An open source pipeline for quantitative immunohistochemistry image analysis of inflammatory skin disease using artificial intelligence
Bibliographic record
Abstract
BACKGROUND: The application of artificial intelligence (AI) to whole slide images has the potential to improve research reliability and ultimately diagnostic efficiency and service capacity. Image annotation plays a key role in AI and digital pathology. However, the work-streams required for tissue-specific (skin) and immunostain-specific annotation has not been extensively studied compared with the development of AI algorithms. OBJECTIVES: The objective of this study is to develop a common workflow for annotating whole slide images of biopsies from inflammatory skin disease immunostained with a variety of epidermal and dermal markers prior to the development of the AI-assisted analysis pipeline. METHODS: A total of 45 slides containing 3-5 sections each were scanned using Aperio AT2 slide scanner (Leica Biosystems). These slides were annotated by hand using a commonly used image analysis tool which resulted in more than 4000 images blocks. We used deep learning (DL) methodology to first sequentially segment (epidermis and upper dermis), with the exclusion of common artefacts and second to quantify the immunostained signal in those two compartments of skin biopsies and the ratio of positive cells. RESULTS: We validated two DL models using 10-fold validation runs and by comparing to ground truth manually annotated data. The models achieved an average (global) accuracy of 95.0% for the segmentation of epidermis and dermis and 86.1% for the segmentation of positive/negative cells. CONCLUSIONS: The application of two DL models in sequence facilitates accurate segmentation of epidermal and dermal structures, exclusion of common artefacts and enables the quantitative analysis of the immunostained signal. However, inaccurate annotation of the slides for training the DL model can decrease the accuracy of the output. Our open source code will facilitate further external validation across different immunostaining platforms and slide scanners.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.022 | 0.015 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".