Prostate lesion segmentation from MR images using deep learning methods

Erkuş İ., Bayram B., Uzar A. M., Çakar T.

7thAdvanced Engineering Days(AED), Mersin, Türkiye, 09 Temmuz 2023, ss.41-43

  • Yayın Türü: Bildiri / Özet Bildiri
  • Basıldığı Şehir: Mersin
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.41-43
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet



for prostate lesion segmentation from MR images. The study explores state-of-the-art deep learning models, including U-Net, PAN, DeepLabV3, DeepLabV3+ for segmentation. A large PICAI dataset of prostate MR images, comprising multi-parametricMRI scans and expert annotations, is utilized for evaluating the developed methods. Performance metrics such as accuracy, precision, recall, specificity, accuracy, IOU, AP Score, PR curve, and AUC curve were employed to compare the proposed deep learning methods. In summary, this research contributes to the field of prostate lesion segmentation by investigating the effectiveness of deep learning methods applied to MR images. The DeepLabV3+ model achieves an IOU of 0.79 and an AP of 0.54 using JaccardLos



for prostate lesion segmentation from MR images. The study explores state-of-the-art deep learning models, including U-Net, PAN, DeepLabV3, DeepLabV3+ for segmentation. A large PICAI dataset of prostate MR images, comprising multi-parametricMRI scans and expert annotations, is utilized for evaluating the developed methods. Performance metrics such as accuracy, precision, recall, specificity, accuracy, IOU, AP Score, PR curve, and AUC curve were employed to compare the proposed deep learning methods. In summary, this research contributes to the field of prostate lesion segmentation by investigating the effectiveness of deep learning methods applied to MR images. The DeepLabV3+ model achieves an IOU of 0.79 and an AP of 0.54 using JaccardLos