Deep Learning in Head and Neck Tumor Multiomics Diagnosis and Analysis: Review of the Literature.
Ontology highlight
ABSTRACT:
SUBMITTER: Wang X
PROVIDER: S-EPMC7902873 | biostudies-literature | 2021
REPOSITORIES: biostudies-literature
Publications
Deep Learning in Head and Neck Tumor Multiomics Diagnosis and Analysis: Review of the Literature.
Frontiers in genetics 20210210
Head and neck tumors are the sixth most common neoplasms. Multiomics integrates multiple dimensions of clinical, pathologic, radiological, and biological data and has the potential for tumor diagnosis and analysis. Deep learning (DL), a type of artificial intelligence (AI), is applied in medical image analysis. Among the DL techniques, the convolution neural network (CNN) is used for image segmentation, detection, and classification and in computer-aided diagnosis. Here, we reviewed multiomics i ...[more]
Similar Datasets
Project description:BackgroundTo build an automatic pathological diagnosis model to assess the lymph node metastasis status of head and neck squamous cell carcinoma (HNSCC) based on deep learning algorithms.Study designA retrospective study.MethodsA diagnostic model integrating two-step deep learning networks was trained to analyze the metastasis status in 85 images of HNSCC lymph nodes. The diagnostic model was tested in a test set of 21 images with metastasis and 29 images without metastasis. All images were scanned from HNSCC lymph node sections stained with hematoxylin-eosin (HE).ResultsIn the test set, the overall accuracy, sensitivity, and specificity of the diagnostic model reached 86%, 100%, and 75.9%, respectively.ConclusionsOur two-step diagnostic model can be used to automatically assess the status of HNSCC lymph node metastasis with high sensitivity.Level of evidenceNA.
| S-EPMC8823170 | biostudies-literature
Project description:Traditional radiomics involves the extraction of quantitative texture features from medical images in an attempt to determine correlations with clinical endpoints. We hypothesize that convolutional neural networks (CNNs) could enhance the performance of traditional radiomics, by detecting image patterns that may not be covered by a traditional radiomic framework. We test this hypothesis by training a CNN to predict treatment outcomes of patients with head and neck squamous cell carcinoma, based solely on their pre-treatment computed tomography image. The training (194 patients) and validation sets (106 patients), which are mutually independent and include 4 institutions, come from The Cancer Imaging Archive. When compared to a traditional radiomic framework applied to the same patient cohort, our method results in a AUC of 0.88 in predicting distant metastasis. When combining our model with the previous model, the AUC improves to 0.92. Our framework yields models that are shown to explicitly recognize traditional radiomic features, be directly visualized and perform accurate outcome prediction.
| S-EPMC6391436 | biostudies-literature
Project description:Early regression-the regression in tumor volume during the initial phase of radiotherapy (approximately 2 weeks after treatment initiation)-is a common occurrence during radiotherapy. This rapid radiation-induced tumor regression may alter target coordinates, necessitating adaptive radiotherapy (ART). We developed a deep learning-based radiomics (DLR) approach to predict early head and neck tumor regression and thereby facilitate ART. Primary gross tumor volume (GTVp) was monitored in 96 patients and nodal GTV (GTVn) in 79 patients during treatment. All patients underwent two computed tomography (CT) scans: one before the start of radiotherapy for initial planning and one during radiotherapy for boost planning. Patients were assigned to regression and nonregression groups according to their median tumor regression rate (ΔGTV/treatment day from initial to boost CT scan). We input a GTV image into the convolutional neural network model, which was pretrained using natural image datasets, via transfer learning. The deep features were extracted from the last fully connected layer. To clarify the prognostic power of the deep features, machine learning models were trained. The models then predicted the regression and nonregression of GTVp and GTVn and evaluated the predictive performance by 0.632 + bootstrap area under the curve (AUC). Predictive performance for GTVp regression was highest using the InceptionResNetv2 model (mean AUC = 0.75) and that for GTVn was highest using NASNetLarge (mean AUC = 0.73). Both models outperformed the handcrafted radiomics features (mean AUC = 0.63 for GTVp and 0.61 for GTVn) or clinical factors (0.64 and 0.67, respectively). DLR may facilitate ART for improved radiation side-effects and target coverage.
