Scholarlink

<p>Ovarian cancer ranks as one of the primary causes of cancer-related deaths in women, and its timely detection is critical for improving survival outcomes. This paper proposed a novel model by leveraging the EfficientNet-B0 and light gradient boosting machine (LightGBM) models for the detection of ovarian cancer variants. EfficientNet-B0 is utilized for excellent feature extraction capabilities, employing deep features to achieve precise classification with LightGBM. In addition, Bayesian optimization is employed to fine-tune the model’s hyperparameters, significantly boosting the model’s effectiveness. The performance of the proposed model is evaluated on an ovarian cancer subtype classification dataset, and The Cancer Genome Atlas Ovarian Histological Images dataset. It achieved superior efficacy compared with baseline methods, validating its overall performance and robustness.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A hybrid deep learning based model for accurate ovarian cancer classification in smart healthcare systems

  • 期刊论文

  • 发表日期：

    2025年12月8日

查看全文
  • Ekta,
  • Vandana Bhatia

摘要

Ovarian cancer ranks as one of the primary causes of cancer-related deaths in women, and its timely detection is critical for improving survival outcomes. This paper proposed a novel model by leveraging the EfficientNet-B0 and light gradient boosting machine (LightGBM) models for the detection of ovarian cancer variants. EfficientNet-B0 is utilized for excellent feature extraction capabilities, employing deep features to achieve precise classification with LightGBM. In addition, Bayesian optimization is employed to fine-tune the model’s hyperparameters, significantly boosting the model’s effectiveness. The performance of the proposed model is evaluated on an ovarian cancer subtype classification dataset, and The Cancer Genome Atlas Ovarian Histological Images dataset. It achieved superior efficacy compared with baseline methods, validating its overall performance and robustness.