Predict Tumor Recurrence Research Articles

Pretreatment and Posttreatment Tumor Metabolic Activity Assessed by FDG-PET/CT as Predictors of Tumor Recurrence and Survival Outcomes in Early-Stage Non-Small Cell Lung Cancer Treated With Stereotactic Body Radiation Therapy

Stereotactic body radiation therapy (SBRT) is considered the standard of care for medically inoperable early-stage non-small cell lung cancer. There is mixed evidence on the prognostic significance of tumor metabolic activity assessed by positron emission tomography combined with computed tomography (PET/CT) using F-18 fluorodeoxyglucose (FDG). The objectives of this study were to evaluate the maximum standardized uptake value (SUVmax) pretreatment and at 3 and 6 months after SBRT for prediction of tumor control and survival outcomes. Consecutive patients from a single institution with T12N0M0 non-small cell lung cancer receiving primary treatment with SBRT with pretreatment FDG-PET/CT (n=163) and follow-up FDG-PET/CT at 3 or 6 months (n=71) were included. Receiver operator characteristic analysis was performed to dichotomize variables for Kaplan-Meier survival analysis. Multivariate analysis was performed with Cox proportional hazards regression. Median follow-up was 19 months. For the whole cohort, 1-year and 2-year local control, progression-free survival (PFS), and overall survival (OS) were 95.0% and 80.3%, 87.1% and 75.4%, and 67.0% and 49.6% respectively. The following pre-SBRT SUVmax cutoffs were significant: SUV > 4.0 for distant failure-free survival (adjusted hazard ratio [aHR], 3.33, P=.006), >12.3 for PFS (aHR, 2.80, P=.011), and >12.6 for OS (aHR, 3.00, P=.003). SUVmax decreases of at least 45% at 3 months (aHR, 0.15, P=.018), and 53% at 6 months (aHR, 0.12, P=.046) were associated with improved local failure-free survival. Pre-SBRT SUVmax cutoffs can predict distant failure, PFS, and OS. At both 3 and 6 months after SBRT, cutoffs for percentage change in SUVmax can potentially stratify risk of local recurrence.

Review of the use of radiomics to assess the risk of recurrence in early-stage non-small cell lung cancer.

Radiomics is an emerging field of advanced image analysis that has shown promise as a non-invasive, companion diagnostic in predicting clinical outcomes and response assessments in solid tumors. Radiomics aims to extract high-content information from medical images not visible to the naked eye, especially in early-stage non-small cell lung cancer (NSCLC) patients. Although these patients are being identified by early detection programs, it remains unclear which patients would benefit from adjuvant treatment versus active surveillance. Having a radiomic signature(s) that could predict early recurrence would be beneficial. In this review, an overview of the basic radiomic approaches used to evaluate solid tumors on radiologic scans, including NSCLC is provided followed by a review of relevant literature that supports the use of radiomics to help predict tumor recurrence in early-stage NSCLC patients. A review of the radiomic literature from 1985 to present focusing on the prediction of disease recurrence in early-stage NSCLC was conducted. PubMed database was searched using key terms for radiomics and NSCLC. A total of 41 articles were identified and 13 studies were considered suitable for inclusion based upon study population, patient number (n>50), use of well described radiomic methodologies, suitable model building features, and well-defined testing/training and validation where feasible. Examples of using radiomics in early-stage NSCLC patients will be presented, where disease free survival is a primary consideration. A summary of the findings demonstrates the importance of both the intratumor and peritumoral radiomic signals as a marker of outcomes. The value of radiomic information for predicting disease recurrence in early-stage NSCLC patients is accumulating. However, overcoming several challenges along with the lack of prospective trials, has inhibited it use as a clinical decision-making support tool in early-stage NSCLC.

Multimodal recurrence scoring system for prediction of clear cell renal cell carcinoma outcome: a discovery and validation study

