Predictive Value of Multiparametric Magnetic Resonance Imaging in Risk Group Stratification of Prostate Adenocarcinoma.

Purpose: The aim of this study was to further assess the clinical utility of multiparametric magnetic resonance imaging (MP-MRI) in prostate cancer (PC) staging following 2023 clinical guideline changes, both as an independent predictor of high-stage (>T3a) or high-risk PC and when combined with patient characteristics. Methods and Materials: The present study was a retrospective review of 171 patients from 2008 to 2018 who underwent MP-MRI before radical prostatectomy at a single institution. The accuracy of clinical staging was compared between conventional staging and MP-MRI-based clinical staging. Sensitivity, specificity, positive predictive value, and negative predictive value were compared, and receiver operating characteristic curves were generated. Linear regression analyses were used to calculate concordance (C-statistic). Results: Of the 171 patients, final pathology revealed 95 (55.6%) with T2 disease, 62 (36.3%) with T3a disease, and 14 (8.2%) with T3b disease. Compared with conventional staging, MP-MRI-based staging demonstrated significantly increased accuracy in identifying T3a disease, intermediate risk, and high/very-high-risk PC. When combined with clinical characteristics, MP-MRI-based staging improved the area under the curve from 0.753 to 0.808 (P = .0175), compared with conventional staging. Conclusions: MP-MRI improved the identification of T3a PC, intermediate-risk PC, and high- or very-high-risk PC. Further, when combined with clinical characteristics, MP-MRI-based staging significantly improved risk stratification, compared with conventional staging. These findings represent further evidence to support the integration of MP-MRI into prostate adenocarcinoma clinical staging guidelines.

NCCN Guidelines® Insights: Kidney Cancer, Version 2.2024.

The NCCN Guidelines for Kidney Cancer provide multidisciplinary recommendations for diagnostic workup, staging, and treatment of patients with renal cell carcinoma (RCC). These NCCN Guidelines Insights focus on the systemic therapy options for patients with advanced RCC and summarize the new clinical data evaluated by the NCCN panel for the recommended therapies in Version 2.2024 of the NCCN Guidelines for Kidney Cancer.

Multi-Institutional Development and Validation of a Radiomic Model to Predict Prostate Cancer Recurrence Following Radical Prostatectomy.

The use of multiparametric magnetic resonance imaging (mpMRI)-derived radiomics has the potential to offer noninvasive, imaging-based biomarkers for the identification of subvisual characteristics indicative of a poor oncologic outcome. The present study, therefore, seeks to develop, validate, and assess the performance of an MRI-derived radiomic model for the prediction of prostate cancer (PC) recurrence following radical prostatectomy (RP) with curative intent. mpMRI imaging was obtained from 251 patients who had undergone an RP for the treatment of localized prostate cancer across two institutions and three surgeons. All patients had a minimum of 2 years follow-up via prostate-specific antigen serum testing. Each prostate mpMRI was individually reviewed, and the prostate was delineated as a single slice (ROI) on axial T2 high-resolution image sets. A total of 924 radiomic features were extracted and tested for stability via intraclass correlation coefficient (ICC) following image normalization via histogram matching. Fourteen important and nonredundant features were found to be predictors of PC recurrence at a mean ± SD of 3.2 ± 2.2 years post-RP. Five-fold, ten-run cross-validation of the model containing these fourteen features yielded an area under the curve (AUC) of 0.89 ± 0.04 in the training set (n = 225). In comparison, the University of California San Fransisco Cancer of the Prostate Risk Assessment score (UCSF-CAPRA) and Memorial Sloan Kettering Cancer Center (MSKCC) Pre-Radical prostatectomy nomograms yielded AUC of 0.66 ± 0.05 and 0.67 ± 0.05, respectively (p < 0.01). When the radiomic model was applied to the test set (n = 26), AUC was 0.78; sensitivity, specificity, positive predictive value, and negative predictive value were 60%, 86%, 52%, and 89%, respectively. Accuracy in predicting PC recurrence was 81%.

3DGAUnet: 3D Generative Adversarial Networks with a 3D U-Net Based Generator to Achieve the Accurate and Effective Synthesis of Clinical Tumor Image Data for Pancreatic Cancer.

