RESUMO
AIM: This study aimed to verify the correlation of the airway-facial phenotype and visualize the morphological variation in Crouzon syndrome patients. Additionally, to develop a non-radiation methodology for airway assessments. METHOD: In this study, 22 patients diagnosed with Crouzon syndrome (Age: 7.80 ± 5.63 years; Gender distribution: 11 females and 11 males) were analysed. The soft tissue surface and airway were three-dimensionally reconstructed, and the entire facial phenotype was topologized and converted into spatial coordinates. Geometric morphometrics was employed to verify the correlation and visualize dynamic phenotypic variation associated with airway volume. A total of 276 linear variables were automatically derived from 24 anatomical landmarks, and principal component analysis (PCA) identified the 20 most significant parameters for airway evaluation. Correlation analyses between parameters and airway volume were performed. Then, patients were classified into three groups based on airway volume, and the differences among the groups were compared for evaluating the differentiating effectiveness of parameters. RESULTS: The facial phenotype was strongly correlated with the airway (coefficient: 0.758). Morphological variation was characterized by (i) mandibular protrusion and anticlockwise rotation; (ii) midface retrusion; (iii) supraorbital frontward and (iv) lengthening of the facial height. All the anthropometric parameters were strongly associated with the airway, and the differences among the groups were statistically significant. CONCLUSION: This study confirmed the strong correlation between facial phenotype and airway parameters in Crouzon syndrome patients. Despite the development of the airway, pathological midface retrusion was still aggravated, suggesting that surgical intervention was inevitable. Three-dimensional facial anthropometry has potential as a non-radiation examination for airway evaluation.
Assuntos
Pontos de Referência Anatômicos , Disostose Craniofacial , Face , Fenótipo , Humanos , Feminino , Masculino , Disostose Craniofacial/diagnóstico por imagem , Criança , Face/anatomia & histologia , Face/diagnóstico por imagem , Imageamento Tridimensional/métodos , Cefalometria/métodos , Análise de Componente Principal , Pré-EscolarRESUMO
This study is to visualize the morphological growth trajectory of the Crouzon population and provide a more comprehensive and perceptual understanding of pathologic aggregation in terms of maxillofacial and soft tissue surfaces. Twenty-two patients with Crouzon syndrome were included in this retrospective surgery. Preoperative computed tomography was segmented into maxillofacial and soft tissue surface morphologies. Fifty-two anatomical landmarks and a standardized template were used to extract the morphological phenotypes and transform them into spatial coordinates. Geometric morphometrics (GM) were applied to visualize the growth trajectory and estimate the morphological variation of the Crouzon population. Cephalometric analysis was conducted to validate the growth trajectory in a clinical aspect. It was found that both maxillofacial and soft tissue surface morphologies were strongly covaried with age. Morphological development of the Crouzon population was characterized by (1) maxillary retrusion and clockwise rotation, (2) mandibular counterclockwise rotation, (3) facial width narrowing and aggregated concave face, and (4) sunken nasal bone. Pathologic maxillary retrusion continuously existed from infancy to adulthood, and rapid aggravation took place at 3 to 6 years old. In conclusion, this study is the first to visualize the dynamic growth trajectories on both maxillofacial and soft tissue surface morphologies. More attention and monitoring of breathing, snoring, intelligence, and global development should be cast on Crouzon patients between 3 and 6 years old in family care. If any functional abnormalities occur during this period, professional consultations and evaluations should be conducted timely to avoid pathologic aggravation. Consistency between GMs and cephalometry validates the reliability of GM potentials in the clinical field, allowing a promising and revolutionary methodology for dynamically and qualitatively analyzing pathologic changes in some rare congenital diseases.
