MétaCan
Menu
Back to cohort
Record W4313031617 · doi:10.1145/3545729.3545731

Exploring a Universal Training Method for Medical Image Classification

2022· article· en· W4313031617 on OpenAlexaff
Han Ding, Kun Yan, Zheyan Tu, Ping Wang

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldMedicine
TopicCOVID-19 diagnosis using AI
Canadian institutionsMcGill University
Fundersnot available
KeywordsComputer scienceArtificial intelligenceModalitiesMachine learningContextual image classificationSupervised learningImage (mathematics)Pattern recognition (psychology)Deep learningField (mathematics)Artificial neural networkMathematics

Abstract

fetched live from OpenAlex

In recent years, with the application of deep learning technology in the field of medical image analysis, computer-aided medical image classification can help doctors diagnose and treat patients better. However, due to the particularity of medical images, the performance of traditional image processing is not satisfactory to all medical images. Self-supervised pretraining followed by supervised finetuning has seen success in image recognition, but has received limited attention in medical image classification. In this paper, we propose a method based on self-supervised pretraining and supervised finetuning. In the pretraining step, we train our backbone on unlabeled ImageNet and MedMNIST to learn different types of image features. In the finetuning step, we carefully compare our training method in two modalities with several mainstream methods. Our pretraining method outperforms supervised baselines pretrained on ImageNet. In addition, we show that with suitable pretraining method adopted, our proposed method could be reused on several similar tasks with little modification.

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)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.728
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
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 integrity0.0000.000
Insufficient payload (model declined to judge)0.0020.000

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 head0.307
GPT teacher head0.418
Teacher spread0.110 · 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 designNot applicable
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

Citations2
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicCOVID-19 diagnosis using AIFrench-language works237,207