RESUMEN
OBJECTIVES: Oral cancer is a leading cause of morbidity and mortality. Screening and mobile Health (mHealth)-based approach facilitates early detection remotely in a resource-limited settings. Recent advances in eHealth technology have enabled remote monitoring and triage to detect oral cancer in its early stages. Although studies have been conducted to evaluate the diagnostic efficacy of remote specialists, to our knowledge, no studies have been conducted to evaluate the consistency of remote specialists. The aim of this study was to evaluate interobserver agreement between specialists through telemedicine systems in real-world settings using store-and-forward technology. MATERIALS AND METHODS: The two remote specialists independently diagnosed clinical images (n=822) from image archives. The onsite specialist diagnosed the same participants using conventional visual examination, which was tabulated. The diagnostic accuracy of two remote specialists was compared with that of the onsite specialist. Images that were confirmed histopathologically were compared with the onsite diagnoses and the two remote specialists. RESULTS: There was moderate agreement (k= 0.682) between two remote specialists and (k= 0.629) between the onsite specialist and two remote specialists in the diagnosis of oral lesions. The sensitivity and specificity of remote specialist 1 were 92.7% and 83.3%, respectively, and those of remote specialist 2 were 95.8% and 60%, respectively, each compared with histopathology. CONCLUSION: The diagnostic accuracy of the two remote specialists was optimal, suggesting that "store and forward" technology and telehealth can be an effective tool for triage and monitoring of patients. CLINICAL RELEVANCE: Telemedicine is a good tool for triage and enables faster patient care in real-world settings.
Asunto(s)
Enfermedades de la Boca , Neoplasias de la Boca , Telemedicina , Humanos , Variaciones Dependientes del Observador , Neoplasias de la Boca/diagnóstico , Neoplasias de la Boca/patología , Telemedicina/métodos , TecnologíaRESUMEN
Management of advanced gingivo-buccal complex cancers involving the masticatory space (T4b) is often managed by compartment resection. The oncological safety of the procedure is now clearly established. Based on the origin and epicenter of the tumor there are two classes of compartmental resection. Those tumors arising from the tuberosity of the maxilla and/or upper gingival sulcus region; the resection involves the tumor, posterior maxilla, and the ipsilateral infratemporal fossa. These tumors can be resected by mandibulotomy approach, preserving the mandible. This constitutes class-1 infratemporal fossa resection. The class-2 infratemporal fossa resection is applied for those tumors arising from the retromolar trigone and/or lower gingivo-buccal sulcus region. In this class, the mandible and often the overlying cheek skin needs to be sacrificed, in addition to the contents of the infratemporal fossa and the posterior maxilla. Both the classes of resections are carried out in an orderly fashion following well-defined steps. These sequential steps maximize the exposure of inaccessible structures, enables protection of critical structures as well as minimizes blood loss. This manuscript describes the surgical steps for the two classes of compartmental resection of the infratemporal fossa for advanced gingivo-buccal complex cancers involving the masticatory space.
RESUMEN
OBJECTIVES: The incidence of young-onset oral squamous cell carcinoma (OSCC) is growing, even among non-smokers/drinkers. The effects of adverse histopathological features on long-term oncologic outcomes between the young and old are controversial and confounded by significant heterogeneity. Few studies have evaluated the socio-economic impact of premature mortality from OSCC. Our study seeks to quantify these differences and their economic impact on society. MATERIALS AND METHODS: Four hundred and seventy-eight young (<45 years) and 1660 old patients (≥45 years) with OSCC were studied. Logistic regression determined predictors of recurrence and death. Survival analysis was calculated via the Kaplan-Meier method. A separate health economic analysis was conducted for India and Singapore. Years of Potential Productive Life Lost (YPPLL) were estimated with the Human Capital Approach, and premature mortality cost was derived using population-level data. RESULTS: Adverse histopathological features were seen more frequently in young OSCC: PNI (42.9% vs. 35%, p = 0.002), LVI (22.4% vs. 17.3%, p = 0.013) and ENE (36% vs. 24.5%, p < 0.001). Although 5-year OS/DSS were similar, the young cohort had received more intensive adjuvant therapy (CCRT 26.9% vs. 16.6%, p < 0.001). Among Singaporean males, the premature mortality cost per death was US $396,528, and per YPPLL was US $45,486. This was US $397,402 and US $38,458 for females. Among Indian males, the premature mortality cost per death was US $30,641, and per YPPLL was US $595. This was US $ 21,038 and US $305 for females. CONCLUSION: Young-onset OSCC is an aggressive disease, mitigated by the ability to receive intensive adjuvant treatment. From our loss of productivity analysis, the socio-economic costs from premature mortality are substantial. Early cancer screening and educational outreach campaigns should be tailored to this cohort. Alongside, more funding should be diverted to genetic research, developing novel biomarkers and improving the efficacy of adjuvant treatment in OSCC.
