Applying radiomics to predict pathology of post chemotherapy retroperitoneal nodal masses in germ cell tumors (GCT).

4559 Background: After chemotherapy, > 50% of patients (pts) with metastatic testicular GCT who undergo retroperitoneal lymph node dissection (RPNLD) for residual masses are found to have fibrosis (F) alone on pathological examination. To minimize overtreatment, better prediction algorithms are needed to identify pts with F who can avoid RPLND. Radiomics uses image processing techniques to extract quantitative textures/features from tumor regions of interest (ROI) to train a classifier that predicts pathological findings. We hypothesized that radiomics may identify pts with a high predicted likelihood of F who may avoid RPLND. Methods: Pts with GCT who had an RPLND for nodal masses > 1cm after first line platinum chemotherapy were included. Preoperative contrast enhanced axial CT images of retroperitoneal ROI were manually contoured. 153 radiomics features trained a radial basis function support vector machine classifier to discriminate between viable GCT /Mature Teratoma (T) vs F. Nested ten-fold cross-validation protocol was employed to determine classifier accuracy. Clinical variables and restricted size criteria were used to optimize the classifier. Results: A total of 82 pts with 102 ROI were analyzed (GCT: 21; T: 41; F: 40). The discriminative accuracy of radiomics to identify GCT/T vs F was 72%(±2.2)(AUC: 0.74 (±0.028); positive predictive value: 67% (48-92%); negative predictive value: 74% (62-84%)(p = 0.001)). No major predictive differences were identified when data was restricted by varying maximal axial diameters (AUC range: 0.58(±0.05) - 0.74(±0.03)). Prediction algorithm using clinical variables alone identified an AUC of 0.71 (±0.15). When these variables were added to the radiomic signature, the best performing classifier was identified when axial tumors were limited to diameter < 2cm (accuracy: 88.2 (±4.4); AUC: 0.80 (±0.05)(p = 0.02)). Conclusions: A predictive radiomics algorithm had an overall discriminative accuracy of 72% that improved to 88% when combined with clinical details. Further independent validation is required to assess whether radiomics, in conjunction with standard clinical predictors, may allow pts with a high predicted likelihood of F to avoid RPLND.

Download Full-text

Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors

JCO Clinical Cancer Informatics ◽

10.1200/cci.18.00004 ◽

2018 ◽

pp. 1-12 ◽

Cited By ~ 3

Author(s):

Jeremy Lewin ◽

Paul Dufort ◽

Jaydeep Halankar ◽

Martin O’Malley ◽

Michael A.S. Jewett ◽

...

Keyword(s):

Germ Cell ◽

Mature Teratoma ◽

Germ Cell Tumors ◽

Area Under The Curve ◽

Prediction Algorithm ◽

Support Vector ◽

Clinical Predictors ◽

Testicular Germ Cell ◽

Clinical Variables ◽

Computed Tomography Images

Purpose After chemotherapy, approximately 50% of patients with metastatic testicular germ cell tumors (GCTs) who undergo retroperitoneal lymph node dissections (RPNLDs) for residual masses have fibrosis. Radiomics uses image processing techniques to extract quantitative textures/features from regions of interest (ROIs) to train a classifier that predicts outcomes. We hypothesized that radiomics would identify patients with a high likelihood of fibrosis who may avoid RPLND. Patients and Methods Patients with GCT who had an RPLND for nodal masses > 1 cm after first-line platinum chemotherapy were included. Preoperative contrast-enhanced axial computed tomography images of retroperitoneal ROIs were manually contoured. Radiomics features (n = 153) were used to train a radial basis function support vector machine classifier to discriminate between viable GCT/mature teratoma versus fibrosis. A nested 10-fold cross-validation protocol was used to determine classifier accuracy. Clinical variables/restricted size criteria were used to optimize the classifier. Results Seventy-seven patients with 102 ROIs were analyzed (GCT, 21; teratoma, 41; fibrosis, 40). The discriminative accuracy of radiomics to identify GCT/teratoma versus fibrosis was 72 ± 2.2% (area under the curve [AUC], 0.74 ± 0.028); sensitivity was 56.2 ± 15.0%, and specificity was 81.9 ± 9.0% ( P = .001). No major predictive differences were identified when data were restricted by varying maximal axial diameters (AUC range, 0.58 ± 0.05 to 0.74 ± 0.03). The prediction algorithm using clinical variables alone identified an AUC of 0.76. When these variables were added to the radiomics signature, the best performing classifier was identified when axial masses were limited to diameter < 2 cm (accuracy, 88.2 ± 4.4; AUC, 0.80 ± 0.05; P = .02). Conclusion A predictive radiomics algorithm had a discriminative accuracy of 72% that improved to 88% when combined with clinical predictors. Additional independent validation is required to assess whether radiomics allows patients with a high predicted likelihood of fibrosis to avoid RPLND.

