Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Cao K

PROVIDER: S-EPMC10590342 | biostudies-literature | 2023 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Cao Ke K Yeung Josephine J Arafat Yasser Y Choi CheukShan C Wei Matthew Y K MYK Chan Steven S Lee Margaret M Baird Paul N PN Yeung Justin M C JMC

Journal of cancer research and clinical oncology 20230804 15

<h4>Purpose</h4>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.<h4>Methods</h4>203 patients (60.87 ± 12.42 years; 97 males, 47.8%) receiving adjuvant chemotherapy (Oxali ...[more]

PMID: 37540253

Similar Datasets

Project description:BackgroundNeoadjuvant chemotherapy (NACT) treatment in locoregionally advanced nasopharyngeal carcinoma (LA-NPC) can lead to considerable toxicity. Loss of skeletal muscle mass showed relevance with increased chemotherapy-related toxicity and poor survival in various cancer types, but its significance in NPC remains unclear. This study aimed to investigate the relationship between body composition parameters and the incidence of NACT toxicity in LA-NPC patients.MethodsNinety-six LA-NPC patients were retrospectively enrolled. All patients had pre-treatment abdominal computed tomography (CT) images to exclude distant metastasis. Lean body mass (LBM, kg) was estimated based on cross-sectional muscle area at the third lumbar vertebra (L3) level on CT, and skeletal muscle index (SMI, cm2/m2) was calculated. Doses of chemotherapeutics were normalized as dose/LBM (mg/kg). Grade 3-4 toxicity was defined as severe. The associations between body composition parameters and severe toxicities were assessed using univariate and multivariate logistic regression analyses. Optimal cutoff points were obtained with a receiver operating characteristic (ROC) curve.ResultsOf the 96 patients, 81.2% received the docetaxel + cisplatin (TP) regimen, and the rest received the gemcitabine + cisplatin (GP) regimen. Males had more LBM and a higher SMI at baseline, and females received a markedly higher dose of docetaxel and gemcitabine per kg LBM (P<0.001). With a cutoff value of 52.7 cm2/m2, patients with higher SMI showed lower risk of severe toxicity. For TP regimen group, those presented with grade 3-4 neutropenia had a higher dose per kg LBM. Univariate and multivariate analyses showed that the LBM-adjusted dose was significantly associated with severe neutropenia in the TP regimen group (P<0.001). The LBM-normalized docetaxel cutoff value of 2.64 mg/kg was a prominent predictor of ≥ grade 3 neutropenia (P=0.003), but a higher dose of docetaxel per kg LBM did not provide a better objective response rate.ConclusionsLA-NPC patients with lower SMI and higher dose of docetaxel per kg LBM are more likely to suffer from severe treatment-related toxicity. Higher docetaxel dose per kg LBM is a prominent predictor for severe neutropenia, but not for NACT response. LBM showed good potential in toxicity risk prediction and dose determination.

Project description:BackgroundImmune checkpoint inhibitors are increasingly used in neoadjuvant therapy for locally advanced gastric cancer. However, the effect of body composition on the efficacy of neoadjuvant therapy has not been reported.MethodsThe computed tomography (CT) images and clinicopathological data of 101 patients with locally advanced gastric cancer who received neoadjuvant chemotherapy combined with immunotherapy (NCI) from 2019 to 2021 were collected. The CT image of L3 vertebral body section was selected, and the body composition before and after the neoadjuvant treatment was calculated using the SliceOmatic software, mainly including skeletal muscle index (SMI), subcutaneous adipose index (SAI), and visceral adipose index (VAI). The relationship between body composition and the efficacy and adverse events of NCI was analyzed.ResultsOf the 101 patients, 81 with evaluable data were included in the analysis. Of the included patients, 77.8% were male; the median age of all the patients was 62 years, and the median neoadjuvant therapy cycle was three. After the neoadjuvant therapy, 62.9% of the tumors were in remission (residual tumor cells ≤ 50%), and 37.1% of the tumors had no remission (residual tumor cells>50%). Moreover, 61.7% of the patients had treatment-related adverse events (TRAEs), and 18.5% had immune-related adverse events (irAEs). After neoadjuvant therapy, the body mass index (from 23 to 22.6 cm2/m2, p=0.042), SAI (from 34.7 to 32.9 cm2/m2, p=0.01) and VAI (from 32.4 to 26.8 cm2/m2, p=0.005) were significantly lower than those before treatment, while the SMI had no significant change (44.7 vs 42.5 cm2/m2, p=0.278). The multivariate logistics regression analysis revealed that low SMI (odds ratio [OR]: 3.23,95% confidence interval [CI]: 1.06-9.81, p=0.047), SMI attenuation (△SMI) ≥ 1.8(OR: 1.45,95%CI: 1.20-3.48, p=0.048), and clinical node positivity (OR: 6.99,95%CI: 2.35-20.82, p=0.001) were independent risk factors for non-remission. Additionally, high SAI is an independent risk factor for irAEs (OR: 14, 95%CI: 1.73-112.7, p=0.013).ConclusionLow SMI and △SMI≥1.8 are independent risk factors for poor tumor regression in patients with advanced gastric cancer receiving NCI. Patients with a high SAI are more likely to develop irAEs.

Project description:PurposeTotal and regional body composition are important indicators of health and mortality risk, but their measurement is usually restricted to controlled environments in clinical settings with expensive and specialized equipment. A method that approaches the accuracy of the current gold standard method, dual-energy x-ray absorptiometry (DXA), while only requiring input from widely available consumer grade equipment, would enable the measurement of these important biometrics in the wild, enabling data collection at a scale that would have previously been prohibitive in time and expense. We describe an algorithm for predicting three-dimensional (3D) body shape and composition from a single frontal 2-dimensional image acquired with a digital consumer camera.MethodsDuplicate 3D optical scans, two-dimensional (2D) optical images, and DXA whole-body scans were available for 183 men and 233 women from the Shape Up! Adults Study. A principal component analysis vector basis was fit to 3D point clouds of a training subset of 152 men and 194 women. The relationship between this vector space and DXA-derived body composition was modeled with linear regression. The principal component 3D shape was then fitted to match a silhouette extracted from a 2D photograph of a novel body. Body composition was predicted from the resulting 3D shape match using the linear mapping between the principal component parameters and the DXA metrics. Accuracy of body composition estimates from the silhouette method was evaluated against a simple model using height and weight as a baseline, and against DXA measurements as ground truth. Test-retest precision of the silhouette method was evaluated using the duplicate 2D optical images and compared against precision of the duplicate DXA scans. Paired t-tests were performed to detect significant differences between the sets.ResultsResults were reported on a held-out set. Body composition prediction achieved R2 s of 0.81 and 0.74 for percent fat prediction of males and females, respectively, on a held-out test set consisting of 31 males and 39 females. Precision estimates for fat mass were 2.31% and 2.06% for males and females, respectively, compared to 1.26% and 0.68% for DXA scans. The t-tests revealed no statistically significant differences between the silhouette method measurements and DXA measurements, or between retests.ConclusionTotal and regional body composition measures can be estimated from a single frontal photograph of a human body. Body composition prediction using consumer level photography can enable early screening and monitoring of possible physiological indicators of metabolic disease in regions where medical imagery or clinical assessment is inaccessible.

Dataset Information

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

Purpose

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets