Weight Pruning‑UNet: Weight Pruning UNet with Depth‑wise Separable Convolutions for Semantic Segmentation of Kidney Tumors
سال انتشار: 1401
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 78
فایل این مقاله در 6 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JMSI-12-2_001
تاریخ نمایه سازی: 28 تیر 1402
چکیده مقاله:
Background: Accurate semantic segmentation of kidney tumors in computed tomography (CT)
images is difficult because tumors feature varied forms and occasionally, look alike. The KiTs۱۹
challenge sets the groundwork for future advances in kidney tumor segmentation. Methods: We
present weight pruning (WP)‑UNet, a deep network model that is lightweight with a small scale;
it involves few parameters with a quick assumption time and a low floating‑point computational
complexity. Results: We trained and evaluated the model with CT images from ۲۱۰ patients. The
findings implied the dominance of our method on the training Dice score (۰.۹۸) for the kidney tumor
region. The proposed model only uses ۱,۲۹۷,۴۴۱ parameters and ۷.۲e floating‑point operations, three
times lower than those for other network models. Conclusions: The results confirm that the proposed
architecture is smaller than that of UNet, involves less computational complexity, and yields good
accuracy, indicating its potential applicability in kidney tumor imaging.
کلیدواژه ها:
نویسندگان
Patike Kiran Rao
Department of Computer Science and Engineering, MS Ramaiah University of Applied Sciences
Subarna Chatterjee
Department of Computer Science and Engineering, Faculty of Engineering and Technology, MS Ramaiah University of Applied Sciences, Bengaluru, Karnataka
Sreedhar Sharma
۳Department of Nephrology, Kurnool Medical College, Kurnool, Andra Pradesh, India