Application of Artificial Intelligence to the Diagnosis and Therapy of Nasopharyngeal Carcinoma

Artificial intelligence (AI) is an interdisciplinary field that encompasses a wide range of computer science disciplines, including image recognition, machine learning, human-computer interaction, robotics and so on. Recently, AI, especially deep learning algorithms, has shown excellent performance in the field of image recognition, being able to automatically perform quantitative evaluation of complex medical image features to improve diagnostic accuracy and efficiency. AI has a wider and deeper application in the medical field of diagnosis, treatment and prognosis. Nasopharyngeal carcinoma (NPC) occurs frequently in southern China and Southeast Asian countries and is the most common head and neck cancer in the region. Detecting and treating NPC early is crucial for a good prognosis. This paper describes the basic concepts of AI, including traditional machine learning and deep learning algorithms, and their clinical applications of detecting and assessing NPC lesions, facilitating treatment and predicting prognosis. The main limitations of current AI technologies are briefly described, including interpretability issues, privacy and security and the need for large amounts of annotated data. Finally, we discuss the remaining challenges and the promising future of using AI to diagnose and treat NPC.

TG-Net: Combining transformer and GAN for nasopharyngeal carcinoma tumor segmentation based on total-body uEXPLORER PET/CT scanner

Nasopharyngeal carcinoma (NPC) is a malignant tumor, and the main treatment is radiotherapy. Accurate delineation of the target tumor is essential for radiotherapy of NPC. NPC tumors are small in size and vary widely in shape and structure, making it a time-consuming and laborious task for even experienced radiologists to manually outline tumors. However, the segmentation performance of current deep learning models is not satisfactory, mainly manifested by poor segmentation boundaries. To solve this problem, this paper proposes a segmentation method for nasopharyngeal carcinoma based on dynamic PET-CT image data, whose input data include CT, PET, and parametric images (Ki images). This method uses a generative adversarial network with a modified UNet integrated with a Transformer as the generator (TG-Net) to achieve automatic segmentation of NPC on combined CT-PET-Ki images. In the coding stage, TG-Net uses moving windows to replace traditional pooling operations to obtain patches of different sizes, which can reduce information loss in the coding process. Moreover, the introduction of Transformer can make the network learn more representative features and improve the discriminant ability of the model, especially for tumor boundaries. Finally, the results of fivefold cross validation with an average Dice similarity coefficient score of 0.9135 show that our method has good segmentation performance. Comparative experiments also show that our network structure is superior to the most advanced methods in the segmentation of NPC. In addition, this work is the first to use Ki images to assist tumor segmentation. We also demonstrated the usefulness of adding Ki images to aid in tumor segmentation.

DCNet: Densely Connected Deep Convolutional Encoder-Decoder Network for Nasopharyngeal Carcinoma Segmentation

Nasopharyngeal Carcinoma segmentation in magnetic resonance imagery (MRI) is vital to radiotherapy. Exact dose delivery hinges on an accurate delineation of the gross tumor volume (GTV). However, the large-scale variation in tumor volume is intractable, and the performance of current models is mostly unsatisfactory with indistinguishable and blurred boundaries of segmentation results of tiny tumor volume. To address the problem, we propose a densely connected deep convolutional network consisting of an encoder network and a corresponding decoder network, which extracts high-level semantic features from different levels and uses low-level spatial features concurrently to obtain fine-grained segmented masks. Skip-connection architecture is involved and modified to propagate spatial information to the decoder network. Preliminary experiments are conducted on 30 patients. Experimental results show our model outperforms all baseline models, with improvements of 4.17%. An ablation study is performed, and the effectiveness of the novel loss function is validated.

Computer-aided diagnosis and regional segmentation of nasopharyngeal carcinoma based on multi-modality medical images

PURPOSE

Nasopharyngeal carcinoma (NPC) is a category of tumors with high incidence in head-and-neck (H&N) body region, and the diagnosis and treatment planning are usually conducted by radiologists manually, which is tedious, time-consuming and unrepeatable. In this paper, we integrated different stages of this process and proposed a computer-aided framework to realize automatic detection, tumor region and sub-region segmentation, and visualization of NPC, which are usually investigated separately in literatures.

METHODS

Multi-modality images are utilized in the framework. Firstly, NPC is detected by a convolutional neural network (CNN) on computed tomography (CT) scans. Then, NPC area is segmented from magnetic resonance imaging (MRI) images by using a multi-modality MRI fusion network. Thirdly, NPC sub-regions with different metabolic activities are divided on CT images of the same patient via an adaptive threshold algorithm. Finally, 3D surface model of NPC is generated for observing its shape, size, and location in the head region. The proposed method is compared with other algorithms by evaluation on the volumes and shapes of detected NPCs.

