MétaCan
Menu
Back to cohort
Record W4409651419 · doi:10.23977/jaip.2025.080206

A two-stage cervical pathology cell detection model based on YOLOv7x and K-means

2025· article· en· W4409651419 on OpenAlexvenueno aff

Bibliographic record

VenueJournal of Artificial Intelligence Practice · 2025
Typearticle
Languageen
FieldComputer Science
TopicAI in cancer detection
Canadian institutionsnot available
Fundersnot available
KeywordsStage (stratigraphy)PathologyMedicineComputer scienceBiologyPaleontology

Abstract

fetched live from OpenAlex

As a malignant tumour that seriously threatens women's health, early diagnosis of cervical cancer is crucial to improve the cure rate. Cervical pathological cell detection is a key link in the early diagnosis of cervical cancer, but the traditional detection methods have the problems of low efficiency and accuracy relying on manual work. In this study, we combined the YOLOv7x target detection model with K-means clustering algorithm to construct a two-stage model YOLOv7x-CH for cervical pathological cell detection. To address the problems in the detection of cervical pathological cells of High-grade Squamous Intraepithelial Lesion (HSIL) category, we firstly constructed the To address the problems in the detection of HSIL, we first constructed the YOLOv7x baseline model, extracted the nucleoplasmic ratio features based on fine segmentation and grey scale symbiosis matrix texture features from the HSIL samples, and then constructed the two-stage model YOLOv7x-CH through K-means clustering. The experimental results show that compared with the baseline model, the two-stage model YOLOv7x-CH can improve the accuracy of cervical pathological cell detection from 0.56 to 0.813, and the average accuracy AP from 0.556 to 0.591, which effectively improves the accuracy of cervical pathological cell detection, and provides a more reliable technical support for the early diagnosis of cervical cancer.

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)0.002
metaresearch head score (Gemma)0.001
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: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.875
Threshold uncertainty score0.624

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
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 head0.034
GPT teacher head0.335
Teacher spread0.301 · 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
GenreMethods

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
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Artificial Intelligence PracticeSame topicAI in cancer detectionFrench-language works237,207