Download Full-text

Clinical outcome of postchemotherapy salvage surgery for metastatic germ cell tumors in Japan

Journal of Clinical Oncology ◽

10.1200/jco.2006.24.18_suppl.14654 ◽

2006 ◽

Vol 24 (18_suppl) ◽

pp. 14654-14654

Author(s):

K. Kakimoto ◽

T. Kinouchi ◽

Y. Ono ◽

N. Meguro ◽

O. Maeda ◽

...

Keyword(s):

Clinical Outcome ◽

Germ Cell ◽

Salvage Surgery ◽

Mature Teratoma ◽

Germ Cell Tumors ◽

Salvage Chemotherapy ◽

Retroperitoneal Lymph Node Dissection ◽

First Line ◽

Residual Cancer ◽

Line Chemotherapy

14654 Background: Salvage surgery including retroperitoneal lymph node dissection (RPLND) following chemotherapy has been considered a critical component in the comprehensive management of advanced germ cell tumors (GCT). The objectives of this study were to determine the pathologic findings and clinical outcome of patients with metastatic GCT who underwent postchemotherapy salvage surgery. Methods: From 1980 to 2004, 157 patients with metastatic diseases underwent postchemotherapy salvage surgery at three institutions. Surgical resection was indicated in the presence of residual radiographic abnormalities. The cause-specific survival rate was calculated using the Kaplan-Meier method. Results: The histology of GCT was pure seminoma in 49 patients and non-seminoma in 108 patients. As first-line chemotherapy, 30 patients were treated with PVB (cisplatin, vinblastine and bleomycin) regimen, 107 patients with PEB (cisplatin, etoposide and bleomycin) regimen and 20 patients with other regimens. Salvage surgery was performed after first-line chemotherapy in 87 patients and after salvage chemotherapy in 70 patients. As salvage surgery, RPLND was performed in 135 patients, resection of pulmonary metastasis in 38, hepatotomy in 2 and resection of metastatic brain tumors in 3. The pathological findings at surgery were necrosis in 87 (55%) patients, mature teratoma in 34 (22%) and residual cancer in 36 (23%). Five of 36 patients with residual cancer performed salvage surgery in the state of marker positive. Of the 31 patients who had residual cancer with normalized marker, salvage surgery was performed after salvage chemotherapy in 11 patients. The sites of residual cancer were retroperitoneal lymph nodes in 34 patients, lung in 4, brain in 2 and liver in 1. The cause-specific 5-year survival rates for patients who had necrosis, mature teratoma and residual cancer were 95%, 96% and 68%, respectively. Conclusions: Residual cancer could not reliably be predicted or discriminated from necrosis or mature teratoma. Therefore, salvage surgery to remove postchemotherapy residual masses remains essential in the successful treatment of metastatic GCT. No significant financial relationships to disclose.

Download Full-text

Management of growing teratoma syndrome: Aachen University experience.

Journal of Clinical Oncology ◽

10.1200/jco.2014.32.4_suppl.385 ◽

2014 ◽

Vol 32 (4_suppl) ◽

pp. 385-385

Author(s):

David J. K. P. Pfister ◽

Daniel Porres ◽

Andrea K. Thissen ◽

Charlotte Piper ◽

Axel Heidenreich

Keyword(s):

