Image Analysis in Neuropathology: Hue-Saturation-Intensity vs. Colour Deconvolution
Bibliographic record
Abstract
As image analysis expands into clinical and basic applications it is important that users be aware of opportunities and limitations. A common image analysis workflow involves the digitization of stained tissue sections into a red-green-blue (RGB) colour model for quantitative interpretation. Upstream of the digital image, quality and variability can be degraded at each step (tissue handling, fixation, sectioning, staining, image acquisition). Digital image analysis presents additional steps where variables can affect data quality. Image analysis platforms are not uniform. Aside from interface preferences, some introduce unintended variability due to their processing architecture that may not be obvious to the end-user. One important component of this is colour space representation: hue-saturation-intensity (HSI) vs. colour deconvolution (CD). A potential weakness of analyses within the HSI colour space is the mis-identification of darkly stained pixels, particularly when more than one stain is present. We were interested to discover whether HSI or CD provided greater fidelity in a typical immunoperoxidase/hematoxylin dataset. Fifty-nine samples were processed using HSI- and CD-based analyses. Processed image pairs were compared with the original sample to determine which processed image provided a more accurate representation. CD proved superior to HSI in 94.9% of the analyzed image pairs. Where the option exists, CD-based image analysis is strongly recommended. LEARNING OBJECTIVES This presentation will enable the learner to: 1. To describe differences between HSI and CD colour spaces 2. To explain limitations in the use of HSI-based analyses 3. To be aware of recent developments in CD-based platforms
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 | 0.007 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.021 | 0.008 |
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".