Xuefan Zha

Shifted Chunk Transformer for Spatio-Temporal Representational Learning

Cornell University - arXiv, Dec 6, 2021

Spatio-temporal representational learning has been widely adopted in various fields such as actio... more Spatio-temporal representational learning has been widely adopted in various fields such as action recognition, video object segmentation, and action anticipation. Previous spatio-temporal representational learning approaches primarily employ ConvNets or sequential models, e.g., LSTM, to learn the intra-frame and interframe features. Recently, Transformer models have successfully dominated the study of natural language processing (NLP), image classification, etc. However, the pure-Transformer based spatio-temporal learning can be prohibitively costly on memory and computation to extract fine-grained features from a tiny patch. To tackle the training difficulty and enhance the spatio-temporal learning, we construct a shifted chunk Transformer with pure self-attention blocks. Leveraging the recent efficient Transformer design in NLP, this shifted chunk Transformer can learn hierarchical spatio-temporal features from a local tiny patch to a global video clip. Our shifted self-attention can also effectively model complicated inter-frame variances. Furthermore, we build a clip encoder based on Transformer to model long-term temporal dependencies. We conduct thorough ablation studies to validate each component and hyper-parameters in our shifted chunk Transformer, and it outperforms previous state-of-the-art approaches on Kinetics-400, Kinetics-600, UCF101, and HMDB51.

Download

Radiomic Signature of Computed Tomography Imaging for Prediction of Survival and Chemotherapeutic Benefits in Gastric Cancer

Social Science Research Network, 2018

Toward automated interpretation of electromyography for intraoperative neurophysiological monitoring using machine learning

Intraoperative neurophysiological monitoring is used during neurosurgery to assess the functional... more Intraoperative neurophysiological monitoring is used during neurosurgery to assess the functional integrity of nerves and alert the surgeon to prevent damage. In current clinical IONM, the neurophysiological data are interpreted in real time by a specialist. This processing by humans is subjective and introduces inter-subject variability into the process. In order to standardize this process and reduce cognitive load on human users, this paper presents a preliminary investigation of the use of machine learning techniques for automated detection of nerve irritation during neurosurgery.

Download

Table_1.docx

Background: To evaluate whether radiomic feature-based computed tomography (CT) imaging signature... more Background: To evaluate whether radiomic feature-based computed tomography (CT) imaging signatures allow prediction of lymph node (LN) metastasis in gastric cancer (GC) and to develop a preoperative nomogram for predicting LN status. Methods: We retrospectively analyzed radiomics features of CT images in 1,689 consecutive patients from three cancer centers. The prediction model was developed in the training cohort and validated in internal and external validation cohorts. Lasso regression model was utilized to select features and build radiomics signature. Multivariable logistic regression analysis was utilized to develop the model. We integrated the radiomics signature, clinical T and N stage, and other independent clinicopathologic variables, and this was presented as a radiomics nomogram. The performance of the nomogram was assessed with calibration, discrimination, and clinical usefulness. Results: The radiomics signature was significantly associated with pathological LN stage in training and validation cohorts. Multivariable logistic analysis found the radiomics signature was an independent predictor of LN metastasis. The nomogram showed good discrimination and calibration. Conclusions: The newly developed radiomic signature was a powerful predictor of LN metastasis and the radiomics nomogram could facilitate the preoperative individualized prediction of LN status.

Download

A Deep Learning Model for Automated Classification of Intraoperative Continuous EMG

IEEE Transactions on Medical Robotics and Bionics, 2021

Objective: Intraoperative neurophysiological monitoring (IONM) is the use of electrophysiological... more Objective: Intraoperative neurophysiological monitoring (IONM) is the use of electrophysiological methods during certain high-risk surgeries to assess the functional integrity of nerves in real time and alert the surgeon to prevent damage. However, the efficiency of IONM in current practice is limited by latency of verbal communications, inter-rater variability, and the subjective manner in which electrophysiological signals are described. Methods: In an attempt to address these shortcomings, we investigate automated classification of free-running electromyogram (EMG) waveforms during IONM. We propose a hybrid model with a convolutional neural network (CNN) component and a long short-term memory (LSTM) component to better capture complicated EMG patterns under conditions of both electrical noise and movement artifacts. Moreover, a preprocessing pipeline based on data normalization is used to handle classification of data from multiple subjects. To investigate model robustness, we also analyze models under different methods for processing of artifacts. Results: Compared with several benchmark modeling methods, CNN-LSTM performs best in classification, achieving accuracy of 89.54% and sensitivity of 94.23% in cross-patient evaluation. Conclusion: The CNN-LSTM model shows promise for automated classification of continuous EMG in IONM. Significance: This technique has potential to improve surgical safety by reducing cognitive load and inter-rater variability.