Tumor Markers ◽

Surgical Resection ◽

Systemic Chemotherapy ◽

Mature Teratoma ◽

Germ Cell Tumors ◽

Vena Cava ◽

Retroperitoneal Lymph Node Dissection ◽

Tumor Diameter ◽

Growing Teratoma Syndrome ◽

Complete Surgical Resection

385 Background: Growing teratoma syndrome (GTS) is an infrequent clinical phenomenon. GTS is defined as an enlarging metastatic mass during systemic chemotherapy for advanced nonseminomatous germ cell tumors (NSGCT) despite decreasing serum tumor markers. Complete surgical resection of the mass is mandatory to achieve a favourable outcome. We report on our single center experience in the management of GTS. Methods: Between January 2000 and August 2009 postchemotherapeutic retroperitoneal lymph node dissection (PCRPLND) was performed in 162 patients (pts) with advanced NSGCT. Fourteen pts (4.9%) fulfilled the criteria of a GTS: enlarging metastatic mass in the retroperitoneum or visceral organs during systemic chemotherapy with normalized or regredient tumor markers. In all cases of GTS a complete radical bilateral PCRPLND including the resection of adjacent visceral and vascular structures was performed. Results: Median patient age was 24.5 (18 to 52) years. All patients exhibited NSGCT with a good or intermediate prognosis according to IGCCCG; in all cases the primary tumor contained predominantly (greater than 50%) mature teratoma; 10 and 4 patients presented with clinical stage IIC and III, resp. Median tumor diameter at time of surgery was 6,5 (3,0-35)cm. Tumor markers were normalized in 12 out of 14 patients and markers plateauted in 2 out of 14 patients. Tumor masses were localized in the retroperitoneum in 12 pts.; two patients had additional pulmonary metastases which were resected in a second approach. Median time from start of chemotherapy to surgery was 4.8 (1.5 to 26.5) months Median surgical time was 265 (165 to 585) minutes, and median blood loss 650 (450 to 2,000) ml. Four pts required resection of the inferior vena cava or abdominal aorta with implantation of a prosthetic graft; adjunctive nephrectomy was performed in three pts. After a median follow-up of 4.2 years two pts developed recurrent disease; the remainder are alive without evidence of disease. Conclusions: GTS is a rare phenomenom among pts with advanced NSGCT and necessitates complete surgical resection of all masses with curative intention. Surgery should be considered at time of progression to facilitate complete removal of the mass. Due to the complex surgery, treatment should be performed at specialized centers.

Download Full-text

Liver metastases in germ cell tumors.

Journal of Clinical Oncology ◽

10.1200/jco.2017.35.6_suppl.403 ◽

2017 ◽

Vol 35 (6_suppl) ◽

pp. 403-403

Author(s):

Suliman Boulos ◽

Jonathan Shamash ◽

Han Hsi Wong ◽

Sarah Maria Rudman ◽

Gary Doherty ◽

...

Keyword(s):

Liver Resection ◽

Germ Cell ◽

Mature Teratoma ◽

Germ Cell Tumour ◽

Germ Cell Tumors ◽

Adverse Outcomes ◽

Cell Tumour ◽

Retroperitoneal Lymph Node Dissection ◽

High Dose ◽

Response To Chemotherapy

403 Background: Metastatic germ cell tumour (GCT) to the liver is considered rare and usually caries adverse outcomes. We aimed to determine the outcome of patients with metastatic GCT to the liver. Methods: We identified retrospectively 36 patients with metastatic germ cell tumour to the liver between the years 2001 and 2015, from which 34 were non-seminomatous germ cell tumours (NSGCT) and two seminomas. 35 patients had other sites of metastases including lungs, bones and brain. Elevated tumour markers were seen in the vast majority of patients (97.2%). 15 patients received treatment with dose intense regime including actinomycin-D, high-dose methotrexate, etoposide and cisplatin (GAMEC) every 14 days, 20 patients received the standard protocol of bleomycin, etoposide and cisplatin (BEP) every 21 days and one patient received POMB/ACE chemotherapy. 20 patients had an induction cycle of cisplatin, vincristine and bleomycin (Baby-BOP) prior to initial treatment. Results: 12 patients had radiological complete response (CR) and 19 patients had radiological partial response (PR) in the liver, with five patients having a CR in all sites with negative markers. Five patients underwent liver resection with no viable tumour seen. Three patients that underwent liver resection also had retroperitoneal lymph node dissection (RPLND) the histology from which was viable seminoma in one case, mature teratoma in one case and necrosis in the final patient.16 patients had marker negative PR, 10 patients had marker positive PR and 5 patients had a marker negative CR. 15 patients eventually relapsed and 10 died with only one liver relapse. Median Overall survival for patients that received BEP was 35.38 months (not reached for GAMEC) (p = 0.0147). The median progression free survival (PFS) for the BEP group was 24.45 months (not reached for GAMEC) (p = 0.22) and the 2-years PFS for the GAMEC and BEP groups were 73% and 55% respectively. Conclusions: Within this cohort, liver metastasis from germ-cell tumour had a good response to chemotherapy, with progression occurring mainly in extra-hepatic sites. There was also a suggestion that dose dense GAMEC regime may offer superior efficacy compared with BEP.These results also question the role of liver metastectomy after initial response to chemotherapy.

