Lisha Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lisha Yao has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Zaiyi Liu
Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China; School of Medicine, South China University of Technology, Guangzhou, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
4 shared publications - Chu Han
Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
2 shared publications Ling Zhang
DAMO Academy, Alibaba Group, New York, NY
2 shared publicationsSuyun Li
Department of Radiology, Guangdong Provincial Peoples Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
2 shared publications- Suyun Li
Department of Radiology, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou 510080, China
2 shared publications - Xin Chen
Department of Radiology, Guangzhou First People’s Hospital, School of Medicine, South China University of Technology, Guangzhou, China
2 shared publications
Latest Publications
- 1 January 2026
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 8 (1) , e250145
Gastric Neoplasm Detection at Contrast-enhanced CT with Deep Learning
Gastric Neoplasm Detection with Artificial Intelligence (GANDA) automatically detected and diagnosed gastric neoplasms in a real-world consecutively collected test dataset using clinical routine contrast-enhanced abdominal CT scans.
- 1 January 2026
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 8 (1) , e250145
Gastric Neoplasm Detection at Contrast-enhanced CT with Deep Learning
Gastric Neoplasm Detection with Artificial Intelligence (GANDA) automatically detected and diagnosed gastric neoplasms in a real-world consecutively collected test dataset using clinical routine contrast-enhanced abdominal CT scans.
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (3) , 1412-1425
MsM-DPM: Multiscale Mamba Diffusion Probabilistic Model for Medical Image Segmentation
Diffusion probabilistic models (DPMs) have recently demonstrated promising performance in medical image segmentation. However, traditional DPM has difficulty handling the irregular structure of images and the inherent similarity between lesions and surrounding tissues. To overcome these challenges, we propose an innovative architecture, the multiscale Mamba DPM (MsM-DPM), designed to enhance medical image segmentation. Specifically, MsM-DPM introduces a multiscale attention fusion module (MSAFM) in a multiscale denoising UNet (Ms-DU) to capture lesion deformations from multilevel features, thereby enhancing the model’s robustness to shape and scale variations. Furthermore, in the segmentation network, a multilayer axial feature module (MLAFM) is used to adaptively aggregate the global context features from the Mamba encoder to enhance the expression of features in the spatial dimension by capturing axial multiscale features. The multilevel global context (MLGC) module is then used to reconstruct skip connections using graph convolutional network inference, and the enhanced features are assigned to each layer in the decoder to capture the contextual relationship of features. Finally, the feature fusion module (FFM) integrates deep features with upsampled features in the decoder, enhancing the network’s ability to capture lesion boundary details. Our MsM-DPM effectively encodes the semantic difference between lesions and background to improve the representation of their internal features. Extensive experiments on six datasets, LUNA16, ATM22, COVID-19, Self-collected datasets, Pancreas, and BT-MSD, show that the proposed MsM-DPM outperforms existing segmentation methods. Our code is publicly available at https://github.com/suhuaqiang/deep-learning
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (3) , 1412-1425
MsM-DPM: Multiscale Mamba Diffusion Probabilistic Model for Medical Image Segmentation
Diffusion probabilistic models (DPMs) have recently demonstrated promising performance in medical image segmentation. However, traditional DPM has difficulty handling the irregular structure of images and the inherent similarity between lesions and surrounding tissues. To overcome these challenges, we propose an innovative architecture, the multiscale Mamba DPM (MsM-DPM), designed to enhance medical image segmentation. Specifically, MsM-DPM introduces a multiscale attention fusion module (MSAFM) in a multiscale denoising UNet (Ms-DU) to capture lesion deformations from multilevel features, thereby enhancing the model’s robustness to shape and scale variations. Furthermore, in the segmentation network, a multilayer axial feature module (MLAFM) is used to adaptively aggregate the global context features from the Mamba encoder to enhance the expression of features in the spatial dimension by capturing axial multiscale features. The multilevel global context (MLGC) module is then used to reconstruct skip connections using graph convolutional network inference, and the enhanced features are assigned to each layer in the decoder to capture the contextual relationship of features. Finally, the feature fusion module (FFM) integrates deep features with upsampled features in the decoder, enhancing the network’s ability to capture lesion boundary details. Our MsM-DPM effectively encodes the semantic difference between lesions and background to improve the representation of their internal features. Extensive experiments on six datasets, LUNA16, ATM22, COVID-19, Self-collected datasets, Pancreas, and BT-MSD, show that the proposed MsM-DPM outperforms existing segmentation methods. Our code is publicly available at https://github.com/suhuaqiang/deep-learning