| S-EPMC9142601 | biostudies-literature
Project description:Once considered nonfunctional, pseudogene transcripts are now known to provide valuable information for cancer susceptibility, including head and neck cancer (HNC), a serious health problem worldwide, with about 50% unimproved overall survival over the last decades. The present review focuses on the role of pseudogene transcripts involved in HNC risk and prognosis. We combined current literature and in silico analyses from The Cancer Genome Atlas (TCGA) database to identify the most deregulated pseudogene transcripts in HNC and their genetic variations. We then built a co-expression network and performed gene ontology enrichment analysis to better understand the pseudogenes' interactions and pathways in HNC. In the literature, few pseudogenes have been studied in HNC. Our in silico analysis identified 370 pseudogene transcripts associated with HNC, where SPATA31D5P, HERC2P3, SPATA31C2, MAGEB6P1, SLC25A51P1, BAGE2, DNM1P47, SPATA31C1, ZNF733P and OR2W5 were found to be the most deregulated and presented several genetic alterations. NBPF25P, HSP90AB2P, ZNF658B and DPY19L2P3 pseudogenes were predicted to interact with 12 genes known to participate in HNC, DNM1P47 was predicted to interact with the TP53 gene, and HLA-H pseudogene was predicted to interact with HLA-A and HLA-B genes. The identified pseudogenes were associated with cancer biology pathways involving cell communication, response to stress, cell death, regulation of the immune system, regulation of gene expression, and Wnt signaling. Finally, we assessed the prognostic values of the pseudogenes with the Kaplan-Meier Plotter database, and found that expression of SPATA31D5P, SPATA31C2, BAGE2, SPATA31C1, ZNF733P and OR2W5 pseudogenes were associated with patients' survival. Due to pseudogene transcripts' potential for cancer diagnosis, progression, and as therapeutic targets, our study can guide new research to HNC understanding and development of new target therapies.
| S-EPMC8391979 | biostudies-literature
Project description:PurposeTo probe the feasibility of deep learning-based super-resolution (SR) reconstruction applied to nonenhanced MR angiography (MRA) of the head and neck.MethodsHigh-resolution 3D thin-slab stack-of-stars quiescent interval slice-selective (QISS) MRA of the head and neck was obtained in eight subjects (seven healthy volunteers, one patient) at 3T. The spatial resolution of high-resolution ground-truth MRA data in the slice-encoding direction was reduced by factors of 2 to 6. Four deep neural network (DNN) SR reconstructions were applied, with two based on U-Net architectures (2D and 3D) and two (2D and 3D) consisting of serial convolutions with a residual connection. SR images were compared to ground-truth high-resolution data using Dice similarity coefficient (DSC), structural similarity index measure (SSIM), arterial diameter, and arterial sharpness measurements. Image review of the optimal DNN SR reconstruction was done by two experienced neuroradiologists.ResultsDNN SR of up to twofold and fourfold lower-resolution (LR) input volumes provided images that resembled those of the original high-resolution ground-truth volumes for intracranial and extracranial arterial segments, and improved DSC, SSIM, arterial diameters, and arterial sharpness relative to LR volumes (P < .001). The 3D DNN SR outperformed 2D DNN SR reconstruction. According to two neuroradiologists, 3D DNN SR reconstruction consistently improved image quality with respect to LR input volumes (P < .001).ConclusionDNN-based SR reconstruction of 3D head and neck QISS MRA offers the potential for up to fourfold reduction in acquisition time for neck vessels without the need to commensurately sacrifice spatial resolution.
