MétaCan
Menu
Back to cohort
Record W4414188134 · doi:10.18280/isi.300714

Lung Mass Identification Using Tiny Deep Learning Based on Lightweight MobileNet and Raspberry Pi 5 for Low Source Medical Diagnostic

2025· article· en· W4414188134 on OpenAlexvenueno aff
Yasir Salam Abdulghafoor, Auns Qusai Al-Neami, Ahmed Faeq Hussein

Bibliographic record

VenueIngénierie des systèmes d information · 2025
Typearticle
Languageen
FieldHealth Professions
TopicArtificial Intelligence in Healthcare
Canadian institutionsnot available
Fundersnot available
KeywordsDeep learningConvolutional neural networkRaspberry piSoftware deploymentIdentification (biology)Deep neural networks

Abstract

fetched live from OpenAlex

Medical imaging analysis has greatly benefited from deep learning, especially Convolutional Neural Networks (CNNs).However, their enormous parameter sizes and high computational cost restrict their use on low-resource systems.This paper suggests a small deep learning solution for resource-constrained contexts that uses a lightweight CNN, MobileNetV2, deployed on a Raspberry Pi 5 to enable lung mass identification from chest X-ray (CXR) pictures.A total of 2,322 NIH CXR pictures tagged as normal or mass were used to assess two iterations of the model: pretrained and trained from scratch.With just 3.4 million parameters and 300 million FLOPs, the pretrained MobileNetV2 obtained a validation accuracy of 95.25%, test accuracy of 89.9%, precision of 91.43%, and F1 score of 90.14%.A validation accuracy of 91.03%, test accuracy of 85.06%, precision of 88.24%, and F1 score of 85.21% were attained by the scratch-trained version.The results show that it is possible to implement precise CNN-based medical diagnostics on inexpensive, lowpower devices, which could increase access to AI-assisted healthcare in underprivileged areas.This study demonstrates the feasibility of a lightweight deep learning model for realtime lung mass detection in resource-constrained medical settings by presenting its end-toend deployment on the Raspberry Pi 5, from training to on-device inference.

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)0.002
metaresearch head score (Gemma)0.011
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.885
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.011
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0020.000
Scholarly communication0.0000.001
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 head0.031
GPT teacher head0.372
Teacher spread0.341 · 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 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 venueIngénierie des systèmes d informationSame topicArtificial Intelligence in HealthcareFrench-language works237,207