-
Applicaiton Required H11-M22_半監督式深度學習方法之分割方法
Update frequency Irregular Page view 2031 Downloads 0This dataset has no description
-
Applicaiton Required H11_M09_高解析度影像的高效率深度學習方法
Update frequency Irregular Page view 4355 Downloads 896Method The goal of the model is to use resnet50 with AMP(AUTOMATIC MIXED PRECISION) to accelerate the training speed and make a high-resolution skin cancer classification. Usage... -
Applicaiton Required H11-M107_Domain generalization for pathology image segmentation
Update frequency Irregular Page view 4497 Downloads 4使用特徵解偶和自適應實例歸一 化重構的域一般性分割模型，以最小化語義信息損失來解開特徵，以提升域一般性分割模型的準確度 -
Applicaiton Required H11-M13_持續性學習之物體偵測模型
Update frequency Irregular Page view 4071 Downloads 3Method 由於現有的病理影像資料集常是以實例分割的方式提供，為了達成更好的持續學習物件偵測效果，本方法於持續學習步驟中每次分為兩階段，於第一階段，先利用現有的持續學習語意分割方法SSUL, NeurIPS 2021生成語意分割先驗知識，再於第二階段以此先驗知識為額外輸入協助達成更好的持續學習物件偵測結果。 Usage 能用於持續性學習之細胞偵測模型... -
Applicaiton Required H11-M01_數位病理全玻片影像二元分類器
Update frequency Irregular Page view 5478 Downloads 7Abstract we propose, RankMix, a data augmentation method of mixing ranked features in a pair of WSIs. RankMix introduces the concepts of pseudo labeling and ranking in order to... -
Applicaiton Required H11-M104_基於多任務一致性之半監督肝腫瘤區域分割模型
Update frequency Irregular Page view 2791 Downloads 3使用半監督式學習訓練之肝臟腫瘤分割模型，利用多任務一致性正規化強化模型擷取影像特徵能力，以提升辨識準確性與Robustness -
Applicaiton Required H11-M114_CSFT
Update frequency Irregular Page view 6797 Downloads 5Histopathological images provide the medical evidences to help the disease diagnosis. However, manually reviewing these images by pathologists is very time consuming. Moreover,... -
Applicaiton Required H11-M23_弱監督式深度學習方法之分割方法
Update frequency Irregular Page view 3738 Downloads 0Common bile duct (CBD) stones caused diseases are life-threatening. Because CBD stones locate in the distal part of the CBD and have relatively small sizes, detecting CBD stones... -
Applicaiton Required H11-M115_CCA-MFNet
Update frequency Irregular Page view 3444 Downloads 0In this paper, we propose a novel criss-cross attention based multi-level fusion network to segment gastric intestinal metaplasia from narrow-band endoscopic images. Our network... -
Applicaiton Required H11-M116_ADMM-SRNet 基於 ADMM 與對比特徵之單分類稀疏表示網路
Update frequency Irregular Page view 1770 Downloads 0Method One-class classification aims to learn one-class models from only in-class training samples. Because of lacking out-of-class samples during training, most conventional... -
Applicaiton Required H11-M113_肝臟纖維分割模型
Update frequency Irregular Page view 3413 Downloads 5主要使用於肝臟纖維分割任務 -
Applicaiton Required H11-M112_基於對比式雙交叉偽監督之肝臟纖維化語意分割模型
Update frequency Irregular Page view 3012 Downloads 2肝臟纖維化之語意分割 -
Applicaiton Required H11-M111_基於空間一致性與對比噪聲標註學習的免疫細胞浸潤分割模型
Update frequency Irregular Page view 3103 Downloads 4使用於肝臟發炎細胞之分割任務 -
Applicaiton Required H11-M110_Domain Generalization with Background Consistency and Texture Reduct...
Update frequency Irregular Page view 3284 Downloads 2使用監督式學習訓練之肝細胞核分割模型，利用抗背景擾動一致性和紋理縮減的集合模型強化模型擷取影像特徵能力，以提升辨識準確性與Robustness -
Applicaiton Required H11-M109_基於課程式學習的完全感知脂肪肝油滴分割模型
Update frequency Irregular Page view 3150 Downloads 3使用課程式學習訓練，提升脂肪肝油滴分割模型對大小型油滴的偵測感知能力 -
Applicaiton Required H11-M108_基於合作式蒸餾的病理分割模型
Update frequency Irregular Page view 2906 Downloads 3利用合作式蒸餾提升大腸腫瘤分割模型效能 -
Applicaiton Required H11-M103_基於對比式聚類之胰臟腺癌不精確標注弱監督分割模型
Update frequency Irregular Page view 3225 Downloads 3使用對比式聚類的弱監督學習方式，從不精確標註資料取得更詳細的標註資訊，透過區塊方式訓練胰臟管線癌的辨識模型。模型會以影像分割方式取得胰臟腺癌區域。 -
Applicaiton Required H11-M102_在核心針活檢之多染色病理全切片影像之變型配準框架模型
Update frequency Irregular Page view 3726 Downloads 10本研究提出了一個核心針活檢組織配準框架。提出的框架主要包括三個主要步驟。 (1）自動去污；（2）通過剛性配準進行初始旋轉和定位；以及（3）變形配準。 -
Applicaiton Required H11-M101_MSCS: 基於異質模型協作多倍率一致性之半監督病理影像分割模型
Update frequency Irregular Page view 3054 Downloads 3使用多倍率半監督式學習訓練之分割模型，以在少量標註資料下提升辨識準確性與模型穩健性 -
Applicaiton Required H11-M105_ACC-GAN
Update frequency Irregular Page view 2960 Downloads 5利用標註一致性引導訓練病理影像的轉換預處理模型保留重要語意特徵，以維持AI模型在不同病理掃描器影像之效能