| S-EPMC8034362 | biostudies-literature
Project description:Solitary fibrous tumors (SFTs) are soft tumors (mesenchymal origin) that most likely develop from adult mesenchymal stem cells. SFTs are not common in the head and neck region, and the characteristics of tumors in this location are unclear. The present study describes the clinicopathological findings of 2 cases of SFTs arising in the parotid gland and buccal space, presenting as salivary gland tumors. The first case is a 76-year-old man presenting with a painless tumor on the right parotid gland who subsequently underwent partial superficial parotidectomy. According to the results of histopathological analysis, the tumor consisted of stellate and spindle-shaped cells proliferating on a mucous-like substrate. Immunohistochemical staining revealed that neoplastic cells were positive for CD34, vimentin, Bcl2, and STAT6. The second case is of a 64-year-old man presenting with a painless lump on his right cheek. Based on the findings of fine needle aspiration cytology, a tumor derived from myoepithelial cells of the minor salivary gland or a nonepithelial tumor was suspected. The patient underwent surgical resection via an intraoral approach. Histopathologically, the tumor consisted of spindle-shaped cells with rod-shaped or irregular nuclei. Immunohistochemical staining revealed that the neoplastic cells were positive for CD34, CD99, Bcl2, and STAT6. Briefly, SFT should be considered in the differential diagnosis of a well-marginalized lesion in the salivary gland and oral cavity. STAT6 immunohistochemistry is the most specific and sensitive method of diagnosing SFT. A thorough understanding of the morphological changes associated with SFT and their correlation with clinical, immunohistochemical, and molecular characteristics is important to avoid misdiagnosis.
| S-EPMC10359685 | biostudies-literature
Project description:Radiomics is a rapidly growing area of research within radiology that involves the extraction and modeling of high-dimensional quantitative imaging features using machine learning/artificial intelligence (ML/AI) methods. In this review, we describe the published clinical evidence on the application of ML methods to improve the performance of ultrasound (US) in head and neck oncology. A systematic search of electronic databases (MEDLINE, PubMed, clinicaltrials.gov) was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Of 15,080 initial articles identified, 34 studies were selected for in-depth analysis. Twenty-five out of 34 studies (74%) focused on the diagnostic application of US radiomics while 6 (18%) studies focused on response assessment and 3 (8%) studies utilized US radiomics for modeling normal tissue toxicity. Support vector machine (SVM) was the most commonly employed ML method (47%) followed by multivariate logistic regression (24%) and k-nearest neighbor analysis (21%). Only 11/34 (~32%) of the studies included an independent validation set. A majority of studies were retrospective in nature (76%) and based on single-center evaluation (85%) with variable numbers of patients (12-1609) and imaging datasets (32-1624). Despite these limitations, the application of ML methods resulted in improved diagnostic and prognostic performance of US highlighting the potential clinical utility of this approach.
| S-EPMC8833587 | biostudies-literature
Project description:In this paper, we first describe the basics of the field of cancer diagnosis, which includes steps of cancer diagnosis followed by the typical classification methods used by doctors, providing a historical idea of cancer classification techniques to the readers. These methods include Asymmetry, Border, Color and Diameter (ABCD) method, seven-point detection method, Menzies method, and pattern analysis. They are used regularly by doctors for cancer diagnosis, although they are not considered very efficient for obtaining better performance. Moreover, considering all types of audience, the basic evaluation criteria are also discussed. The criteria include the receiver operating characteristic curve (ROC curve), Area under the ROC curve (AUC), F1 score, accuracy, specificity, sensitivity, precision, dice-coefficient, average accuracy, and Jaccard index. Previously used methods are considered inefficient, asking for better and smarter methods for cancer diagnosis. Artificial intelligence and cancer diagnosis are gaining attention as a way to define better diagnostic tools. In particular, deep neural networks can be successfully used for intelligent image analysis. The basic framework of how this machine learning works on medical imaging is provided in this study, i.e., pre-processing, image segmentation and post-processing. The second part of this manuscript describes the different deep learning techniques, such as convolutional neural networks (CNNs), generative adversarial models (GANs), deep autoencoders (DANs), restricted Boltzmann's machine (RBM), stacked autoencoders (SAE), convolutional autoencoders (CAE), recurrent neural networks (RNNs), long short-term memory (LTSM), multi-scale convolutional neural network (M-CNN), multi-instance learning convolutional neural network (MIL-CNN). For each technique, we provide Python codes, to allow interested readers to experiment with the cited algorithms on their own diagnostic problems. The third part of this manuscript compiles the successfully applied deep learning models for different types of cancers. Considering the length of the manuscript, we restrict ourselves to the discussion of breast cancer, lung cancer, brain cancer, and skin cancer. The purpose of this bibliographic review is to provide researchers opting to work in implementing deep learning and artificial neural networks for cancer diagnosis a knowledge from scratch of the state-of-the-art achievements.
