Search

The early diagnosis of lymph node metastasis in breast cancer is essential for enhancing treatment outcomes and overall prognosis. Unfortunately, pathologists often fail to identify small or subtle metastatic deposits, leading them to rely on cytokeratin stains for improved detection, although this approach is not without its flaws. To address the need for early detection, multiple-instance learning (MIL) has emerged as the preferred deep learning method for automatic tumor detection on whole slide images (WSIs). However, existing methods often fail to identify some small lesions due to insufficient attention to small regions. Attention-based multiple-instance learning (ABMIL)-based methods can be particularly problematic because they may focus too much on normal regions, leaving insufficient attention for small-tumor lesions. In this paper, we propose a new ABMIL-based model called normal representative keyset ABMIL (NRK-ABMIL), which addresseses this issue by adjusting the attention mechanism to give more attention to lesions. To accomplish this, the NRK-ABMIL creates an optimal keyset of normal patch embeddings called the normal representative keyset (NRK). The NRK roughly represents the underlying distribution of all normal patch embeddings and is used to modify the attention mechanism of the ABMIL. We evaluated NRK-ABMIL on the publicly available Camelyon16 and Camelyon17 datasets and found that it outperformed existing state-of-the-art methods in accurately identifying small tumor lesions that may spread over a few patches. Additionally, the NRK-ABMIL also performed exceptionally well in identifying medium/large tumor lesions.

Early detection and accurate segmentation of cerebral aneurysm is important for clinical diagnosis and prevention of rupture, which would be life threatening. 3D images can provide abundant information for characterizing the aneurysm. But the traditional manual segmentation of aneurysms takes lots of time and effort. Therefore, accurate and rapid automatic algorithm for 3D segmentation of aneurysm is needed. U-Net is a widely used deep learning network in medical image segmentation, but its performance is limited by the amount of data. In this challenge of aneurysm segmentation, we proposed to add attention gate and Models Genesis pretraining mechanisms to the classical U-Net model to improve the results. The dice of 3D U-net, 3D Attention U-Net, pretrained 3D U-Net and pretrained 3D Attention U-Net are 0.881, 0.884, 0.890 and 0.907, respectively. The experimental results show that the use of attention gate and Models Genesis can significantly improve the performance of U-Net model in segmenting aneurysms. This work achieved rank one in CADA 2020- Aneurysm Segmentation Challenge.

Early diagnosis and treatment of cerebral aneurysms are important for reducing the risk of aneurysm rupture. Fast and accurate detection of aneurysms on blood vessels is a key step in diagnosis of aneurysm. To date, a large number of deep learning algorithms, especially the UNet network, have been developed for detection of aneurysms. However, when the amount of data for training is small, it is difficult to obtain a reliable deep learning network to effectively identify aneurysms. In order to address this issue and improve the accuracy of aneurysm detection, here we proposed to combine the deep learning approach with specially designed preprocessing and postprocessing algorithm. We first determined the rough locations of the aneurysms based on the features on the vascular skeleton before aneurysms segmentation with deep learning network, i.e. 3D Attention UNet in this work, thus reducing the missed detection rate of the UNet network. We could obtain the shape and texture related to the aneurysm. Then we used the random forest algorithm to implement the feature classification model to find out the false aneurysms incorrectly detected by the U-Net network. The experimental results show that our method can accurately identify aneurysms in the case of small data sets.