Measurable imaging-based changes in enhancement of intrahepatic cholangiocarcinoma after radiotherapy reflect physical mechanisms of response.

Background: Although escalated doses of radiation therapy (RT) for intrahepatic cholangiocarcinoma (iCCA) are associated with durable local control (LC) and prolonged survival, uncertainties persist regarding personalized RT based on biological factors. Compounding this knowledge gap, the assessment of RT response using traditional size-based criteria via computed tomography (CT) imaging correlates poorly with outcomes. We hypothesized that quantitative measures of enhancement would more accurately predict clinical outcomes than size-based assessment alone and developed a model to optimize RT. Methods: Pre-RT and post-RT CT scans of 154 patients with iCCA were analyzed retrospectively for measurements of tumor dimensions (for RECIST) and viable tumor volume using quantitative European Association for Study of Liver (qEASL) measurements. Binary classification and survival analyses were performed to evaluate the ability of qEASL to predict treatment outcomes, and mathematical modeling was performed to identify the mechanistic determinants of treatment outcomes and to predict optimal RT protocols. Results: Multivariable analysis accounting for traditional prognostic covariates revealed that percentage change in viable volume following RT was significantly associated with OS, outperforming stratification by RECIST. Binary classification identified ≥33% decrease in viable volume to optimally correspond to response to RT. The model-derived, patient-specific tumor enhancement growth rate emerged as the dominant mechanistic determinant of treatment outcome and yielded high accuracy of patient stratification (80.5%), strongly correlating with the qEASL-based classifier. Conclusion: Following RT for iCCA, changes in viable volume outperformed radiographic size-based assessment using RECIST for OS prediction. CT-derived tumor-specific mathematical parameters may help optimize RT for resistant tumors.

Phase I trial of single-photon emission computed tomography-guided liver-directed radiotherapy for patients with low functional liver volume.

BACKGROUND: Traditional constraints specify that 700 cc of liver should be spared a hepatotoxic dose when delivering liver-directed radiotherapy to reduce the risk of inducing liver failure. We investigated the role of single-photon emission computed tomography (SPECT) to identify and preferentially avoid functional liver during liver-directed radiation treatment planning in patients with preserved liver function but limited functional liver volume after receiving prior hepatotoxic chemotherapy or surgical resection. METHODS: This phase I trial with a 3 + 3 design evaluated the safety of liver-directed radiotherapy using escalating functional liver radiation dose constraints in patients with liver metastases. Dose-limiting toxicities were assessed 6-8 weeks and 6 months after completing radiotherapy. RESULTS: All 12 patients had colorectal liver metastases and received prior hepatotoxic chemotherapy; 8 patients underwent prior liver resection. Median computed tomography anatomical nontumor liver volume was 1584 cc (range = 764-2699 cc). Median SPECT functional liver volume was 1117 cc (range = 570-1928 cc). Median nontarget computed tomography and SPECT liver volumes below the volumetric dose constraint were 997 cc (range = 544-1576 cc) and 684 cc (range = 429-1244 cc), respectively. The prescription dose was 67.5-75 Gy in 15 fractions or 75-100 Gy in 25 fractions. No dose-limiting toxicities were observed during follow-up. One-year in-field control was 57%. One-year overall survival was 73%. CONCLUSION: Liver-directed radiotherapy can be safely delivered to high doses when incorporating functional SPECT into the radiation treatment planning process, which may enable sparing of lower volumes of liver than traditionally accepted in patients with preserved liver function. TRIAL REGISTRATION: NCT02626312.

Daily Vaginal Dilator Use During Radiation for Women With Squamous Cell Carcinoma of the Anus: Vaginal Wall Dosimetry and Patient-Reported Sexual Function.

PURPOSE: At our institution, we treat patients with a daily vaginal dilator (VD) during chemoradiation (CRT) for squamous cell carcinoma of the anus (SCCA). We evaluated compliance with daily VD use, radiation dose to the vaginal wall (VW), and anterior vaginal wall (AVW), and patient-reported long-term sexual function. METHODS AND MATERIALS: We included women with SCCA who received definitive, intensity-modulated radiation therapy-based CRT. Women who were alive without evidence of disease received a patient-reported outcome survey, which included the Female Sexual Function Index (FSFI). We identified factors associated with FSFI, such as radiation dose to the VW and AVW using linear regression models and used Youden index analysis to estimate a dose cutoff to predict sexual dysfunction. RESULTS: Three hundred thirty-nine consecutively treated women were included in the analysis; 285 (84.1%) were treated with a daily VD. Of 184 women alive without disease, 90 patients (49%) completed the FSFI, and 51 (56.7%) were sexually active with valid FSFI scores. All received therapy with a daily VD. Forty-one women (80%) had sexual dysfunction. Univariate analysis showed higher dose to 50% (D50%) of the AVW correlated with worse FSFI (ß -.262; P = .043), worse desire FSFI subscore (ß -.056; P = .003), and worse pain FSFI subscore (ß -.084; P = .009). Younger age correlated with worse pain FSFI subscale (ß .067; P = .026). Age (ß .070; P = .013) and AVW D50% (ß -.087; P = .009) were significant on multivariable analysis. AVW D50% >48 Gy predicted increased risk of sexual dysfunction. CONCLUSIONS: Daily VD use is safe and well tolerated during CRT for SCCA. Using a VD during treatment to displace the AVW may reduce the risk for sexual dysfunction. Limiting the AVW D50% <48 Gy may further reduce the risk but additional data are needed to validate this constraint.