RESUMO
Electricity generation triggered by the ubiquitous water evaporation process provides an intriguing way to harvest energy from water. Meanwhile, natural water evaporation is also a fundamental way to obtain fresh water for human beings. Here, a wafer-scale nanostructured silicon-based device that takes advantage of its well-aligned configuration that simultaneously realizes solar steam generation (SSG) for freshwater collection and hydrovoltaic effect generation for electricity output is developed. An ingenious porous, black carbon nanotube fabric (CNF) electrode endows the device with sustainable water self-pumping capability, excellent durable conductivity, and intense solar spectrum harvesting. A combined device based on the CNF electrode integrated with nanostructured silicon nanowire arrays (SiNWs) provided an aligned numerous surface-to-volume water evaporation interface that enables a recorded continuous short-circuit current 8.65 mA and a water evaporation rate of 1.31 kg m-2 h-1 under one sun illumination. Such wafer-scale SiNWs-based SSG and hydrovoltaic integration devices would unchain the bottleneck of the weak and discontinuous electrical output of hydrovoltaic devices, which inspires other sorts of semiconductor-based hydrovoltaic device designs to target superior performance.
RESUMO
OBJECTIVE: To discuss and study the application of composite tissue flaps pedicled with the superficial temporal artery (STA) and its branches in the repair of various defects, analyze the advantages and disadvantages of such composite tissue flaps, and provide a reference for the personalized design of various maxillofacial defect repairs. MATERIALS AND METHODS: In recent years, 12 cases of various maxillofacial defects were repaired with composite tissue flaps pedicled with the STA and its branches. The application strategies of this type of tissue flaps were summarized by summarizing experience and reviewing literature. RESULTS: According to the different defect characteristics of patients and the requirements of patients for surgery, different tissue flaps have been designed, and good results have been obtained. Except for 2 patients who developed dark purple skin flap within 48 hours after operation, the remaining patients were followed up for 6 to 24 months without serious complications. CONCLUSION: The composite tissue flap pedicled with the STA and its branches is a kind of functional tissue flap for facial defect repair. Individualized repair schemes can be designed according to different defect types of patients.
Assuntos
Procedimentos de Cirurgia Plástica , Lesões dos Tecidos Moles , Humanos , Transplante de Pele/métodos , Artérias Temporais/cirurgia , Resultado do Tratamento , Lesões dos Tecidos Moles/cirurgiaRESUMO
Three-dimensional digital technology has been widely applied in craniofacial surgeries, particularly in conventional procedures such as facial contouring and orthognathic surgery. To some extent, the process has already been standardized. As to reconstruction surgeries of complex craniofacial deformity, however, surgical plans need to be patient-specific. Traditionally, individualized surgical treatment largely relies on the surgeon's clinical experience. The application of digital technology mainly focuses on preoperative planning and postoperative evaluation of surgical outcomes rather than intraoperative patient-specific implants or osteotomy guides. For patients with complex craniofacial deformities, requirements for accurate 3-dimensional digital technology can be much higher. This study presents a favorable surgical reconstruction of the severe craniofacial deformity using 3-dimensional digital technology, providing references for craniofacial surgeons, which could be beneficial to clinical practice and treatment efficacy.
Assuntos
Anormalidades Craniofaciais , Implantes Dentários , Cirurgia Assistida por Computador , Humanos , Anormalidades Craniofaciais/cirurgia , Resultado do Tratamento , Imageamento Tridimensional/métodos , Cirurgia Assistida por Computador/métodosRESUMO
OBJECTIVE: To discuss and summarize the comprehensive serial surgical treatment of Treacher Collins syndrome. MATERIALS AND METHODS: From September 2012 to January 2020, 12 patients with Treacher Collins syndrome were treated by autologous fat graft, mandibular distraction osteogenesis, orbitozygomatic reconstruction with calvarial external lamina, orthognathic surgery combined with postoperative orthodontics, transplantation of upper eyelid orbicularis myocutaneous flap, lateral canthal ligament reduction, and other methods. The authors evaluated the postoperative improvement, summarized experiences, and reviewed literatures about the comprehensive serial treatment of Treacher Collins syndrome. RESULTS: All patients showed significant improvement in appearance and function, and no complications were found during the follow-up period of 5 months to 3 years. CONCLUSIONS: The deformities of Treacher Collins syndrome involves multiple craniofacial region, and only by formulating comprehensive serial treatment strategies according to the malformation characteristics of different patients can the best effect be achieved.