Asunto(s)
Carcinoma de Células Escamosas , Neoplasias de Cabeza y Cuello , Neoplasias de la Boca , Anciano , Femenino , Masculino , Humanos , Carcinoma de Células Escamosas/epidemiología , Carcinoma de Células Escamosas/terapia , Carcinoma de Células Escamosas de Cabeza y Cuello , Neoplasias de la Boca/epidemiología , Neoplasias de la Boca/terapia , Adyuvantes Inmunológicos , EscolaridadRESUMEN
Dynamic interactions within the tumor micro-environment drive patient response to immune checkpoint inhibitors. Existing preclinical models lack true representation of this complexity. Using a Head and Neck cancer patient derived TruTumor histoculture platform, the response spectrum of 70 patients to anti-PD1 treatment is investigated in this study. With a subset of 55 patient samples, multiple assays to characterize T-cell reinvigoration and tumor cytotoxicity are performed. Based on levels of these two response parameters, patients are stratified into five sub-cohorts, with the best responder and non-responder sub-cohorts falling at extreme ends of the spectrum. The responder sub-cohort exhibits high T-cell reinvigoration, high tumor cytotoxicity with T-cells homing into the tumor upon treatment whereas immune suppression and tumor progression pathways are pre-dominant in the non-responders. Some moderate responders benefit from combination of anti-CTLA4 with anti-PD1, which is evident from better cytotoxic T-cell: T-regulatory cell ratio and enhancement of tumor cytotoxicity. Baseline and on-treatment gene expression signatures from this study stratify responders and non-responders in unrelated clinical datasets.
Asunto(s)
Neoplasias de Cabeza y Cuello , Humanos , Neoplasias de Cabeza y Cuello/tratamiento farmacológico , Microambiente TumoralRESUMEN
BACKGROUND: Despite introduction of extranodal extension (ENE) into the AJCC 8th edition of oral cancer staging, previous criticisms persist, such as limited discrimination between sub-stages and doubtful prognostic value of contralateral nodal disease. The purpose of this study was to compare our novel nodal staging system, based on the number of positive nodes and ENE, to the AJCC staging system in surgically treated patients. METHODS: Retrospective analysis of 4710 patients with oral squamous cell carcinoma (OSCC) treated with surgery±adjuvant therapy in 8 institutions in Australia, North America and Asia. With overall survival (OS) and disease specific survival (DSS) as endpoint, the prognostic performance of AJCC 8th and 7th editions were compared using hazard consistency, hazard discrimination, likelihood difference and balance. RESULTS: Our new nodal staging system (PN) a progressive and linear increase in hazard ratio (HR) from pN0 to pN3, with good separation of Kaplan Meier curves. Using the predetermined criteria for evaluation of a staging system, our proposed staging model outperformed AJCC 8th and 7th editions in prediction of OS and DSS. CONCLUSION: PN was the lymph node staging system that provided the most accurate prediction of OS and DSS for patients in our cohort of OSCC. Additionally, it can be easily adopted, addresses the shortcomings of the existing systems and should be considered for future editions of the TNM staging system.
