Xuming Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xuming Chen has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Guoqi Zhao
Department of Radiation Oncology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
2 shared publications- Kun Han
Department of Computer Science, University of California at Irvine, Irvine, CA, USA
2 shared publications Narisu Bai
DeepVoxel Inc., Irvine, USA
2 shared publicationsQianqian Liu
Department of Radiation Oncology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
2 shared publications- Shanlin Sun
University of California Irvine
2 shared publications - Shengyu Yao
Department of Oncology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, No. 100 Haining Road, Hongkou District, Shanghai, 200080, China.
2 shared publications
Latest Publications
- 29 September 2025
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 213, 111176
18F-FDG PET/CT directed radiotherapy dose escalation in locally advanced esophageal cancer (LAEC), a phase I study
- 29 September 2025
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 213, 111176
18F-FDG PET/CT directed radiotherapy dose escalation in locally advanced esophageal cancer (LAEC), a phase I study
- Top Cited PapersOpen Access
- 1 July 2021
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 160, 175-184
A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy
- 1 July 2021
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 160, 175-184
Top Cited PapersOpen AccessA deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy
- 1 May 2021
- Published by Elsevier in Biochemical and Biophysical Research Communications
- Vol. 554, 49-55
Nrf2 alleviates radiation-induced rectal injury by inhibiting of necroptosis
- 1 May 2021
- Published by Elsevier in Biochemical and Biophysical Research Communications
- Vol. 554, 49-55
Nrf2 alleviates radiation-induced rectal injury by inhibiting of necroptosis
- Open Access
- 1 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 938-948
Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
Multi-organ segmentation is one of most successful applications of deep learning in medical image analysis. Deep convolutional neural nets (CNNs) have shown great promise in achieving clinically applicable image segmentation performance on CT or MRI images. State-of-the-art CNN segmentation models apply either 2D or 3D convolutions on input images, with pros and cons associated with each method: 2D convolution is fast, less memory-intensive but inadequate for extracting 3D contextual information from volumetric images, while the opposite is true for 3D convolution. To fit a 3D CNN model on CT or MRI images on commodity GPUs, one usually has to either downsample input images or use cropped local regions as inputs, which limits the utility of 3D models for multi-organ segmentation. In this work, we propose a new framework for combining 3D and 2D models, in which the segmentation is realized through high-resolution 2D convolutions, but guided by spatial contextual information extracted from a low-resolution 3D model. We implement a self-attention mechanism to control which 3D features should be used to guide 2D segmentation. Our model is light on memory usage but fully equipped to take 3D contextual information into account. Experiments on multiple organ segmentation datasets demonstrate that by taking advantage of both 2D and 3D models, our method is consistently outperforms existing 2D and 3D models in organ segmentation accuracy, while being able to directly take raw whole-volume image data as inputs.
- 1 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 938-948
Open AccessSpatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
Multi-organ segmentation is one of most successful applications of deep learning in medical image analysis. Deep convolutional neural nets (CNNs) have shown great promise in achieving clinically applicable image segmentation performance on CT or MRI images. State-of-the-art CNN segmentation models apply either 2D or 3D convolutions on input images, with pros and cons associated with each method: 2D convolution is fast, less memory-intensive but inadequate for extracting 3D contextual information from volumetric images, while the opposite is true for 3D convolution. To fit a 3D CNN model on CT or MRI images on commodity GPUs, one usually has to either downsample input images or use cropped local regions as inputs, which limits the utility of 3D models for multi-organ segmentation. In this work, we propose a new framework for combining 3D and 2D models, in which the segmentation is realized through high-resolution 2D convolutions, but guided by spatial contextual information extracted from a low-resolution 3D model. We implement a self-attention mechanism to control which 3D features should be used to guide 2D segmentation. Our model is light on memory usage but fully equipped to take 3D contextual information into account. Experiments on multiple organ segmentation datasets demonstrate that by taking advantage of both 2D and 3D models, our method is consistently outperforms existing 2D and 3D models in organ segmentation accuracy, while being able to directly take raw whole-volume image data as inputs.