Assuntos
Disostose Mandibulofacial , Osteogênese por Distração , Procedimentos de Cirurgia Plástica , Humanos , Disostose Mandibulofacial/cirurgia , Ossos Faciais/cirurgia , Mandíbula/cirurgia , Osteogênese por Distração/métodosRESUMO
BACKGROUND: Skeletal dentofacial asymmetry decreases patient's attractiveness by deteriorating symmetry of facial appearance which is of great significance to individuals. Surgery-first orthognathic approach manifests its advantages of shortening treatment time and improving patient's quality of life. However, current literature on surgery-first approach mainly focuses on treating prognathism, overlooking its efficacy in improving facial symmetry of skeletal dentofacial asymmetry patients. This study aimed to assess SFA's efficacy in improving facial appearance by analyzing morphological features of asymmetric bone and facial soft tissue in a three-dimensional manner. METHODS: Thirty-four patients who received orthognathic surgery in a surgery-first fashion were included. Based on three-dimensional CT reconstruction, bilateral preoperative morphological features and postoperative symmetry of hard tissue were compared respectively. Efficacy of facial soft tissue symmetry restoration was evaluated using root mean square deviation (RMSD). RESULTS: Asymmetric features mainly located in menton, mandibular body length, angulation between ramus and midsagittal plane (MSP), distance between gonion and MSP and so on, which were significantly restored after the whole treatment. RMSD of facial soft tissue surface were significantly declined after the treatment and prognathism was corrected simultaneously if existed. CONCLUSIONS: Surgery-first orthognathic approach is proved to be capable of treating skeletal dentofacial asymmetry effectively and efficiently.
Assuntos
Má Oclusão Classe III de Angle , Cirurgia Ortognática , Procedimentos Cirúrgicos Ortognáticos , Prognatismo , Humanos , Prognatismo/diagnóstico por imagem , Prognatismo/cirurgia , Qualidade de Vida , Assimetria Facial/diagnóstico por imagem , Assimetria Facial/cirurgia , Procedimentos Cirúrgicos Ortognáticos/métodos , Resultado do Tratamento , Má Oclusão Classe III de Angle/diagnóstico por imagem , Má Oclusão Classe III de Angle/cirurgia , Cefalometria/métodos , Mandíbula/cirurgia , Imageamento Tridimensional/métodosRESUMO
AIM: To develop a novel and simplified parameter for mandible angle asymmetry (MAA) evaluation for facial countering surgeries in Chinese females. MATERIALS AND METHODS: A total of 250 craniofacial computer tomography of healthy Chinese individuals were collected in this retrospective study. Mimics 21.0 was applied for 3-dimensional anthropometry. The Frankfort and Green planes were set as referenced vertical and horizontal planes for measuring the distances to gonions. The differences in both orientations were analyzed to verify the symmetry. Mandible angle asymmetry (â Go-N-ANS, MAA) which comprehensively represented horizontal and vertical placements was defined qas the novel parameter for asymmetric evaluation and quantitative analysis was conducted to generate referenced materials. RESULTS: Mandible angle asymmetry was divided into horizontal and vertical asymmetry. No significant differences were found in either horizontal or vertical orientations. The horizontal difference was 3.09±2.52 mm, the reference range was (0.28, 7.54) mm, whereas the±ertical difference was 2.59±2.48 mm, the reference range was (0.12, 6.34) mm. The difference of MAA was 1.74±1.30 degrees, and the reference range was (0.10,4.32ï¼degrees. CONCLUSION: This study provided a novel parameter for asymmetric evaluation in the mandible angle region through quantitative 3-dimensional anthropometry, arousing plastic surgeons' attention to both aesthetics and symmetry in facial contouring surgery.