Pancreatic ductal adenocarcinoma (PDAC) presents a critical global health challenge, and early detection is crucial for improving the 5-year survival rate. Recent medical imaging and computational algorithm advances offer potential solutions for early diagnosis. Deep learning, particularly in the form of convolutional neural networks (CNNs), has demonstrated success in medical image analysis tasks, including classification and segmentation. However, the limited availability of clinical data for training purposes continues to represent a significant obstacle. Data augmentation, generative adversarial networks (GANs), and cross-validation are potential techniques to address this limitation and improve model performance, but effective solutions are still rare for 3D PDAC, where the contrast is especially poor, owing to the high heterogeneity in both tumor and background tissues. In this study, we developed a new GAN-based model, named 3DGAUnet, for generating realistic 3D CT images of PDAC tumors and pancreatic tissue, which can generate the inter-slice connection data that the existing 2D CT image synthesis models lack. The transition to 3D models allowed the preservation of contextual information from adjacent slices, improving efficiency and accuracy, especially for the poor-contrast challenging case of PDAC. PDAC's challenging characteristics, such as an iso-attenuating or hypodense appearance and lack of well-defined margins, make tumor shape and texture learning challenging. To overcome these challenges and improve the performance of 3D GAN models, our innovation was to develop a 3D U-Net architecture for the generator, to improve shape and texture learning for PDAC tumors and pancreatic tissue. Thorough examination and validation across many datasets were conducted on the developed 3D GAN model, to ascertain the efficacy and applicability of the model in clinical contexts. Our approach offers a promising path for tackling the urgent requirement for creative and synergistic methods to combat PDAC. The development of this GAN-based model has the potential to alleviate data scarcity issues, elevate the quality of synthesized data, and thereby facilitate the progression of deep learning models, to enhance the accuracy and early detection of PDAC tumors, which could profoundly impact patient outcomes. Furthermore, the model has the potential to be adapted to other types of solid tumors, hence making significant contributions to the field of medical imaging in terms of image processing models.

radioGWAS: link radiome to genome to discover driver genes with somatic mutations for heterogeneous tumor image phenotype in pancreatic cancer.

Addressing the significant level of variability exhibited by pancreatic cancer necessitates the adoption of a systems biology approach that integrates molecular data, biological properties of the tumors, and clinical features of the patients. In this study, a comprehensive multi-omics methodology was employed to examine a distinctive collection patient dataset containing rapid autopsy tumor and normal tissue samples as well as longitudinal imaging with a focus on pancreatic cancer. By performing a whole exome sequencing analysis on tumor and normal tissues to identify somatic gene variants and a radiomics feature analysis to tumor CT images, the genome-wide association approach established a connection between pancreatic cancer driver genes and relevant radiomics features, enabling a thorough and quantitative assessment of the heterogeneity of pancreatic tumors. The significant association between sets of genes and radiomics features revealed the involvement of genes in shaping tumor morphological heterogeneity. Some results of the association established a connection between the molecular level mechanism and their outcomes at the level of tumor structural heterogeneity. Because tumor structure and tumor structural heterogeneity are related to the patients' overall survival, patients who had pancreatic cancer driver gene mutations with an association to a certain radiomics feature have been observed to experience worse survival rates than cases without these somatic mutations. Furthermore, the outcome of the association analysis has revealed potential gene mutations and radiomics feature candidates that warrant further investigation in future research endeavors.

Comparison of sequential versus concurrent chemoradiation regimens in non-metastatic muscle-invasive bladder cancer.

