Impact factors for microinvasion in intrahepatic cholangiocarcinoma: a possible system for defining clinical target volume

Interpretable machine learning-based clinical prediction model for predicting lymph node metastasis in patients with intrahepatic cholangiocarcinoma

OBJECTIVE

Prediction of lymph node metastasis (LNM) for intrahepatic cholangiocarcinoma (ICC) is critical for the treatment regimen and prognosis. We aim to develop and validate machine learning (ML)-based predictive models for LNM in patients with ICC.

METHODS

A total of 345 patients with clinicopathological characteristics confirmed ICC from Jan 2007 to Jan 2019 were enrolled. The predictors of LNM were identified by the least absolute shrinkage and selection operator (LASSO) and logistic analysis. The selected variables were used for developing prediction models for LNM by six ML algorithms, including Logistic regression (LR), Gradient boosting machine (GBM), Extreme gradient boosting (XGB), Random Forest (RF), Decision tree (DT), Multilayer perceptron (MLP). We applied 10-fold cross validation as internal validation and calculated the average of the areas under the receiver operating characteristic (ROC) curve to measure the performance of all models. A feature selection approach was applied to identify importance of predictors in each model. The heat map was used to investigate the correlation of features. Finally, we established a web calculator using the best-performing model.

RESULTS

In multivariate logistic regression analysis, factors including alcoholic liver disease (ALD), smoking, boundary, diameter, and white blood cell (WBC) were identified as independent predictors for LNM in patients with ICC. In internal validation, the average values of AUC of six models ranged from 0.820 to 0.908. The XGB model was identified as the best model, the average AUC was 0.908. Finally, we established a web calculator by XGB model, which was useful for clinicians to calculate the likelihood of LNM.

CONCLUSION

The proposed ML-based predicted models had a good performance to predict LNM of patients with ICC. XGB performed best. A web calculator based on the ML algorithm showed promise in assisting clinicians to predict LNM and developed individualized medical plans.

Nomogram based on preoperative clinical and MRI features to estimate the microvascular invasion status and the prognosis of solitary intrahepatic mass-forming cholangiocarcinoma

PURPOSE

To develop a nomogram based on preoperative clinical and magnetic resonance imaging (MRI) features for the microvascular invasion (MVI) status in solitary intrahepatic mass-forming cholangiocarcinoma (sIMCC) and to evaluate whether it could predict recurrence-free survival (RFS).

METHODS

We included 115 cases who experienced MRI examinations for sIMCC with R0 resection. The preoperative clinical and MRI features were extracted. Independent predictors related to MVI+ were evaluated by stepwise multivariate logistic regression, and a nomogram was constructed. A receiver operating characteristic (ROC) curve was used to assess the predictive ability. All patients were classified into high- and low-risk groups of MVI. Then, the correlations of the nomogram with RFS in patents with sIMCC were analyzed by Kaplan-Meier method.

RESULTS

The occurrence rate of MVI+ was 38.3% (44/115). The preoperative independent predictors of MVI+ were carbohydrate antigen 19-9 > 37 U/ml, tumor size > 5 cm, and an ill-defined tumor boundary. Integrating these predictors, the nomogram exerted a favorable diagnostic performance with areas under the ROC curve of 0.767 (95% confidence interval [CI] 0.654-0.881) in the development cohort, and 0.760 (95% CI 0.591-0.929) in the validation cohort. In the RFS analysis, significant differences were observed between the high- and low-risk MVI groups (6-month RFS rates: 64.5% vs. 78.8% and 46.7% vs. 82.4% in the development and validation cohorts, respectively) (P < 0.05).

CONCLUSIONS

A nomogram based on clinical and MRI features is a potential biomarker of MVI and may be a potent method to classify the risk of recurrence in patients with sIMCC.

Imaging features based on CT and MRI for predicting prognosis of patients with intrahepatic cholangiocarcinoma: a single-center study and meta-analysis

BACKGROUND

To evaluate the prognostic role of imaging features based on CT and MRI in intrahepatic cholangiocarcinoma (ICC).

METHODS

Two hundred and four patients from a single-center database who underwent radical ICC surgery from 2010 to 2019 were enrolled in the study. Cox proportional hazard model was used for survival analysis of imaging features. A meta-analysis was performed to determine imaging features that predict overall survival (OS) and event-free survival (EFS) in ICC.

RESULTS

In the CT group of the retrospective cohort, tumor multiplicity, infiltrative tumor margin, lymph node metastasis, enhancement pattern in hepatic arterial phase and tumor necrosis correlated with poorer EFS and OS; moreover, enhancing capsules, high carcinoembryonic antigen levels contributed to poor OS. In the MRI group, tumor multiplicity and enhancement pattern were prognostic factors for OS; tumor multiplicity and enhancement pattern resulted in poor EFS. A total of 13 articles containing 1822 patients with ICC were enrolled in the adjusted hazard ratios meta-analysis. The results showed that enhancement pattern and infiltrative tumor margin were predictors of OS and EFS, whereas bile duct invasion was a predictor of OS.