Assuntos
População do Leste Asiático , Assimetria Facial , Humanos , Feminino , Estudos Retrospectivos , Assimetria Facial/diagnóstico por imagem , Assimetria Facial/cirurgia , Estética Dentária , Mandíbula/diagnóstico por imagem , Mandíbula/cirurgia , Cefalometria/métodosRESUMO
ABSTRACT: This study aims to verify that the craniofacial plastic surgery robot with piezosurgery is more accurate and safer than traditional operations in genioplasty. This study chose data from the Digital Plastic Surgery of Plastic Surgery Hospital in the Chinese Academy of Medical Sciences and Peking Union Medical College. The CT data of the patient's skull were reconstructed in the software, and the authors designed the measurement index. The surgical plan was designed as an ideal scheme (control group). Patients underwent traditional surgery according to the preoperative surgery plan (clinical group). Guided by surgical navigation, the osteotomy was operated on patients' same size plaster model using the surgery robot equipped with a piezosurgery (robot group). At last, the accuracy was calculated by CT data. There was no significant difference between the robotic group and control groups in the postoperative measurement index (P < 0.05). There was no significant difference between the robotic group and the control group (Pâ>â0.05) in the line of osteotomy, but there was a significant difference between the clinical group and the control group in the line of the osteotomy.
RESUMO
We report a new system for the silylation of aryl C-H bonds. The combination of [Ir(cod)(OMe)]2 and 2,9-Me2-phenanthroline (2,9-Me2-phen) catalyzes the silylation of arenes at lower temperatures and with faster rates than those reported previously, when the hydrogen byproduct is removed, and with high functional group tolerance and regioselectivity. Inhibition of reactions by the H2 byproduct is shown to limit the silylation of aryl C-H bonds in the presence of the most active catalysts, thereby masking their high activity. Analysis of initial rates uncovered the high reactivity of the catalyst containing the sterically hindered 2,9-Me2-phen ligand but accompanying rapid inhibition by hydrogen. With this catalyst, under a flow of nitrogen to remove hydrogen, electron-rich arenes, including those containing sensitive functional groups, undergo silylation in high yield for the first time, and arenes that underwent silylation with prior catalysts react over much shorter times with lower catalyst loadings. The synthetic value of this methodology is demonstrated by the preparation of key intermediates in the synthesis of medicinally important compounds in concise sequences comprising silylation and functionalization. Mechanistic studies demonstrate that the cleavage of the aryl C-H bond is reversible and that the higher rates observed with the 2,9-Me2-phen ligand are due to a more thermodynamically favorable oxidative addition of aryl C-H bonds.
Assuntos
Derivados de Benzeno/síntese química , Complexos de Coordenação/química , Compostos de Organossilício/síntese química , Fenantrolinas/química , Catálise , Deutério/química , Irídio/química , Cinética , Ligantes , Modelos QuímicosRESUMO
OBJECTIVES: The purpose of this study was to develop an automatic tracking method for the muscle cross-sectional area (CSA) on ultrasound (US) images using a convolutional neural network (CNN). The performance of the proposed method was evaluated and compared with that of the state-of-the art muscle segmentation method. METHODS: A real-time US image sequence was obtained from the rectus femoris muscle during voluntary contraction. A CNN was built to segment the rectus femoris muscle and calculate the CSA in each US frame. This network consisted of 2 stages: feature extraction and score map reconstruction. The training of the network was divided into 3 steps with output score map resolutions of one-fourth, one-half, and all of the original image. We evaluated the segmentation performance of our method with 5-fold cross-validation. The mean precision, recall, and dice similarity score were calculated. RESULTS: The mean precision, recall, and Dice's coefficient (DSC) ± SD were 0.936 ± 0.029, 0.882 ± 0.045, and 0.907 ± 0.023, respectively. Compared with the state-of-the-art muscle segmentation method (constrained mutual-information-based free-form deformation), the proposed method using CNN showed high performance. CONCLUSIONS: The automated method proposed in this study provides an accurate and efficient approach to the estimation of the muscle CSA during muscle contraction.