Radiomics Signature on Computed Tomography Imaging: Association With Lymph Node Metastasis in Patients With Gastric Cancer

Frontiers in Oncology

Background: To evaluate whether radiomic feature-based computed tomography (CT) imaging signature... more Background: To evaluate whether radiomic feature-based computed tomography (CT) imaging signatures allow prediction of lymph node (LN) metastasis in gastric cancer (GC) and to develop a preoperative nomogram for predicting LN status. Methods: We retrospectively analyzed radiomics features of CT images in 1,689 consecutive patients from three cancer centers. The prediction model was developed in the training cohort and validated in internal and external validation cohorts. Lasso regression model was utilized to select features and build radiomics signature. Multivariable logistic regression analysis was utilized to develop the model. We integrated the radiomics signature, clinical T and N stage, and other independent clinicopathologic variables, and this was presented as a radiomics nomogram. The performance of the nomogram was assessed with calibration, discrimination, and clinical usefulness. Results: The radiomics signature was significantly associated with pathological LN stage in training and validation cohorts. Multivariable logistic analysis found the radiomics signature was an independent predictor of LN metastasis. The nomogram showed good discrimination and calibration. Conclusions: The newly developed radiomic signature was a powerful predictor of LN metastasis and the radiomics nomogram could facilitate the preoperative individualized prediction of LN status.

Download

A Comparison of 1-D and 2-D Deep Convolutional Neural Networks in ECG Classification

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2018

Effective detection of arrhythmia is an important task in the remote monitoring of electrocardiog... more Effective detection of arrhythmia is an important task in the remote monitoring of electrocardiogram (ECG). The traditional ECG recognition depends on the judgment of the clinicians' experience, but the results suffer from the probability of human error due to the fatigue. To solve this problem, an ECG signal classification method based on the images is presented to classify ECG signals into normal and abnormal beats by using two-dimensional convolutional neural networks (2D-CNNs). First, we compare the accuracy and robustness between one-dimensional ECG signal input method and two-dimensional image input method in AIexNet network. Then, in order to alleviate the overfitting problem in two-dimensional network, we initialize AIexNet-like network with weights trained on ImageNet, to fit the training ECG images and fine-tune the model, and to further improve the accuracy and robustness of ECG classification. The performance evaluated on the MIT-BIH arrhythmia database demonstrates ...

Radiomics signature of computed tomography imaging for prediction of survival and chemotherapeutic benefits in gastric cancer

EBioMedicine, Jan 14, 2018

To develop and validate a radiomics signature for the prediction of gastric cancer (GC) survival ... more To develop and validate a radiomics signature for the prediction of gastric cancer (GC) survival and chemotherapeutic benefits. In this multicenter retrospective analysis, we analyzed the radiomics features of portal venous-phase computed tomography in 1591 consecutive patients. A radiomics signature was generated by using the Lasso-Cox regression model in 228 patients and validated in internal and external validation cohorts. Radiomics nomograms integrating the radiomics signature were constructed, demonstrating the incremental value of the radiomics signature to the traditional staging system for individualized survival estimation. The performance of the nomograms was assessed with respect to calibration, discrimination, and clinical usefulness. The radiomics signature consisted of 19 selected features and was significantly associated with DFS (disease-free survival) and OS (overall survival). Multivariate analysis demonstrated that the radiomics signature was an independent progn...

Radiomics Signature on Computed Tomography Imaging: Association With Lymph Node Metastasis in Patients With Gastric Cancer

Frontiers in Oncology, Apr 26, 2019

Background: To evaluate whether radiomic feature-based computed tomography (CT) imaging signature... more Background: To evaluate whether radiomic feature-based computed tomography (CT) imaging signatures allow prediction of lymph node (LN) metastasis in gastric cancer (GC) and to develop a preoperative nomogram for predicting LN status. Methods: We retrospectively analyzed radiomics features of CT images in 1,689 consecutive patients from three cancer centers. The prediction model was developed in the training cohort and validated in internal and external validation cohorts. Lasso regression model was utilized to select features and build radiomics signature. Multivariable logistic regression analysis was utilized to develop the model. We integrated the radiomics signature, clinical T and N stage, and other independent clinicopathologic variables, and this was presented as a radiomics nomogram. The performance of the nomogram was assessed with calibration, discrimination, and clinical usefulness. Results: The radiomics signature was significantly associated with pathological LN stage in training and validation cohorts. Multivariable logistic analysis found the radiomics signature was an independent predictor of LN metastasis. The nomogram showed good discrimination and calibration. Conclusions: The newly developed radiomic signature was a powerful predictor of LN metastasis and the radiomics nomogram could facilitate the preoperative individualized prediction of LN status.

Download

Uploads

Papers by Xuefan Zha

Log In