Utility of Fully Automated Body Composition Measures on Pretreatment Abdominal CT for Predicting Survival in Patients With Colorectal Cancer

Methodology for a fully automated pipeline of AI-based body composition tools for abdominal CT

Accurate, reproducible body composition analysis from abdominal computed tomography (CT) images is critical for both clinical research and patient care. We present a fully automated, artificial intelligence (AI)-based pipeline that streamlines the entire process-from data normalization and anatomical landmarking to automated tissue segmentation and quantitative biomarker extraction. Our methodology ensures standardized inputs and robust segmentation models to compute volumetric, density, and cross-sectional area metrics for a range of organs and tissues. Additionally, we capture selected DICOM header fields to enable downstream analysis of scan parameters and facilitate correction for acquisition-related variability. By emphasizing portability and compatibility across different scanner types, image protocols, and computational environments, we ensure broad applicability of our framework. This toolkit is the basis for the Opportunistic Screening Consortium in Abdominal Radiology (OSCAR) and has been shown to be robust and versatile, critical for large multi-center studies.

Artificial intelligence measured 3D lumbosacral body composition and clinical outcomes in rectal cancer patients

INTRODUCTION

Patient body composition (BC) has been shown to help predict clinical outcomes in rectal cancer patients. Artificial intelligence algorithms have allowed for easier acquisition of BC measurements, creating a comprehensive BC profile in patients using data from an entire three-dimensional (3D) region of the body. This study has utilized AI technology to measure BC from the entire lumbosacral (L1-S5) region and assessed the associations between BC and clinical outcomes in rectal cancer patients who have undergone neoadjuvant therapy followed by surgery.

METHODS

A retrospective, cross sectional analysis was performed on locally advanced rectal cancer (LARC) patients treated with neoadjuvant long-course chemoradiotherapy followed by curative resection with total mesorectal excision at a tertiary referral centre, Western Health, Melbourne, Australia. A pre-trained and validated in-house AI segmentation model was used to automatically segment and measure intramuscular adipose tissue (IMAT), visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT) and skeletal muscle (SM) from CT slices across the entire L1-S5 level of each patient. Multivariate analysis between patient BC and clinical outcomes was performed.

RESULTS

Two hundred and fourteen patients were included in the study. One hundred and fifty-one (70.6%) patients were male and 63 (29.4%) patients were female. The average age at diagnosis was 62.4 (±12.7) years. SM density, but not volume, was associated with better overall survival (OS) (HR 0.24, P = 0.029), recurrence-free survival (RFS) (HR 0.45, P = 0.048) and decreased length of stay (LoS) (HR 1.58, P = 0.036). Both IMAT volume (HR 0.13, P = 0.008) and density (HR 0.26, P = 0.006) were associated with better OS.

CONCLUSION

This study measured 3D BC from the entire lumbosacral region of rectal cancer patients. SM density was the most significant BC parameter, and was associated with improved OS, RFS and LoS. This adds to growing evidence that SM is a key component of BC in cancer patients and should be optimized prior to treatment. IMAT was also a prognostic factor, giving rise to avenues of future research into the role of adiposity on nutrition and tumour immunology.

Improving the prediction of chemotherapy dose-limiting toxicity in colon cancer patients using an AI-CT-based 3D body composition of the entire L1-L5 lumbar spine

PURPOSE

Chemotherapy dose-limiting toxicities (DLT) pose a significant challenge in successful colon cancer treatment. Body composition analysis may enable tailored interventions thereby supporting the mitigation of chemotherapy toxic effects. This study aimed to evaluate and compare the effectiveness of using three-dimensional (3D) CT body composition measures from the entire lumbar spine levels (L1-L5) versus a single vertebral level (L3), the current gold standard, in predicting chemotherapy DLT in colon cancer patients.

METHODS

Retrospective analysis of 184 non-metastatic colon cancer patients receiving adjuvant chemotherapy was performed. DLT was defined as any occurrence of dose reduction or discontinuation due to chemotherapy toxicity. Using artificial intelligence (AI) auto-segmentation, 3D body composition measurements were obtained from patients' L1-L5 levels on CT imaging. The effectiveness of patients' 3D L3 body composition measurement and incorporating data from the entire L1-L5 (including L3) region in predicting DLT was examined.

