MétaCan
Menu
Back to cohort

Optimizing Breast Cancer Classification: A Comparative Study of Filter Pruning, Neuron Pruning, and Knowledge Distillation

2025· article· W7116986978 on OpenAlexaff
J Ephi Smily, Iwin Thanakumar Joseph, Mahendran Selvakumar, G Prabaharan, S. Velliangiri, Kiruthika M

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicAI in cancer detection
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsContext (archaeology)Deep learningDistillationBreast cancerFilter (signal processing)InferenceComputational model

Abstract

fetched live from OpenAlex

The application of deep learning (DL) in medical diagnostics, especially for breast cancer classification, has shown great potential in improving diagnostic accuracy. However, the computational complexity of these models poses significant challenges for deployment on edge devices and clinical systems. This paper explores various model compression techniques to optimize deep learning models without sacrificing predictive accuracy. Specifically, filter pruning, neuron pruning, and knowledge distillation are examined in the context of the ResNet50 model applied to the Breast Cancer Wisconsin (Diagnostic) dataset. The results show that while each compression technique effectively reduces model size and inference time, there are trade-offs in terms of accuracy. Knowledge distillation emerged as the most efficient approach, yielding a compact model with high accuracy and reduced computational requirements. The findings suggest that these compression techniques hold significant potential for deploying deep learning models in real-world medical applications where computational resources are limited.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.008
Version: metacan-v3-hybrid-931329e0061cValidation 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: Empirical
Teacher disagreement score0.011
Threshold uncertainty score0.022

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.008
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.060
GPT teacher head0.343
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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
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
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicAI in cancer detectionFrench-language works237,207