MétaCan
Menu
Back to cohort
Record W4294974890 · doi:10.1109/ichi54592.2022.00049

Quality Control of Whole Slide Images using the YOLO Concept

2022· article· en· W4294974890 on OpenAlexafffund
Kimia Hemmatirad, Morteza Babaie, Mehdi Afshari, Danial Maleki, Mahjabin Saiadi, Hamid R. Tizhoosh

Bibliographic record

Venue2022 IEEE 10th International Conference on Healthcare Informatics (ICHI) · 2022
Typearticle
Languageen
FieldComputer Science
TopicAI in cancer detection
Canadian institutionsVector InstituteUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsWorkflowComputer scienceComputer visionArtificial intelligenceDigitizationDigital pathologyIntersection (aeronautics)Jaccard indexFocus (optics)Computer graphics (images)Pattern recognition (psychology)OpticsDatabase

Abstract

fetched live from OpenAlex

Computational pathology applies computer vision algorithms on whole slide images. The digitization of tissue glass slides marks a significant change in the clinical diagnostic workflow. One of the challenges in digital pathology is the presence of artifacts such as tissue fold, air bubbles, and ink-markers on archived cases. These artifacts may affect the focus points in digital scanners, and their presence may negatively affect the quality of the output tissue image and the subsequent diagnosis. Manual review of whole slide images requires experts, and it is a laborious and time-consuming task. In this paper, we trained the YOLO-v4 (You-Only-Look-Once) model to detect air bubble edges, tissue folds, which can happen during slide preparation, and ink-marked tissue glass slides, which occur when pathologists highlight regions of interest on glass slides. Our method is not only fast but also highly accurate. The experiments showed 99.5 % IOU calculation (intersection over union, also called Jaccard Index) for locating artifacts.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.945
Threshold uncertainty score0.759

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0020.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.087
GPT teacher head0.366
Teacher spread0.278 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations5
Published2022
Admission routes2
Has abstractyes

Explore more

Same venue2022 IEEE 10th International Conference on Healthcare Informatics (ICHI)Same topicAI in cancer detectionFrench-language works237,207