Download Full-text

Validation of the two best models to predict “benign” pathohistology in patients with advanced nonseminomatous germ cell tumors (NSGCT) undergoing postchemotherapy retroperitoneal lymph node dissection (PC-RPLND).

Journal of Clinical Oncology ◽

10.1200/jco.2020.38.6_suppl.389 ◽

2020 ◽

Vol 38 (6_suppl) ◽

pp. 389-389

Author(s):

Tim Nestler ◽

Pia Paffenholz ◽

Bettina Baeßler ◽

Martin Hellmich ◽

Andreas Hiester ◽

...

Keyword(s):

Error Rate ◽

Prediction Models ◽

Validation Cohort ◽

Germ Cell Tumors ◽

Benign Disease ◽

Training Dataset ◽

Retroperitoneal Lymph Node Dissection ◽

Support Vector ◽

Surveillance Strategy ◽

Viable Tumor

389 Background: The aim of our study is to validate and evaluate the two currently best performing prediction models (Vergouwe and Leao) for final pathohistology in NSGCT patients undergoing PC-RPLND and we introduce a new radiomics approach. Methods: We performed a retrospective analysis including 496 patients who underwent a PC-RPLND between 2008 and 2018 to validate the two prediction models using published formulas and thresholds. ROC were plotted and AUC was calculated. We determined the optimal cut point and used bootstrapping (1,000 replications) to estimate its variability. For radiomics, lymph nodes of 80 patients were identified on CT images, semiautomatically segmented with 93 radiographic features (pyRadiomics package). A linear support vector machine algorithm was applied to analyze reproducible radiomics features. A continuous reduction of features analyzed was performed using Random Forest algorithms and ROC analysis. Results: In our validation cohort, the Vergouwe model had a significantly better AUC compared to Leao model (0.749 [CI 0.706-0.792] vs. 0.689 [0.642-0.736], p=0.004) to predict benign histology. At a threshold of > 70% for the probability of benign disease, the Leao model would have avoided PC-RPLND in 8.6% with benign disease with an error rate of 5.6% for viable tumor. The Vergouwe model would avoid PC-RPLND in 23.4% with benign disease with an error rate of 12.7% for viable tumor/teratoma. Of the 93 radiomic features analyzed, 51 features were reproducible. Applying the trained algorithm on the training dataset resulted in an accuracy of 0.96 (93% sensitivity, 100% specificity, 100% PPV), on an independent validation cohort the accuracy was 0.81 (88% sensitivity, 72% specificity, 78% PPV). Conclusions: According to our data, the discriminatory accuracy of both models is not sufficient to safely select patients for surveillance strategy instead of PC-RPLND. The radiomics model is promising but needs prospective validation. Further studies including new biomarkers are needed to optimize the accuracy of potential prediction models.

Download Full-text

Paternity in men with stage I testis tumors on surveillance.

Journal of Clinical Oncology ◽

10.1200/jco.1998.16.2.733 ◽

1998 ◽

Vol 16 (2) ◽

pp. 733-734 ◽

Cited By ~ 30

Author(s):

H W Herr ◽

N Bar-Chama ◽

M O'Sullivan ◽

P C Sogani

Keyword(s):

Clinical Stage ◽

Germ Cell Tumors ◽

Stage I ◽

Retroperitoneal Lymph Node Dissection ◽

Nerve Sparing ◽

Testis Tumor ◽

Fertility Potential ◽

Testis Tumors ◽

Nonseminomatous Germ Cell Tumors

PURPOSE We report long-term paternity in men with stage I testis tumors who were managed initially by surveillance. PATIENTS AND METHODS One hundred five patients with clinical stage I nonseminomatous germ cell tumors of the testis were entered on a surveillance protocol and followed up for more than 10 years. Actual fertility potential was assessed by pregnancy. RESULTS Of the 105 patients, 41 (39%) have fathered children, which includes 36 of 78 (46%) patients while on active surveillance and five of 27 (19%) patients after treatment for relapse. Of 63 couples who attempted a pregnancy on surveillance or were presumed capable of impregnation (whether they tried or not), 41 (65%) were successful. CONCLUSION These results show that the majority of men with stage I testis tumor who are on surveillance after orchiectomy, have a suitable partner, and attempt impregnation achieve a successful pregnancy. Pregnancy rates appear to be less than reported in men who have a nerve-sparing retroperitoneal lymph node dissection (RPLND) because more patients on surveillance require treatment for relapse, which reduces their chances for pregnancy.