- 29 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 284
Multi-phase feature-aligned fusion model for automated colorectal cancer segmentation in contrast-enhanced CT scans
- 29 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 284
Multi-phase feature-aligned fusion model for automated colorectal cancer segmentation in contrast-enhanced CT scans
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (4) , 7395-7406
A Colorectal Coordinate-Driven Method for Colorectum and Colorectal Cancer Segmentation in Conventional CT Scans
Automated colorectal cancer (CRC) segmentation in medical imaging is the key to achieving automation of CRC detection, staging, and treatment response monitoring. Compared with magnetic resonance imaging (MRI) and computed tomography colonography (CTC), conventional computed tomography (CT) has enormous potential because of its broad implementation, superiority for the hollow viscera (colon), and convenience without needing bowel preparation. However, the segmentation of CRC in conventional CT is more challenging due to the difficulties presenting with the unprepared bowel, such as distinguishing the colorectum from other structures with similar appearance and distinguishing the CRC from the contents of the colorectum. To tackle these challenges, we introduce DeepCRC-SL, the first automated segmentation algorithm for CRC and colorectum in conventional contrast-enhanced CT scans. We propose a topology-aware deep learning-based approach, which builds a novel 1-D colorectal coordinate system and encodes each voxel of the colorectum with a relative position along the coordinate system. We then induce an auxiliary regression task to predict the colorectal coordinate value of each voxel, aiming to integrate global topology into the segmentation network and thus improve the colorectum’s continuity. Self-attention layers are utilized to capture global contexts for the coordinate regression task and enhance the ability to differentiate CRC and colorectum tissues. Moreover, a coordinate-driven self-learning (SL) strategy is introduced to leverage a large amount of unlabeled data to improve segmentation performance. We validate the proposed approach on a dataset including 227 labeled and 585 unlabeled CRC cases by fivefold cross-validation. Experimental results demonstrate that our method outperforms some recent related segmentation methods and achieves the segmentation accuracy in DSC for CRC of 0.669 and colorectum of 0.892, reaching to the performance (at 0.639 and 0.890, respectively) of a medical resident with two years of specialized CRC imaging fellowship.
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (4) , 7395-7406
A Colorectal Coordinate-Driven Method for Colorectum and Colorectal Cancer Segmentation in Conventional CT Scans
Automated colorectal cancer (CRC) segmentation in medical imaging is the key to achieving automation of CRC detection, staging, and treatment response monitoring. Compared with magnetic resonance imaging (MRI) and computed tomography colonography (CTC), conventional computed tomography (CT) has enormous potential because of its broad implementation, superiority for the hollow viscera (colon), and convenience without needing bowel preparation. However, the segmentation of CRC in conventional CT is more challenging due to the difficulties presenting with the unprepared bowel, such as distinguishing the colorectum from other structures with similar appearance and distinguishing the CRC from the contents of the colorectum. To tackle these challenges, we introduce DeepCRC-SL, the first automated segmentation algorithm for CRC and colorectum in conventional contrast-enhanced CT scans. We propose a topology-aware deep learning-based approach, which builds a novel 1-D colorectal coordinate system and encodes each voxel of the colorectum with a relative position along the coordinate system. We then induce an auxiliary regression task to predict the colorectal coordinate value of each voxel, aiming to integrate global topology into the segmentation network and thus improve the colorectum’s continuity. Self-attention layers are utilized to capture global contexts for the coordinate regression task and enhance the ability to differentiate CRC and colorectum tissues. Moreover, a coordinate-driven self-learning (SL) strategy is introduced to leverage a large amount of unlabeled data to improve segmentation performance. We validate the proposed approach on a dataset including 227 labeled and 585 unlabeled CRC cases by fivefold cross-validation. Experimental results demonstrate that our method outperforms some recent related segmentation methods and achieves the segmentation accuracy in DSC for CRC of 0.669 and colorectum of 0.892, reaching to the performance (at 0.639 and 0.890, respectively) of a medical resident with two years of specialized CRC imaging fellowship.