| S-EPMC6770116 | biostudies-literature
Project description:Background and objectiveAs the spine is pivotal in the support and protection of human bodies, much attention is given to the understanding of spinal diseases. Quick, accurate, and automatic analysis of a spine image greatly enhances the efficiency with which spine conditions can be diagnosed. Deep learning (DL) is a representative artificial intelligence technology that has made encouraging progress in the last 6 years. However, it is still difficult for clinicians and technicians to fully understand this rapidly evolving field due to the diversity of applications, network structures, and evaluation criteria. This study aimed to provide clinicians and technicians with a comprehensive understanding of the development and prospects of DL spine image analysis by reviewing published literature.MethodsA systematic literature search was conducted in the PubMed and Web of Science databases using the keywords "deep learning" and "spine". Date ranges used to conduct the search were from 1 January, 2015 to 20 March, 2021. A total of 79 English articles were reviewed.Key content and findingsThe DL technology has been applied extensively to the segmentation, detection, diagnosis, and quantitative evaluation of spine images. It uses static or dynamic image information, as well as local or non-local information. The high accuracy of analysis is comparable to that achieved manually by doctors. However, further exploration is needed in terms of data sharing, functional information, and network interpretability.ConclusionsThe DL technique is a powerful method for spine image analysis. We believe that, with the joint efforts of researchers and clinicians, intelligent, interpretable, and reliable DL spine analysis methods will be widely applied in clinical practice in the future.
| S-EPMC9131328 | biostudies-literature
Project description:ImportanceIn addition to their patient management value, multidisciplinary tumor boards have been recognized as effective learning tools. However, the value of using a virtual tumor board as a learning tool for head and neck surgical oncology fellows has not been studied.ObjectiveTo describe the structure and content of the American Head and Neck Society (AHNS) Virtual Tumor Board and assess its educational value as perceived by attendees.Design, setting, and participantsAll sessions of the AHNS Virtual Tumor Board from April 8, 2020, to June 1, 2022, were reviewed. Topics, presenters, participants, and viewership data were collected as of October 15, 2022, from session recordings posted to an online video sharing and social media platform. Additionally, an anonymous, 14-question online survey was designed to elicit feedback from head and neck surgery trainees on virtual tumor board engagement, strengths, and weaknesses. The survey was electronically distributed in June and July 2022 to the 101 fellows enrolled in AHNS-accredited programs between July 1, 2020, and June 30, 2022.Main outcomes and measuresThe primary aim was to tabulate online viewership of the sessions. The secondary aim was to qualitatively assess the experience of head and neck trainees with the AHNS Virtual Tumor Board using a survey.ResultsForty-two sessions of the virtual tumor board were held between April 8, 2020, and June 1, 2022. Almost all sessions (41 [98%]) were case based. One hundred and sixteen cases were presented, representing 2 to 3 cases per session, by 75 unique faculty members. Each session was viewed a mean of 217 times (range, 64-2216 views). In the 2021 to 2022 academic year, a mean of 60 viewers (range, 30-92 viewers) attended each live session. In all, 29 survey responses were collected from 101 fellows in AHNS-accredited programs (29% response rate). Most respondents felt the format allowed for excellent teaching (18 of 26 respondents [69%]) and discussion (19 of 26 respondents [73%]). Most respondents (22 of 29 respondents [76%]) believed that practicing head and neck surgeons would benefit from the sessions.Conclusions and relevanceThis survey study found that the AHNS Virtual Tumor Board was well-attended and well-reviewed by head and neck surgical oncology trainees. The virtual tumor board format could be used as model of remote learning for other organizations.
| S-EPMC10450583 | biostudies-literature