The potential of artificial intelligence to detect lymphovascular invasion in testicular cancer
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 tumo...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
MDPI
2021
|
| _version_ | 1826260573970497536 |
|---|---|
| author | Ghosh, A Sirinukunwattana, K Khalid Alham, N Browning, L Colling, R Protheroe, A Protheroe, E Jones, S Aberdeen, A Rittscher, J Verrill, C |
| author_facet | Ghosh, A Sirinukunwattana, K Khalid Alham, N Browning, L Colling, R Protheroe, A Protheroe, E Jones, S Aberdeen, A Rittscher, J Verrill, C |
| author_sort | Ghosh, A |
| collection | OXFORD |
| description | 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. |
| first_indexed | 2024-03-06T19:07:49Z |
| format | Journal article |
| id | oxford-uuid:15c476a7-f91f-4e0d-b9e5-116376b5b259 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T19:07:49Z |
| publishDate | 2021 |
| publisher | MDPI |
| record_format | dspace |
| spelling | oxford-uuid:15c476a7-f91f-4e0d-b9e5-116376b5b2592022-03-26T10:27:18ZThe potential of artificial intelligence to detect lymphovascular invasion in testicular cancerJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:15c476a7-f91f-4e0d-b9e5-116376b5b259EnglishSymplectic ElementsMDPI2021Ghosh, ASirinukunwattana, KKhalid Alham, NBrowning, LColling, RProtheroe, AProtheroe, EJones, SAberdeen, ARittscher, JVerrill, CTesticular 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. |
| spellingShingle | 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 |
| title | The potential of artificial intelligence to detect lymphovascular invasion in testicular cancer |
| title_full | The potential of artificial intelligence to detect lymphovascular invasion in testicular cancer |
| title_fullStr | The potential of artificial intelligence to detect lymphovascular invasion in testicular cancer |
| title_full_unstemmed | The potential of artificial intelligence to detect lymphovascular invasion in testicular cancer |
| title_short | The potential of artificial intelligence to detect lymphovascular invasion in testicular cancer |
| title_sort | potential of artificial intelligence to detect lymphovascular invasion in testicular cancer |
| work_keys_str_mv | AT ghosha thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT sirinukunwattanak thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT khalidalhamn thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT browningl thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT collingr thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT protheroea thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT protheroee thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT joness thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT aberdeena thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT rittscherj thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT verrillc thepotentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT ghosha potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT sirinukunwattanak potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT khalidalhamn potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT browningl potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT collingr potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT protheroea potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT protheroee potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT joness potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT aberdeena potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT rittscherj potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer AT verrillc potentialofartificialintelligencetodetectlymphovascularinvasionintesticularcancer |