MétaCan
Menu
Back to cohort

Lightseg: Efficient Yet Effective Medical Image Segmentation

2022· article· en· W4225004743 on OpenAlex
Most Husne Jahan, Abdullah-Al-Zubaer Imran

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venue2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI) · 2022
Typearticle
Languageen
FieldMedicine
TopicCOVID-19 diagnosis using AI
Canadian institutionsToronto Metropolitan University
Fundersnot available
KeywordsRobustness (evolution)Computer scienceSegmentationImage segmentationArtificial intelligenceMarket segmentationDeep learningScale-space segmentationSegmentation-based object categorizationSeparable spaceComputer visionImage (mathematics)Pattern recognition (psychology)Machine learningMathematics

Abstract

fetched live from OpenAlex

While recent development in deep learning-based medical image segmentation has been fascinating, effectiveness mostly comes with the expense of expensive computing resources. In search of more affordable and convenient solutions, we propose a lightweight and faster yet effective medical image segmentation approach namely LightSeg. LightSeg leverages separable convolutional layers to decrease the model parameters and an attention mechanism to maintain segmentation quality. Our experimental evaluations on two different backbone networks (U-Net and ResU-Net) in segmenting the lungs from two publicly available chest X-ray datasets demonstrate the robustness of LightSeg while substantially reducing the network parameters.

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.

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)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.620
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0080.000

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 head0.009
GPT teacher head0.315
Teacher spread0.306 · 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