psoas muscles on CT: method 1 (total psoas index TPI, which is total psoas area TPA normalized by height), method 2 ("pseudoarea" = anterior-posterior × transverse dimensions), method 3 (average HU), method 4 (TPA × HU), and method 5 ("pseudoarea" × HU). RESULTS For all five CT measures, mortality was greatest for the lowest quartile by univariate and adjusted Cox proportional hazard analyses at all time points up to 1-year. The C-statistic was highest for Method 4, using a composite index of TPA and Hounsfield Units, indicating the greatest predictive ability to estimate mortality at all time points. CONCLUSION Muscle quality and muscle size can be used in tandem to refine risk assessment of older patients undergoing emergency abdominal surgery. Routine calculation of the composite score of psoas cross-sectional area and HU in the emergency room setting may provide surgeons and patients valuable insight on the risk of 1-year mortality to guide preoperative decision-making and counseling. CLINICAL IMPACT Muscle quality and size, both strong independent predictors of surgical outcomes in older patients undergoing emergency abdominal surgery, may be used in tandem to refine risk assessment. A composite score of psoas muscle cross-sectional area and Hounsfield units on CT may provide insight on 1-year mortality in this patient population.
Collapse
|
19
|
Lee MH, Zea R, Garrett JW, Graffy PM, Summers RM, Pickhardt PJ. Abdominal CT Body Composition Thresholds Using Automated AI Tools for Predicting 10-year Adverse Outcomes. Radiology 2023; 306:e220574. [PMID: 36165792 PMCID: PMC9885340 DOI: 10.1148/radiol.220574] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2022] [Revised: 07/18/2022] [Accepted: 08/03/2022] [Indexed: 01/26/2023]
Abstract
Background CT-based body composition measures derived from fully automated artificial intelligence tools are promising for opportunistic screening. However, body composition thresholds associated with adverse clinical outcomes are lacking. Purpose To determine population and sex-specific thresholds for muscle, abdominal fat, and abdominal aortic calcium measures at abdominal CT for predicting risk of death, adverse cardiovascular events, and fragility fractures. Materials and Methods In this retrospective single-center study, fully automated algorithms for quantifying skeletal muscle (L3 level), abdominal fat (L3 level), and abdominal aortic calcium were applied to noncontrast abdominal CT scans from asymptomatic adults screened from 2004 to 2016. Longitudinal follow-up documented subsequent death, adverse cardiovascular events (myocardial infarction, cerebrovascular event, and heart failure), and fragility fractures. Receiver operating characteristic (ROC) curve analysis was performed to derive thresholds for body composition measures to achieve optimal ROC curve performance and high specificity (90%) for 10-year risks. Results A total of 9223 asymptomatic adults (mean age, 57 years ± 7 [SD]; 5152 women and 4071 men) were evaluated (median follow-up, 9 years). Muscle attenuation and aortic calcium had the highest diagnostic performance for predicting death, with areas under the ROC curve of 0.76 for men (95% CI: 0.72, 0.79) and 0.72 for women (95% CI: 0.69, 0.76) for muscle attenuation. Sex-specific thresholds were higher in men than women (P < .001 for muscle attenuation for all outcomes). The highest-performing markers for risk of death were muscle attenuation in men (31 HU; 71% sensitivity [164 of 232 patients]; 72% specificity [1114 of 1543 patients]) and aortic calcium in women (Agatston score, 167; 70% sensitivity [152 of 218 patients]; 70% specificity [1427 of 2034 patients]). Ninety-percent specificity thresholds for muscle attenuation for both risk of death and fragility fractures were 23 HU (men) and 13 HU (women). For aortic calcium and risk of death and adverse cardiovascular events, 90% specificity Agatston score thresholds were 1475 (men) and 735 (women). Conclusion Sex-specific thresholds for automated abdominal CT-based body composition measures can be used to predict risk of death, adverse cardiovascular events, and fragility fractures. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Ohliger in this issue.