Improved markers for predicting recurrence are needed to stratify patients with localised (stage I-III) renal cell carcinoma after surgery for selection of adjuvant therapy. We developed a novel assay integrating three modalities-clinical, genomic, and histopathological-to improve the predictive accuracy for localised renal cell carcinoma recurrence. In this retrospective analysis and validation study, we developed a histopathological whole-slide image (WSI)-based score using deep learning allied to digital scanning of conventional haematoxylin and eosin-stained tumour tissue sections, to predict tumour recurrence in a development dataset of 651 patients with distinctly good or poor disease outcome. The six single nucleotide polymorphism-based score, which was detected in paraffin-embedded tumour tissue samples, and the Leibovich score, which was established using clinicopathological risk factors, were combined with the WSI-based score to construct a multimodal recurrence score in the training dataset of 1125 patients. The multimodal recurrence score was validated in 1625 patients from the independent validation dataset and 418 patients from The Cancer Genome Atlas set. The primary outcome measured was the recurrence-free interval (RFI). The multimodal recurrence score had significantly higher predictive accuracy than the three single-modal scores and clinicopathological risk factors, and it precisely predicted the RFI of patients in the training and two validation datasets (areas under the curve at 5 years: 0·825-0·876 vs 0·608-0·793; p<0·05). The RFI of patients with low stage or grade is usually better than that of patients with high stage or grade; however, the RFI in the multimodal recurrence score-defined high-risk stage I and II group was shorter than in the low-risk stage III group (hazard ratio [HR] 4·57, 95% CI 2·49-8·40; p<0·0001), and the RFI of the high-risk grade 1 and 2 group was shorter than in the low-risk grade 3 and 4 group (HR 4·58, 3·19-6·59; p<0·0001). Our multimodal recurrence score is a practical and reliable predictor that can add value to the current staging system for predicting localised renal cell carcinoma recurrence after surgery, and this combined approach more precisely informs treatment decisions about adjuvant therapy. National Natural Science Foundation of China, and National Key Research and Development Program of China.

Long term follow-up analysis of plasma miR371 expression to detect early relapse in patients with clinical stage I testicular germ cell tumors on surveillance.

5006 Background: Clinical Stage I (CSI) is the most common presentation of germ cell testicular tumors (GCT) and patients are usually managed with active surveillance, in absence of reliable biomarkers of relapse. Circulating plasma miR371a-3p (miR371) has demonstrated high sensitivity and specificity in advanced non teratoma GCT. However, its operating characteristics and power to detect early relapse are still undefined. Methods: CSI GCT patients enrolled in the British Columbia provincial biobank with available plasma samples after radical orchiectomy were included in this study. Plasma miR371 was qualitatively assessed by RT-PCR. Sensitivity, specificity, negative and positive predictive values (NPV, PPV) and AUC in predicting tumor recurrence were evaluated in the post-orchiectomy blood samples and/or during the follow-up prior to or at the time of the clinically evident relapse. Relapse free survival (RFS) was correlated to post-orchiectomy miR371 status. Results: One-hundred-one patients were analyzed, 35 (34.6%) experienced a disease relapse with a median follow-up of 41 months. miR371 was positive in 22/35 of the relapsed patients. The specificity and PPV were 100% (95% CI: 94.5 - 100 for both), sensitivity 62.8% (95% CI: 44.9 - 78.5), NPV 83.5% (95%CI: 76.7 - 88.6) and AUC 0.81 (95% CI: 0.71 - 0.91). No false positive results were observed. The RFS of the patients with positive post-orchiectomy miR37 was significantly shorter (median: 3.5 months vs. not reached; p&lt;0.0001) compared to the patients with a negative post-orchiectomy miR371 (HR: 16.9; 95% CI: 2.1 - 135.7; p&lt;0.0001). miR371 sensitivity correlated with tumor burden, time between tumor relapse and miRNA testing and histology (nonseminoma &gt; seminoma). Conclusions: miR371 has high specificity and PPV in detecting GCT at an early stage and could be used to predict GCT relapse during surveillance and to guide treatment selection after orchiectomy. Further studies have been planned for validation of miR371 clinical utility.

Perfusion-Weighted Imaging: The Use of a Novel Perfusion Scoring Criteria to Improve the Assessment of Brain Tumor Recurrence versus Treatment Effects.

Imaging surveillance of contrast-enhancing lesions after the treatment of malignant brain tumors with radiation is plagued by an inability to reliably distinguish between tumor recurrence and treatment effects. Magnetic resonance perfusion-weighted imaging (PWI)-among other advanced brain tumor imaging modalities-is a useful adjunctive tool for distinguishing between these two entities but can be clinically unreliable, leading to the need for tissue sampling to confirm diagnosis. This may be partially because clinical PWI interpretation is non-standardized and no grading criteria are used for assessment, leading to interpretation discrepancies. This variance in the interpretation of PWI and its subsequent effect on the predictive value has not been studied. Our objective is to propose structured perfusion scoring criteria and determine their effect on the clinical value of PWI. Patients treated at a single institution between 2012 and 2022 who had prior irradiated malignant brain tumors and subsequent progression of contrast-enhancing lesions determined by PWI were retrospectively studied from CTORE (CNS Tumor Outcomes Registry at Emory). PWI was given two separate qualitative scores (high, intermediate, or low perfusion). The first (control) was assigned by a neuroradiologist in the radiology report in the course of interpretation with no additional instruction. The second (experimental) was assigned by a neuroradiologist with additional experience in brain tumor interpretation using a novel perfusion scoring rubric. The perfusion assessments were divided into three categories, each directly corresponding to the pathology-reported classification of residual tumor content. The interpretation accuracy in predicting the true tumor percentage, our primary outcome, was assessed through Chi-squared analysis, and inter-rater reliability was assessed using Cohen's Kappa. Our 55-patient cohort had a mean age of 53.5 ± 12.2 years. The percentage agreement between the two scores was 57.4% (κ: 0.271). Upon conducting the Chi-squared analysis, we found an association with the experimental group reads (p-value: 0.014) but no association with the control group reads (p-value: 0.734) in predicting tumor recurrence versus treatment effects. With our study, we showed that having an objective perfusion scoring rubric aids in improved PWI interpretation. Although PWI is a powerful tool for CNS lesion diagnosis, methodological radiology evaluation greatly improves the accurate assessment and characterization of tumor recurrence versus treatment effects by all neuroradiologists. Further work should focus on standardizing and validating scoring rubrics for PWI evaluation in tumor patients to improve diagnostic accuracy.