Asunto(s)
Carcinoma de Células Escamosas , Neoplasias de la Boca , Humanos , Neoplasias de la Boca/cirugía , Neoplasias de la Boca/patología , Carcinoma de Células Escamosas/patología , Estudios Retrospectivos , Pronóstico , Estadificación de NeoplasiasRESUMEN
OBJECTIVE: The 2x2 factorial design is an effective method that allows for multiple comparisons, especially in the context of interactions between different interventions, without substantially increasing the required sample size. In view of the considerable preclinical evidence for Curcumin and Metformin in preventing the development and progression of head and neck squamous cell carcinoma (HNSCC), this study describes the protocol of the clinical trial towards applying the drug combination in prevention of second primary tumors. METHODS: We have applied the trial design to a large phase IIB/III double-blind, multi-centric, placebo-controlled, randomized clinical trial to determine the safety and efficacy of Metformin and Curcumin in the prevention of second primary tumours (SPT) of the aerodigestive tract following treatment of HNSCC (n=1,500) [Clinical Registry of India, CTRI/2018/03/012274]. Patients recruited in this trial will receive Metformin (with placebo), Curcumin (with placebo), Metformin, and Curcumin or placebo alone for a period of 36 months. The primary endpoint of this trial is the development of SPT, while the secondary endpoints are toxicities associated with the agents, incidence of recurrence, and identifying potential biomarkers. In this article, we discuss the 2x2 factorial design and how it applies to the head and neck cancer chemoprevention trial. CONCLUSION: 2x2 factorial design is an effective trial design for chemoprevention clinical trials where the effectiveness of multiple interventions needs to be tested parallelly.
Asunto(s)
Curcumina , Neoplasias de Cabeza y Cuello , Metformina , Neoplasias Primarias Secundarias , Adulto , Anciano , Femenino , Humanos , Masculino , Persona de Mediana Edad , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapéutico , Curcumina/uso terapéutico , Método Doble Ciego , Estudios de Seguimiento , Neoplasias de Cabeza y Cuello/prevención & control , Neoplasias de Cabeza y Cuello/tratamiento farmacológico , Metformina/uso terapéutico , Neoplasias Primarias Secundarias/prevención & control , Pronóstico , Ensayos Clínicos Controlados Aleatorios como Asunto , Proyectos de Investigación , Carcinoma de Células Escamosas de Cabeza y Cuello/prevención & control , Carcinoma de Células Escamosas de Cabeza y Cuello/tratamiento farmacológico , Ensayos Clínicos Fase II como Asunto , Estudios Multicéntricos como Asunto , Ensayos Clínicos Fase III como AsuntoRESUMEN
INTRODUCTION: Facial contour deformities presents with varied aetiology and degrees severity. Accurate assessment, selecting a suitable tissue and sculpturing it to fill the defect is challenging and largely subjective. Objective assessment with imaging and software is not always feasible and preparing a template is complicated. A three-dimensional (3D) wax template pre-fabricated over the facial moulage aids surgeons to fulfil these tasks. Severe deformities demand a stable vascular tissue for an acceptable outcome. MATERIALS AND METHODS: We present review of eight consecutive patients who underwent augmentation of facial contour defects with free flaps between June 2005 and January 2011. De-epithelialised free anterolateral thigh (ALT) flap in three, radial artery forearm flap and fibula osteocutaneous flap in two each and groin flap was used in one patient. A 3D wax template was fabricated by augmenting the deformity on facial moulage. It was utilised to select the flap, to determine the exact dimensions and to sculpture intraoperatively. Ancillary procedures such as genioplasty, rhinoplasty and coloboma correction were performed. RESULTS: The average age at the presentation was 25 years and average disease free interval was 5.5 years and all flaps survived. Mean follow-up period was 21.75 months. The correction was aesthetically acceptable and was maintained without any recurrence or atrophy. CONCLUSION: The 3D wax template on facial moulage is simple, inexpensive and precise objective tool. It provides accurate guide for the planning and execution of the flap reconstruction. The selection of the flap is based on the type and extent of the defect. Superiority of vascularised free tissue is well-known and the ALT flap offers a versatile option for correcting varying degrees of the deformities. Ancillary procedures improve the overall aesthetic outcomes and minor flap touch-up procedures are generally required.