PURPOSE: The treatment approach for non-metastatic bladder cancer is guided by an invasion of the muscular layer of the bladder wall. Radical cystectomy is the recommended treatment for muscle-invasive disease. However, it has considerable morbidity and mortality and is not suited for many patients. Trimodality therapy consisting of chemoradiation after transurethral resection of bladder tumor offers a definitive approach with bladder-sparing potential. However, there is a lack of research defining the optimal combination of chemotherapy and radiation in this setting. MATERIALS AND METHODS: We extracted patient data from the National Cancer Database to compare survival outcomes and demographic factors in 2,227 non-metastatic bladder cancer patients who were treated with chemotherapy sequential to or concurrently with radiation. Sequential treatment was defined as chemotherapy beginning >14 days before radiation, and concurrent was defined as beginning within 14 days of the first radiation. RESULTS: The sequential treatment group patients were younger (mean age, 74 vs. 78 years; p < 0.001) with more advanced disease. We found no difference in overall survival between patients who received chemotherapy sequential to radiation and those who received concurrent chemoradiation only (p = 0.533). CONCLUSION: Our data are concordant with a previous prospective study, and support that chemotherapy prior to radiation does not decrease survival outcomes relative to patients receiving only concurrent chemoradiation. Given that the sequential group had an overall higher stage but no difference in survival, downstaging chemotherapy prior to radiation may be helpful in these patients. Further studies including a larger, multi-institutional clinical trial are indicated to support clinical decision-making.

The Use of MRI-Derived Radiomic Models in Prostate Cancer Risk Stratification: A Critical Review of Contemporary Literature.

The development of precise medical imaging has facilitated the establishment of radiomics, a computer-based method of quantitatively analyzing subvisual imaging characteristics. The present review summarizes the current literature on the use of diagnostic magnetic resonance imaging (MRI)-derived radiomics in prostate cancer (PCa) risk stratification. A stepwise literature search of publications from 2017 to 2022 was performed. Of 218 articles on MRI-derived prostate radiomics, 33 (15.1%) generated models for PCa risk stratification. Prediction of Gleason score (GS), adverse pathology, postsurgical recurrence, and postradiation failure were the primary endpoints in 15 (45.5%), 11 (33.3%), 4 (12.1%), and 3 (9.1%) studies. In predicting GS and adverse pathology, radiomic models differentiated well, with receiver operator characteristic area under the curve (ROC-AUC) values of 0.50-0.92 and 0.60-0.92, respectively. For studies predicting post-treatment recurrence or failure, ROC-AUC for radiomic models ranged from 0.73 to 0.99 in postsurgical and radiation cohorts. Finally, of the 33 studies, 7 (21.2%) included external validation. Overall, most investigations showed good to excellent prediction of GS and adverse pathology with MRI-derived radiomic features. Direct prediction of treatment outcomes, however, is an ongoing investigation. As these studies mature and reach potential for clinical integration, concerted effort to validate these radiomic models must be undertaken.

Radiation therapy for pineal parenchymal tumor of intermediate differentiation: A case series and literature review.

Pineal parenchymal tumor of intermediate differentiation (PPTID) is a rare, primary tumor of the pineal gland. Due to its rarity, there is no consensus on optimal therapeutic strategies or standard characterization of the tumor's behavior. Here, we report 2 new cases of PPTID and an extensive review of the literature involving the use and extent of radiation therapy. Patient 1 is a 54-year-old male who presented with PPTID and drop metastases in the spinal cord, received cranial spinal irradiation (CSI), and experienced recurrence 3.5 years after treatment. Stereotactic body radiation therapy (SBRT) helped the patient into remission for 9 months. Patient 2 is a 32-year-old male with a local PPTID at presentation who went on to receive surgical resection followed by focused adjuvant radiation therapy to the pineal tumor bed. He then presented 6 years after treatment with extensive disseminated recurrence and died due to leptomeningeal disease (LMD) about 4 years after recurrence. The available literature on PPTID is limited and reported cases of LMD with ongoing follow-up in PPTID are scarce. Our report adds to the current known PPTID cases, contributing to the information available regarding prognosis and treatment response. Although an optimal therapeutic strategy for PPTID still cannot be determined, data from the literature suggest that utilizing radiation therapy in patients with low-risk disease and gross total resections as well as the use of upfront CSI have the potential to improve patient progression and survival outcomes.

Immunotherapy plus stereotactic body radiation therapy or whole-brain radiation therapy in brain metastases.

