Pelvic insufficiency fractures and pelvic bone metastases after neoadjuvant (chemo)radiotherapy for rectal cancer.

BACKGROUND: Pelvic insufficiency fractures (PIFs) are a late complication of radiotherapy for pelvic malignancies. We evaluated the incidence, radiologic findings, clinical course, and outcome of PIFs in patients treated with neoadjuvant (chemo)radiotherapy ((C)RT) for rectal cancer. MATERIAL AND METHODS: Data of patients diagnosed with rectal cancer from a large teaching hospital treated from 2002 to 2012 were extracted from the Dutch Cancer Registry. All hospital records were reviewed for the diagnosis of PIFs or pelvic bone metastases. An expert radiologist reassessed all imaging procedures of the lower back, abdomen, and pelvis. RESULTS: A total of 513 rectal cancer patients were identified of whom 300 patients (58.5%) were treated with neoadjuvant (C)RT (long- vs. short-course radiotherapy: 91 patients [17.7%] vs. 209 [40.7%], respectively). Twelve PIFs were diagnosed initially according to hospital records and imaging reports of all 513 patients. These 12 patients were treated with neoadjuvant (C)RT. After reassessment of all pelvic imaging procedures done in this patient group (432 patients (84.2%)), 20 additional PIFs were detected in patients treated with neoadjuvant (C)RT, resulting in a 10.7% PIF rate in irradiated patients. One PIF was detected in the group of patients not treated with neoadjuvant (C)RT for rectal cancer. This patient had palliative radiotherapy for prostate cancer and is left out of the analysis. Median follow-up time of 32 PIF patients was 49 months. Median time between start of neoadjuvant (C)RT and diagnosis of PIF was 17 months (IQR 9-28). Overall median survival for patients with PIF was 63.5 months (IQR 44-120). CONCLUSION: PIFs are a relatively common late complication of neoadjuvant (C)RT for rectal cancer but are often missed or misdiagnosed as pelvic bone metastases. The differentiation of PIFs from pelvic bone metastases is important because of a different treatment and disease outcome.

CT-Based Radiomics Analysis Before Thermal Ablation to Predict Local Tumor Progression for Colorectal Liver Metastases.

PURPOSE: Predicting early local tumor progression after thermal ablation treatment for colorectal liver metastases patients is critical for the decision of subsequent follow-up and treatment. Radiomics features derived from medical images show great potential for prediction and prognosis. The aim is to develop and validate a machine learning radiomics model to predict local tumor progression based on the pre-ablation CT scan of colorectal liver metastases patients. MATERIALS AND METHODS: Ninety patients with colorectal liver metastases (140 lesions) treated by ablation were included in the study and were randomly divided into a training (n = 63 patients/n = 94 lesions) and validation (n = 27 patients/n = 46 lesions) cohort. After manual lesion volume segmentation and preprocessing, 1593 radiomics features were extracted for each lesion. Three machine learning survival models were constructed based on (1) radiomics features, (2) clinical features and (3) a combination of clinical and radiomics features to predict local tumor progression free survival. Feature reduction and machine learning modeling were performed and optimized with sequential model-based optimization. RESULTS: Median follow-up was 24 months (range 6-115). Thirty-one (22%) lesions developed local tumor progression. The concordance index in the validation set to predict local tumor progression free survival was 0.78 (95% confidence interval [CI]: 0.77-0.79) for the radiomics model, 0.56 (95%CI: 0.55-0.57) for the clinical model and 0.79 (95%CI: 0.78-0.80) for the combined model. CONCLUSION: A machine learning-based radiomics analysis of routine clinical CT imaging pre-ablation could act as a valuable biomarker model to predict local tumor progression with curative intent for colorectal liver metastases patients.

Machine learning-based analysis of CT radiomics model for prediction of colorectal metachronous liver metastases.

PURPOSE: Early identification of patients at risk of developing colorectal liver metastases can help personalizing treatment and improve oncological outcome. The aim of this study was to investigate in patients with colorectal cancer (CRC) whether a machine learning-based radiomics model can predict the occurrence of metachronous metastases. METHODS: In this multicentre study, the primary staging portal venous phase CT of 91 CRC patients were retrospectively analysed. Two groups were assessed: patients without liver metastases at primary staging, or during follow-up of ≥ 24 months (n = 67) and patients without liver metastases at primary staging but developed metachronous liver metastases < 24 months after primary staging (n = 24). After liver parenchyma segmentation, 1767 radiomics features were extracted for each patient. Three predictive models were constructed based on (1) radiomics features, (2) clinical features and (3) a combination of clinical and radiomics features. Stability of features across hospitals was assessed by the Kruskal-Wallis test and inter-correlated features were removed if their correlation coefficient was higher than 0.9. Bayesian-optimized random forest with wrapper feature selection was used for prediction models. RESULTS: The three predictive models that included radiomics features, clinical features and a combination of radiomics with clinical features resulted in an AUC in the validation cohort of 86% (95%CI 85-87%), 71% (95%CI 69-72%) and 86% (95% CI 85-87%), respectively. CONCLUSION: A machine learning-based radiomics analysis of routine clinical CT imaging at primary staging can provide valuable biomarkers to identify patients at high risk for developing colorectal liver metastases.

Comparison of MRI and colonoscopy in determining tumor height in rectal cancer.

BACKGROUND AND AIM: Endoscopy and magnetic resonance imaging (MRI) are used routinely in the diagnostic and preoperative work-up of rectal cancer. We aimed to compare colonoscopy and MRI in determining rectal tumor height. METHODS: Between 2002 and 2012, all patients with rectal cancer with available MRIs and endoscopy reports were included. All MRIs were reassessed for tumor height by two abdominal radiologists. To obtain insight in techniques used for endoscopic determination of tumor height, a survey among regional endoscopists was conducted. RESULTS: A total of 211 patients with rectal cancer were included. Tumor height was significantly lower when assessed by MRI than by endoscopy with a mean difference of 2.5 cm (95% CI: 2.1-2.8). Although the agreement between tumor height as measured by MRI and endoscopy was good (intraclass correlation coefficient (ICC) 0.7 (95% CI: 0.7-0.8)), the 95% limits of agreement varied from -3.0 cm to 8.0 cm. In 45 patients (21.3%), tumors were regarded as low by MRI and middle-high by endoscopy. MRI inter- and intraobserver agreements were excellent with an ICC of 0.8 (95% CI: 0.7-0.9) and 0.9 (95% CI: 0.9-1.0), respectively. The survey showed no consensus among endoscopists as to how to technically measure tumor height. CONCLUSION: This study showed large variability in rectal tumor height as measured by colonoscopy and MRI. Since MRI measurements showed excellent inter- and intraobserver agreement, we suggest using tumor height measurement by MRI for diagnostic purposes and treatment allocation.