RESUMEN
OBJECTIVE: To evaluate the pharmacokinetics, pharmacodynamics, and safety of a novel U500 insulin aspart formulation (AT278 U500) compared with insulin aspart (IAsp U100). RESEARCH DESIGN AND METHODS: This single-center, randomized, double-blind study was conducted in 38 men with type 1 diabetes (body weight ≤100 kg and total insulin dose <1.2 units/kg/day). Participants received a single dose of either AT278 U500 or IAsp U100 (0.3 units/kg s.c.) in a crossover design, followed by an 8-h euglycemic clamp in the absence of basal insulin. RESULTS: With AT278 U500, onset of appearance in serum was 6 min earlier (P < 0.0001) and reached 50% of maximum concentration 23 min faster (P < 0.0001). Insulin exposure with AT278 U500 was 4.0-fold higher within the first 30 min (95% CI 3.29, 4.90), 1.5-fold higher within the first 60 min (95% CI 1.35, 1.76), and statistically superior up to 90 min postdose (P < 0.05). With AT278 U500, onset of action was 10 min earlier (P < 0.0001) and reached 50% of maximum glucose infusion rate 20 min faster (P < 0.0001). The glucose-lowering effect with AT278 U500 was 8.9-fold higher within the first 30 min (95% CI 5.96, 17.46), 2.4-fold higher within the first 60 min (95% CI 1.92, 3.22), and statistically superior up to 2 h postdose (P < 0.0001). Overall insulin exposure and glucose-lowering effect were comparable. No significant safety findings were observed. CONCLUSIONS: AT278 U500 offers rapid-acting characteristics in a reduced dose volume, with accelerated absorption and onset of action compared with IAsp U100 in the studied population.
Asunto(s)
Diabetes Mellitus Tipo 1 , Hipoglucemiantes , Insulina Aspart , Humanos , Masculino , Diabetes Mellitus Tipo 1/tratamiento farmacológico , Insulina Aspart/efectos adversos , Insulina Aspart/farmacocinética , Insulina Aspart/farmacología , Hipoglucemiantes/efectos adversos , Hipoglucemiantes/farmacocinética , Hipoglucemiantes/farmacología , Adolescente , Adulto Joven , Adulto , Persona de Mediana EdadRESUMEN
The high prevalence of oral potentially-malignant disorders exhibits diverse severity and risk of malignant transformation, which mandates a Point-of-Care diagnostic tool. Low patient compliance for biopsies underscores the need for minimally-invasive diagnosis. Oral cytology, an apt method, is not clinically applicable due to a lack of definitive diagnostic criteria and subjective interpretation. The primary objective of this study was to identify and evaluate the efficacy of biomarkers for cytology-based delineation of high-risk oral lesions. A comprehensive systematic review and meta-analysis of biomarkers recognized a panel of markers (n: 10) delineating dysplastic oral lesions. In this observational cross sectional study, immunohistochemical validation (n: 131) identified a four-marker panel, CD44, Cyclin D1, SNA-1, and MAA, with the best sensitivity (>75%; AUC>0.75) in delineating benign, hyperplasia, and mild-dysplasia (Low Risk Lesions; LRL) from moderate-severe dysplasia (High Grade Dysplasia: HGD) along with cancer. Independent validation by cytology (n: 133) showed that expression of SNA-1 and CD44 significantly delineate HGD and cancer with high sensitivity (>83%). Multiplex validation in another cohort (n: 138), integrated with a machine learning model incorporating clinical parameters, further improved the sensitivity and specificity (>88%). Additionally, image automation with SNA-1 profiled data set also provided a high sensitivity (sensitivity: 86%). In the present study, cytology with a two-marker panel, detecting aberrant glycosylation and a glycoprotein, provided efficient risk stratification of oral lesions. Our study indicated that use of a two-biomarker panel (CD44/SNA-1) integrated with clinical parameters or SNA-1 with automated image analysis (Sensitivity >85%) or multiplexed two-marker panel analysis (Sensitivity: >90%) provided efficient risk stratification of oral lesions, indicating the significance of biomarker-integrated cytopathology in the development of a Point-of-care assay.