Machine Learning Classifier for Preoperative Prediction of Early Recurrence After Bronchial Arterial Chemoembolization Treatment in Lung Cancer Patients

Bronchial arterial chemoembolization (BACE) was deemed as an effective and safe approach for advanced standard treatment-ineligible/rejected lung cancer patients. However, the therapeutic outcome of BACE varies greatly and there is no reliable prognostic tool in clinical practice. This study aimed to investigate the effectiveness of radiomics features in predicting tumor recurrence after BACE treatment in lung cancer patients. A total of 116 patients with pathologically confirmed lung cancer who received BACE treatment were retrospectively recruited. All patients underwent contrast-enhanced CT within 2 weeks before BACE treatment and were followed up for more than 6months. We conducted a machine learning-based characterization of each lesion on the preoperative contrast-enhanced CT images. In the training cohort, recurrence-related radiomics features were screened by least absolute shrinkage and selection operator (LASSO) regression. Three predictive radiomics signatures were built with linear discriminant analysis (LDA), support vector machine (SVM) and logistic regression (LR) algorithms, respectively. Univariate and multivariate LR analyses were performed to select the independent clinical predictors for recurrence. The radiomics signature with best predictive performance was integrated with the clinical predictors to form a combined model, which was visualized as a nomogram. The performance of the combined model was assessed by receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA). Nine recurrence-related radiomics features were screened out, and three radiomics signatures (RadscoreLDA, RadscoreSVM and RadscoreLR) were built based on these features. Patients were classified into the low-risk and high-risk groups based on the optimal threshold of three signatures. Progression-free survival (PFS) analysis showed that patients of low-risk group achieved longer PFS than patients of high-risk group (P<0.05). The combined model including RadscoreLDA and independent clinical predictors (tumor size, carcinoembryonic antigen and pro-gastrin releasing peptide) achieved the best predictive performance for recurrence after BACE treatment. It yields AUCs of 0.865 and 0.867 in the training and validation cohorts, with accuracy (ACC) of 0.804 and 0.750, respectively. Calibration curves indicated that the probability of recurrence predicted by the model fits well with the actual recurrence probability. DCA showed that the radiomics nomogram was clinically useful. The radiomics and clinical predictors-based nomogram can predict tumor recurrence after BACE treatment effectively, which allowing oncologists to identify potential recurrence and enable better patient management and clinical decision-making.

Development of a Machine Learning Model to Predict Recurrence of Oral Tongue Squamous Cell Carcinoma.

Despite diagnostic advancements, the development of reliable prognostic systems for assessing the risk of cancer recurrence still remains a challenge. In this study, we developed a novel framework to generate highly representative machine-learning prediction models for oral tongue squamous cell carcinoma (OTSCC) cancer recurrence. We identified cases of 5- and 10-year OTSCC recurrence from the SEER database. Four classification models were trained using the H2O ai platform, whose performances were assessed according to their accuracy, recall, precision, and the area under the curve (AUC) of their receiver operating characteristic (ROC) curves. By evaluating Shapley additive explanation contribution plots, feature importance was studied. Of the 130,979 patients studied, 36,042 (27.5%) were female, and the mean (SD) age was 58.2 (13.7) years. The Gradient Boosting Machine model performed the best, achieving 81.8% accuracy and 97.7% precision for 5-year prediction. Moreover, 10-year predictions demonstrated 80.0% accuracy and 94.0% precision. The number of prior tumors, patient age, the site of cancer recurrence, and tumor histology were the most significant predictors. The implementation of our novel SEER framework enabled the successful identification of patients with OTSCC recurrence, with which highly accurate and sensitive prediction models were generated. Thus, we demonstrate our framework's potential for application in various cancers to build generalizable screening tools to predict tumor recurrence.

Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning

Tumor recurrence affects up to 70% of early-stage hepatocellular carcinoma (HCC) patients, depending on treatment option. Deep learning algorithms allow in-depth exploration of imaging data to discover imaging features that may be predictive of recurrence. This study explored the use of convolutional neural networks (CNN) to predict HCC recurrence in patients with early-stage HCC from pre-treatment magnetic resonance (MR) images. This retrospective study included 120 patients with early-stage HCC. Pre-treatment MR images were fed into a machine learning pipeline (VGG16 and XGBoost) to predict recurrence within six different time frames (range 1–6 years). Model performance was evaluated with the area under the receiver operating characteristic curves (AUC–ROC). After prediction, the model’s clinical relevance was evaluated using Kaplan–Meier analysis with recurrence-free survival (RFS) as the endpoint. Of 120 patients, 44 had disease recurrence after therapy. Six different models performed with AUC values between 0.71 to 0.85. In Kaplan–Meier analysis, five of six models obtained statistical significance when predicting RFS (log-rank p < 0.05). Our proof-of-concept study indicates that deep learning algorithms can be utilized to predict early-stage HCC recurrence. Successful identification of high-risk recurrence candidates may help optimize follow-up imaging and improve long-term outcomes post-treatment.

N2 Lymph Node Metastasis Is a Useful Predictor of Recurrence in Patients With Stage III Rectal Cancer Undergoing Adjuvant Chemotherapy Using Tegafur-uracil/leucovorin.

Fluoropyrimidine therapy or oxaliplatin combination therapy is recommended for patients with stage III colorectal cancer as adjuvant chemotherapy (AC). However, the criterion for selecting these regimens is still unclear in patients with stage III rectal cancer (RC). In order to select an appropriate regimen of AC for such patients, it is needed to identify characteristics associated with tumor recurrence. The records of 45 patients with stage III RC undergoing AC using tegafur-uracil/leucovorin (UFT/LV) were retrospectively reviewed. The cut-off value of characteristics was determined using a receiver operating characteristic curve for recurrence. Univariate analyses using Cox-Hazard model for predicting recurrence were performed with clinical characteristics. Survival analysis was performed using Kaplan-Meier method and log-rank test. Thirty patients (66.7%) completed AC using UFT/LV. Fifteen patients (33.3%) did not complete AC because of adverse events, tumor recurrence and others. Sixteen patients (35.6%) had recurrence. Univariate analyses revealed that lymph node metastasis (N2/N1) (p=0.002) was associated with tumor recurrence. Survival analysis showed that lymph node metastasis (N2/N1) could stratify recurrence-free survival (p<0.001). N2 lymph node metastasis can predict tumor recurrence in patients with stage III RC undergoing AC using UFT/LV.

Pre- to postoperative alpha-fetoprotein ratio-based nomogram to predict tumor recurrence in patients with hepatocellular carcinoma.

This study aimed to investigate the role of the alpha fetoprotein (AFP) ratio before and after curative resection in the prognosis of patients with hepatocellular carcinoma (HCC) and to develop a novel pre- to postoperative AFP ratio nomogram to predict recurrence free survival (RFS) for HCC patients after curative resection. A total of 485 pathologically confirmed HCC patients who underwent radical hepatectomy from January 2010 to December 2018 were retrospectively analyzed. The independent prognostic factors of hepatocellular carcinoma were identified by multivariate COX proportional model analysis, and the nomogram model was constructed. The receiver operating characteristic and the C-index were used to evaluate the accuracy and efficacy of the model prediction, the correction curve was used to assess the calibration of the prediction model, and decision curve analysis was used to evaluate the clinical application value of the nomogram model. A total of 485 HCC patients were divided into the training cohort (n = 340) and the validation cohort (n = 145) by random sampling at a ratio of 7:3. Using X-tile software, it was found that the optimal cut-off value of the AFP ratio in the training cohort was 0.8. In both cohorts, the relapse-free survival of patients with an AFP ratio <0.8 (high-risk group) was significantly shorter than in those with an AFP ratio ≥0.8 (low-risk group) (P < 0.05). An AFP ratio <0.8 was an independent risk factor for recurrence of HCC after curative resection. Based on the AFP ratio, BCLC stage and cirrhosis diagnosis, a satisfactory nomogram was developed. The AUC of our nomogram for predicting 1-, 3-, and 5-year RFS was 0.719, 0.690, and 0.708 in the training cohort and 0.721, 0.682, and 0.681 in the validation cohort, respectively. Furthermore, our model demonstrated excellent stratification as well as clinical applicability. The AFP ratio was a reliable biomarker for tumor recurrence. This easy-to-use AFP ratio-based nomogram precisely predicted tumor recurrence in HCC patients after curative resection.

