MétaCan
Menu
Back to cohort
Record W4386849477 · doi:10.54254/2753-8818/5/20230386

Function tissue unit segmentation based on UNext model

2023· article· en· W4386849477 on OpenAlexaff
Hongyu Sun, Qi Zhang, Qiangdi Zhang, Zifeng Zhou

Bibliographic record

VenueTheoretical and Natural Science · 2023
Typearticle
Languageen
FieldComputer Science
TopicAI in cancer detection
Canadian institutionsDalhousie University
Fundersnot available
KeywordsComputer sciencePyramid (geometry)SegmentationPoolingArtificial intelligenceInferencePattern recognition (psychology)Image segmentationData miningComputer visionMathematics

Abstract

fetched live from OpenAlex

Accurate segmentation for Functional Tissue Units (FTUs) is a challenging issue in past decades. In this study, a model using the dataset of tissue section images will be built to evaluate and mark FTUs across five human organs as clearly as possible. We have the Human Protein Atlas (HPA) as training data and the data from Human BioMolecular Atlas Program (HuBMAP) as testing data. To balance accuracy and inference speed, this study applied Unext, an efficient network based on Unet, as the basic model. We also aim to use some tricks to further improve the performance of the model. First, we used several image enhancement methods to diversify the input image. Second, several structures like Feature Pyramid Network (FPN) and the Atrous Spatial Pyramid Pooling are added to improve model performance and convergence speed. As a result, we successfully segment functional tissue units among images of different sizes. Our proposed model scored 0.56 out of 1.00 by the judge of the competition.

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: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.825
Threshold uncertainty score0.248

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.012
GPT teacher head0.274
Teacher spread0.262 · 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 designTheoretical or conceptual
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

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueTheoretical and Natural ScienceSame topicAI in cancer detectionFrench-language works237,207