article · Advances in respiratory medicine
A diagnostic framework has been evaluated for lung and colon cancer classification using deep learning architectures, specifically DenseNet, ResNet50, and MobileNet models. Tested across multiple data splits including 70-30, 80-20, and 90-10 ratios, the classification system achieves up to 100 percent accuracy. Robust performance is further supported by five-fold and ten-fold cross-validation assessments alongside F1-scores that consistently exceed 99.9 percent. Alongside automated classification, the framework integrates functionalities for real-time notifications and secure remote clinical consultations. These tools are designed to increase the overall efficiency and transparency of diagnostic workflows. By facilitating rapid communication and highly accurate disease screening, the approach aims to support streamlined cancer care management and contribute towards improved patient outcomes.
Accurate and transparent diagnostic tools can significantly assist clinical teams in detecting lung and colon cancers. Combining near-perfect classification performance with real-time alerting and remote consultation features helps speed up diagnosis, reduce administrative friction, and enable timely clinical interventions, ultimately supporting better patient care management.
This framework could serve as a clinical decision-support and teleconsultation platform for hospital oncology departments and diagnostic imaging centres. Based on the reported validation metrics and data split testing, the software represents applied research tested in computational settings, needing clinical trials and regulatory clearance before reaching commercial market deployment.
AI-generated from the published abstract. Always read the original work before citing.
The proposed framework achieves an impressive accuracy of 100% for lung and colon cancer classification using DenseNet, ResNet50, and MobileNet models with different split ratios (70-30, 80-20, 90-10). The <i>F</i>1-<i>score</i> and k-fold cross-validation accuracy (5-fold and 10-fold) also demonstrate exceptional performance, with values exceeding 99.9%. Real-time notifications and secure remote consultations enhance the efficiency and transparency of the diagnostic process, contributing to better patient outcomes and streamlined cancer care management.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/arm92050037
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