Using Adversarial Images to Assess the Robustness of Deep Learning Models Trained on Diagnostic Images in Oncology.

PURPOSE: Deep learning (DL) models have rapidly become a popular and cost-effective tool for image classification within oncology. A major limitation of DL models is their vulnerability to adversarial images, manipulated input images designed to cause misclassifications by DL models. The purpose of the study is to investigate the robustness of DL models trained on diagnostic images using adversarial images and explore the utility of an iterative adversarial training approach to improve the robustness of DL models against adversarial images. METHODS: We examined the impact of adversarial images on the classification accuracies of DL models trained to classify cancerous lesions across three common oncologic imaging modalities. The computed tomography (CT) model was trained to classify malignant lung nodules. The mammogram model was trained to classify malignant breast lesions. The magnetic resonance imaging (MRI) model was trained to classify brain metastases. RESULTS: Oncologic images showed instability to small pixel-level changes. A pixel-level perturbation of 0.004 (for pixels normalized to the range between 0 and 1) resulted in most oncologic images to be misclassified (CT 25.6%, mammogram 23.9%, and MRI 6.4% accuracy). Adversarial training improved the stability and robustness of DL models trained on oncologic images compared with naive models ([CT 67.7% v 26.9%], mammogram [63.4% vs 27.7%], and MRI [87.2% vs 24.3%]). CONCLUSION: DL models naively trained on oncologic images exhibited dramatic instability to small pixel-level changes resulting in substantial decreases in accuracy. Adversarial training techniques improved the stability and robustness of DL models to such pixel-level changes. Before clinical implementation, adversarial training should be considered to proposed DL models to improve overall performance and safety.

Comparison of radiomic feature aggregation methods for patients with multiple tumors.

Radiomic feature analysis has been shown to be effective at analyzing diagnostic images to model cancer outcomes. It has not yet been established how to best combine radiomic features in cancer patients with multifocal tumors. As the number of patients with multifocal metastatic cancer continues to rise, there is a need for improving personalized patient-level prognosis to better inform treatment. We compared six mathematical methods of combining radiomic features of 3,596 tumors in 831 patients with multiple brain metastases and evaluated the performance of these aggregation methods using three survival models: a standard Cox proportional hazards model, a Cox proportional hazards model with LASSO regression, and a random survival forest. Across all three survival models, the weighted average of the largest three metastases had the highest concordance index (95% confidence interval) of 0.627 (0.595-0.661) for the Cox proportional hazards model, 0.628 (0.591-0.666) for the Cox proportional hazards model with LASSO regression, and 0.652 (0.565-0.727) for the random survival forest model. This finding was consistent when evaluating patients with different numbers of brain metastases and different tumor volumes. Radiomic features can be effectively combined to estimate patient-level outcomes in patients with multifocal brain metastases. Future studies are needed to confirm that the volume-weighted average of the largest three tumors is an effective method for combining radiomic features across other imaging modalities and tumor types.

Prevalence of Missing Data in the National Cancer Database and Association With Overall Survival.

Importance: Cancer registries are important real-world data sources consisting of data abstraction from the medical record; however, patients with unknown or missing data are underrepresented in studies that use such data sources. Objective: To assess the prevalence of missing data and its association with overall survival among patients with cancer. Design, Setting, and Participants: In this retrospective cohort study, all variables within the National Cancer Database were reviewed for missing or unknown values for patients with the 3 most common cancers in the US who received diagnoses from January 1, 2006, to December 31, 2015. The prevalence of patient records with missing data and the association with overall survival were assessed. Data analysis was performed from February to August 2020. Exposures: Any missing data field within a patient record among 63 variables of interest from more than 130 total variables in the National Cancer Database. Main Outcomes and Measures: Prevalence of missing data in the medical records of patients with cancer and associated 2-year overall survival. Results: A total of 1 198 749 patients with non-small cell lung cancer (mean [SD] age, 68.5 [10.9] years; 628 811 men [52.5%]), 2 120 775 patients with breast cancer (mean [SD] age, 61.0 [13.3] years; 2 101 758 women [99.1%]), and 1 158 635 patients with prostate cancer (mean [SD] age, 65.2 [9.0] years; 100% men) were included in the analysis. Among those with non-small cell lung cancer, 851 295 patients (71.0%) were missing data for variables of interest; 2-year overall survival was 33.2% for patients with missing data and 51.6% for patients with complete data (P < .001). Among those with breast cancer, 1 161 096 patients (54.7%) were missing data for variables of interest; 2-year overall survival was 93.2% for patients with missing data and 93.9% for patients with complete data (P < .001). Among those with prostate cancer, 460 167 patients (39.7%) were missing data for variables of interest; 2-year overall survival was 91.0% for patients with missing data and 95.6% for patients with complete data (P < .001). Conclusions and Relevance: This study found that within a large cancer registry-based real-world data source, there was a high prevalence of missing data that were unable to be ascertained from the medical record. The prevalence of missing data among patients with cancer was associated with heterogeneous differences in overall survival. Improvements in documentation and data quality are necessary to make optimal use of real-world data for clinical advancements.

