|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | M^(2)LC-Net: A Multi-Modal Multi-Disease Long-Tailed Classification Network for Real Clinical Scenes显示文摘Leveraging deep learning-based techniques to classify diseases has attracted extensive research interest in recent years.Nevertheless,most of the current studies only consider single-modal medical images,and the number of ophthalmic diseases that can be classified is relatively small.Moreover,imbalanced data distribution of different ophthalmic diseases is not taken into consideration,which limits the application of deep learning techniques in realistic clinical scenes.In this paper,we propose a Multimodal Multi-disease Long-tailed Classification Network(M^(2)LC-Net)in response to the challenges mentioned above.M^(2)LC-Net leverages ResNet18-CBAM to extract features from fundus images and Optical Coherence Tomography(OCT)images,respectively,and conduct feature fusion to classify 11 common ophthalmic diseases.Moreover,Class Activation Mapping(CAM)is employed to visualize each mode to improve interpretability of M^(2)LC-Net.We conduct comprehensive experiments on realistic dataset collected from a Grade III Level A ophthalmology hospital in China,including 34,396 images of 11 disease labels.Experimental results demonstrate effectiveness of our proposed model M^(2)LC-Net.Compared with the stateof-the-art,various performance metrics have been improved significantly.Specifically,Cohen’s kappa coefficient κ has been improved by 3.21%,which is a remarkable improvement. | Zhonghong Ou Wenjun Chai Lifei Wang Ruru Zhang Jiawen He Meina Song Lifei Yuan Shengjuan Zhang Yanhui Wang Huan Li Xin Jia Rujian Huang | 2021 | China Communications2021，18，9： | 0 |
| 2 | A mechanistic study of selective propane dehydrogenations on MoS_(2) supported single Fe atoms显示文摘On-purpose propane dehydrogenation(PDH) has emerged as a profitable alternative to the traditional cracking of oil products for propylene production. By means of density functional theory(DFT) calculations, the present work demonstrates that Fe atoms may atomically disperse on MoS_(2)(Fe_(1)/MoS_(2)) and serve as a promising single-atom catalyst(SAC) for PDH. The catalytic activity of Fe_(1)/MoS_(2)is attributed to the highly exposed d orbitals of single Fe atoms, while the propylene selectivity is originated from the kinetic inhibition of propylene dehydrogenation resulting from fast propenyl hydrogenation. The unique catalytic selectivity of Fe_(1)/MoS_(2)may inspire further investigations of on-purpose dehydrogenations of propane on SACs. | Yingke Yang Ruru Song Xing Fan Yunxia Liu Ningning Kong Haiping Lin Youyong Li | 2023 | Chinese Chemical Letters2023，34，2： | 0 |
| 3 | FSCIL-EACA:Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification显示文摘The ability to learn incrementally is critical to the long-term operation of AI systems.Benefiting from the power of few-shot class-incremental learning(FSCIL),deep learning models can continuously recognize new classes with only a few samples.The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes.Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters,but ignoring embedding network transferability and classifier adaptation(CA),failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes.In this paper,we propose a simple and novel approach from two perspectives:embedding bias and classifier bias.The method learns an embedding augmented(EA)network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias.Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias.We conduct extensive experiments on two popular natural image datasets and two medical datasets.The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results. | Ruru ZHANG Haihong E Meina SONG | 2024 | Chinese Journal of Electronics2024，33，1： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员