- 7 September 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12329, 143-285
Research on sentiment analysis of hotel reviews based on Word2vec method
This paper takes sentiment analysis as the research direction and collects the data of users' comments on hotel rooms. The research methods used include text corpus preprocessing, Word2vec model, support vector machine, AUC value calculation, feature classification based on supervised learning method, emotion analysis and ordered logistic regression model, etc. Word2vec is used to map words into k-dimensional vector space, and PCA algorithm is used to reduce the dimensionality of the results. According to Word2vec, the comment corpus can be divided into 7 categories of feature dimensions, and then feature recognition is carried out, and emotion scores are calculated by emotion analysis technology. Finally, classify and summarize the emotional scores of each comment in different feature categories. In this paper, through the establishment of Word2vec model, the analysis of consumers' emotional tendency to the hotel, to provide the direction of improving the service level for the hotel, is conducive to the management and development of the hotel.
- 7 September 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12329, 143-285
Research on sentiment analysis of hotel reviews based on Word2vec method
This paper takes sentiment analysis as the research direction and collects the data of users' comments on hotel rooms. The research methods used include text corpus preprocessing, Word2vec model, support vector machine, AUC value calculation, feature classification based on supervised learning method, emotion analysis and ordered logistic regression model, etc. Word2vec is used to map words into k-dimensional vector space, and PCA algorithm is used to reduce the dimensionality of the results. According to Word2vec, the comment corpus can be divided into 7 categories of feature dimensions, and then feature recognition is carried out, and emotion scores are calculated by emotion analysis technology. Finally, classify and summarize the emotional scores of each comment in different feature categories. In this paper, through the establishment of Word2vec model, the analysis of consumers' emotional tendency to the hotel, to provide the direction of improving the service level for the hotel, is conducive to the management and development of the hotel.
- 16 March 2020
- Published by SPIE-Intl Soc Optical Eng
- Vol. 11312, 113124B-156
Non-local texture learning approach for CT imaging problems using convolutional neural network
Deep learning-based algorithms have been widely used in the low-dose CT imaging field, and have achieved promising results. However, most of these algorithms only consider the information of the desired CT image itself, ignoring the external information that can help improve the imaging performance. Therefore, in this study, we present a convolutional neural network for low-dose CT reconstruction with non-local texture learning (NTL-CNN) approach. Specifically, different from the traditional network in CT imaging, the presented NTL- CNN approach takes into consideration the non-local features within the adjacent slices in 3D CT images. Then, both low-dose target CT images and the non-local features feed into the residual network to produce desired high-quality CT images. Real patient datasets are used to evaluate the performance of the presented NTL-CNN. The corresponding experiment results demonstrate that the presented NTL-CNN approach can obtain better CT images compared with the competing approaches, in terms of noise-induced artifacts reduction and structure details preservation.
- 16 March 2020
- Published by SPIE-Intl Soc Optical Eng
- Vol. 11312, 113124B-156
Non-local texture learning approach for CT imaging problems using convolutional neural network
Deep learning-based algorithms have been widely used in the low-dose CT imaging field, and have achieved promising results. However, most of these algorithms only consider the information of the desired CT image itself, ignoring the external information that can help improve the imaging performance. Therefore, in this study, we present a convolutional neural network for low-dose CT reconstruction with non-local texture learning (NTL-CNN) approach. Specifically, different from the traditional network in CT imaging, the presented NTL- CNN approach takes into consideration the non-local features within the adjacent slices in 3D CT images. Then, both low-dose target CT images and the non-local features feed into the residual network to produce desired high-quality CT images. Real patient datasets are used to evaluate the performance of the presented NTL-CNN. The corresponding experiment results demonstrate that the presented NTL-CNN approach can obtain better CT images compared with the competing approaches, in terms of noise-induced artifacts reduction and structure details preservation.