Aim: To investigate the association of stereotactic radiation therapy (SRT) or whole-brain radiation therapy (WBRT) plus immunotherapy with the overall survival (OS) of cancer patients with brain metastases (BMs) regardless of the primary cancer. Patients & methods: Patients diagnosed with BMs were identified from the National Cancer Database. Results: A total of 34,286 patients were included. SRT plus immunotherapy was associated with improved OS compared with SRT without immunotherapy (hazard ratio: 0.774; 95% CI: 0.687-0.872; p < 0.001), and WBRT plus immunotherapy was associated with improved OS compared with WBRT without immunotherapy (hazard ratio: 0.724; 95% CI; 0.673-0.779; p < 0.001). Conclusion: SRT plus immunotherapy was associated with improved OS compared with SRT. WBRT plus immunotherapy was associated with improved OS compared with WBRT in cancer patients who had BMs at the time of primary cancer diagnosis.

Aim: The purpose of this study was to examine if adding immunotherapy to the two types of brain radiation therapy (stereotactic radiation therapy [SRT] or whole-brain radiation therapy [WBRT]) will improve the overall survival of cancer patients with brain metastases (BMs). Patients & methods: Patients diagnosed with BMs were identified from the National Cancer Database. Results: This study included 34,286 patients. Patients who received SRT plus immunotherapy or WBRT plus immunotherapy were on average 23% and 28% less likely to die of any cause compared with patients who received SRT or WBRT without immunotherapy (hazard ratio: 0.774; 95% CI: 0.687­0.872; p < 0.001 and hazard ratio: 0.724; 95% CI: 0.673­0.779; p < 0.001, respectively). Conclusion: BMs patients who received SRT plus immunotherapy or WBRT plus immunotherapy had better overall survival compared with patients who received SRT or WBRT without immunotherapy.

The Association of Immunotherapy With the Overall Survival of Inoperable Stage III Non-small Cell Lung Cancer Patients Who Do Not Receive Chemoradiation.

Immunotherapy has been approved for stage III non-small cell lung cancer (NSCLC) as consolidation therapy after chemoradiation in patients whose disease does not progress after chemoradiation. However, many patients do not receive chemoradiation due to either the drugs' side effects or poor performance status. This study's objective is to investigate the association of immunotherapy combined with chemotherapy or Radiotherapy (RT) with the overall survival (OS) of stage III NSCLC patients who do not receive chemoradiation. Patients with stage III NSCLC who received either chemotherapy or RT with or without immunotherapy were identified from NCDB. The Cox proportional hazard regression analysis was implied to assess the effect of immunotherapy on survival after adjusting the model for age at diagnosis, race, sex, education, treatment facility type, insurance status, comorbidity score, histology year of diagnosis, and treatment types, such as chemotherapy and radiation therapy. The final analysis included 32,328 patients, among whom 3,205 (9.9%) received immunotherapy. In the multivariable analysis adjusted for all the factors previously mentioned, immunotherapy was associated with significantly improved OS (HR: 0.76, CI: 0.71-0.81) compared with no immunotherapy. Treatment with chemotherapy plus immunotherapy was significantly associated with improved OS (HR: 0.83, CI: 0.77-0.90) compared with chemotherapy without immunotherapy. Further, RT plus immunotherapy was associated with significantly improved OS (HR: 0.62, CI: 0.54-0.70) compared with RT alone. In this comprehensive analysis, the addition of immunotherapy to chemotherapy or radiotherapy was associated with improved OS compared with chemotherapy or radiation therapy without immunotherapy in stage III NSCLC patients.

Survival Outcomes After Radiotherapy for the Treatment of Synchronous Oligometastatic Prostate Cancer.

This cohort study assesses biochemical progression-free survival among patients receiving radiotherapy for the treatment of synchronous oligometastatic prostate cancer.

Using Quantitative Imaging for Personalized Medicine in Pancreatic Cancer: A Review of Radiomics and Deep Learning Applications.

