NPCNet: Jointly Segment Primary Nasopharyngeal Carcinoma Tumors and Metastatic Lymph Nodes in MR Images

Li, Yang; Dan, Tingting; Li, Haojiang; Chen, Jiazhou; Peng, Hong; Liu, Lizhi; Cai, Hongming

doi:10.1109/tmi.2022.3144274

Cited by 30 publications

(9 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nasopharyngeal carcinoma (NPC) is the most common malignant tumor in the human nasopharynx. According to the World Health Organization report, about 80% of NPC patients worldwide are concentrated in China, and most of the remaining patients are found in Southeast Asia and the Middle East and North Africa [ 1 , 2 ]. According to statistics, the incidence of NPC in Guangzhou is 17.8 per 100,000 people, the incidence rate is rising, and the incidence is younger [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

Multidimensional CNN-Based Deep Segmentation Method for Tumor Identification

Martin

Sharma

Kaur

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Weighted MR images of 421 patients with nasopharyngeal cancer were obtained at the head and neck level, and the tumors in the images were assessed by two expert doctors. 346 patients’ multimodal pictures and labels served as training sets, whereas the remaining 75 patients’ multimodal images and labels served as independent test sets. Convolutional neural network (CNN) for modal multidimensional information fusion and multimodal multidimensional information fusion (MMMDF) was used. The three models’ performance is compared, and the findings reveal that the multimodal multidimensional fusion model performs best, while the two-modal multidimensional information fusion model performs second. The single-modal multidimensional information fusion model has the poorest performance. In MR images of nasopharyngeal cancer, a convolutional network can precisely and efficiently segment tumors.

show abstract

Section: Introductionmentioning

confidence: 99%

Multidimensional CNN-Based Deep Segmentation Method for Tumor Identification

Martin

Sharma

Kaur

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…The NPCNet was conducted on the dataset of 9124 samples collected from 754 patients. The results demonstrated that NPCNet achieved state-of-the-art performance ( Li et al., 2022 ). Similarly, Tao and colleagues developed a sequential method (SeqSeg) to achieve accurate nasopharyngeal carcinoma segmentation.…”

Section: Discussionmentioning

confidence: 95%

Add-on individualizing prediction of nasopharyngeal carcinoma using deep-learning based on MRI: A multicentre, validation study

et al. 2022

View full text Add to dashboard Cite

“… Zhao et al (2019) fed dual-modality PET-CT images into an Unet-like network with auxiliary paths to introduce deep supervision and allow the hidden layers of the decoder to learn additional representative features. For precisely contouring NPC tumors and lymph nodes, NPCNet utilizes ResNet-101 to extract features and then enhances these features by channel attention, spatial attention, and object contextual representation block ( Li et al, 2022 ).…”

Section: Related Studiesmentioning

confidence: 99%

“…Semi-supervised models are hot spots for less number of NPC datasets, but the performance of these models still cannot be compared to the models trained by all labeled datasets ( Luo et al, 2021 ; Hu et al, 2022 ). Some studies focused on variable locations and irregular boundaries of NPC tumors but paid less attention to the bilateral symmetry of the head and complementary information of multiple modality-specific features ( Li et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

BSMM-Net: Multi-modal neural network based on bilateral symmetry for nasopharyngeal carcinoma segmentation

Zhou

Chen

et al. 2023

Front. Hum. Neurosci.

Self Cite

View full text Add to dashboard Cite

IntroductionAutomatically and accurately delineating the primary nasopharyngeal carcinoma (NPC) tumors in head magnetic resonance imaging (MRI) images is crucial for patient staging and radiotherapy. Inspired by the bilateral symmetry of head and complementary information of different modalities, a multi-modal neural network named BSMM-Net is proposed for NPC segmentation.MethodsFirst, a bilaterally symmetrical patch block (BSP) is used to crop the image and the bilaterally flipped image into patches. BSP can improve the precision of locating NPC lesions and is a simulation of radiologist locating the tumors with the bilateral difference of head in clinical practice. Second, modality-specific and multi-modal fusion features (MSMFFs) are extracted by the proposed MSMFF encoder to fully utilize the complementary information of T1- and T2-weighted MRI. The MSMFFs are then fed into the base decoder to aggregate representative features and precisely delineate the NPC. MSMFF is the output of MSMFF encoder blocks, which consist of six modality-specific networks and one multi-modal fusion network. Except T1 and T2, the other four modalities are generated from T1 and T2 by the BSP and DT modal generate block. Third, the MSMFF decoder with similar structure to the MSMFF encoder is deployed to supervise the encoder during training and assure the validity of the MSMFF from the encoder. Finally, experiments are conducted on the dataset of 7633 samples collected from 745 patients.Results and discussionThe global DICE, precision, recall and IoU of the testing set are 0.82, 0.82, 0.86, and 0.72, respectively. The results show that the proposed model is better than the other state-of-the-art methods for NPC segmentation. In clinical diagnosis, the BSMM-Net can give precise delineation of NPC, which can be used to schedule the radiotherapy.

show abstract

NPCNet: Jointly Segment Primary Nasopharyngeal Carcinoma Tumors and Metastatic Lymph Nodes in MR Images

Cited by 30 publications

References 39 publications

Multidimensional CNN-Based Deep Segmentation Method for Tumor Identification

Multidimensional CNN-Based Deep Segmentation Method for Tumor Identification

Add-on individualizing prediction of nasopharyngeal carcinoma using deep-learning based on MRI: A multicentre, validation study

BSMM-Net: Multi-modal neural network based on bilateral symmetry for nasopharyngeal carcinoma segmentation

Contact Info

Product

Resources

About