1
|
Chatrian A, Colling RT, Browning L, Alham NK, Sirinukunwattana K, Malacrino S, Haghighat M, Aberdeen A, Monks A, Moxley-Wyles B, Rakha E, Snead DRJ, Rittscher J, Verrill C. Artificial intelligence for advance requesting of immunohistochemistry in diagnostically uncertain prostate biopsies. Mod Pathol 2021; 34:1780-1794. [PMID: 34017063 PMCID: PMC8376647 DOI: 10.1038/s41379-021-00826-6] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2021] [Revised: 04/23/2021] [Accepted: 04/27/2021] [Indexed: 12/29/2022]
Abstract
The use of immunohistochemistry in the reporting of prostate biopsies is an important adjunct when the diagnosis is not definite on haematoxylin and eosin (H&E) morphology alone. The process is however inherently inefficient with delays while waiting for pathologist review to make the request and duplicated effort reviewing a case more than once. In this study, we aimed to capture the workflow implications of immunohistochemistry requests and demonstrate a novel artificial intelligence tool to identify cases in which immunohistochemistry (IHC) is required and generate an automated request. We conducted audits of the workflow for prostate biopsies in order to understand the potential implications of automated immunohistochemistry requesting and collected prospective cases to train a deep neural network algorithm to detect tissue regions that presented ambiguous morphology on whole slide images. These ambiguous foci were selected on the basis of the pathologist requesting immunohistochemistry to aid diagnosis. A gradient boosted trees classifier was then used to make a slide-level prediction based on the outputs of the neural network prediction. The algorithm was trained on annotations of 219 immunohistochemistry-requested and 80 control images, and tested by threefold cross-validation. Validation was conducted on a separate validation dataset of 222 images. Non IHC-requested cases were diagnosed in 17.9 min on average, while IHC-requested cases took 33.4 min over multiple reporting sessions. We estimated 11 min could be saved on average per case by automated IHC requesting, by removing duplication of effort. The tool attained 99% accuracy and 0.99 Area Under the Curve (AUC) on the test data. In the validation, the average agreement with pathologists was 0.81, with a mean AUC of 0.80. We demonstrate the proof-of-principle that an AI tool making automated immunohistochemistry requests could create a significantly leaner workflow and result in pathologist time savings.
Collapse
Affiliation(s)
- Andrea Chatrian
- Institute of Biomedical Engineering (IBME), Department of Engineering Science, University of Oxford, Old Road Campus Research Building Oxford, Oxford, UK.
- Oxford Big Data Institute, University of Oxford, Li Ka Shing Centre for Health Information and Discovery, Oxford, UK.
| | - Richard T Colling
- Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Headington, Oxford, UK
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headington, Oxford, UK
| | - Lisa Browning
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headington, Oxford, UK
- NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headington, Oxford, UK
| | - Nasullah Khalid Alham
- Institute of Biomedical Engineering (IBME), Department of Engineering Science, University of Oxford, Old Road Campus Research Building Oxford, Oxford, UK
- Oxford Big Data Institute, University of Oxford, Li Ka Shing Centre for Health Information and Discovery, Oxford, UK
| | - Korsuk Sirinukunwattana
- Institute of Biomedical Engineering (IBME), Department of Engineering Science, University of Oxford, Old Road Campus Research Building Oxford, Oxford, UK
- Oxford Big Data Institute, University of Oxford, Li Ka Shing Centre for Health Information and Discovery, Oxford, UK
| | - Stefano Malacrino
- Institute of Biomedical Engineering (IBME), Department of Engineering Science, University of Oxford, Old Road Campus Research Building Oxford, Oxford, UK
- Oxford Big Data Institute, University of Oxford, Li Ka Shing Centre for Health Information and Discovery, Oxford, UK
- Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Headington, Oxford, UK
| | - Maryam Haghighat
- Institute of Biomedical Engineering (IBME), Department of Engineering Science, University of Oxford, Old Road Campus Research Building Oxford, Oxford, UK
- Oxford Big Data Institute, University of Oxford, Li Ka Shing Centre for Health Information and Discovery, Oxford, UK
| | - Alan Aberdeen
- Ground Truth Labs, 9400 Garsington Road, Oxford Business Park, Oxford, UK
| | - Amelia Monks
- Institute of Biomedical Engineering (IBME), Department of Engineering Science, University of Oxford, Old Road Campus Research Building Oxford, Oxford, UK
| | - Benjamin Moxley-Wyles
- Department of Cellular Pathology, Buckinghamshire Healthcare NHS Trust, Amersham, UK
| | - Emad Rakha
- School of Medicine, University of Nottingham, Nottingham, Nottinghamshire, UK
| | - David R J Snead
- Department of Pathology, University Hospitals Coventry and Warwickshire NHS Trust, Coventry, West Midlands, UK
| | - Jens Rittscher
- Institute of Biomedical Engineering (IBME), Department of Engineering Science, University of Oxford, Old Road Campus Research Building Oxford, Oxford, UK.
- Oxford Big Data Institute, University of Oxford, Li Ka Shing Centre for Health Information and Discovery, Oxford, UK.
- NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headington, Oxford, UK.
- Ludwig Institute for Cancer Research, Nuffield Department of Clinical Medicine, University of Oxford, Oxford, UK.
| | - Clare Verrill
- Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Headington, Oxford, UK.
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headington, Oxford, UK.
- NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headington, Oxford, UK.
| |
Collapse
|
2
|
Stewart CJR, Moses J. NKX3.1 expression in cervical 'adenoid basal cell carcinoma': another gynaecological lesion with prostatic differentiation? Pathology 2020; 53:193-198. [PMID: 33032811 DOI: 10.1016/j.pathol.2020.07.011] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/28/2020] [Revised: 07/07/2020] [Accepted: 07/20/2020] [Indexed: 10/23/2022]
Abstract
Adenoid basal cell carcinoma (ABC) is considered a rare cervical neoplasm which when present in 'pure' form, uniquely amongst apparently malignant cervical tumours, has never been reported to metastasise or lead to fatal patient outcome. We recently encountered a case of ABC that was morphologically reminiscent of prostatic differentiation, more specifically basal cell hyperplasia of the prostate. Immunohistochemistry was strongly positive for the prostate related marker NKX3.1 in the glandular cells, but there was no expression of prostate specific antigen (PSA) or prostatic acid phosphatase (PAP). However, subsequent review of five additional cervical ABCs demonstrated focal PAP expression in two of four tested cases, and all were NKX3.1 positive. NKX3.1 expression was also demonstrated in the glandular epithelium of 10 additional gynaecological lesions considered to show prostatic differentiation including five cases of cervical ectopic prostatic tissue, three ovarian teratomas with prostatic differentiation, and two vaginal tubulosquamous polyps. We suggest that some lesions traditionally classified as ABC may in fact represent a variant of prostatic differentiation within the cervix, possibly analogous to basal cell hyperplasia of the prostate.
Collapse
Affiliation(s)
- Colin J R Stewart
- Department of Pathology, King Edward Memorial Hospital, Perth, WA, Australia; School of Women's and Infants' Health, University of Western Australia, WA, Australia.
| | - Joanne Moses
- LabPlus, Auckland City Hospital, Auckland, New Zealand
| |
Collapse
|