Prognostic value of total tumor volume in patients with colorectal liver metastases: A secondary analysis of the randomized CAIRO5 trial with external cohort validation.

BACKGROUND: This study aimed to assess the prognostic value of total tumor volume (TTV) for early recurrence (within 6 months) and overall survival (OS) in patients with colorectal liver metastases (CRLM), treated with induction systemic therapy followed by complete local treatment. METHODS: Patients with initially unresectable CRLM from the multicenter randomized phase 3 CAIRO5 trial (NCT02162563) who received induction systemic therapy followed by local treatment were included. Baseline TTV and change in TTV as response to systemic therapy were calculated using the CT scan before and the first after systemic treatment, and were assessed for their added prognostic value. The findings were validated in an external cohort of patients treated at a tertiary center. RESULTS: In total, 215 CAIRO5 patients were included. Baseline TTV and absolute change in TTV were significantly associated with early recurrence (P = 0.005 and P = 0.040, respectively) and OS in multivariable analyses (P = 0.024 and P = 0.006, respectively), whereas RECIST1.1 was not prognostic for early recurrence (P = 0.88) and OS (P = 0.35). In the validation cohort (n = 85), baseline TTV and absolute change in TTV remained prognostic for early recurrence (P = 0.041 and P = 0.021, respectively) and OS in multivariable analyses (P < 0.0001 and P = 0.012, respectively), and showed added prognostic value over conventional clinicopathological variables (increase C-statistic, 0.06; 95 % CI, 0.02 to 0.14; P = 0.008). CONCLUSION: Total tumor volume is strongly prognostic for early recurrence and OS in patients who underwent complete local treatment of initially unresectable CRLM, both in the CAIRO5 trial and the validation cohort. In contrast, RECIST1.1 did not show prognostic value for neither early recurrence nor OS.

Identifying Genetic Mutation Status in Patients with Colorectal Cancer Liver Metastases Using Radiomics-Based Machine-Learning Models.

For patients with colorectal cancer liver metastases (CRLM), the genetic mutation status is important in treatment selection and prognostication for survival outcomes. This study aims to investigate the relationship between radiomics imaging features and the genetic mutation status (KRAS mutation versus no mutation) in a large multicenter dataset of patients with CRLM and validate these findings in an external dataset. Patients with initially unresectable CRLM treated with systemic therapy of the randomized controlled CAIRO5 trial (NCT02162563) were included. All CRLM were semi-automatically segmented in pre-treatment CT scans and radiomics features were calculated from these segmentations. Additionally, data from the Netherlands Cancer Institute (NKI) were used for external validation. A total of 255 patients from the CAIRO5 trial were included. Random Forest, Gradient Boosting, Gradient Boosting + LightGBM, and Ensemble machine-learning classifiers showed AUC scores of 0.77 (95%CI 0.62-0.92), 0.77 (95%CI 0.64-0.90), 0.72 (95%CI 0.57-0.87), and 0.86 (95%CI 0.76-0.95) in the internal test set. Validation of the models on the external dataset with 129 patients resulted in AUC scores of 0.47-0.56. Machine-learning models incorporating CT imaging features could identify the genetic mutation status in patients with CRLM with a good accuracy in the internal test set. However, in the external validation set, the models performed poorly. External validation of machine-learning models is crucial for the assessment of clinical applicability and should be mandatory in all future studies in the field of radiomics.

Deep learning models for automatic tumor segmentation and total tumor volume assessment in patients with colorectal liver metastases.

BACKGROUND: We developed models for tumor segmentation to automate the assessment of total tumor volume (TTV) in patients with colorectal liver metastases (CRLM). METHODS: In this prospective cohort study, pre- and post-systemic treatment computed tomography (CT) scans of 259 patients with initially unresectable CRLM of the CAIRO5 trial (NCT02162563) were included. In total, 595 CT scans comprising 8,959 CRLM were divided into training (73%), validation (6.5%), and test sets (21%). Deep learning models were trained with ground truth segmentations of the liver and CRLM. TTV was calculated based on the CRLM segmentations. An external validation cohort was included, comprising 72 preoperative CT scans of patients with 112 resectable CRLM. Image segmentation evaluation metrics and intraclass correlation coefficient (ICC) were calculated. RESULTS: In the test set (122 CT scans), the autosegmentation models showed a global Dice similarity coefficient (DSC) of 0.96 (liver) and 0.86 (CRLM). The corresponding median per-case DSC was 0.96 (interquartile range [IQR] 0.95-0.96) and 0.80 (IQR 0.67-0.87). For tumor segmentation, the intersection-over-union, precision, and recall were 0.75, 0.89, and 0.84, respectively. An excellent agreement was observed between the reference and automatically computed TTV for the test set (ICC 0.98) and external validation cohort (ICC 0.98). In the external validation, the global DSC was 0.82 and the median per-case DSC was 0.60 (IQR 0.29-0.76) for tumor segmentation. CONCLUSIONS: Deep learning autosegmentation models were able to segment the liver and CRLM automatically and accurately in patients with initially unresectable CRLM, enabling automatic TTV assessment in such patients. RELEVANCE STATEMENT: Automatic segmentation enables the assessment of total tumor volume in patients with colorectal liver metastases, with a high potential of decreasing radiologist's workload and increasing accuracy and consistency. KEY POINTS: • Tumor response evaluation is time-consuming, manually performed, and ignores total tumor volume. • Automatic models can accurately segment tumors in patients with colorectal liver metastases. • Total tumor volume can be accurately calculated based on automatic segmentations.

Physical performance has a strong association with poor surgical outcome in older patients with colorectal cancer.

