1
|
Ghosh A, Sirinukunwattana K, Khalid Alham N, Browning L, Colling R, Protheroe A, Protheroe E, Jones S, Aberdeen A, Rittscher J, Verrill C. The Potential of Artificial Intelligence to Detect Lymphovascular Invasion in Testicular Cancer. Cancers (Basel) 2021; 13:cancers13061325. [PMID: 33809521 PMCID: PMC7998792 DOI: 10.3390/cancers13061325] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2021] [Revised: 03/08/2021] [Accepted: 03/12/2021] [Indexed: 11/16/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Abhisek Ghosh
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford OX3 9DU, UK; (L.B.); (R.C.); (C.V.)
- Nuffield Department of Clinical and Laboratory Sciences, Oxford University, John Radcliffe Hospital, Oxford OX3 9DU, UK
- Correspondence:
| | - Korsuk Sirinukunwattana
- Big Data Institute, Li Ka Shing Centre for Health Information and Discovery, University of Oxford, Oxford OX3 7LF, UK; (K.S.); (N.K.A.); (J.R.)
- Oxford NIHR Biomedical Research Centre, Oxford University, Oxford OX3 9DU, UK
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, UK
- Ground Truth Labs, Oxford OX4 2HN, UK;
| | - Nasullah Khalid Alham
- Big Data Institute, Li Ka Shing Centre for Health Information and Discovery, University of Oxford, Oxford OX3 7LF, UK; (K.S.); (N.K.A.); (J.R.)
- Oxford NIHR Biomedical Research Centre, Oxford University, Oxford OX3 9DU, UK
| | - Lisa Browning
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford OX3 9DU, UK; (L.B.); (R.C.); (C.V.)
- Oxford NIHR Biomedical Research Centre, Oxford University, Oxford OX3 9DU, UK
| | - Richard Colling
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford OX3 9DU, UK; (L.B.); (R.C.); (C.V.)
- Nuffield Department of Surgical Sciences, Oxford University, Oxford OX3 9DU, UK;
| | - Andrew Protheroe
- Department of Oncology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford OX3 9DU, UK; (A.P.); (E.P.)
| | - Emily Protheroe
- Department of Oncology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford OX3 9DU, UK; (A.P.); (E.P.)
| | - Stephanie Jones
- Nuffield Department of Surgical Sciences, Oxford University, Oxford OX3 9DU, UK;
| | | | - Jens Rittscher
- Big Data Institute, Li Ka Shing Centre for Health Information and Discovery, University of Oxford, Oxford OX3 7LF, UK; (K.S.); (N.K.A.); (J.R.)
- Oxford NIHR Biomedical Research Centre, Oxford University, Oxford OX3 9DU, UK
| | - Clare Verrill
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford OX3 9DU, UK; (L.B.); (R.C.); (C.V.)
- Oxford NIHR Biomedical Research Centre, Oxford University, Oxford OX3 9DU, UK
- Nuffield Department of Surgical Sciences, Oxford University, Oxford OX3 9DU, UK;
| |
Collapse
|
2
|
Olsson-Brown A, Hughes D, Purshouse K, Lee L, Cheng V, Lee A, Protheroe E, Smith A, Curley H, Arnold R, Cazier JB, D'Costa J, Palles C, Campton N, Varnai C, Sivakumar S, Kerr R, Middleton G. 1703P UK Coronavirus Cancer Monitoring Project (UKCCMP): A national reporting network for real time data of the COVID-19 pandemic. Ann Oncol 2020. [PMCID: PMC7506390 DOI: 10.1016/j.annonc.2020.08.1767] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022] Open
|