Using a new artificial intelligence-aided method to assess body composition CT segmentation in colorectal cancer patients.

INTRODUCTION: This study aimed to evaluate the accuracy of our own artificial intelligence (AI)-generated model to assess automated segmentation and quantification of body composition-derived computed tomography (CT) slices from the lumber (L3) region in colorectal cancer (CRC) patients. METHODS: A total of 541 axial CT slices at the L3 vertebra were retrospectively collected from 319 patients with CRC diagnosed during 2012-2019 at a single Australian tertiary institution, Western Health in Melbourne. A two-dimensional U-Net convolutional network was trained on 338 slices to segment muscle, visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT). Manual reading of these same slices of muscle, VAT and SAT was created to serve as ground truth data. The Dice similarity coefficient was used to assess the U-Net-based segmentation performance on both a validation dataset (68 slices) and a test dataset (203 slices). The measurement of cross-sectional area and Hounsfield unit (HU) density of muscle, VAT and SAT were compared between two methods. RESULTS: The segmentation for muscle, VAT and SAT demonstrated excellent performance for both the validation (Dice similarity coefficients >0.98, respectively) and test (Dice similarity coefficients >0.97, respectively) datasets. There was a strong positive correlation between manual and AI segmentation measurements of body composition for both datasets (Spearman's correlation coefficients: 0.944-0.999, P < 0.001). CONCLUSIONS: Compared to the gold standard, this fully automated segmentation system exhibited a high accuracy for assessing segmentation and quantification of abdominal muscle and adipose tissues of CT slices at the L3 in CRC patients.

Body composition assessment by artificial intelligence can be a predictive tool for short-term postoperative complications in Hartmann's reversals.

BACKGROUND: Hartmann's reversal, a complex elective surgery, reverses and closes the colostomy in individuals who previously underwent a Hartmann's procedure due to colonic pathology like cancer or diverticulitis. It demands careful planning and patient optimisation to help reduce postoperative complications. Preoperative evaluation of body composition has been useful in identifying patients at high risk of short-term postoperative outcomes following colorectal cancer surgery. We sought to explore the use of our in-house derived Artificial Intelligence (AI) algorithm to measure body composition within patients undergoing Hartmann's reversal procedure in the prediction of short-term postoperative complications. METHODS: A retrospective study of all patients who underwent Hartmann's reversal within a single tertiary referral centre (Western) in Melbourne, Australia and who had a preoperative Computerised Tomography (CT) scan performed. Body composition was measured using our previously validated AI algorithm for body segmentation developed by the Department of Surgery, Western Precinct, University of Melbourne. Sarcopenia in our study was defined as a skeletal muscle index (SMI), calculated as Skeletal Muscle Area (SMA) /height2 < 38.5 cm2/m2 in women and < 52.4 cm2/m2 in men. RESULTS: Between 2010 and 2020, 47 patients (mean age 63.1 ± 12.3 years; male, n = 28 (59.6%) underwent body composition analysis. Twenty-one patients (44.7%) were sarcopenic, and 12 (25.5%) had evidence of sarcopenic obesity. The most common postoperative complication was surgical site infection (SSI) (n = 8, 17%). Sarcopenia (n = 7, 87.5%, p = 0.02) and sarcopenic obesity (n = 5, 62.5%, p = 0.02) were significantly associated with SSIs. The risks of developing an SSI were 8.7 times greater when sarcopenia was present. CONCLUSION: Sarcopenia and sarcopenic obesity were related to postoperative complications following Hartmann's reversal. Body composition measured by a validated AI algorithm may be a beneficial tool for predicting short-term surgical outcomes for these patients.

Artificial intelligence measured 3D body composition to predict pathological response in rectal cancer patients.

BACKGROUND: The treatment of locally advanced rectal cancer (LARC) is moving towards total neoadjuvant therapy and potential organ preservation. Of particular interest are predictors of pathological complete response (pCR) that can guide personalized treatment. There are currently no clinical biomarkers which can accurately predict neoadjuvant therapy (NAT) response but body composition (BC) measures present as an emerging contender. The primary aim of the study was to determine if artificial intelligence (AI) derived body composition variables can predict pCR in patients with LARC. METHODS: LARC patients who underwent NAT followed by surgery from 2012 to 2023 were identified from the Australian Comprehensive Cancer Outcomes and Research Database registry (ACCORD). A validated in-house pre-trained 3D AI model was used to measure body composition via computed tomography images of the entire Lumbar-3 vertebral level to produce a volumetric measurement of visceral fat (VF), subcutaneous fat (SCF) and skeletal muscle (SM). Multivariate analysis between patient body composition and histological outcomes was performed. RESULTS: Of 214 LARC patients treated with NAT, 22.4% of patients achieved pCR. SM volume (P = 0.015) and age (P = 0.03) were positively associated with pCR in both male and female patients. SCF volume was associated with decreased likelihood of pCR (P = 0.059). CONCLUSION: This is the first study in the literature utilizing AI-measured 3D Body composition in LARC patients to assess their impact on pathological response. SM volume and age were positive predictors of pCR disease in both male and female patients following NAT for LARC. Future studies investigating the impact of body composition on clinical outcomes and patients on other neoadjuvant regimens such as TNT are potential avenues for further research.

