Efficient Multi-Organ Segmentation From 3D Abdominal CT Images With Lightweight Network and Knowledge Distillation.

Accurate segmentation of multiple abdominal organs from Computed Tomography (CT) images plays an important role in computer-aided diagnosis, treatment planning and follow-up. Currently, 3D Convolution Neural Networks (CNN) have achieved promising performance for automatic medical image segmentation tasks. However, most existing 3D CNNs have a large set of parameters and huge floating point operations (FLOPs), and 3D CT volumes have a large size, leading to high computational cost, which limits their clinical application. To tackle this issue, we propose a novel framework based on lightweight network and Knowledge Distillation (KD) for delineating multiple organs from 3D CT volumes. We first propose a novel lightweight medical image segmentation network named LCOV-Net for reducing the model size and then introduce two knowledge distillation modules (i.e., Class-Affinity KD and Multi-Scale KD) to effectively distill the knowledge from a heavy-weight teacher model to improve LCOV-Net's segmentation accuracy. Experiments on two public abdominal CT datasets for multiple organ segmentation showed that: 1) Our LCOV-Net outperformed existing lightweight 3D segmentation models in both computational cost and accuracy; 2) The proposed KD strategy effectively improved the performance of the lightweight network, and it outperformed existing KD methods; 3) Combining the proposed LCOV-Net and KD strategy, our framework achieved better performance than the state-of-the-art 3D nnU-Net with only one-fifth parameters. The code is available at https://github.com/HiLab-git/LCOVNet-and-KD.

HAMIL: High-Resolution Activation Maps and Interleaved Learning for Weakly Supervised Segmentation of Histopathological Images.

Semantic segmentation of histopathological images is important for automatic cancer diagnosis, and it is challenged by time-consuming and labor-intensive annotation process that obtains pixel-level labels for training. To reduce annotation costs, Weakly Supervised Semantic Segmentation (WSSS) aims to segment objects by only using image or patch-level classification labels. Current WSSS methods are mostly based on Class Activation Map (CAM) that usually locates the most discriminative object part with limited segmentation accuracy. In this work, we propose a novel two-stage weakly supervised segmentation framework based on High-resolution Activation Maps and Interleaved Learning (HAMIL). First, we propose a simple yet effective Classification Network with High-resolution Activation Maps (HAM-Net) that exploits a lightweight classification head combined with Multiple Layer Fusion (MLF) of activation maps and Monte Carlo Augmentation (MCA) to obtain precise foreground regions. Second, we use dense pseudo labels generated by HAM-Net to train a better segmentation model, where three networks with the same structure are trained with interleaved learning: The agreement between two networks is used to highlight reliable pseudo labels for training the third network, and at the same time, the two networks serve as teachers for guiding the third network via knowledge distillation. Extensive experiments on two public histopathological image datasets of lung cancer demonstrated that our proposed HAMIL outperformed state-of-the-art weakly supervised and noisy label learning methods, respectively. The code is available at https://github.com/HiLab-git/HAMIL.

[Automatic epileptic seizure detection algorithm based on dual density dual tree complex wavelet transform].

It is very important for epilepsy treatment to distinguish epileptic seizure and non-seizure. In this study, an automatic seizure detection algorithm based on dual density dual tree complex wavelet transform (DD-DT CWT) for intracranial electroencephalogram (iEEG) was proposed. The experimental data were collected from 15 719 competition data set up by the National Institutes of Health (NINDS) in Kaggle. The processed database consisted of 55 023 seizure epochs and 501 990 non-seizure epochs. Each epoch was 1 second long and contained 174 sampling points. Firstly, the signal was resampled. Then, DD-DT CWT was used for EEG signal processing. Four kinds of features include wavelet entropy, variance, energy and mean value were extracted from the signal. Finally, these features were sent to least squares-support vector machine (LS-SVM) for learning and classification. The appropriate decomposition level was selected by comparing the experimental results under different wavelet decomposition levels. The experimental results showed that the features selected in this paper were different between seizure and non-seizure. Among the eight patients, the average accuracy of three-level decomposition classification was 91.98%, the sensitivity was 90.15%, and the specificity was 93.81%. The work of this paper shows that our algorithm has excellent performance in the two classification of EEG signals of epileptic patients, and can detect the seizure period automatically and efficiently.