RESULTS

Of the 184 patients, 112 (60.9%) experienced DLT. Neuropathy was the most common toxicity (49/112, 43.8%) followed by diarrhea (35.7%) and nausea/vomiting (33%). Patients with DLT had lower muscle volume at all lumbar levels compared to those without. The machine learning model incorporating L1-L5 data and patient clinical data achieved high predictive performance (AUC = 0.75, accuracy = 0.75), outperforming the prediction using single L3 level (AUC = 0.65, accuracy = 0.65).

CONCLUSION

Evaluating a patient's body composition allowed prediction of chemotherapy toxicities for colon cancer. Incorporating fully automated body composition analysis of CT slices from the entire lumbar region offers promising performance in early identification of high-risk individuals, with the ultimate aim of improving patient's quality of life.

Comparing fully automated AI body composition measures derived from thin and thick slice CT image data

PURPOSE

To compare fully automated artificial intelligence body composition measures derived from thin (1.25 mm) and thick (5 mm) slice abdominal CT data.

METHODS

In this retrospective study, fully automated CT-based body composition algorithms for quantifying bone attenuation, muscle attenuation, muscle area, liver attenuation, liver volume, spleen volume, visceral-to-subcutaneous fat ratio (VSR) and aortic calcium were applied to both thin (1.25 × 0.625 mm) and thick (5 × 3 mm) abdominal CT series from two patient cohorts: unenhanced scans in asymptomatic adults undergoing colorectal cancer screening, and post-contrast scans in patients with colorectal cancer. Body composition measures derived from thin and thick slice data were compared, including correlation coefficients and Bland-Altman analysis.

RESULTS

A total of 9882 CT scans (mean age, 57.0 years; 4527 women, 5355 men) were evaluated, including 8947 non-contrast and 935 contrast-enhanced CT exams. Very strong positive correlation was observed for all soft tissue measures: muscle attenuation (r2 = 0.97), muscle area (r2 = 0.98), liver attenuation (r2 = 0.99), liver volume (r2 = 0.98) and spleen volume (r2 = 0.99), VSR (r2 = 0.98), and aortic calcium (r2 = 0.92); (p < 0.001 for all). Moderate positive correlation was observed for bone attenuation (r2 = 0.35). Bland-Altman analysis showed strong agreement for muscle attenuation, muscle area, liver attenuation, liver volume and spleen volume. Mean percentage differences amongst body composition measures were less than 5% for VSR (4.6%), muscle area (- 0.5%), liver attenuation (0.4%) and liver volume (2.7%) and less than 10% for muscle attenuation (- 5.5%) and spleen volume (5.1%). For aortic calcium, thick slice overestimated for Agatston scores between 0 and 100 and > 400 burden in 3.1% and 0.3% relative to thin slice, respectively, but underestimated scores between 100 and 400.

CONCLUSION

Automated body composition measures derived from thin and thick abdominal CT data are strongly correlated and show agreement, particularly for soft tissue applications, making it feasible to use either series for these CT-based body composition algorithms.

Canadian Association of Radiologists Practice Guidelines for Computed Tomography Colonography

Colon cancer is the third most common malignancy in Canada. Computed tomography colonography (CTC) provides a creditable and validated option for colon screening and assessment of known pathology in patients for whom conventional colonoscopy is contraindicated or where patients self-select to use imaging as their primary modality for initial colonic assessment. This updated guideline aims to provide a toolkit for both experienced imagers (and technologists) and for those considering launching this examination in their practice. There is guidance for reporting, optimal exam preparation, tips for problem solving to attain high quality examinations in challenging scenarios as well as suggestions for ongoing maintenance of competence. We also provide insight into the role of artificial intelligence and the utility of CTC in tumour staging of colorectal cancer. The appendices provide more detailed guidance into bowel preparation and reporting templates as well as useful information on polyp stratification and management strategies. Reading this guideline should equip the reader with the knowledge base to perform colonography but also provide an unbiased overview of its role in colon screening compared with other screening options.

Management Algorithm for Osseous Metastatic Disease: What the Treatment Teams Want to Know

Radiologists play a primary role in identifying, characterizing, and classifying spinal metastases and can play a lifesaving role in the care of these patients by triaging those with instability to urgent spine surgery consultation. For this reason, an understanding of current treatment algorithms and principles of spinal stability in patients with cancer is vital for all who interpret spine studies. In addition, advances in imaging allow radiologists to provide more accurate diagnoses and characterize pathology, thereby improving patient safety.