Assuntos
Processamento de Imagem Assistida por Computador/métodos , Músculo Esquelético/anatomia & histologia , Redes Neurais de Computação , Ultrassonografia/métodos , Adulto , Feminino , Humanos , Masculino , Músculo Esquelético/diagnóstico por imagem , Valores de ReferênciaRESUMO
BACKGROUND: Wogonin is an encouraging choice for clinical use owing to its potent anti-tumor and anti-inflammatory effects with the high safety profile. However, wogonin for targeted therapy of lymphoma was not well addressed. In this study, we focused on its anticancer effect alongside with the underlying mechanisms for targeted therapy in EBV-positive lymphoma. This will facilitate its introduction to clinical use, which is planned in the near future. METHODS: Cell proliferation was studied by CCK8. Flow cytometry was used to analyze the apoptosis and the cycle arrest of cells. Further, we also used immunofluorescent staining to detect the morphologic changes of the apoptotic cells. The expression of LMP1/miR-155/p65/pp65/PU.1 was evaluated by quantitative real-time PCR (qRT-PCR) and western blot, while that of NF-κB was analyzed by EMSA. At last, immunohistochemical staining was applied to assess the expression of target proteins and relevant molecules. RESULTS: In vitro, wogonin induced the apoptosis of Raji cells by downregulating the expression of NF-κB through LMP1/miR-155/NF-κB/PU.1 pathway, which was in a dose and time-dependent manner. In vivo, wogonin could suppress tumor growth, associated with the downregulation of ki67, p65 and upregulation of PU.1. CONCLUSIONS: Wogonin could suppress tumor growth and induce cell apoptosis by inhibiting the expression of NF-κB. Taken these findings, we concluded that wogonin could be a potential targeted therapeutic agent for EBV-positive lymphoma with the expression of LMP1 through the pathway of LMP1/NF-κB/miR-155/PU.1.
Assuntos
Antineoplásicos Fitogênicos/administração & dosagem , Infecções por Vírus Epstein-Barr/tratamento farmacológico , Flavanonas/administração & dosagem , Linfoma de Células B/tratamento farmacológico , Linfoma de Células B/virologia , Animais , Antineoplásicos Fitogênicos/farmacologia , Linhagem Celular Tumoral , Proliferação de Células/efeitos dos fármacos , Sobrevivência Celular/efeitos dos fármacos , Flavanonas/farmacologia , Regulação Neoplásica da Expressão Gênica/efeitos dos fármacos , Humanos , Camundongos , MicroRNAs/genética , NF-kappa B/metabolismo , Proteínas Proto-Oncogênicas/genética , Transdução de Sinais/efeitos dos fármacos , Transativadores/genética , Proteínas da Matriz Viral/genética , Ensaios Antitumorais Modelo de XenoenxertoRESUMO
Perovskite materials are promising candidates for the implementation of electrically pumped lasers considering the enhanced performance of perovskite-based light-emitting diodes. Nonetheless, current methods of fabricating perovskite optical microcavities require complex patterning technologies to build suitable resonant cavities for perovskite laser emission, burdening the device structure design. To address this issue, we applied inkjet printing, a maskless patterning technique, to directly create spontaneous formations of polycrystalline perovskite microcavity arrays to explore their laser-emitting action. The substrate surface tension was tuned to modulate the perovskite crystallization process in combination with optimization of printing ink recipes. As a result, polycrystalline perovskite microcavity arrays were achieved, contributing to the laser emission at 528 nm with a lasing threshold of 1.37 mJ/cm2, while simultaneously achieving high-definition patterning of flexible display. These results clearly illustrate the efficiency of inkjet printing technology in the preparation of polycrystalline perovskite optical microcavities and promote the development of flexible laser arrayed displays, providing a facile process toward the realization of perovskite-cavity laser devices.
RESUMO
Balanced charge injection is key to achieving perovskite light-emitting diodes (PeLEDs) with a low efficiency roll-off at a high brightness. The use of zinc oxide (ZnO) with a high electron mobility as the charge transport layers is desirable; however, photoluminescence (PL) quenching of a perovskite on ZnO always occurs. Here, a quasi-two-dimensional perovskite on ZnO is explored to uncover the PL quenching mechanism, mainly ascribed to the deprotonation of ammonium cations on the ZnO film in association with the decomposition of low-dimensional perovskite phases. Surprisingly, crystal plane-dependent PL quenching results indicate that the deprotonation rate strongly correlates with the crystal orientation of the ZnO surface. We developed a strategy for suppressing perovskite PL quenching by incorporating an atomic layer deposited Al2O3 onto the ZnO film. Consequently, an efficient inverted PeLED was achieved with a maximum external quantum efficiency of 17.7% and a less discernible efficiency roll-off at a high current density.
