Advancements in Lossless and Reversible Compression of Digital Pathology Images via Auto-Recursive Set Partitioning in Hierarchical Trees and Wavelet Decomposition
Bibliographic record
Abstract
Set Partitioning in Hierarchical Trees (SPIHT) represents a leading-edge algorithm in nearlossless image compression, leveraging the Discrete Wavelet Transform.However, its effectiveness diminishes when applied to high-resolution images such as Digital Pathology Images (DPIs).This research aims to enhance the SPIHT algorithm specifically for DPIs by investigating the impact of applying various wavelets in the wavelet decomposition process and the introduction of auto-recursion in the SPIHT algorithm.An extensive selection of wavelet types were tested within the wavelet decomposition process integral to the SPIHT algorithm.The ultimate goal was to identify the wavelet that yields the highest compression ratio and the one that maintains the highest data consistency.The proposed auto-recursion was also examined against the original n-recursive algorithm to discern differences in compression performance.The results indicated that the BIOR 5.5 wavelet is more apt for achieving a high compression ratio, while the BIOR 3.9 wavelet is more suitable for securing high compression quality in the compression of high-resolution DPIs.The newly introduced auto-recursion feature contributes significantly to optimizing the quality of the compressed image.Visual verification of the compressed image's quality, for any potential loss of detail, was carried out through expert validation in a clinical setting.This expert validation confirmed that the proposed algorithm can produce higher quality compressed images with negligible loss of quality.Thus, this research offers a partial solution to current challenges in digital pathology related to storage, transfer, and archiving of high-resolution DPIs, by providing a more effective compression algorithm.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".