Development of a deep pathomics score for predicting hepatocellular carcinoma recurrence after liver transplantation

Background and purposeTumor recurrence after liver transplantation (LT) impedes the curative chance for hepatocellular carcinoma (HCC) patients. This study aimed to develop a deep pathomics score (DPS) for predicting tumor recurrence after liver transplantation using deep learning.Patients and methodsTwo datasets of 380 HCC patients who underwent LT were enrolled. Residual convolutional neural networks were used to identify six histological structures of HCC. The individual risk score of each structure and DPS were derived by a modified DeepSurv network. Cox regression analysis and Concordance index were used to evaluate the prognostic significance. The cellular exploration of prognostic immune biomarkers was performed by quantitative and spatial proximity analysis according to three panels of 7-color immunofluorescence.ResultsThe overall classification accuracy of HCC tissue was 97%. At the structural level, immune cells were the most significant tissue category for predicting post-LT recurrence (HR 1.907, 95% CI 1.490–2.440). The C-indices of DPS achieved 0.827 and 0.794 in the training and validation cohorts, respectively. Multivariate analysis for recurrence-free survival (RFS) showed that DPS (HR 4.795, 95% CI 3.017–7.619) was an independent risk factor. Patients in the high-risk subgroup had a shorter RFS, larger tumor diameter and a lower proportion of clear tumor borders. At the cellular level, a higher infiltration of intratumoral NK cells was negatively correlated with recurrence risk.ConclusionsThis study established an effective DPS. Immune cells were the most significant histological structure related to HCC recurrence. DPS performed well in post-LT recurrence prediction and the identification of clinicopathological features.

Abstract 1037: Circulating tumor DNA-based molecular residual disease predicts relapse in patients with resectable gastric cancer

Abstract Background: Circulating tumor DNA (ctDNA)-based molecular residual disease (MRD) detection has been shown to predict postoperative relapse in several cancers. Currently, fixed and personalized panel-based tumor-informed (TI) ctDNA testing strategies are available for MRD assessment. Here, we aim to evaluate the prognostic value of MRD in resectable gastric cancer (GC) and assess MRD with fixed and personalized panels for comparison. Methods: We prospectively enrolled patients with stage I-III GC who underwent R0 resection at Ruijin Hospital. Blood samples were collected on the day of surgery preoperatively and during the second-fourth week postoperatively. Tissue samples were collected shortly thereafter at the time of curative-intent resection. Both the Patient-specific pROgnostic and Potential tHErapeutic marker Tracking (brPROPHET, a personalized panel-based TI assay, Burning Rock Biotech) and a 168-gene panel-based TI assay (Burning Rock Biotech) were used to quantify ctDNA. Results: A total of 55 patients (19 females and 36 males) with a median age of 65 years (range: 35-87) were enrolled. Precise 5 and 41 patients were treated with neoadjuvant therapy and adjuvant therapy, respectively. The median duration of follow-up was 784 days (range: 582-853). All patients underwent the fixed panel-based TI assay. Of which, 19 patients were collected with postoperative blood samples. The MRD status of postoperative blood by the fixed panel showed a significant association with recurrence-free survival (RFS, MRD-positive [MRD+] vs. MRD-negative [MRD-]: 484 days vs. not reached [NR], hazard ratio [HR] = 8.0, p = 0.02). Of the 55 enrolled patients, 19 patients underwent both personalized and fixed panel-based TI assays. For the personalized panel, preoperative ctDNA was detected in 94.7% (18/19) of the patients with 100% (4/4), 66.7% (2/3), and 91.7% (11/12) in stage I, II, and III, respectively. The numbers were 36.8% (7/19), 0% (0/4), 0% (0/3), and 58.3% (7/12) with the fixed panel, respectively. Among the 19 patients, three of the 13 patients who had postoperative blood samples developed tumor recurrence during the follow-up visit. The sensitivity of the personalized panel for predicting tumor recurrence achieved 100% (3/3) with 90% (9/10) specificity. The sensitivity of the fixed panel was 33.3% (1/3) with 100% (10/10) specificity. In addition, patients with MRD+ by the personalized panel had a significantly shorter RFS than those with MRD- (566 days vs. NR, HR &amp;gt; 100, p = 0.003). Conclusion: Our study indicates that MRD+ by either the personalized or fixed panel was associated with an unfavorable survival outcome. ctDNA-based MRD detection by the personalized panel-based TI assay might be a powerful prognostic biomarker to identify GC patients who underwent radical resection at a higher risk of relapse or with an unfavorable survival outcome. Citation Format: Pei Xue, Yanfei Shao, Xueliang Zhou, Haiyan Li, Yang Wang, Chenyang Wang, Hao Zhang, Bing Li, Shuo Shi, Haiwei Du, Jing Sun. Circulating tumor DNA-based molecular residual disease predicts relapse in patients with resectable gastric cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 1037.