Collapse
Affiliation(s)
- Matthew H. Lee
- From the Departments of Radiology (M.H.L., R.Z., J.W.G., P.M.G.,
P.J.P.) and Medical Physics (J.W.G.), University of Wisconsin School of Medicine
and Public Health, 600 Highland Ave, Madison, WI 53792; and Imaging Biomarkers
and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences,
National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Ryan Zea
- From the Departments of Radiology (M.H.L., R.Z., J.W.G., P.M.G.,
P.J.P.) and Medical Physics (J.W.G.), University of Wisconsin School of Medicine
and Public Health, 600 Highland Ave, Madison, WI 53792; and Imaging Biomarkers
and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences,
National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - John W. Garrett
- From the Departments of Radiology (M.H.L., R.Z., J.W.G., P.M.G.,
P.J.P.) and Medical Physics (J.W.G.), University of Wisconsin School of Medicine
and Public Health, 600 Highland Ave, Madison, WI 53792; and Imaging Biomarkers
and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences,
National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Peter M. Graffy
- From the Departments of Radiology (M.H.L., R.Z., J.W.G., P.M.G.,
P.J.P.) and Medical Physics (J.W.G.), University of Wisconsin School of Medicine
and Public Health, 600 Highland Ave, Madison, WI 53792; and Imaging Biomarkers
and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences,
National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Ronald M. Summers
- From the Departments of Radiology (M.H.L., R.Z., J.W.G., P.M.G.,
P.J.P.) and Medical Physics (J.W.G.), University of Wisconsin School of Medicine
and Public Health, 600 Highland Ave, Madison, WI 53792; and Imaging Biomarkers
and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences,
National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Perry J. Pickhardt
- From the Departments of Radiology (M.H.L., R.Z., J.W.G., P.M.G.,
P.J.P.) and Medical Physics (J.W.G.), University of Wisconsin School of Medicine
and Public Health, 600 Highland Ave, Madison, WI 53792; and Imaging Biomarkers
and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences,
National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| |
Collapse
|
20
|
Vogele D, Otto S, Sollmann N, Haggenmüller B, Wolf D, Beer M, Schmidt SA. Sarcopenia - Definition, Radiological Diagnosis, Clinical Significance. ROFO-FORTSCHR RONTG 2023; 195:393-405. [PMID: 36630983 DOI: 10.1055/a-1990-0201] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/13/2023]
Abstract
BACKGROUND Sarcopenia is an age-related syndrome characterized by a loss of muscle mass and strength. As a result, the independence of the elderly is reduced and the hospitalization rate and mortality increase. The onset of sarcopenia often begins in middle age due to an unbalanced diet or malnutrition in association with a lack of physical activity. This effect is intensified by concomitant diseases such as obesity or metabolic diseases including diabetes mellitus. METHOD With effective preventative diagnostic procedures and specific therapeutic treatment of sarcopenia, the negative effects on the individual can be reduced and the negative impact on health as well as socioeconomic effects can be prevented. Various diagnostic options are available for this purpose. In addition to basic clinical methods such as measuring muscle strength, sarcopenia can also be detected using imaging techniques like dual X-ray absorptiometry (DXA), computed tomography (CT), magnetic resonance imaging (MRI), and sonography. DXA, as a simple and cost-effective method, offers a low-dose option for assessing body composition. With cross-sectional imaging techniques such as CT and MRI, further diagnostic possibilities are available, including MR spectroscopy (MRS) for noninvasive molecular analysis of muscle tissue. CT can also be used in the context of examinations performed for other indications to acquire additional parameters of the skeletal muscles (opportunistic secondary use of CT data), such as abdominal muscle mass (total abdominal muscle area - TAMA) or the psoas as well as the pectoralis muscle index. The importance of sarcopenia is already well studied for patients with various tumor entities and also infections such as SARS-COV2. RESULTS AND CONCLUSION Sarcopenia will become increasingly important, not least due to demographic changes in the population. In this review, the possibilities for the diagnosis of sarcopenia, the clinical significance, and therapeutic options are described. In particular, CT examinations, which are repeatedly performed on tumor patients, can be used for diagnostics. This opportunistic use can be supported by the use of artificial intelligence. KEY POINTS · Sarcopenia is an age-related syndrome with loss of muscle mass and strength.. · Early detection and therapy can prevent negative effects of sarcopenia.. · In addition to DEXA, cross-sectional imaging techniques (CT, MRI) are available for diagnostic purposes.. · The use of artificial intelligence (AI) offers further possibilities in sarcopenia diagnostics.. CITATION FORMAT · Vogele D, Otto S, Sollmann N et al. Sarcopenia - Definition, Radiological Diagnosis, Clinical Significance. Fortschr Röntgenstr 2023; DOI: 10.1055/a-1990-0201.