BACKGROUND: Low lumbar skeletal muscle mass and density have been associated with adverse outcomes in different populations with colorectal cancer (CRC). We aimed to determine whether skeletal muscle mass, density, and physical performance are associated with postoperative complications and overall survival (OS) in older CRC patients. METHODS: We analysed consecutive patients (≥70 years) undergoing elective surgery for non-metastatic CRC (stage I-III). Lumbar skeletal muscle mass and muscle density were measured using abdominal CT-images obtained prior to surgery. Low skeletal muscle mass and low muscle density were defined using commonly used thresholds and by gender-specific quartiles (Q). The preoperative use of a mobility aid served as a marker for physical performance. Cox regression proportional hazard models were used to investigate the association between the independent variables and OS. RESULTS: 174 Patients were included (mean age 78.0), with median follow-up 2.6 years. 36 Patients (21%) used a mobility aid preoperatively. Low muscle density (Q1 vs Q4) and not muscle mass was associated with worse postoperative outcomes, including severe complications (p < 0.05). Use of a mobility aid was associated with more complications, including severe complications (39% vs 17%, p = 0.004) and OS (HR 2.65, CI 1.29-5.44, p = 0.01). However, patients with mobility aid use and low skeletal muscle mass had worse OS (HR 5.68, p = 0.003). CONCLUSION: Low skeletal muscle density and not muscle mass was associated with more complications after colorectal surgery in older patients. Physical performance has the strongest association for poor surgical outcomes and should be investigated when measuring skeletal muscle mass and density.

Prediction of presence of kidney disease in a general patient population undergoing intravenous iodinated contrast enhanced computed tomography.

OBJECTIVE: To assess which risk factors can be used to reduce superfluous estimated glomerular filtration rate (eGFR) measurements before intravenous contrast medium administration. METHODS: In consecutive patients, all decreased eGFR risk factors were assessed: diabetes mellitus (DM), history of urologic/nephrologic disease (HUND), nephrotoxic medication, cardiovascular disease, hypertension, age > 60 years, anaemia, malignancy and multiple myeloma/M. Waldenström. We studied four models: (1) all risk factors, (2) DM, HUND, hypertension, age > 60 years; (3) DM, HUND, cardiovascular disease, hypertension; (4) DM, HUND, age > 75 years and congestive heart failure. For each model, association with eGFR < 60 ml/min/1.73 m(2) or eGFR < 45 ml/min/1.73 m(2) was studied. RESULTS: A total of 998 patients, mean age 59.94 years were included; 112 with eGFR < 60 ml/min/1.73 m(2) and 30 with eGFR < 45 ml/min/1.73 m(2). Model 1 detected 816 patients: 108 with eGFR < 60 ml/min/1.73 m(2) and all 30 with eGFR < 45 ml/min/1.73 m(2). Model 2 detected 745 patients: 108 with eGFR < 60 ml/min/1.73 m(2) and all 30 with eGFR < 45 ml/min/1.73 m(2). Model 3 detected 622 patients: 100 with eGFR < 60 ml/min/1.73 m(2) and all 30 with eGFR < 45 ml/min/1.73 m(2). Model 4 detected 440 patients: 86 with eGFR < 60 ml/min/1.73 m(2) and all 30 with eGFR < 45 ml/min/1.73 m(2). Associations were significant (p < 0.001). CONCLUSION: Model 4 is most effective, resulting in the lowest proportion of superfluous eGFR measurements while detecting all patients with eGFR < 45 ml/min/1.73 m(2) and most with eGFR < 60 ml/min/1.73 m(2). KEY POINTS: A major risk factor for contrast-induced nephropathy (CIN) is kidney disease. Risk factors are used to identify patients with pre-existent kidney disease. Evidence for risk factors to identify patients with kidney disease is limited. The number of eGFR measurements to detect kidney disease can be reduced.

Contrast induced nephropathy in patients undergoing intravenous (IV) contrast enhanced computed tomography (CECT) and the relationship with risk factors: a meta-analysis.

PURPOSE: To summarize the incidence of contrast-induced nephropathy (CIN) and associations between CIN incidence and risk factors in patients undergoing intravenous contrast-enhanced computed tomography (CECT) with low- or iso-osmolar iodinated contrast medium. METHODS: This review is performed in accordance with the preferred reporting items in systematic reviews and meta-analysis (PRISMA) guidelines. We searched the MEDLINE, EMBASE and Cochrane databases from 2002 till November 2012. Two reviewers included papers and extracted data. The pooled data were analysed by either fixed or random-effects approach depending on heterogeneity defined as the I(2) index. RESULTS: 42 articles with 18,790 patients (mean age 61.5 years (range: 38-83 years)) were included. The mean baseline eGFR was 59.8 mL/min and ranged from 4 to 256 mL/min. Of all patients 45.0% had an estimated glomerular filtration rate (eGFR)<60 mL/min, 55.2% had hypertension; 20.2% had diabetes mellitus (DM) and 6.5% had congestive heart failure (CHF). The overall pooled CIN incidence, defined as a SCr increase of ≥ 25% or ≥ 0.5mg/dL, was 4.96% (95%CI: 3.79-6.47). Data analysis showed associations between CIN and the presence of renal insufficiency, DM, malignancy, age>65 years and use of non-steroidal anti-inflammatory drugs (NSAID's) with odds ratios of 1.73 (95%CI: 1.06-2.82), 1.87 (95%CI: 1.55-2.26), 1.79 (95%CI: 1.03-3.11), 1.95 (95%CI: 1.02-3.70) and 2.32 (95%CI: 1.04-5.19), respectively while hypertension, anaemia and CFH were not associated (p=0.13, p=0.38, p=0.40). CONCLUSION: The mean incidence of CIN after intravenous iodinated CECT was low and associated with renal insufficiency, diabetes, presence of malignancy, old age and NSAID's use.