PD13-04 DEVELOPMENT OF A NOVEL GENE EXPRESSION SCORING SYSTEM FOR RECURRENCE IN NON-MUSCLE-INVASIVE BLADDER CANCER AFTER TRANSURETHRAL RESECTION OF BLADDER TUMOR

You have accessJournal of UrologyCME1 Apr 2023PD13-04 DEVELOPMENT OF A NOVEL GENE EXPRESSION SCORING SYSTEM FOR RECURRENCE IN NON-MUSCLE-INVASIVE BLADDER CANCER AFTER TRANSURETHRAL RESECTION OF BLADDER TUMOR Emina Kayama, Motohide Uemura, Yusuke Kirihana, Akifumi Onagi, Seiji Hoshi, Tomoyuki Koguchi, Tomohiko Yanagida, Fusao Murakami, and Yoshiyuki Kojima Emina KayamaEmina Kayama More articles by this author , Motohide UemuraMotohide Uemura More articles by this author , Yusuke KirihanaYusuke Kirihana More articles by this author , Akifumi OnagiAkifumi Onagi More articles by this author , Seiji HoshiSeiji Hoshi More articles by this author , Tomoyuki KoguchiTomoyuki Koguchi More articles by this author , Tomohiko YanagidaTomohiko Yanagida More articles by this author , Fusao MurakamiFusao Murakami More articles by this author , and Yoshiyuki KojimaYoshiyuki Kojima More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003260.04AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Non-muscle-invasive bladder cancer (NMIBC) frequently recurs after transurethral resection of bladder tumor (TURBT). However, clinical prognostic factors do not always accurately predict tumor recurrence. Therefore, we developed a new gene expression scoring system that is practical for distinguishing between high- and low-risk NMIBC that recur after TURBT. METHODS: We included 89 patients (median age 75) diagnosed with NMIBC after initial TURBT without prior or concurrent upper tract urothelial carcinoma at our institution between 2008 and 2019. This study obtained the approval of the institutional ethics board and the patient's consent. Variations in the expression signature of 14,400 genes within each patient were measured by our microarray analysis which has no mRNA amplification bias, not requiring validation by quantitative reverse transcriptase PCR. A hierarchical cluster analysis was performed to identify a set of genes that discriminates between high- and low-risk NMIBC. RESULTS: Eleven genes were extracted that predict tumor recurrence after TURBT. The cumulative equivalent of the 11 genes (microarray score) was obtained from each sample, and the optimal cutoff score was calculated to be 1.29 (area under the curve 0.83). A Kaplan-Meier curve showed the 5-year recurrence-free survival (RFS) rate was 38.2% in the “high microarray score group” (microarray score ≥1.29, n=39), which was significantly lower than in the “low microarray score group” (82.6%, p=0.002, Figure 1). The 5-year RFS rate in patients with single, Ta low grade tumor <3 cm in diameter without CIS (n=15) was 90.0%, which was higher than in the rest (55.2%); however, no significant difference was observed (p=0.063). Multivariate Cox regression analysis showed that a microarray score ≥1.29 was an independent factor for disease recurrence (hazard ratio 3.89, p=0.005), but clinical factors were not. CONCLUSIONS: Our novel gene expression scoring system proved to be more useful in predicting recurrence in patients with NMIBC after TURBT than clinical prognostic factors. This scoring system may enable individualized strategic management of high-risk NMIBC patients. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e406 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Emina Kayama More articles by this author Motohide Uemura More articles by this author Yusuke Kirihana More articles by this author Akifumi Onagi More articles by this author Seiji Hoshi More articles by this author Tomoyuki Koguchi More articles by this author Tomohiko Yanagida More articles by this author Fusao Murakami More articles by this author Yoshiyuki Kojima More articles by this author Expand All Advertisement PDF downloadLoading ...

The predictive value of the modified AFP model for liver transplantation outcomes in multinodular hepatocellular carcinoma patients

BackgroundThere is a lack of studies focusing on the benefit of liver transplantation (LT) in hepatocellular carcinoma (HCC) patients with > 3 tumors. This study aims to establish a model to effectively predict overall survival in Chinese HCC patients with multiple tumors (> 3 tumors) who undergo LT.MethodsThis retrospective study included 434 HCC liver transplant recipients from the China Liver Transplant Registry. All HCC patients had more than 3 tumor nodules. Three selection criteria systems (i.e., AFP, Metroticket 2.0, and Up-to-7) were compared regarding the prediction of HCC recurrence. The modified AFP model was established by univariate and multivariate competing risk analyses.ResultsThe AFP score 2 and the AFP score ≥ 3 groups had 5-year recurrence rates of 19.6% and 40.5% in our cohort. The prediction of HCC recurrence based on the AFP model was associated with a c-statistic of 0.606, which was superior to the Up-to-7 and Metroticket 2.0 models. AFP level > 1000 ng/mL, largest tumor size ≥ 8 cm, vascular invasion, and MELD score ≥ 15 were associated with overall survival. The 5-year survival rate in the modified AFP score 0 group was 71.7%.ConclusionsThe AFP model is superior in predicting tumor recurrence in HCC patients with > 3 tumors prior to LT. With the modified AFP model, patients likely to derive sufficient benefit from LT can be identified.

