Contrast enhancement boosts cervical cancer classification accuracy in CNNs

A new research paper published on arXiv explores the effectiveness of image preprocessing techniques for improving cervical cancer classification using deep learning models. The study evaluated two methods, a PMD filter for noise reduction and CLAHE for contrast enhancement, across three CNN architectures: ResNet-34, MobileNet-V2, and DenseNet-121. Results indicated that CLAHE significantly boosted classification accuracy for ResNet-34 and DenseNet-121, while the PMD filter showed limited improvement and slightly degraded MobileNet-V2 performance, suggesting contrast enhancement is more beneficial than noise reduction for this task. AI

IMPACT Demonstrates that contrast enhancement techniques can significantly improve the accuracy of deep learning models in medical image classification tasks.

RANK_REASON Research paper published on arXiv detailing a systematic comparison of image preprocessing techniques for medical image classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• cervix uterine cancer
• CNN
• Contrast Limited Adaptive Histogram Equalization
• DenseNet 121
• MobileNetV2
• Pap test
• PMD filter
• ResNet-34
• SIPaKMeD

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →