Computation Time for Lung Cancer Histopathology Image Analysis Methods

Nepolian Vailankanni published a dataset on 2026-04-27 containing computation time metrics for various machine learning methods. The data, stored in a 5.5 KB XLS file, likely compares the performance of different techniques for lung cancer diagnosis from histopathological images. The research described used images from the LungHist700, LC25000, and TCGA UT datasets.

Use Cases

• Benchmarking the computational efficiency of different self-supervised learning techniques based on the described methods (Deep Cluster, BYOL, SimCLR).
• Comparing the runtime performance of feature selection methods like Minimum Redundancy Maximum Relevance (mRMR) against other approaches.
• Evaluating the computational cost of Vision Graph Convolutional Neural Network classifiers for medical image analysis.
• Analyzing trade-offs between model accuracy and computation time in lung cancer prediction pipelines.

Strengths

• Dataset is openly licensed under CC-BY-4.0.
• The associated research reports a balanced accuracy of 97% for the proposed method on the LungHist700 dataset.
• Methodology is described in detail, involving three public datasets (LungHist700, LC25000, TCGA UT).

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, suggesting limited scope.

Provenance

Source

figshare

Collection Method

Likely generated from experiments comparing machine learning methods for lung cancer diagnosis.

Time Range

null

Freshness

Last updated 2026-04-27 17:29:22; freshness should be verified.

Geography

null