- Open Access
- 1 July 2018
- Published by Wolters Kluwer Health in American Journal of Clinical Oncology
- Vol. 41 (7) , 619-625
Phase II Study of Adjuvant Chemoradiotherapy Using Docetaxel/Cisplatin/5-Fluorouracil Before and After Intensity-modulated Radiotherapy With Concurrent Docetaxel in Patients With Completely (R0) Resected Gastric Carcinoma
The Intergroup 0116 study has demonstrated a significant survival benefit for completely resected (R0) gastric cancer patients treated with a fluorouracil/leucovorin chemoradiotherapy regimen. However, this regimen is also toxic and less effective in terms of distant disease control. Therefore, a more efficacious and safer regimen is urgently needed. Patients with R0 resected gastric carcinoma received up to two 21-day cycles of postoperative adjuvant preradiation and postradiation DCF chemotherapy (docetaxel 37.5 mg/m2 on days 1 and 8, cisplatin 25 mg/m2 on days 1 to 3, and a continuous infusion of fluorouracil 750 mg/m2 on days 1 to 5), respectively. Chemoradiotherapy between preradiation and postradiation chemotherapy was initiated on day 43 and consisted of intensity-modulated radiotherapy (45 Gy) plus concurrent docetaxel 20 mg/m2 weekly for 5 weeks. A total of 55 patients were evaluated and 76% (42) of patients completed the prescribed therapy. With a median follow-up of 61 months, the 3- and 5-year progression-free survival rates were 67% (95% confidence interval [CI], 54%-80%) and 59% (95% CI, 46%-72%), respectively; and the 3- and 5-year overall survival rates were 72% (95% CI, 60%-84%) and 61% (95% CI, 48%-74%), respectively. The most common grade 3 or greater toxicity, during the chemotherapy phase, was neutropenia (24%). Common grade 3/4 toxicities during concurrent chemoradiotherapy were nausea (32%), vomiting (26%), fatigue (15%), and anorexia (19%). These results demonstrate that this adjuvant regimen is active with an acceptable toxicity profile. A randomized phase 3 trial comparing the Intergroup 0116 chemoradiotherapy regimen with this regimen is underway. This is an open-access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License 4.0 (CCBY-NC-ND), where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal. http://creativecommons.org/licenses/by-nc-nd/4.0/
- 1 July 2018
- Published by Wolters Kluwer Health in American Journal of Clinical Oncology
- Vol. 41 (7) , 619-625
Open AccessPhase II Study of Adjuvant Chemoradiotherapy Using Docetaxel/Cisplatin/5-Fluorouracil Before and After Intensity-modulated Radiotherapy With Concurrent Docetaxel in Patients With Completely (R0) Resected Gastric Carcinoma
The Intergroup 0116 study has demonstrated a significant survival benefit for completely resected (R0) gastric cancer patients treated with a fluorouracil/leucovorin chemoradiotherapy regimen. However, this regimen is also toxic and less effective in terms of distant disease control. Therefore, a more efficacious and safer regimen is urgently needed. Patients with R0 resected gastric carcinoma received up to two 21-day cycles of postoperative adjuvant preradiation and postradiation DCF chemotherapy (docetaxel 37.5 mg/m2 on days 1 and 8, cisplatin 25 mg/m2 on days 1 to 3, and a continuous infusion of fluorouracil 750 mg/m2 on days 1 to 5), respectively. Chemoradiotherapy between preradiation and postradiation chemotherapy was initiated on day 43 and consisted of intensity-modulated radiotherapy (45 Gy) plus concurrent docetaxel 20 mg/m2 weekly for 5 weeks. A total of 55 patients were evaluated and 76% (42) of patients completed the prescribed therapy. With a median follow-up of 61 months, the 3- and 5-year progression-free survival rates were 67% (95% confidence interval [CI], 54%-80%) and 59% (95% CI, 46%-72%), respectively; and the 3- and 5-year overall survival rates were 72% (95% CI, 60%-84%) and 61% (95% CI, 48%-74%), respectively. The most common grade 3 or greater toxicity, during the chemotherapy phase, was neutropenia (24%). Common grade 3/4 toxicities during concurrent chemoradiotherapy were nausea (32%), vomiting (26%), fatigue (15%), and anorexia (19%). These results demonstrate that this adjuvant regimen is active with an acceptable toxicity profile. A randomized phase 3 trial comparing the Intergroup 0116 chemoradiotherapy regimen with this regimen is underway. This is an open-access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License 4.0 (CCBY-NC-ND), where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal. http://creativecommons.org/licenses/by-nc-nd/4.0/