MétaCan
Menu
Back to cohort
Record W4396689305 · doi:10.1016/j.aej.2024.04.072

An explainable transfer learning framework for multi-classification of lung diseases in chest X-rays

2024· article· en· W4396689305 on OpenAlex

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.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueAlexandria Engineering Journal · 2024
Typearticle
Languageen
FieldMedicine
TopicCOVID-19 diagnosis using AI
Canadian institutionsBrandon University
FundersNatural Sciences and Engineering Research Council of CanadaBrandon University
KeywordsInterpretabilityComputer scienceTransfer of learningArtificial intelligenceField (mathematics)Machine learningIdentification (biology)Deep learningProcess (computing)Data science

Abstract

fetched live from OpenAlex

In the field of medical imaging, the increasing demand for advanced computer-aided diagnosis systems is crucial in radiography. Accurate identification of various diseases, such as COVID-19, pneumonia, tuberculosis, and pulmonary lung nodules, holds vital significance. Despite substantial progress in the medical field, a persistent research gap necessitates the development of models that excel in precision and provide transparency in decision-making processes. In order to address this issue, this work introduces an approach that utilizes transfer learning through the EfficientNet-B4 architecture, leveraging a pre-trained model to enhance the classification performance on a comprehensive dataset of lung X-rays. The integration of explainable artificial intelligence (XAI), specifically emphasizing Grad-CAM, contributes to model interpretability by providing insights into the neural network’s decision-making process, elucidating the salient features and activation regions influencing multi-disease classifications. The result is a robust multi-disease classification system achieving an impressive 96% accuracy, accompanied by visualizations highlighting critical regions in X-ray images. This investigation not only advances the progression of computer-aided diagnosis systems but also sets a pioneering benchmark for the development of dependable and transparent diagnostic models for lung disease identification.

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)0.000
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: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.564
Threshold uncertainty score0.566

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 integrity0.0000.001
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 head0.035
GPT teacher head0.331
Teacher spread0.296 · 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