Deep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumors
<strong>Aims</strong> To evaluate if a deep learning algorithm can be trained to identify tumour-infiltrating lymphocytes (TILs) in tissue samples of testicular germ cell tumours and to assess whether the TIL counts correlate with relapse status of the patient. <br/><br/> <...
| Автори: | , , , , , , , , , |
|---|---|
| Формат: | Journal article |
| Опубліковано: |
BMJ Publishing Group
2018
|
| _version_ | 1826281184463683584 |
|---|---|
| author | Linder, N Taylor, J Colling, R Pell, R Alveyn, E Joseph, J Protheroe, A Lundin, M Lundin, J Verrill, C |
| author_facet | Linder, N Taylor, J Colling, R Pell, R Alveyn, E Joseph, J Protheroe, A Lundin, M Lundin, J Verrill, C |
| author_sort | Linder, N |
| collection | OXFORD |
| description | <strong>Aims</strong> To evaluate if a deep learning algorithm can be trained to identify tumour-infiltrating lymphocytes (TILs) in tissue samples of testicular germ cell tumours and to assess whether the TIL counts correlate with relapse status of the patient. <br/><br/> <strong>Methods</strong> TILs were manually annotated in 259 tumour regions from 28 whole-slide images (WSIs) of H&E-stained; tissue samples. A deep learning algorithm was trained on half of the regions and tested on the other half. The algorithm was further applied to larger areas of tumour WSIs from 89 patients and correlated with clinicopathological data. <br/><br/> <strong>Results</strong> A correlation coefficient of 0.89 was achieved when comparing the algorithm with the manual TIL count in the test set of images in which TILs were present (n=47). In the WSI regions from the 89 patient samples, the median TIL density was 1009/mm2. In seminomas, none of the relapsed patients belonged to the highest TIL density tertile (>2011/mm2). TIL quantifications performed visually by three pathologists on the same tumours were not significantly associated with outcome. The average interobserver agreement between the pathologists when assigning a patient into TIL tertiles was 0.32 (Kappa test) compared with 0.35 between the algorithm and the experts, respectively. A higher TIL density was associated with a lower clinical tumour stage, seminoma histology and lack of lymphovascular invasion. <br/><br/> <strong>Conclusions</strong> Deep learning–based image analysis can be used for detecting TILs in testicular germ cell cancer more objectively and it has potential for use as a prognostic marker for disease relapse. |
| first_indexed | 2024-03-07T00:24:59Z |
| format | Journal article |
| id | oxford-uuid:7dd6ad79-25a4-4f64-801f-d4791b43386f |
| institution | University of Oxford |
| last_indexed | 2024-03-07T00:24:59Z |
| publishDate | 2018 |
| publisher | BMJ Publishing Group |
| record_format | dspace |
| spelling | oxford-uuid:7dd6ad79-25a4-4f64-801f-d4791b43386f2022-03-26T21:06:15ZDeep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumorsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:7dd6ad79-25a4-4f64-801f-d4791b43386fSymplectic Elements at OxfordBMJ Publishing Group2018Linder, NTaylor, JColling, RPell, RAlveyn, EJoseph, JProtheroe, ALundin, MLundin, JVerrill, C<strong>Aims</strong> To evaluate if a deep learning algorithm can be trained to identify tumour-infiltrating lymphocytes (TILs) in tissue samples of testicular germ cell tumours and to assess whether the TIL counts correlate with relapse status of the patient. <br/><br/> <strong>Methods</strong> TILs were manually annotated in 259 tumour regions from 28 whole-slide images (WSIs) of H&E-stained; tissue samples. A deep learning algorithm was trained on half of the regions and tested on the other half. The algorithm was further applied to larger areas of tumour WSIs from 89 patients and correlated with clinicopathological data. <br/><br/> <strong>Results</strong> A correlation coefficient of 0.89 was achieved when comparing the algorithm with the manual TIL count in the test set of images in which TILs were present (n=47). In the WSI regions from the 89 patient samples, the median TIL density was 1009/mm2. In seminomas, none of the relapsed patients belonged to the highest TIL density tertile (>2011/mm2). TIL quantifications performed visually by three pathologists on the same tumours were not significantly associated with outcome. The average interobserver agreement between the pathologists when assigning a patient into TIL tertiles was 0.32 (Kappa test) compared with 0.35 between the algorithm and the experts, respectively. A higher TIL density was associated with a lower clinical tumour stage, seminoma histology and lack of lymphovascular invasion. <br/><br/> <strong>Conclusions</strong> Deep learning–based image analysis can be used for detecting TILs in testicular germ cell cancer more objectively and it has potential for use as a prognostic marker for disease relapse. |
| spellingShingle | Linder, N Taylor, J Colling, R Pell, R Alveyn, E Joseph, J Protheroe, A Lundin, M Lundin, J Verrill, C Deep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumors |
| title | Deep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumors |
| title_full | Deep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumors |
| title_fullStr | Deep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumors |
| title_full_unstemmed | Deep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumors |
| title_short | Deep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumors |
| title_sort | deep learning for detecting tumour infiltrating lymphocytes in testicular germ cell tumors |
| work_keys_str_mv | AT lindern deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT taylorj deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT collingr deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT pellr deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT alveyne deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT josephj deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT protheroea deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT lundinm deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT lundinj deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors AT verrillc deeplearningfordetectingtumourinfiltratinglymphocytesintesticulargermcelltumors |