Asunto(s)
Bioensayo , Receptores de Hialuranos , Humanos , Hiperplasia/diagnóstico , Automatización , Biopsia , Glicosilación , Estudios Observacionales como AsuntoRESUMEN
Oral Cancer is one of the most common causes of morbidity and mortality. Screening and mobile Health (mHealth) based approach facilitates remote early detection of Oral cancer in a resource-constrained settings. The emerging eHealth technology has aided specialist reach to rural areas enabling remote monitoring and triaging to downstage Oral cancer. Though the diagnostic accuracy of the remote specialist has been evaluated, there are no studies evaluating the consistency among the remote specialists, to the best of our knowledge. The purpose of the study was to evaluate the interobserver agreement between the specialists through telemedicine systems in real-world settings using store and forward technology. Two remote specialists independently diagnosed the clinical images from image repositories, and the diagnostic accuracy was compared with onsite specialist and histopathological diagnosis when available. Moderate agreement (k = 0.682) between two remote specialists and (k = 0.629) between the onsite specialist and two remote specialists in diagnosing oral lesions. The sensitivity and specificity of remote specialist 1 were 92.7% and 83.3%, whereas remote specialist 2 was 95.8% and 60%, respectively, compared to histopathology. The store and forward technology and telecare can be effective tools in triaging and surveillance of patients.
RESUMEN
Convolutional neural networks have demonstrated excellent performance in oral cancer detection and classification. However, the end-to-end learning strategy makes CNNs hard to interpret, and it can be challenging to fully understand the decision-making procedure. Additionally, reliability is also a significant challenge for CNN based approaches. In this study, we proposed a neural network called the attention branch network (ABN), which combines the visual explanation and attention mechanisms to improve the recognition performance and interpret the decision-making simultaneously. We also embedded expert knowledge into the network by having human experts manually edit the attention maps for the attention mechanism. Our experiments have shown that ABN performs better than the original baseline network. By introducing the Squeeze-and-Excitation (SE) blocks to the network, the cross-validation accuracy increased further. Furthermore, we observed that some previously misclassified cases were correctly recognized after updating by manually editing the attention maps. The cross-validation accuracy increased from 0.846 to 0.875 with the ABN (Resnet18 as baseline), 0.877 with SE-ABN, and 0.903 after embedding expert knowledge. The proposed method provides an accurate, interpretable, and reliable oral cancer computer-aided diagnosis system through visual explanation, attention mechanisms, and expert knowledge embedding.
RESUMEN
Oral tongue squamous cell carcinoma (OTSCC) is one of the major causes of fatality in India due to very high percentage of patients with habits of smoking and chewing tobacco and associated products. Being highly heterogeneous in nature, every patient poses a different challenge clinically. To understand disease progression in an improved way, knowledge of crosstalk between tumor stroma and the tumor cells becomes indispensable. Patientderived in vitro cell line models are helpful to understand the complexity of diseases. However, they have very low efficiency of establishment from the tumor samples, particularly the cancerassociated fibroblasts (CAFs). In the present study, two novel autologous pairs were immortalized spontaneously from nonhabitual, HPVpositive patients, who presented with OTSCC. The epithelial and fibroblast cell lines had typical polygonal and spindleshaped morphology, respectively. Positive staining with epithelial specific Pancytokeratin (PanCK) and fibroblast specific protein (FSP1) further confirmed their epithelial and fibroblast origin. Unique Short Tandem Repeat (STR) profile of the cultures confirmed their novelty, while the similarity of the STR profiles between the epithelial and fibroblast cells from the same patient, confirmed their autologous nature. DNA analysis revealed aneuploidy of the established cultures. An increase in the tumorigenic potential of the established epithelial cultures upon treatment with CAFconditioned medium proved the 'CAFness' of the established fibroblast cells. The established cultures are the first of their kind which would serve as a useful platform in understanding the tumorstroma crosstalk in tongue cancer progression.
