Scholarlink

<p>Automatic object detection is increasingly used in the medical field to enhance clinical workflows before, during, and after diagnosis of various conditions. One example is prostate detection and prostate volume estimation, which can aid in triaging patients for prostate cancer through risk-stratification using prostate-specific antigen density. In this paper, a baseline prostate detection framework is presented, highlighting that current state-of-the-art object detection models can detect the prostate in difficult to interpret surface-based ultrasound images. A 5-fold cross-validation study returned intersection-over-union, precision, recall, F1, and average-precision values above <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\({{\boldsymbol{0.7}}}\)</EquationSource> <EquationSource Format="MATHML"><math> <mi mathvariant="bold-italic">0.7</mi> </math></EquationSource> </InlineEquation> with real-time capabilities possible. Additionally, a simple size calculation based on the detection results showed high correlation with ground truth measurements, with Pearson Correlation Coefficients ranging from <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\({{\boldsymbol{0.55}}}\)</EquationSource> <EquationSource Format="MATHML"><math> <mi mathvariant="bold-italic">0.55</mi> </math></EquationSource> </InlineEquation> to <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\({{\boldsymbol{0.84}}}\)</EquationSource> <EquationSource Format="MATHML"><math> <mi mathvariant="bold-italic">0.84</mi> </math></EquationSource> </InlineEquation> for prostate volume estimates. These findings will contribute to the development of a real-time prostate detection and size estimation platform for prostate cancer risk-stratification to reduce unnecessary biopsy rates in healthcare systems.</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

Object detection as an aid for locating the prostate in surface-based abdominal ultrasound images

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月28日

查看全文
  • Rory D. Bennett,
  • Tristan Barrett,
  • Vincent J. Gnanapragasam,
  • Zion Tsz Ho Tse

摘要

Automatic object detection is increasingly used in the medical field to enhance clinical workflows before, during, and after diagnosis of various conditions. One example is prostate detection and prostate volume estimation, which can aid in triaging patients for prostate cancer through risk-stratification using prostate-specific antigen density. In this paper, a baseline prostate detection framework is presented, highlighting that current state-of-the-art object detection models can detect the prostate in difficult to interpret surface-based ultrasound images. A 5-fold cross-validation study returned intersection-over-union, precision, recall, F1, and average-precision values above \({{\boldsymbol{0.7}}}\) 0.7 with real-time capabilities possible. Additionally, a simple size calculation based on the detection results showed high correlation with ground truth measurements, with Pearson Correlation Coefficients ranging from \({{\boldsymbol{0.55}}}\) 0.55 to \({{\boldsymbol{0.84}}}\) 0.84 for prostate volume estimates. These findings will contribute to the development of a real-time prostate detection and size estimation platform for prostate cancer risk-stratification to reduce unnecessary biopsy rates in healthcare systems.