MétaCan
Menu
Back to cohort
Record W7132967250

Deep Learning for Cell Segmentation in Cervical and Vaginal Samples

2023· dissertation· W7132967250 on OpenAlexaff
Harrison Edwards

Bibliographic record

VenueTSpace · 2023
Typedissertation
Language
FieldBiochemistry, Genetics and Molecular Biology
TopicSingle-cell and spatial transcriptomics
Canadian institutionsVector Institute
Fundersnot available
KeywordsDeep learningSegmentationDigital image analysisImage segmentationSupervised learningPattern recognition (psychology)Automation
DOInot available

Abstract

fetched live from OpenAlex

Deep Learning has emerged as a quintessential tool for the 21st century. Herein, current state-of-the-art deep learning methods for image analysis are employed alongside a hardware platform to two sample types in the field of sexual and reproductive health: cervical cytobrush samples and vaginal swab samples. These samples constitute hurdles that are of paramount importance for healthcare but are neglected by the scientific community due to the difficulty inherent in their acquisition and processing.The common thread for this work is segmentation of cells, but the applications are unique. First, a hardware platform is introduced that uses digital microfluidics alongside a Q-switched laser to acquire the contents of a single cell for downstream processing. Cells are selected for lysis via a deep learning segmentation model, and it is shown that the contents retrieved are suitable for downstream analysis by genomics, transcriptomics, or proteomics. A paper describing this Digital Isolation of Single Cells for ‘Omics (DISCO) platform was published. Second, the difficulty of identifying cells in cervical cytobrush samples for analysis is addressed. Cervical cytobrush samples have great potential for non-invasive prenatal testing. However, these samples also contain a comparatively overwhelming number of maternal cells. A deep-learning – and machine learning – method is introduced and discussed as a potential method for discerning fetal from maternal cell type via morphological and fluorescent marker affinity characteristics. Finally, the problem of identifying cells in vaginal swab samples is examined, focusing on the processing of evidence in sexual assault crimes. In this context, a critical first step is the detection and quantification of sperm cells – which serves to inform technicians of the validity of the claimant’s statement, the time since the event occurred, and the care that will be required to process the sample – with low cell number samples requiring higher care. Presented here is a fully automated deep-learning method that uses only brightfield microscopy to quantify sperm cells within vaginal swab samples in less than 10 minutes.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.138
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0010.000
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 head0.022
GPT teacher head0.307
Teacher spread0.284 · 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.

Study designBench or experimental
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 venueTSpaceSame topicSingle-cell and spatial transcriptomicsFrench-language works237,207