Colorectal cancer treatment outcomes during the pandemic: Our experience of COVID-19 at a tertiary referral center.

BACKGROUNDS: The coronavirus disease 2019 (COVID-19) has led to major shifts in the management of colorectal cancer (CRC). This study aims to identify the impact and early outcomes of COVID-19 following CRC management at a tertiary referral center in Victoria, Australia. METHODS: This was a retrospective study, utilizing the Australian Comprehensive Cancer Outcomes and Research Database and inpatient records. Patients presenting for CRC management at our institution were identified coinciding with the first Victorian outbreak of COVID-19 (March 26 to September 26, 2020) (COVID). Management decisions including chemoradiotherapy utilization and surgical outcomes were analyzed within 6 months and compared with the corresponding period in 2019 (pre-COVID). RESULTS: A total of 276 patients were included in this study (147 pre-COVID period, 129 COVID period). During the COVID period, more patients (47.6% vs. 60.5%; p = 0.033) presented symptomatically and less for surveillance (10.9% vs. 2.3%; p < 0.01). Eighty-four pre-COVID and 69 COVID period patients proceeded to surgery. The average time from diagnosis date to surgery was 15.6 days less during the COVID period. There were no significant differences in postoperative utilization of higher care (p = 0.74), complications (p = 0.93), median hospital length of stay (p = 0.67), 30-day readmission (p = 0.50), or 30-day reoperation (p = 0.74). In 1.6% of cases, pandemic impacts resulted in a change in management. CONCLUSION: Presentation of patients with CRC varied, with a significant increase in symptomatic presentations and decreased numbers for surveillance. Through flexibility and change in practice, our institution helped improve access to surgical intervention and oncological therapies. Further prospective work is required to identify long-term outcomes and characterize the effects of ongoing disruptions.

Identification of Differences in Body Composition Measures Using 3D-Derived Artificial Intelligence from Multiple CT Scans across the L3 Vertebra Compared to a Single Mid-Point L3 CT Scan.

Purpose: Body composition analysis in colorectal cancer (CRC) typically utilises a single 2D-abdominal axial CT slice taken at the mid-L3 level. The use of artificial intelligence (AI) allows for analysis of the entire L3 vertebra (non-mid-L3 and mid-L3). The goal of this study was to determine if the use of an AI approach offered any additional information on capturing body composition measures. Methods: A total of 2203 axial CT slices of the entire L3 level (4-46 slices were available per patient) were retrospectively collected from 203 CRC patients treated at Western Health, Melbourne (97 males; 47.8%). A pretrained artificial intelligence (AI) model was used to segment muscle, visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT) on these slices. The difference in body composition measures between mid-L3 and non-mid-L3 scans was compared for each patient, and for males and females separately. Results: Body composition measures derived from non-mid-L3 scans exhibited a median range of 0.85% to 6.28% (average percent difference) when compared to the use of a single mid-L3 scan. Significant variation in the VAT surface area (p = 0.02) was observed in females compared to males, whereas male patients exhibited a greater variation in SAT surface area (p < 0.001) and radiodensity (p = 0.007). Conclusion: Significant differences in various body composition measures were observed when comparing non-mid-L3 slices to only the mid-L3 slice. Researchers should be aware that considering only the use of a single midpoint L3 CT scan slice will impact the estimate of body composition measurements.

Can AI-based body composition assessment outperform body surface area in predicting dose-limiting toxicities for colonic cancer patients on chemotherapy?

PURPOSE: Gold standard chemotherapy dosage is based on body surface area (BSA); however many patients experience dose-limiting toxicities (DLT). We aimed to evaluate the effectiveness of BSA, two-dimensional (2D) and three-dimensional (3D) body composition (BC) measurements derived from Lumbar 3 vertebra (L3) computed tomography (CT) slices, in predicting DLT in colon cancer patients. METHODS: 203 patients (60.87 ± 12.42 years; 97 males, 47.8%) receiving adjuvant chemotherapy (Oxaliplatin and/or 5-Fluorouracil) were retrospectively evaluated. An artificial intelligence segmentation model was used to extract 2D and 3D body composition measurements from each patients' single mid-L3 CT slice as well as multiple-L3 CT scans to produce a 3D BC report. DLT was defined as any incidence of dose reduction or discontinuation due to chemotherapy toxicities. A receiver operating characteristic (ROC) analysis was performed on BSA and individual body composition measurements to demonstrate their predictive performance. RESULTS: A total of 120 (59.1%) patients experienced DLT. Age and BSA did not vary significantly between DLT and non-DLT group. Females were significantly more likely to experience DLT (p = 4.9 × 10-3). In all patients, the predictive effectiveness of 2D body composition measurements (females: AUC = 0.50-0.54; males: AUC = 0.50-0.61) was equivalent to that of BSA (females: AUC = 0.49; males: AUC = 0.58). The L3 3D skeletal muscle volume was the most predictive indicator of DLT (AUC of 0.66 in females and 0.64 in males). CONCLUSION: Compared to BSA and 2D body composition measurements, 3D L3 body composition measurements had greater potential to predict DLT in CRC patients receiving chemotherapy and this was sex dependent.