HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Medical Object Detection On Deeplesion

평가 지표

Sensitivity

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Sensitivity	Paper Title	Repository
P3D	88.55	Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training
MELD	86.6	Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets	-
Improved RetinaNet	82.36	Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels
MVP Net	83.64	MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
FCOS	86.05	An Efficient Anchor-free Universal Lesion Detection in CT-scans	-
AlignShift	86.83	Conditional Training with Bounding Map for Universal Lesion Detection	-
MULAN	85.22	MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation
DKMA-ULD	87.16	DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection	-
MP3D	86.74	Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices
3DCE	75.55	3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection

0 of 10 row(s) selected.