Download Full-text

Prediction of Incident Cancers in the Lifelines Population-Based Cohort

Cancers ◽

10.3390/cancers13092133 ◽

2021 ◽

Vol 13 (9) ◽

pp. 2133

Author(s):

Francisco O. Cortés-Ibañez ◽

Sunil Belur Nagaraj ◽

Ludo Cornelissen ◽

Gerjan J. Navis ◽

Bert van der Vegt ◽

...

Keyword(s):

Cancer Incidence ◽

Binary Classification ◽

Predictive Performance ◽

Population Based ◽

Support Vector ◽

Clinical Variables ◽

Incident Cancer ◽

History Of ◽

Diagnosis Of Cancer ◽

Auc Value

Cancer incidence is rising, and accurate prediction of incident cancers could be relevant to understanding and reducing cancer incidence. The aim of this study was to develop machine learning (ML) models that could predict an incident diagnosis of cancer. Participants without any history of cancer within the Lifelines population-based cohort were followed for a median of 7 years. Data were available for 116,188 cancer-free participants and 4232 incident cancer cases. At baseline, socioeconomic, lifestyle, and clinical variables were assessed. The main outcome was an incident cancer during follow-up (excluding skin cancer), based on linkage with the national pathology registry. The performance of three ML algorithms was evaluated using supervised binary classification to identify incident cancers among participants. Elastic net regularization and Gini index were used for variables selection. An overall area under the receiver operator curve (AUC) <0.75 was obtained, the highest AUC value was for prostate cancer (random forest AUC = 0.82 (95% CI 0.77–0.87), logistic regression AUC = 0.81 (95% CI 0.76–0.86), and support vector machines AUC = 0.83 (95% CI 0.78–0.88), respectively); age was the most important predictor in these models. Linear and non-linear ML algorithms including socioeconomic, lifestyle, and clinical variables produced a moderate predictive performance of incident cancers in the Lifelines cohort.

Download Full-text

Teratomatous Elements in Orchiectomy Specimens Are Associated with a Reduced Relapse-Free Survival in Metastasized Testicular Germ Cell Tumors

Urologia Internationalis ◽

10.1159/000515715 ◽

2021 ◽

pp. 1-7

Author(s):

Pia Paffenholz ◽

Tim Nestler ◽

Yasmine Maatoug ◽

Melanie von Brandenstein ◽

Barbara Köditz ◽

...

Keyword(s):

Germ Cell ◽

Germ Cell Tumors ◽

Retroperitoneal Lymph Node Dissection ◽

Advanced Tumor Stage ◽

Testicular Germ Cell Tumors ◽

Relapse Free Survival ◽

Testicular Germ Cell ◽

Free Survival ◽

Advanced Tumor ◽

The Impact

Introduction: The impact of teratomatous elements in orchiectomy specimens of metastasized testicular germ cell tumors (TGCT) regarding oncological outcome is still unclear. Methods: We performed a retrospective analysis including 146 patients with metastasized TGCT analysing patient characteristics. Results: Twenty-six (18%) of all patients showed teratomatous elements in the orchiectomy specimens. TGCT with teratomatous elements showed a significantly higher frequency of clinical-stage 2C-3 disease (73 vs. 49%, p = 0.031), visceral metastases (58 vs. 32%, p = 0.015), and poor prognosis (p = 0.011) than TGCT without teratomatous elements. Teratoma-containing TGCT revealed a significantly higher rate of post-chemotherapy retroperitoneal lymph node dissection (PC-RPLND, 54 vs. 32%, p = 0.041), with teratomatous elements being more often present in the PC-RPLND specimens (43 vs. 11%, p = 0.020) than nonteratoma-containing primaries. In the Kaplan-Meier estimates, the presence of teratomatous elements in orchiectomy specimens was associated with a significantly reduced relapse-free survival (RFS) (p = 0.049) during a median follow-up of 36 months (10–115.5). Conclusions: The presence of teratomatous elements in orchiectomy specimens is associated with an advanced tumor stage, worse treatment response as well as a reduced RFS in metastasized TGCT. Consequently, the presence of teratomatous elements might act as a reliable stratification tool for treatment decision in TGCT patients.

Download Full-text