As the most lethal major cancer, pancreatic cancer is a global healthcare challenge. Personalized medicine utilizing cutting-edge multi-omics data holds potential for major breakthroughs in tackling this critical problem. Radiomics and deep learning, two trendy quantitative imaging methods that take advantage of data science and modern medical imaging, have shown increasing promise in advancing the precision management of pancreatic cancer via diagnosing of precursor diseases, early detection, accurate diagnosis, and treatment personalization and optimization. Radiomics employs manually-crafted features, while deep learning applies computer-generated automatic features. These two methods aim to mine hidden information in medical images that is missed by conventional radiology and gain insights by systematically comparing the quantitative image information across different patients in order to characterize unique imaging phenotypes. Both methods have been studied and applied in various pancreatic cancer clinical applications. In this review, we begin with an introduction to the clinical problems and the technology. After providing technical overviews of the two methods, this review focuses on the current progress of clinical applications in precancerous lesion diagnosis, pancreatic cancer detection and diagnosis, prognosis prediction, treatment stratification, and radiogenomics. The limitations of current studies and methods are discussed, along with future directions. With better standardization and optimization of the workflow from image acquisition to analysis and with larger and especially prospective high-quality datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through big data-based high-precision personalization.

Kidney Cancer, Version 3.2022, NCCN Clinical Practice Guidelines in Oncology.

The NCCN Guidelines for Kidney Cancer focus on the screening, diagnosis, staging, treatment, and management of renal cell carcinoma (RCC). Patients with relapsed or stage IV RCC typically undergo surgery and/or receive systemic therapy. Tumor histology and risk stratification of patients is important in therapy selection. The NCCN Guidelines for Kidney Cancer stratify treatment recommendations by histology; recommendations for first-line treatment of ccRCC are also stratified by risk group. To further guide management of advanced RCC, the NCCN Kidney Cancer Panel has categorized all systemic kidney cancer therapy regimens as "Preferred," "Other Recommended Regimens," or "Useful in Certain Circumstances." This categorization provides guidance on treatment selection by considering the efficacy, safety, evidence, and other factors that play a role in treatment selection. These factors include pre-existing comorbidities, nature of the disease, and in some cases consideration of access to agents. This article summarizes surgical and systemic therapy recommendations for patients with relapsed or stage IV RCC.

An evaluation of adjuvant chemotherapy following neoadjuvant chemotherapy and resection for borderline resectable and locally advanced pancreatic cancer.

BACKGROUND: In borderline resectable and locally advanced (BRLA) pancreatic cancer patients, the role of adjuvant therapy (AT) after neoadjuvant therapy (NAT) and curative-intent resection is poorly understood. METHODS: Using the National Cancer Database (NCDB) between 2011 and 2017, we identified BRLA patients who received NAT and resection. Kaplan-Meier analysis and multivariable Cox proportional hazards (PH) regression were performed to examine the association between AT and overall survival (OS). RESULTS: Of 17,905 BRLA patients identified, 764 received NAT and resection, of which 203 received AT. Median age was 63 years, and 53.1% were female. Kaplan Meier analysis revealed no differences in median OS between AT vs non-AT groups (28.9 vs 30.1months, p = 0.498). In the multivariable Cox PH model, after adjusting for other factors, when margin was positive, AT was associated with an improved survival (HR 0.54, 95%CI 0.32-0.90, p = 0.031). CONCLUSION: AT was not associated with survival in BRLA patients who received NAT and resection except in patients with positive margins. Further research is necessary to better understand the role of AT following NAT in patients with BRLA.

Systemic Immune-Inflammatory Index Association with Survival in Patients Undergoing Trimodality Therapy for Lung Cancer.

PURPOSE: The systemic immune-inflammation index (SII) is correlated with patient survival in various solid malignancies including non-small-cell lung cancer (NSCLC). However, limited information is available on the prognostic implication of the SII in patients undergoing trimodality therapy for stage III NSCLC. METHODS: At our institution, 81 patients underwent curative intent trimodality therapy (neoadjuvant chemoradiotherapy followed by surgical resection) for stage III NSCLC from 2004 to 2019. The SII was calculated at the time of diagnosis as platelet count × neutrophil count/lymphocyte count. χ2 analysis was used to compare categorical variables. A Kaplan-Meier analysis was performed to estimate disease-free survival (DFS), overall survival (OS), and freedom from recurrence (FFR) rates, with Cox regression used to determine absolute hazards. RESULTS: Patients underwent neoadjuvant radiation therapy to a median dose of 4,500 cGy concurrent with a median of 3 cycles of chemotherapy (most commonly carboplatin and paclitaxel) followed by surgical resection (86.4% lobectomy and 13.6% pneumonectomy) with mediastinal lymph node dissection. At a median follow-up of 68.4 months, a low SII (<1,260) at diagnosis was independently associated with an improved OS (hazard ratio [HR]: 0.448, p = 0.004), DFS (HR: 0.366, p < 0.001), and FFR (HR: 0.325, p = 0.002). CONCLUSIONS: We identified that a low SII was associated with improved OS, DFS, and FFR in patients undergoing trimodality therapy for stage III NSCLC. The interplay of the immune system and lung cancer outcomes remains an active area of investigation for which further study is warranted.