RESUMO
Matrix-enhanced delivery of cells is a promising approach to improving current cell therapies. Our objective was to create cell-laden composite microbeads that combine the attractive features of the natural polymers chitosan and fibrin. Liquid polydimethylsiloxane was used to emulsify a chitosan-fibrinogen solution containing suspended human fibroblast cells, followed by initiation of thrombin-mediated polymerization of fibrin and thermal/pH-mediated gelation of chitosan. Chitosan/fibrin weight percent (wt%) ratios of 100/0, 75/25, 50/50 and 25/75 were investigated. Microbead diameters ranged from 275 ± 99 µm to 38 ± 10 µm using impeller speeds from 600 to 1400 rpm. Fibroblasts remained viable on day 1 post-fabrication in all matrices, but cell viability was markedly higher in high-fibrin microbeads by day 8 post-fabrication. Cell spreading and interaction with the extracellular matrix was also markedly increased in high-fibrin matrices. Such composite microbeads containing viable entrapped cells have potential for minimally invasive delivery of cells for a variety of tissue repair applications.
Assuntos
Transplante de Células/métodos , Terapia Baseada em Transplante de Células e Tecidos/métodos , Quitosana/química , Fibrina/química , Microesferas , Cicatrização , Sobrevivência Celular , Células Imobilizadas , Matriz Extracelular/metabolismo , Fibroblastos/citologia , Fibroblastos/metabolismo , Fibroblastos/transplante , Humanos , Tamanho da Partícula , Transição de Fase , PolimerizaçãoRESUMO
INTRODUCTION: Distraction osteogenesis (DO) is a widely used for cleft and palate related maxillary hypoplasia. There has been little research on temporomandibular joint (TMJ) dislocation after maxillary DO. We present these 3 cases and analyze the possible causes for reference by other clinicians. PATIENT CONCERNS: In the late stages of maxillary DO, the patients gradually felt a decrease in mandibular mobility and suffered from limited mouth opening. Case 2 and 3 could open their mouth up to 1 and 2 fingers and Case 1 barely able to open her mouth at the completion of distraction. DIAGNOSIS: Case 1 and Case 3 were diagnosed as right TMJ dislocation and Case 2 had a TMJ dislocation on her left side. INTERVENTIONS: Patients with TMJ dislocation were repositioned with manipulation as soon as detected. OUTCOMES: There was no recurrence in all three cases during the postoperative follow-up period. CONCLUSIONS: Maxillary DO can sufficiently advance the maxilla in cleft lip and palate patients. Clinicians should be mindful of the TMJ dislocations that maxillary DO can exert on patients.
Assuntos
Fenda Labial/cirurgia , Fissura Palatina/cirurgia , Luxações Articulares/etiologia , Maxila/cirurgia , Osteogênese por Distração/efeitos adversos , Adolescente , Criança , Fenda Labial/complicações , Fissura Palatina/complicações , Feminino , Seguimentos , Humanos , Fixadores Internos/normas , Luxações Articulares/cirurgia , Masculino , Maxila/anormalidades , Osteogênese por Distração/instrumentação , Transtornos da Articulação Temporomandibular/fisiopatologia , Resultado do Tratamento , Adulto JovemRESUMO
A guide RNA (gRNA) directs the function of a CRISPR protein effector to a target gene of choice, providing a versatile programmable platform for engineering diverse modes of synthetic regulation (edit, silence, induce, bind). However, the fact that gRNAs are constitutively active places limitations on the ability to confine gRNA activity to a desired location and time. To achieve programmable control over the scope of gRNA activity, here we apply principles from dynamic RNA nanotechnology to engineer conditional guide RNAs (cgRNAs) whose activity is dependent on the presence or absence of an RNA trigger. These cgRNAs are programmable at two levels, with the trigger-binding sequence controlling the scope of the effector activity and the target-binding sequence determining the subject of the effector activity. We demonstrate molecular mechanisms for both constitutively active cgRNAs that are conditionally inactivated by an RNA trigger (ON â OFF logic) and constitutively inactive cgRNAs that are conditionally activated by an RNA trigger (OFF â ON logic). For each mechanism, automated sequence design is performed using the reaction pathway designer within NUPACK to design an orthogonal library of three cgRNAs that respond to different RNA triggers. In E. coli expressing cgRNAs, triggers, and silencing dCas9 as the protein effector, we observe a median conditional response of ≈4-fold for an ON â OFF "terminator switch" mechanism, ≈15-fold for an ON â OFF "splinted switch" mechanism, and ≈3-fold for an OFF â ON "toehold switch" mechanism; the median crosstalk within each cgRNA/trigger library is <2%, ≈2%, and ≈20% for the three mechanisms. To test the portability of cgRNA mechanisms prototyped in bacteria to mammalian cells, as well as to test generalizability to different effector functions, we implemented the terminator switch in HEK 293T cells expressing inducing dCas9 as the protein effector, observing a median ON â OFF conditional response of ≈4-fold with median crosstalk of ≈30% for three orthogonal cgRNA/trigger pairs. By providing programmable control over both the scope and target of protein effector function, cgRNA regulators offer a promising platform for synthetic biology.