RESULTS

Experiments are conducted on CT images of 130 NPC patients and 102 subjects without NPC and MRI images of 149 NPC patients, among which 52 subjects are overlapped with both CT and MRI images. The reference for evaluation is generated by three experienced radiologists. The results demonstrated that our utilized models outperform other strategies with detection accuracy 0.882 and Dice similarity coefficient 0.719 for NPC segmentation. Sub-region division and the 3D visualized models show great acceptability in clinical usage.

CONCLUSION

The remarkable performance indicated the potential of our framework in alleviating workload of radiologist. Furthermore, the combined usage of multi-modality images is able to generate reliable segmentations of NPC area and sub-regions, which provide evidence to judge the heterogeneity among patients and guide the dose painting for radiation therapy.

Automatic Nasopharyngeal Carcinoma Segmentation Using Fully Convolutional Networks with Auxiliary Paths on Dual-Modality PET-CT Images

Nasopharyngeal carcinoma (NPC) is prevalent in certain areas, such as South China, Southeast Asia, and the Middle East. Radiation therapy is the most efficient means to treat this malignant tumor. Positron emission tomography-computed tomography (PET-CT) is a suitable imaging technique to assess this disease. However, the large amount of data produced by numerous patients causes traditional manual delineation of tumor contour, a basic step for radiotherapy, to become time-consuming and labor-intensive. Thus, the demand for automatic and credible segmentation methods to alleviate the workload of radiologists is increasing. This paper presents a method that uses fully convolutional networks with auxiliary paths to achieve automatic segmentation of NPC on PET-CT images. This work is the first to segment NPC using dual-modality PET-CT images. This technique is identical to what is used in clinical practice and offers considerable convenience for subsequent radiotherapy. The deep supervision introduced by auxiliary paths can explicitly guide the training of lower layers, thus enabling these layers to learn more representative features and improve the discriminative capability of the model. Results of threefold cross-validation with a mean dice score of 87.47% demonstrate the efficiency and robustness of the proposed method. The method remarkably outperforms state-of-the-art methods in NPC segmentation. We also validated by experiments that the registration process among different subjects and the auxiliary paths strategy are considerably useful techniques for learning discriminative features and improving segmentation performance.

Toward Effective Medical Image Analysis Using Hybrid Approaches—Review, Challenges and Applications

Accurate medical images analysis plays a vital role for several clinical applications. Nevertheless, the immense and complex data volume to be processed make difficult the design of effective algorithms. The first aim of this paper is to examine this area of research and to provide some relevant reference sources related to the context of medical image analysis. Then, an effective hybrid solution to further improve the expected results is proposed here. It allows to consider the benefits of the cooperation of different complementary approaches such as statistical-based, variational-based and atlas-based techniques and to reduce their drawbacks. In particular, a pipeline framework that involves different steps such as a preprocessing step, a classification step and a refinement step with variational-based method is developed to identify accurately pathological regions in biomedical images. The preprocessing step has the role to remove noise and improve the quality of the images. Then the classification is based on both symmetry axis detection step and non linear learning with SVM algorithm. Finally, a level set-based model is performed to refine the boundary detection of the region of interest. In this work we will show that an accurate initialization step could enhance final performances. Some obtained results are exposed which are related to the challenging application of brain tumor segmentation.

3D segmentation of nasopharyngeal carcinoma from CT images using cascade deep learning

In the paper, we propose a new deep learning-based method for segmenting nasopharyngeal carcinoma (NPC) in the nasopharynx from three orthogonal CT images. The proposed method introduces a cascade strategy composed of two-phase manners. In CT images, there are organs, called non-target organs, which NPC never invades. Therefore, the first phase is to detect and eliminate non-target organ regions from the CT images. In the second phase, NPC is extracted from the remained regions in the CT images. Convolutional neural networks (CNNs) are applied to detect non-target organs and NPCs. The proposed system determines the final NPC segmentation by integrating three results obtained from coronal, axial and sagittal images. Moreover, we construct two CNN-based NPC detection systems using one kind of overlapping patches with a fixed size and various overlapping patches with different sizes. From the experiments using CT images of 70 NPC patients, our proposed systems, especially the system using various patches, achieves the best performance for detecting NPC compared with conventional NPC detection methods.

