Back to all available

A lightweight Texture-Aware Deep Convolutional Neural Network (TADCNN) for histopathological classification of lung cancer

algorithms-and-analysis-of-algorithms
artificial-intelligence
computer-vision
data-mining-and-machine-learning
neural-networks

Abstract

Background: Accurate lung–cancer subtype classification from microscopic tissue images is difficult because textures are highly similar and morphological differences are subtle. Recent, CNN/Transformer approaches can be accurate. However, their heavy backbones introduce high latency and memory demands and offer limited mechanisms to encode pathology–specific texture priors, constraining clinical deployment. Method: We present TADCNN, a lightweight, texture-aware CNN that operates across modalities (histology tiles and CT slices) without architecture changes. TADCNN couples a scale-conditional multiscale texture encoder (SC-PTEM) with a texture-aware attention module (TAAM). Results: Together, these modules jointly model spatial and channel saliency. Under the same training protocol, TADCNN attains 99.84% accuracy on LC25000 and 99.55% on IQ-OTH/NCCD. It outperforms heavy CNN/Transformer backbones and lightweight mobile baselines (MobileNetV2, ShuffleNetV2). Despite higher accuracy, TADCNN uses fewer parameters and FLOPs than the mobile baselines and runs in real time, enabling point-of-care deployment. These results show that careful multi-scale texture encoding plus joint spatial + channel attention delivers state-of-the-art accuracy with deployable efficiency and cross-modal versatility.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].