Characterization and outcome of patients with testicular germ cell tumours treated in a comprehensive cancer centre

Aims To identify clinicopathological features and outcomes in patients with late relapse (LR) of testicular germ cell tumours (GCTs) in order to guide follow-up policy. Materials and Methods The Edinburgh Cancer Centre (ECC) database identified all patients diagnosed with testicular GCT between 1988 and 2002. Of 703 patients, six relapsed more than 24 months after their initial treatment. A retrospective casenote review was performed to extract clinical, pathological, treatment and outcome data. Results Six patients (0.85%) underwent late relapse. All patients presented initially with stage I disease and five were classified as good risk (International Germ Cell Consensus Classification, IGCCC). Median time to LR was 31 months. Two patients had previously relapsed less than 24 months from initial diagnosis. Markers at the time of relapse were normal in all patients. In all cases of late relapse disease was confined to axial lymphadenopathy. Three patients were treated with chemotherapy alone, two patients underwent surgical resection and one patient received combined treatment. All patients obtained a complete response and all remain disease free with a median follow-up of 52 months. Conclusions The incidence of late relapse in this series is low. Chemo-naive patients with LR were successfully salvaged with chemotherapy alone and patients previously exposed to cisplatin-based chemotherapy were salvaged with complete surgical excision. The optimal length of follow-up in patients with testicular germ cell tumours is not known and practice varies widely. In this cohort of 703 patients, only one patient who relapsed was picked up by additional clinic follow-up between 5 and 10 years. Thus, on the basis of this small series, the authors suggest that follow-up after five years may not be justified.

Download Full-text

The Potential of Artificial Intelligence to Detect Lymphovascular Invasion in Testicular Cancer

Cancers ◽

10.3390/cancers13061325 ◽

2021 ◽

Vol 13 (6) ◽

pp. 1325

Author(s):

Abhisek Ghosh ◽

Korsuk Sirinukunwattana ◽

Nasullah Khalid Alham ◽

Lisa Browning ◽

Richard Colling ◽

...

Keyword(s):

Artificial Intelligence ◽

Testicular Cancer ◽

Germ Cell ◽

Lymphovascular Invasion ◽

Automatic Segmentation ◽

Prognostic Significance ◽

Germ Cell Tumours ◽

Testicular Germ Cell ◽

Testicular Germ Cell Tumours ◽

Whole Slide Images

Testicular cancer is the most common cancer in men aged from 15 to 34 years. Lymphovascular invasion refers to the presence of tumours within endothelial-lined lymphatic or vascular channels, and has been shown to have prognostic significance in testicular germ cell tumours. In non-seminomatous tumours, lymphovascular invasion is the most powerful prognostic factor for stage 1 disease. For the pathologist, searching multiple slides for lymphovascular invasion can be highly time-consuming. The aim of this retrospective study was to develop and assess an artificial intelligence algorithm that can identify areas suspicious for lymphovascular invasion in histological digital whole slide images. Areas of possible lymphovascular invasion were annotated in a total of 184 whole slide images of haematoxylin and eosin (H&E) stained tissue from 19 patients with testicular germ cell tumours, including a mixture of seminoma and non-seminomatous cases. Following consensus review by specialist uropathologists, we trained a deep learning classifier for automatic segmentation of areas suspicious for lymphovascular invasion. The classifier identified 34 areas within a validation set of 118 whole slide images from 10 patients, each of which was reviewed by three expert pathologists to form a majority consensus. The precision was 0.68 for areas which were considered to be appropriate to flag, and 0.56 for areas considered to be definite lymphovascular invasion. An artificial intelligence tool which highlights areas of possible lymphovascular invasion to reporting pathologists, who then make a final judgement on its presence or absence, has been demonstrated as feasible in this proof-of-concept study. Further development is required before clinical deployment.

Download Full-text