Weakly supervised deep learning to predict recurrence in low-grade endometrial cancer from multiplexed immunofluorescence images

Predicting recurrence in low-grade, early-stage endometrial cancer (EC) is both challenging and clinically relevant. We present a weakly-supervised deep learning framework, NaroNet, that can learn, without manual expert annotation, the complex tumor-immune interrelations at three levels: local phenotypes, cellular neighborhoods, and tissue areas. It uses multiplexed immunofluorescence for the simultaneous visualization and quantification of CD68 + macrophages, CD8 + T cells, FOXP3 + regulatory T cells, PD-L1/PD-1 protein expression, and tumor cells. We used 489 tumor cores from 250 patients to train a multilevel deep-learning model to predict tumor recurrence. Using a tenfold cross-validation strategy, our model achieved an area under the curve of 0.90 with a 95% confidence interval of 0.83–0.95. Our model predictions resulted in concordance for 96,8% of cases (κ = 0.88). This method could accurately assess the risk of recurrence in EC, outperforming current prognostic factors, including molecular subtyping.

The value of adding DWI and FLAIR signal changes in the resection cavity on the diagnostic performance of BT-RADS category 3 for tumor progression prediction in post-treated glioma patients: a prospective pilot study

BackgroundBT-RADS is a structured reporting system of post-treatment glioma. BT-RADS category 3 carries a probability of recurrent malignancy versus treatment-related changes. The aim of this study is to evaluate the additive value of DWI and resection cavity FLAIR signal changes to BT-RADS category 3 in the prediction of tumor progression. We prospectively evaluated follow-up contrast-enhanced MR imaging where 27 post-treated glioma patients were assigned BT-RADS category 3. In all images, FLAIR signal, enhancement component, mass effect, and ADCmean were assessed. We used imaging follow-up from the second stage of the study as the gold standard for comparing the diagnostic performance of BT-RADS category 3 for predicting tumor recurrence before and after the addition of DWI and resection cavity FLAIR signal changes. ROC curves analyses were assessed and compared using the Delong test.Results48.1% of patients had tumor recurrence and 51.9% of patients had treatment-related changes. There was significant difference between ADCmean in recurrent and non-recurrent groups measuring 0.9 and 1.15 × 10−3mm2/s, respectively (p value < 0.001). BT-RADS, BT-RADS added DWI, and BT-RADS added DWI and resection cavity FLAIR signal had a specificity of 64.3, 71.4, and 71.4%, sensitivity of 76.9, 84.6, and 92.3%, and accuracy of 70.5, 77.8, and 81.5%, with improved AUC from 0.706 (95% CI of 0.50–0.86) to 0.78 (95% CI of 0.58–0.92) to 0.819 (95% CI of 0.64–0.94), respectively.ConclusionsAdding DWI and resection cavity FLAIR signal alteration improves the diagnostic performance of BT-RADS category 3.

Longitudinal evaluation of plasma miR371 to detect minimal residual disease and early relapse of germ cell tumors.

407 Background: Active surveillance is routinely recommended to manage patients (pts) with clinical stage I (CSI) germ cell testicular tumors (GCT), the most common presentation of newly diagnosed GCT. Circulating plasma miR371a-3p (miR371) has shown high sensitivity and specificity in pts with metastatic non teratoma GCT or in pts with clinically detectable testicular GCT prior to orchiectomy. However, limited data are available about this biomarker accuracy to detect minimal residual disease post-orchiectomy in pts on active surveillance for early stage disease. Methods: CSI GCT pts with available plasma samples after radical orchiectomy enrolled in the British Columbia provincial biobank research program were selected for this study. RT-PCR was used for qualitative miR371 analysis. Sensitivity, specificity, negative and positive predictive values (NPV, PPV) and AUC in predicting tumor recurrence were evaluated for miR371 and compared to the same operating characteristics of current gold standard diagnostic tests. Relapse free survival (RFS) was correlated to post-orchiectomy miR371 (positive or negative) status. Fisher’s exact test was used to evaluate the sensitivity and specificity, unpaired t-test for comparison of miR371 expression. RFS was calculated using the Kaplan-Meier method, and differences between groups were estimated using the log rank test, 2-sided and with 5% significance threshold. Results: With a median follow-up of 41 months, 101 pts with CSI GTCwere included, of whom 35 (34.6%) experienced a disease relapse during the follow-up. miR371 was positive in 22/35 (62.8%) of the relapsed pts. miR371 positivity preceded clinical evident disease by a median of 3 months (range: 1-12 months).The specificity and PPV were 100% (95% CI: 94.5 - 100 for both), sensitivity 62.8% (95% CI: 44.9 - 78.5), NPV 83.5% (95% CI: 76.7 - 88.6) and AUC 0.81 (95% CI: 0.71 - 0.91). No false positive results were observed. The RFS of the pts with positive post-orchiectomy miR371 was significantly shorter (median: 3.5 months vs. not reached; p&lt;0.0001) compared to the pts with a negative post-orchiectomy miR371 (HR: 16.9; 95% CI: 2.1 - 135.7; p&lt;0.0001). miR371 sensitivity correlated with tumor burden, time between tumor relapse and miRNA testing and histology (nonseminoma &gt; seminoma). Conclusions: miR371 has high specificity and PPV in detecting GCT at an early stage and could be used to guide treatment selection after orchiectomy. Further studies, including the SWOG S1823 clinical trial, are ongoing or have been planned in this setting for validation of clinical utility.

