این سایت در حال حاضر پشتیبانی نمی شود و امکان دارد داده های نشریات بروز نباشند
Journal of Biostatistics and Epidemiology، جلد ۱۱، شماره ۱، صفحات ۱۵-۳۵
عنوان فارسی
چکیده فارسی مقاله
کلیدواژه‌های فارسی مقاله
عنوان انگلیسی A quantitative comparison between Focal loss and Binary Cross-Entropy loss in Brain Tumor Auto-segmentation using U-net
چکیده انگلیسی مقاله Purpose: Brain tumors are among the fatal cancers and cause the death of many people annually. Early diagnosis of a brain tumor can help save the patient’s life. Method: We have collected a dataset consisting of 314 brain MRI images in all planes taken by giving a contrast medium with the dimension of 800*512, which offers the highest resolution. First, skull stripping has been implemented to separate the brain from other parts in the images. Next, we have annotated the tumors in the images under the supervision of experienced radiologists to create ground truth. To determine the most effective model versions for all three loss functions, hyperparameter tuning was performed. Following the comparison, the study further evaluates the effectiveness of two loss functions, Binary Cross-Entropy (BCE) and Focal loss, specifically in handling tumor regions within the dataset. Result: The two proposed loss functions were evaluated using 5-fold cross-validation, and the average precision, recall, and f1 were 76.16%, 71.9%, and 74.52 for BCE loss and 82.92%, 79.32%, and 81% for the Focal loss on the test data, respectively. Moreover, the accuracy for BCE loss was 99.03% and 99.44% for the Focal loss. Conclusion: We recommend using BCE loss cautiously in classification tasks without data imbalance and emphasize the adoption of Focal loss for more accurate and reliable results in brain tumor segmentation.
کلیدواژه‌های انگلیسی مقاله
نویسندگان مقاله | Mahdi Shafiei Neyestanak
Tehran University of Medical Science


| Hamid Jahani
Tarbiat Modares University


| Mohsen Khodarahmi
Bahar imaging center


| Javad Zahiri
University of California San Diego


| Mostafa Hosseini
Tehran University of Medical Sciences


| Amirali Fatoorchi
K. N. Toosi University of Technology


| Mir Saeed Yekaninejad
Tehran University of Medical Sciences
نشانی اینترنتی https://jbe.tums.ac.ir/index.php/jbe/article/view/1594
فایل مقاله فایلی برای مقاله ذخیره نشده است
کد مقاله (doi)
زبان مقاله منتشر شده
موضوعات مقاله منتشر شده
نوع مقاله منتشر شده
برگشت به: صفحه اول پایگاه   |   نسخه مرتبط   |   نشریه مرتبط   |   فهرست نشریات