Comparison of Radiomic Feature Aggregation Methods for Patients with Multiple Tumors.

Background: Radiomic feature analysis has been shown to be effective at modeling cancer outcomes. It has not yet been established how to best combine these radiomic features in patients with multifocal disease. As the number of patients with multifocal metastatic cancer continues to rise, there is a need for improving personalized patient-level prognostication to better inform treatment. Methods: We compared six mathematical methods of combining radiomic features of 3596 tumors in 831 patients with multiple brain metastases and evaluated the performance of these aggregation methods using three survival models: a standard Cox proportional hazards model, a Cox proportional hazards model with LASSO regression, and a random survival forest. Results: Across all three survival models, the weighted average of the largest three metastases had the highest concordance index (95% confidence interval) of 0.627 (0.595-0.661) for the Cox proportional hazards model, 0.628 (0.591-0.666) for the Cox proportional hazards model with LASSO regression, and 0.652 (0.565-0.727) for the random survival forest model. Conclusions: Radiomic features can be effectively combined to establish patient-level outcomes in patients with multifocal brain metastases. Future studies are needed to confirm that the volume-weighted average of the largest three tumors is an effective method for combining radiomic features across other imaging modalities and disease sites.

Applications of artificial intelligence in neuro-oncology.

PURPOSE OF REVIEW: To discuss recent applications of artificial intelligence within the field of neuro-oncology and highlight emerging challenges in integrating artificial intelligence within clinical practice. RECENT FINDINGS: In the field of image analysis, artificial intelligence has shown promise in aiding clinicians with incorporating an increasing amount of data in genomics, detection, diagnosis, classification, risk stratification, prognosis, and treatment response. Artificial intelligence has also been applied in epigenetics, pathology, and natural language processing. SUMMARY: Although nascent, applications of artificial intelligence within neuro-oncology show significant promise. Artificial intelligence algorithms will likely improve our understanding of brain tumors and help drive future innovations in neuro-oncology.

Association between prolonged metastatic free interval and recurrent metastatic breast cancer survival: findings from the SEER database.

PURPOSE: The prevalence of patients living with prolonged interval between initial breast cancer diagnosis and development of subsequent metastatic disease may be increasing with improved treatment. In order to counsel these patients as to their prognosis, we investigated the association between metastatic free interval (MFI) and subsequent survival from newly diagnosed metastatic breast cancer (MBC) in a population-level U.S. cohort. METHODS: The Surveillance, Epidemiology and End Results database was used to identify patients with both an initial stage 1-3 breast cancer diagnosis and subsequent MBC diagnosis recorded from 1988 to 2014. Patients were stratified by MFI (< 5 years, 5-10 years, > 10 years). The association between MFI and metastatic breast cancer-specific mortality (MBCSM) was analyzed with Fine-Gray competing risks regression. RESULTS: Five-year recurrent metastatic breast cancer-specific survival rate was 23%, 26%, and 35% for patients with MFI < 5, 5-10, and > 10 years, respectively. Patients with > 10 year MFI were less likely to die of breast cancer when compared with a referent group with < 5 years MFI (standard hazard ratio (SHR) 0.77 [95% CI 0.65-0.90] P < 0.001). There was no significant difference for patients with MFI of 5-10 years (SHR 0.92 [95% CI 0.81-1.04, P 0.191]) compared to < 5 years. Other prognostic factors like White race, lower tumor grade, and ER/PR-positive receptors were also associated with improved cancer-specific survival after diagnosis of MBC. CONCLUSION: Prolonged MFI greater than 10 years between initial breast cancer diagnosis and subsequent metastatic disease was found to be associated with improved recurrent MBC 5-year survival and decreased risk of breast cancer-specific mortality. This has potential implications for counseling patients as to prognosis, choice of treatment, as well as the stratification of patients considered for MBC clinical trials.