Training workflows for the PSN framework.

Training workflows for the PSN framework.

<p>(a) PSN<sub>adaptive</sub>: the model is fine-tuned on cumulatively increasing fractions and tested on subsequent ones. (b) PSN<sub>sequence</sub>: the model is sequentially fine-tuned using the previously trained weights for each next fraction. DL<sub>g</su...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Joonil Hwang (22278797) (author)
مؤلفون آخرون: Byung-Hee Kang (13264776) (author), Younghee Park (1430620) (author), Dong Hyeok Choi (12562048) (author), Jin Sung Kim (679262) (author), Seungryong Cho (4857196) (author), Eungman Lee (11219256) (author)
منشور في: 2025
الموضوعات:
Cell Biology
Genetics
Molecular Biology
Biotechnology
Cancer
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
swin unetr architecture
streamlining workflow efficiency
static personalization methods
percentile hausdorff distance
mean surface distance
ethos therapy system
dice similarity coefficient
daily anatomical variations
daily anatomical changes
clinical target volume
beam computed tomography
anatomically complex regions
743 &# 8201
035 &# 8201
segmentation using cone
efficient auto segmentation
tuning via psn
th </ sup
div >< p
psn framework uses
improving segmentation precision
dsc ), 95
psn framework
specific segmentation
segmentation performance
training followed
stage strategy
specific network
specific fine
potentially reducing
physician contours
manual editing
manual corrections
initial pre
hd ),
findings support
fifth fraction
deformable registration
continuously adapts
clinically feasible
adaptive radiotherapy
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

مواد مشابهة