CONCLUSIONS

Arterial enhancement patterns and tumor margin status were associated with both OS and EFS of ICC patients following resection.

Progress in Radiotherapy for Cholangiocarcinoma

Cholangiocarcinoma (CCA) originates from the epithelium of the bile duct and is highly malignant with a poor prognosis. Radical resection is the only treatment option to completely cure primary CCA. Due to the insidious onset of CCA, most patients are already in an advanced stage at the time of the initial diagnosis and may lose the chance of radical surgery. Radiotherapy is an important method of local treatment, which plays a crucial role in preoperative neoadjuvant therapy, postoperative adjuvant therapy, and palliative treatment of locally advanced lesions. However, there is still no unified and clear recommendation on the timing, delineating the range of target area, and the radiotherapy dose for CCA. This article reviews recent clinical studies on CCA, including the timing of radiotherapy, delineation of the target area, and dose of radiotherapy. Further, we summarize large fraction radiotherapy (stereotactic body radiotherapy [SBRT]; proton therapy) in CCA and the development of immunotherapy and the use of targeted drugs combined with radiotherapy.

Carbon-ion radiotherapy for cholangiocarcinoma: a multi-institutional study by and the Japan carbon-ion radiation oncology study group (J-CROS)

To evaluate the safety and efficacy of carbon-ion radiotherapy (CIRT) for cholangiocarcinoma via a multicenter retrospective study. Clinical data were collected from patients with cholangiocarcinoma who had received CIRT at one of four treating institutions in Japan. Of 56 eligible patients, none received surgery for cholangiocarcinoma before or after CIRT. The primary endpoint was overall survival (OS). Based on the tumor site, the 56 cases were categorized as intrahepatic cholangiocarcinoma (IHC) (n=27) or perihilar cholangiocarcinoma (PHC) (n=29). In all patients, the median tumor size was 37 (range, 15‒110) mm, and the most commonly prescribed dose was 76 Gy (relative biological effectiveness) in 20 fractions. The median survival was 14.8 (range, 2.1-129.2) months, and the 1- and 2-year OS rates were 69.7% and 40.9%, respectively. The median survival times of the patients with IHC and those with PHC were 23.8 and 12.6 months, respectively. Both univariate and multivariate analyses revealed that cholangitis pre-CIRT and Child‒Pugh class B were significant prognostic factors for an unfavorable OS. Of four patients who died of liver failure, one with IHC was suspected to have radiation-induced liver disease because of newly developed ascites, and died at 4.3 months post-CIRT. Grade 3 CIRT-related bile duct stenosis was observed in one IHC case. No other CIRT-related severe adverse events, including gastrointestinal events, were observed. These results suggest that CIRT yields relatively favorable treatment outcomes, especially for patients with IHC, and acceptable toxicities were observed in patients with cholangiocarcinoma who did not receive surgery.

An atlas for clinical target volume definition, including elective nodal irradiation in definitive radiotherapy of biliary cancer

Radiotherapy (RT) is a treatment option for advanced biliary tract cancer (BTC), often combined with sequential and/or concurrent chemotherapy. The use of modern RT techniques requires accurate clinical target volume (CTV) definition and delineation. However, guidelines for CTV delineation in BTC are lacking. Therefore, the aim of this study was to propose a computer tomography (CT) atlas for CTV definition of BTC. We previously proposed guidelines to define the nodal CTV (CTV-N) in BTC. In this study, based on a literature analysis, we defined the margins to be added to the gross tumor volume (GTV; subclinical and microscopic disease) to define the primary tumor CTV (CTV-T). An abdominal contrast enhanced planning CT scan was performed on three different patients with unresectable intrahepatic cholangiocarcinoma (CC), extrahepatic CC and gallbladder cancer. The GTV and anatomical reference structures were outlined on CT images. Then, based on our guidelines, the CTV-T and CTV-N were delineated and merged to define the final CTV in the three patients. An atlas, showing the defined CTV, was generated from the reference CT images to illustrate the CTV for intra-hepatic CC, extra-hepatic CC and gallbladder cancer. This atlas can be used as an aid for CTV definition in patients with BTC treated with modern RT techniques.

External radiotherapy and brachytherapy in the management of extrahepatic and intrahepatic cholangiocarcinoma: available evidence

This review aims to summarize the currently available evidence for the role of external radiotherapy and brachytherapy in the management of cholangiocarcinoma. High locoregional disease recurrence rates after surgical resection alone for both the extrahepatic cholangiocarcinoma (EHCC) and intrahepatic cholangiocarcinoma (IHCC) provide a rationale for using adjuvant radiotherapy with chemotherapy. We performed a literature search related to radiotherapy in cholangiocarcinoma published between 2000 and 2016. The role of radiation is discussed in the adjuvant, neoadjuvant, definitive and the palliative setting. Evidence from Phase II trials have demonstrated efficacy of adjuvant chemoradiation in combination with chemotherapy in EHCC. Locally advanced cholangiocarcinoma may be treated with neoadjuvant chemoradiotherapy. In the case of downsizing, assessment for resection may be considered. Brachytherapy offers dose escalation after external radiotherapy. Selected unresectable cases of cholangiocarcinoma may be considered for stereotactic body radiation therapy with neoadjuvant and/or concurrent chemotherapy. Liver transplantation is a treatment option in selected patients with EHCC and IHCC after neoadjuvant chemoradiation. Stenting in combination with palliative external radiotherapy and/or brachytherapy provides improved stent patency and survival. Newer advanced radiation techniques provide a scope for achieving better disease control with reduced morbidity. Effective multimodality treatment incorporating radiotherapy is the way forward for improving survival in patients with cholangiocarcinoma.

