{
  "id": 80881,
  "title": "Fuzzy based residual shufflenet based breast cancer detection using mammogram images",
  "url": "https://urgent.news/2026/08/03/fuzzy-based-residual-shufflenet-based-breast-cancer-detection-using",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-03T00:00:00.000Z",
  "source": {
    "name": "Scientific Reports",
    "slug": "scientific-reports",
    "url": "https://www.nature.com/articles/s41598-026-63858-5"
  },
  "original_language": "en",
  "account": "Breast cancer is a condition where abnormal breast cells grow and divide uncontrollably, leading to the formation of cancerous tissue. Early detection of breast cancer plays a crucial role in improving survival rates and diagnostic outcomes. Although various Deep Learning (DL) frameworks have been proposed for detecting breast cancer, achieving accurate results remains a challenging task.\n\nTo address this issue, researchers have proposed the Fuzzy-based Residual-ShuffleNet (Fuzzy RS-Net) for detecting breast cancer using mammogram images. The process begins with preprocessing, where the mammogram image is filtered in the wavelet domain to reduce noise. Next, Object Segmentation Network (O-SegNet) is utilized to segregate the affected region. Subsequently, image augmentation techniques, such as rotation, shifting, and erasing, are applied. Feature extraction is performed by extracting texture features, Pyramid Histogram of Oriented Gradients (PHOG), and Weber Local Binary Pattern (WLBP).\n\nThe Fuzzy RS-Net leverages these extracted features to detect breast cancer. Its architecture is derived by merging the Deep Residual Network (DRN), the Fuzzy concept, and ShuffleNet. In extensive testing, the developed Fuzzy RS-Net demonstrated remarkable performance, achieving the highest accuracy of 94.999%, sensitivity of 95.899%, and specificity of 93.889%.\n\nAccording to the World Health Organization (WHO), breast cancer is the most common malignancy causing a high death rate in women. In 2018, over 2.1 million women were diagnosed with breast cancer globally, and by the end of 2020, more than 2.3 million women had been diagnosed. WHO reports that over 685,000 women died from breast cancer worldwide in 2020. Thus, preventing breast cancer and ensuring early detection at the preliminary stage is of utmost importance.\n\nWhile mammography is the most widely used screening method for breast cancer, even specialist radiologists often struggle to detect abnormalities during the early stages of cancer. Nevertheless, mammography plays a vital role in identifying approximately 80-90% of breast cancer cases in women. By detecting doubtful areas in X-ray images, mammography supports early diagnosis and reduces the risk of the disease progressing. Moreover, computer-aided detection, digital mammography, and breast tomosynthesis have shown promise in enhancing the accuracy of breast cancer detection.",
  "summary": "Scientific Reports, Published online: 03 August 2026; doi:10.1038/s41598-026-63858-5 Fuzzy based residual shufflenet based breast cancer detection using mammogram images",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}