Development of bullous pemphigoid following radiation therapy combined with nivolumab for renal cell carcinoma: A case report of abscopal toxicities.

RATIONALE: Concern for immune-related adverse events from immunotherapy and radiation therapy are well-documented; however, side effects are mostly mild to moderate. However, high-grade, potentially life-threatening adverse events are increasing. While case reports regarding immunotherapy-related bullous pemphigoid (BP) have been rising, only 1 has described BP following concomitant use of both nivolumab and radiation therapy (RT). For that patient, nivolumab was used for 10 weeks prior to RT and development of PB followed 7 weeks later. This case presents a patient who tolerated nivolumab well for 38 months prior to developing BP less than 2 weeks after completing RT. PATIENT CONCERNS: We present the case of DH, a 67-year-old gentleman on nivolumab for metastatic renal cell carcinoma to the lung since May of 2017. Following progressing lung nodules, the patient had his nivolumab paused and completed a course of short-beam radiation therapy. After restarting nivolumab post-radiation, the patient presented with itchy rash and blisters on his arm, legs, and trunk. DIAGNOSIS: DH consulted dermatology following development of rash and was diagnosed with bullous dermatosis, likely bullous pemphigoid. Bullous pemphigoid following concomitant nivolumab (OPDIVO), despite prior tolerance and no history of autoimmune disease, was confirmed by biopsy a month later. INTERVENTIONS: Initial treatment was betamethasone 0.05% cream mixed 1:1 with powder to form paste applied twice daily. Given progressive symptoms and confirmatory biopsy of BP, nivolumab was held and 100 mg doxycycline and 80 mg prednisone daily was prescribed for a week, reduced to 60 mg during the second week. OUTCOMES: A week following discontinuation of nivolumab and beginning of doxycycline and prednisone, the blistering and rash was almost entirely resolved. Four months later, nivolumab was restarted and the patient continued low-dose tapering of prednisone until December. Since completing prednisone, the patient has shown no recurrence of bullous pemphigoid and has not developed any other immune-related adverse events to nivolumab upon rechallenge. Follow-up through October 2021 demonstrates the patient's sites of disease, both in- and out-field, have remained responsive to treatment. LESSONS: Treating physicians should be aware of off-target effects of radiotherapy for oligoprogressive disease, which may include abscopal toxicities and the development of new immune-related adverse effects.

p53/FBXL20 axis negatively regulates the protein stability of PR55α, a regulatory subunit of PP2A Ser/Thr phosphatase.

We have previously reported an important role of PR55α, a regulatory subunit of PP2A Ser/Thr phosphatase, in the support of critical oncogenic pathways required for oncogenesis and the malignant phenotype of pancreatic cancer. The studies in this report reveal a novel mechanism by which the p53 tumor suppressor inhibits the protein-stability of PR55α via FBXL20, a p53-target gene that serves as a substrate recognition component of the SCF (Skp1_Cullin1_F-box) E3 ubiquitin ligase complex that promotes proteasomal degradation of its targeted proteins. Our studies show that inactivation of p53 by siRNA-knockdown, gene-deletion, HPV-E6-mediated degradation, or expression of the loss-of-function mutant p53R175H results in increased PR55α protein stability, which is accompanied by reduced protein expression of FBXL20 and decreased ubiquitination of PR55α. Subsequent studies demonstrate that knockdown of FBXL20 by siRNA mimics p53 deficiency, reducing PR55α ubiquitination and increasing PR55α protein stability. Functional tests indicate that ectopic p53R175H or PR55α expression results in an increase of c-Myc protein stability with concomitant dephosphorylation of c-Myc-T58, which is a PR55α substrate, whose phosphorylation otherwise promotes c-Myc degradation. A significant increase in anchorage-independent proliferation is also observed in normal human pancreatic cells expressing p53R175H or, to a greater extent, overexpressing PR55α. Consistent with the common loss of p53 function in pancreatic cancer, FBXL20 mRNA expression is significantly lower in pancreatic cancer tissues compared to pancreatic normal tissues and low FBXL20 levels correlate with poor patient survival. Collectively, these studies delineate a novel mechanism by which the p53/FBXL20 axis negatively regulates PR55α protein stability.

Effects of interobserver and interdisciplinary segmentation variabilities on CT-based radiomics for pancreatic cancer.

Radiomics is a method to mine large numbers of quantitative imaging features and develop predictive models. It has shown exciting promise for improved cancer decision support from early detection to personalized precision treatment, and therefore offers a desirable new direction for pancreatic cancer where the mortality remains high despite the current care and intense research. For radiomics, interobserver segmentation variability and its effect on radiomic feature stability is a crucial consideration. While investigations have been reported for high-contrast cancer sites such as lung cancer, no studies to date have investigated it on CT-based radiomics for pancreatic cancer. With three radiation oncology observers and three radiology observers independently contouring on the contrast CT of 21 pancreatic cancer patients, we conducted the first interobserver segmentation variability study on CT-based radiomics for pancreatic cancer. Moreover, our novel investigation assessed whether there exists an interdisciplinary difference between the two disciplines. For each patient, a consensus tumor volume was generated using the simultaneous truth and performance level expectation algorithm, using the dice similarity coefficient (DSC) to assess each observer's delineation against the consensus volume. Radiation oncology observers showed a higher average DSC of 0.81 ± 0.06 than the radiology observers at 0.69 ± 0.16 (p = 0.002). On a panel of 1277 radiomic features, the intraclass correlation coefficients (ICC) was calculated for all observers and those of each discipline. Large variations of ICCs were observed for different radiomic features, but ICCs were generally higher for the radiation oncology group than for the radiology group. Applying a threshold of ICC > 0.75 for considering a feature as stable, 448 features (35%) were found stable for the radiation oncology group and 214 features (16%) were stable from the radiology group. Among them, 205 features were found stable for both groups. Our results provide information for interobserver segmentation variability and its effect on CT-based radiomics for pancreatic cancer. An interesting interdisciplinary variability found in this study also introduces new considerations for the deployment of radiomics models.

The Potential Use of Radiomics with Pre-Radiation Therapy MR Imaging in Predicting Risk of Pseudoprogression in Glioblastoma Patients.

Glioblastoma (GBM) is the most common adult glioma. Differentiating post-treatment effects such as pseudoprogression from true progression is paramount for treatment. Radiomics has been shown to predict overall survival and MGMT (methylguanine-DNA methyltransferase) promoter status in those with GBM. A potential application of radiomics is predicting pseudoprogression on pre-radiotherapy (RT) scans for patients with GBM. A retrospective review was performed with radiomic data analyzed using pre-RT MRI scans. Pseudoprogression was defined as post-treatment findings on imaging that resolved with steroids or spontaneously on subsequent imaging. Of the 72 patients identified for the study, 35 were able to be assessed for pseudoprogression, and 8 (22.9%) had pseudoprogression. A total of 841 radiomic features were examined along with clinical features. Receiver operating characteristic (ROC) analyses were performed to determine the AUC (area under ROC curve) of models of clinical features, radiomic features, and combining clinical and radiomic features. Two radiomic features were identified to be the optimal model combination. The ROC analysis found that the predictive ability of this combination was higher than using clinical features alone (mean AUC: 0.82 vs. 0.62). Additionally, combining the radiomic features with clinical factors did not improve predictive ability. Our results indicate that radiomics is potentially capable of predicting future development of pseudoprogression in patients with GBM using pre-RT MRIs.