Microinvasion of liver metastases from colorectal cancer: predictive factors and application for determining clinical target volume

OBJECTIVES

This study evaluates the microscopic characteristics of liver metastases from colorectal cancer (LMCRC) invasion and provides a reference for expansion from gross tumor volume (GTV) to clinical targeting volume (CTV).

METHODS

Data from 129 LMCRC patients treated by surgical resection at our hospital between January 2008 and September 2009 were collected for study. Tissue sections used for pathology and clinical data were reviewed. Patient information used for the study included gender, age, original tumor site, number of tumors, tumor size, levels of carcinoembryonic antigen (CEA) and carbohydrate antigen 199 (CA199), synchronous or metachronous liver metastases, and whether patients received chemotherapy. The distance of liver microinvasion from the tumor boundary was measured microscopically by two senior pathologists.

RESULTS

Of 129 patients evaluated, 81 (62.8 %) presented microinvasion distances from the tumor boundary ranging between 1.0 - 7.0 mm. A GTV-to-CTV expansion of 5, 6.7, or 7.0 mm was required to provide a 95, 99, or 100 % probability, respectively, of obtaining clear resection margins by microscopic observation. The extent of invasion was not related to gender, age, synchronous or metachronous liver metastases, tumor size, CA199 level, or chemotherapy. The extent of invasion was related to original tumor site, CEA level, and number of tumors. A scoring system was established based on the latter three positive predictors. Using this system, an invasion distance less than 3 mm was measured in 93.4 % of patients with a score of ≤1 point, but in only 85.7 % of patients with a score of ≤2 points.

CONCLUSIONS

The extent of tumor invasion in our LMCRC patient cohort correlated with original tumor site, CEA level, and number of tumors. These positive predictors may potentially be used as a scoring system for determining GTV-to-CTV expansion.

Imaging and image-guided radiation therapy in liver cancer

Imaging for radiation therapy treatment planning and delivery is a critical component of the radiation planning process for liver cancer. Because of the lack of inherent contrast between liver tumors and the surrounding liver, intravenous contrast is required for accurate target delineation on the planning computed tomography scan. The appropriate phase of contrast is tumor specific, with arterial phase imaging usually used to define hepatocellular carcinoma and venous phase imaging for vascular thrombosis related to hepatocellular carcinoma and most types of liver metastases. Breathing motion and changes in the liver position day to day may be substantial and need to be considered at the time of radiation planning and treatment. Many types of integrated imaging-radiation treatment systems and image-guidance strategies are available to produce volumetric and/or planar imaging at the time of treatment delivery to reduce the negative impact of geometric changes that may occur. Image-guided radiation therapy facilitates reduced PTV margins and dose escalation and improves the precision of radiation therapy, so the prescribed doses are more likely to represent those actually delivered.

Prediction of the lymph node status in patients with intrahepatic cholangiocarcinoma: analysis of 320 surgical cases

PURPOSE

This study was conducted to identify factors involved in lymph node metastasis (LNM) and evaluate their role in predicting LNM in clinically lymph node negative (clinical stage I-III) intrahepatic cholangiocarcinoma (ICC).

MATERIALS AND METHODS

We selected 320 patients who were diagnosed with ICC with no apparent clinical LNM (T(1-3)N(0)M(0)). Age, gender, tumor boundary, histological differentiation, tumor size, and carbohydrate antigen 19-9 value were the studied factors. Univariate and multivariate logistic analysis were conducted. Receiver operating characteristics curve analysis was used to test the predicting value of each factor and a test which combined the associated factors was used to predict LNM.

RESULTS

LNM was observed in 76 cases (76/320, 23.8%). Univariate and multivariate analysis showed that histological differentiation as well as tumor boundary and tumor size significantly correlated with LNM. The sensitivity and negative predictive value for LNM for the three factors when combined was 96.1 and 95% respectively. This means that 5% of the patients who did not have the risk factors mentioned above developed LNM.

CONCLUSION

This model used the combination of three factors (low-graded histological differentiation, distinct tumor boundary, small tumor size) and they proved to be useful in predicting LNM in ICC with clinically lymph node negative cases. In patients with these criteria, lymph node dissection or lymph node irradiation may be omitted and such cases may also be good candidates for stereotactic body radiotherapy (SBRT).