Collapse
Affiliation(s)
- Daniel Vogele
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Germany
| | - Stephanie Otto
- Comprehensive Cancer Center (CCCU), University Hospital Ulm, Germany
| | - Nico Sollmann
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Germany
| | - Benedikt Haggenmüller
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Germany
| | - Daniel Wolf
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Germany
| | - Meinrad Beer
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Germany
| | | |
Collapse
|
21
|
Naser MA, Wahid KA, Grossberg AJ, Olson B, Jain R, El-Habashy D, Dede C, Salama V, Abobakr M, Mohamed ASR, He R, Jaskari J, Sahlsten J, Kaski K, Fuller CD. Deep learning auto-segmentation of cervical skeletal muscle for sarcopenia analysis in patients with head and neck cancer. Front Oncol 2022; 12:930432. [PMID: 35965493 PMCID: PMC9366009 DOI: 10.3389/fonc.2022.930432] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2022] [Accepted: 06/29/2022] [Indexed: 12/22/2022] Open
Abstract
Background/Purpose Sarcopenia is a prognostic factor in patients with head and neck cancer (HNC). Sarcopenia can be determined using the skeletal muscle index (SMI) calculated from cervical neck skeletal muscle (SM) segmentations. However, SM segmentation requires manual input, which is time-consuming and variable. Therefore, we developed a fully-automated approach to segment cervical vertebra SM. Materials/Methods 390 HNC patients with contrast-enhanced CT scans were utilized (300-training, 90-testing). Ground-truth single-slice SM segmentations at the C3 vertebra were manually generated. A multi-stage deep learning pipeline was developed, where a 3D ResUNet auto-segmented the C3 section (33 mm window), the middle slice of the section was auto-selected, and a 2D ResUNet auto-segmented the auto-selected slice. Both the 3D and 2D approaches trained five sub-models (5-fold cross-validation) and combined sub-model predictions on the test set using majority vote ensembling. Model performance was primarily determined using the Dice similarity coefficient (DSC). Predicted SMI was calculated using the auto-segmented SM cross-sectional area. Finally, using established SMI cutoffs, we performed a Kaplan-Meier analysis to determine associations with overall survival. Results Mean test set DSC of the 3D and 2D models were 0.96 and 0.95, respectively. Predicted SMI had high correlation to the ground-truth SMI in males and females (r>0.96). Predicted SMI stratified patients for overall survival in males (log-rank p = 0.01) but not females (log-rank p = 0.07), consistent with ground-truth SMI. Conclusion We developed a high-performance, multi-stage, fully-automated approach to segment cervical vertebra SM. Our study is an essential step towards fully-automated sarcopenia-related decision-making in patients with HNC.
Collapse
Affiliation(s)
- Mohamed A. Naser
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Kareem A. Wahid
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Aaron J. Grossberg
- Department of Radiation Medicine, Oregon Health & Science University, Portland, OR, United States
| | - Brennan Olson
- Medical Scientist Training Program, Oregon Health & Science University, Portland, OR, United States
| | - Rishab Jain
- Department of Radiation Medicine, Oregon Health & Science University, Portland, OR, United States
| | - Dina El-Habashy
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
- Department of Clinical Oncology, Menoufia University Shibin El Kom, Shibin El Kom, Egypt
| | - Cem Dede
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Vivian Salama
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Moamen Abobakr
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Abdallah S. R. Mohamed
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Renjie He
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Joel Jaskari
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Jaakko Sahlsten
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Kimmo Kaski
- Department of Computer Science, Aalto University School of Science, Espoo, Finland
| | - Clifton D. Fuller
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
- *Correspondence: Clifton D. Fuller,
| |
Collapse
|
22
|
CT-Derived Body Composition Assessment as a Prognostic Tool in Oncologic Patients: From Opportunistic Research to Artificial Intelligence-Based Clinical Implementation. AJR Am J Roentgenol 2022; 219:671-680. [PMID: 35642760 DOI: 10.2214/ajr.22.27749] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
CT-based body composition measures are well established in research settings as prognostic markers in oncologic patients. Numerous retrospective studies have shown the role of objective measurements extracted from abdominal CT images of skeletal muscle, abdominal fat, and bone mineral density in providing more accurate assessments of frailty and cancer cachexia in comparison with traditional clinical methods. Quantitative CT-based measurements of liver fat and aortic atherosclerotic calcification have received relatively less attention in cancer care but also provide prognostic information. Patients with cancer routinely undergo serial CT scans for staging, treatment response, and surveillance, providing the opportunity for performing quantitative body composition assessment as part of routine clinical care. The emergence of fully automated artificial intelligence-based segmentation and quantification tools to replace earlier time-consuming manual and semi-automated methods for body composition analysis will allow these opportunistic measures to transition from the research realm to clinical practice. With continued investigation, the measurements may ultimately be applied to achieve more precise risk stratification as a component of personalized oncologic care.
Collapse
|