RESUMO
OBJECTIVES: To evaluate the application of a deep learning architecture, based on the convolutional neural network (CNN) technique, to perform automatic tumor segmentation of magnetic resonance imaging (MRI) for nasopharyngeal carcinoma (NPC). MATERIALS AND METHODS: In this prospective study, 87 MRI containing tumor regions were acquired from newly diagnosed NPC patients. These 87 MRI were augmented to >60,000 images. The proposed CNN network is composed of two phases: feature representation and scores map reconstruction. We designed a stepwise scheme to train our CNN network. To evaluate the performance of our method, we used case-by-case leave-one-out cross-validation (LOOCV). The ground truth of tumor contouring was acquired by the consensus of two experienced radiologists. RESULTS: The mean values of dice similarity coefficient, percent match, and their corresponding ratio with our method were 0.89±0.05, 0.90±0.04, and 0.84±0.06, respectively, all of which were better than reported values in the similar studies. CONCLUSIONS: We successfully established a segmentation method for NPC based on deep learning in contrast-enhanced magnetic resonance imaging. Further clinical trials with dedicated algorithms are warranted.
Assuntos
Imageamento por Ressonância Magnética/métodos , Carcinoma Nasofaríngeo/patologia , Algoritmos , Aprendizado Profundo , Humanos , Processamento de Imagem Assistida por Computador/métodos , Aprendizado de Máquina , Redes Neurais de Computação , Estudos ProspectivosRESUMO
Purpose: In this study, we proposed an automated deep learning (DL) method for head and neck cancer (HNC) gross tumor volume (GTV) contouring on positron emission tomography-computed tomography (PET-CT) images. Materials and Methods: PET-CT images were collected from 22 newly diagnosed HNC patients, of whom 17 (Database 1) and 5 (Database 2) were from two centers, respectively. An oncologist and a radiologist decided the gold standard of GTV manually by consensus. We developed a deep convolutional neural network (DCNN) and trained the network based on the two-dimensional PET-CT images and the gold standard of GTV in the training dataset. We did two experiments: Experiment 1, with Database 1 only, and Experiment 2, with both Databases 1 and 2. In both Experiment 1 and Experiment 2, we evaluated the proposed method using a leave-one-out cross-validation strategy. We compared the median results in Experiment 2 (GTVa) with the performance of other methods in the literature and with the gold standard (GTVm). Results: A tumor segmentation task for a patient on coregistered PET-CT images took less than one minute. The dice similarity coefficient (DSC) of the proposed method in Experiment 1 and Experiment 2 was 0.481â¼0.872 and 0.482â¼0.868, respectively. The DSC of GTVa was better than that in previous studies. A high correlation was found between GTVa and GTVm (R = 0.99, P < 0.001). The median volume difference (%) between GTVm and GTVa was 10.9%. The median values of DSC, sensitivity, and precision of GTVa were 0.785, 0.764, and 0.789, respectively. Conclusion: A fully automatic GTV contouring method for HNC based on DCNN and PET-CT from dual centers has been successfully proposed with high accuracy and efficiency. Our proposed method is of help to the clinicians in HNC management.