Prognostic Value of CXCL12 in Non-Small Cell Lung Cancer Patients Undergoing Tumor Resection

Adjuvant chemotherapy is commonly indicated in lung cancer patients undergoing surgical therapy because tumor recurrence is frequent. A biomarker that can predict tumor recurrence in the postoperative period is currently unavailable. CXCR4 receptor and its ligand CXCL12 play important roles in metastasis. This study investigated the value of tumor CXCL12 expression to predict prognosis and indicate adjuvant chemotherapy in non-small cell lung cancer patients. This study enrolled 82 non-small cell lung cancer patients. The expression of CXCL12 was evaluated by immunohistochemistry. The degree of CXCL12 expression was assessed using the Allred score system. Among all subjects, the progression-free survival and overall survival were significantly prolonged in cancer patients with low tumor expression of CXCL12 compared to patients with high tumor expression. Multivariate analysis showed that the increased level of CXCL12 is a significant predictor of progression-free survival and overall survival in NSCLC patients. Among subjects with high tumor CXCL12 expression, progression-free survival and overall survival were significantly improved in patients treated with adjuvant chemotherapy compared to untreated patients. These results suggest the potential value of tumor CXCL12 expression as a marker to predict prognosis and to indicate adjuvant chemotherapy after surgical tumor resection in non-small cell lung cancer patients.

Single-cell sequencing identifies differentiation-related markers for molecular classification and recurrence prediction of PitNET

Pituitary neuroendocrine tumor (PitNET) is one of the most common intracranial tumors with variable recurrence rate. Currently, the recurrence prediction is unsatisfying and can be improved by understanding the cellular origins and differentiation status. Here, to comprehensively reveal the origin of PitNET, we perform comparative analysis of single-cell RNA sequencing data from 3 anterior pituitary glands and 21 PitNETs. We identify distinct genes representing major subtypes of well and poorly differentiated PitNETs in each lineage. To further verify the predictive value of differentiation biomarkers, we include an independent cohort of 800 patients with an average follow-up of 7.2 years. In both PIT1 and TPIT lineages, poorly differentiated groups show significantly higher recurrence rates while well-differentiated groups show higher recurrence rates in SF1 lineage. Our findings reveal the possible origin and differentiation status of PitNET based on which new differentiation classification is proposed and verified to predict tumor recurrence.

Predicting melanoma survival and metastasis with interpretable histopathological features and machine learning models.

Melanoma is the fifth most common cancer in US, and the incidence is increasing 1.4% annually. The overall survival rate for early-stage disease is 99.4%. However, melanoma can recur years later (in the same region of the body or as distant metastasis), and results in a dramatically lower survival rate. Currently there is no reliable method to predict tumor recurrence and metastasis on early primary tumor histological images. To identify rapid, accurate, and cost-effective predictors of metastasis and survival, in this work, we applied various interpretable machine learning approaches to analyze melanoma histopathological H&E images. The result is a set of image features that can help clinicians identify high-risk-of-metastasis patients for increased clinical follow-up and precision treatment. We use simple models (i.e., logarithmic classification and KNN) and "human-interpretable" measures of cell morphology and tissue architecture (e.g., cell size, staining intensity, and cell density) to predict the melanoma survival on public and local Stage I-III cohorts as well as the metastasis risk on a local cohort. We use penalized survival regression to limit features available to downstream classifiers and investigate the utility of convolutional neural networks in isolating tumor regions to focus morphology extraction on only the tumor region. This approach allows us to predict survival and metastasis with a maximum F1 score of 0.72 and 0.73, respectively, and to visualize several high-risk cell morphologies. This lays the foundation for future work, which will focus on using our interpretable pipeline to predict metastasis in Stage I & II melanoma.