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. Graphical

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. 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. 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). 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.

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.

Objectives: For patients with colorectal liver metastases (CRLM), total tumor volume (TTV) is prognostic. A deep-learning segmentation model for CRLM to assess TTV called COlorectal cAncer Liver metastases Assessment (COALA) has been developed. This study evaluated COALA’s performance and practical utility in the radiological picture archiving and communication system (PACS). A secondary aim was to provide lessons for future researchers on the implementation of artificial intelligence (AI) models. Methods: Patients discussed between January and December 2023 in a multidisciplinary meeting for CRLM were included. In those patients, CRLM was automatically segmented in portal-venous phase CT scans by COALA and integrated with PACS. Eight expert abdominal radiologists completed a questionnaire addressing segmentation accuracy and PACS integration. They were also asked to write down general remarks. Results: In total, 57 patients were evaluated. Of those patients, 112 contrast-enhanced portal-venous phase CT scans were analyzed. Of eight radiologists, six (75%) evaluated the model as user-friendly in their radiological workflow. Areas of improvement of the COALA model were the segmentation of small lesions, heterogeneous lesions, and lesions at the border of the liver with involvement of the diaphragm or heart. Key lessons for implementation were a multidisciplinary approach, a robust method prior to model development and organizing evaluation sessions with end-users early in the development phase. Conclusion: This study demonstrates that the deep-learning segmentation model for patients with CRLM (COALA) is user-friendly in the radiologist’s PACS. Future researchers striving for implementation should have a multidisciplinary approach, propose a robust methodology and involve end-users prior to model development. Critical relevance statement: Many segmentation models are being developed, but none of those models are evaluated in the (radiological) workflow or clinically implemented. Our model is implemented in the radiological work system, providing valuable lessons for researchers to achieve clinical implementation. Key Points: Developed segmentation models should be implemented in the radiological workflow. Our implemented segmentation model provides valuable lessons for future researchers. If implemented in clinical practice, our model could allow for objective radiological evaluation. Graphical

This study aimed to assess whether total tumor volume (TTV) outperforms RECIST1.1 for treatment response assessment in patients with colorectal liver metastases (CRLM), and to investigate TTV as a predictive biomarker for the optimal systemic treatment regimen for individual patients with initially unresectable CRLM. Patients with initially unresectable liver-only CRLM from the phase 3 CAIRO5 trial (NCT02162563) were included. All patients received induction systemic treatment. Baseline TTV and changes in TTV and RECIST1.1 in response to systemic treatment were calculated using the CT scans before systemic treatment and at first follow-up, and were assessed for their prognostic and predictive value with multivariable Cox regression models. Results In total, 425 patients were included. In multivariable analyses, baseline TTV (adjusted HR [aHR] for 100 mL vs 10 mL, 2.44 [95 % CI, 1.25-4.76]; P = 0.006) and relative change in TTV were the strongest predictors for OS (aHR for 0 % change vs 50 % decrease, 2.57 [1.83-3.60]; P < 0.0001). In contrast, RECIST1.1 was not independently associated with OS (aHR for partial response vs progressive disease, 0.63 [95 % CI, 0.33-1.20]). Higher baseline TTV predicted a stronger treatment benefit of FOLFOX-/FOLFIRI-bevacizumab vs FOLFOX-/FOLFIRI-panitumumab on OS (P_interaction=0.017). This study demonstrates that TTV (i) outperforms traditional risk factors for OS prognostication, and (ii) may be a more accurate and sensitive treatment response assessment method compared to the currently used RECIST1.1 system in patients with initially unresectable CRLM. Moreover, TTV assessment is a promising approach for individualized clinical decision-making between bevacizumab and panitumumab.

Total tumor number (TTN) and total tumor volume (TTV) reflect tumor burden and have been linked to outcomes in metastatic colorectal cancer (mCRC). We hypothesize that these measures can identify patients who benefit most from maintenance therapy. This exploratory analysis assessed the prognostic and predictive value of TTN and TTV in mCRC. Patients with liver and/or lung metastases from the CAIRO3 trial, which randomized between maintenance therapy and observation, were included. All lesions were counted, and their volumes were quantified using automated deep-learning segmentation models. Cox regression models were used to assess the prognostic value of TTN and TTV for progression-free (PFS) and overall survival (OS), as well as potential interactions with treatment arm (maintenance vs observation). A total of 3989 metastatic lesions were segmented in 104 patients (median age, 64 years; 65% male). At randomization, median TTN was 10 and median TTV was 37 mL. Higher TTN and TTV were associated with shorter PFS (TTN p = 0.006; TTV p = 0.2) and OS (TTN p = 0.005; TTV p = 0.001). In multivariable analyses, both TTN and TTV were independently prognostic for PFS/OS. The 1-year PFS benefit of maintenance therapy was more pronounced in patients with lower TTV (P_interaction=0.0002). This exploratory analysis showed that a higher tumor burden, quantified by number or volume, was independently associated with poor outcomes. Patients with lower tumor burden, especially lower TTV, appeared to derive the greatest benefit from maintenance therapy, supporting their potential as predictive biomarkers.