Nasopharyngeal carcinoma segmentation based on enhanced convolutional neural networks using multi-modal metric learning

Multi-modality examinations have been extensively applied in current clinical cancer management. Leveraging multi-modality medical images can be highly beneficial for automated tumor segmentation as they provide complementary information that could make the segmentation of tumors more accurate. This paper investigates CNN-based methods for automated nasopharyngeal carcinoma (NPC) segmentation using computed tomography (CT) and magnetic resonance (MR) images. Specially, a multi-modality convolutional neural network (M-CNN) is designed to jointly learn a multi-modal similarity metric and segmentation of paired CT-MR images. By jointly optimizing the similarity learning error and the segmentation error, the feature learning processes of both modalities are mutually guided. In doing so, the segmentation sub-networks are able to take advantage of the other modality's information. Considering that each modality possesses certain distinctive characteristics, we combine the higher-layer features extracted by a single-modality CNN (S-CNN) and M-CNN to form a combined CNN (C-CNN) for each modality, which is able to further utilize the complementary information of different modalities and improve the segmentation performance. The proposed M-CNN and C-CNN were evaluated on 90 CT-MR images of NPC patients. Experimental results demonstrate that our methods achieve improved segmentation performance compared to their counterparts without multi-modal information fusion and the existing CNN-based multi-modality segmentation methods.

Automated nasopharyngeal carcinoma segmentation in magnetic resonance images by combination of convolutional neural networks and graph cut

Accurate and reliable segmentation of nasopharyngeal carcinoma (NPC) in medical images is an import task for clinical applications, including radiotherapy. However, NPC features large variations in lesion size and shape, as well as inhomogeneous intensities within the tumor and similar intensity to that of nearby tissues, making its segmentation a challenging task. The present study proposes a novel automated NPC segmentation method in magnetic resonance (MR) images by combining a deep convolutional neural network (CNN) model and a 3-dimensional (3D) graph cut-based method in a two-stage manner. First, a multi-view deep CNN-based segmentation method is performed. A voxel-wise initial segmentation is generated by integrating the inferential classification information of three trained single-view CNNs. Instead of directly using the CNN classification results to achieve a final segmentation, the proposed method uses a 3D graph cut-based method to refine the initial segmentation. Specifically, the probability response map obtained using the multi-view CNN method is utilized to calculate the region cost, which represents the likelihood of a voxel being assigned to the tumor or non-tumor. Structure information in 3D from the original MR images is used to calculate the boundary cost, which measures the difference between the two voxels in the 3D neighborhood. The proposed method was evaluated on T1-weighted images from 30 NPC patients using the leave-one-out method. The experimental results demonstrated that the proposed method is effective and accurate for NPC segmentation.

Automatic metastatic brain tumor segmentation for stereotactic radiosurgery applications

The objective of this study is to develop an automatic segmentation strategy for efficient and accurate metastatic brain tumor delineation on contrast-enhanced T1-weighted (T1c) magnetic resonance images (MRI) for stereotactic radiosurgery (SRS) applications. The proposed four-step automatic brain metastases segmentation strategy is comprised of pre-processing, initial contouring, contour evolution, and contour triage. First, T1c brain images are preprocessed to remove the skull. Second, an initial tumor contour is created using a multi-scaled adaptive threshold-based bounding box and a super-voxel clustering technique. Third, the initial contours are evolved to the tumor boundary using a regional active contour technique. Fourth, all detected false-positive contours are removed with geometric characterization. The segmentation process was validated on a realistic virtual phantom containing Gaussian or Rician noise. For each type of noise distribution, five different noise levels were tested. Twenty-one cases from the multimodal brain tumor image segmentation (BRATS) challenge dataset and fifteen clinical metastases cases were also included in validation. Segmentation performance was quantified by the Dice coefficient (DC), normalized mutual information (NMI), structural similarity (SSIM), Hausdorff distance (HD), mean value of surface-to-surface distance (MSSD) and standard deviation of surface-to-surface distance (SDSSD). In the numerical phantom study, the evaluation yielded a DC of 0.98  ±  0.01, an NMI of 0.97  ±  0.01, an SSIM of 0.999  ±  0.001, an HD of 2.2  ±  0.8 mm, an MSSD of 0.1  ±  0.1 mm, and an SDSSD of 0.3  ±  0.1 mm. The validation on the BRATS data resulted in a DC of 0.89  ±  0.08, which outperform the BRATS challenge algorithms. Evaluation on clinical datasets gave a DC of 0.86  ±  0.09, an NMI of 0.80  ±  0.11, an SSIM of 0.999  ±  0.001, an HD of 8.8  ±  12.6 mm, an MSSD of 1.5  ±  3.2 mm, and an SDSSD of 1.8  ±  3.4 mm when comparing to the physician drawn ground truth. The result indicated that the developed automatic segmentation strategy yielded accurate brain tumor delineation and presented as a useful clinical tool for SRS applications.