Asunto(s)
Carcinoma de Células Escamosas , Neoplasias de Cabeza y Cuello , Neoplasias de la Lengua , Carcinoma de Células Escamosas/patología , Línea Celular Tumoral , Humanos , Carcinoma de Células Escamosas de Cabeza y Cuello , Lengua/patología , Neoplasias de la Lengua/genética , Neoplasias de la Lengua/patologíaRESUMEN
Desmoid fibromatosis (DF) arising from musculoaponeurotic structures rarely affects the head and neck region with the abdomen being the most common site of origin. These are benign tumors with locally infiltrative nature usually presenting as painless swellings that are rapidly growing. The infratemporal fossa DF is an extremely rare location with few clinical reports. This article discusses the management of a 2-year-old child with DF of the infratemporal fossa (ITF) along with literature review.
RESUMEN
Subramanian Kannan Serum thyroglobulin (Tg) and thyroglobulin antibody (TgAb) levels are used to monitor patients with differentiated thyroid cancer (DTC) after total thyroidectomy with or without radioiodine (RAI) ablation. However, they are also measured in patients who are treated with thyroid lobectomy (TL)/hemithyroidectomy (HT). Data on the levels of Tg and its trend in those undergoing TL/HT is sparse in India. We reviewed retrospective data of DTC patients who underwent TL/HT and were followed-up with postoperative Tg levels between 2015 and 2020. Out of 247 patients, 17 had undergone either TL or HT, which included papillary thyroid cancer ( n = 12), follicular thyroid cancer ( n = 4), and noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) in 1 patient. All patients with DTC had tumor size < 4 cm (T1/2, clinical N0, Mx). The median follow-up was 15 months (range, 1-125) and the median Tg level was 7.5 ng/mL (interquartile range [IQR]; 3.6, 7.5) and ranged from 0.9 to 36.7 ng/mL. The median thyroid-stimulating hormone (TSH) level was 2.03 IU/L (IQR; 1.21, 3.59) and it ranged from 0.05 to 8.54 IU/L. As of last follow-up, none of them underwent completion thyroidectomy; however, eight patients had a decline in Tg ranging from 8 to 64%, four patients had increase in Tg ranging from 14 to 145%, three patients had stable Tg, and one of them had an increase in TgAb titers. As per American Thyroid Association (ATA) response-to-treatment category, six patients had indeterminate response, five patients had biochemical incomplete response, four patients had excellent response, and two did not have follow-up Tg and TgAb levels. While absolute values of Tg were well below 30 ng/mL in almost all patients with HT/TL, the Tg trends were difficult to predict, and only 23% of patients were able to satisfy the criteria for "excellent response" on follow-up. We suggest keeping this factor in mind in follow-up and while counselling for HT in patients with low-risk DTC.
RESUMEN
BACKGROUND: Despite revised staging criteria, stratification of patients with advanced oral squamous cell carcinoma (OSCC) remains difficult. Well-established features like perineural invasion (PNI), differentiation, and lymphovascular-invasion (LVI) are controversial, and hence omitted from staging. We endeavor to better stratify this cohort by identifying predictors of survival in advanced OSCC (T3-4). METHODS: Seven hundred and forty-two patients with T3-4 OSCC underwent surgery from 2006 to 2013. Cox regression was performed to determine predictors of overall survival (OS). RESULTS: OS was adversely impacted by PNI (p = 0.046), LVI (p = 0.038), moderate/poor differentiation (p = 0.001), close/involved surgical margins (p = 0.002), pT (p = 0.034), and pN (p < 0.001). The cumulative number of adverse histopathological features predicted poorer OS; HR 2.64 (CI 1.42-4.90) for one adverse feature and HR 4.23 (CI 2.34-7.67) for ≥2. CONCLUSION: In advanced OSCC, stratification with histopathologic risk factors can predict survival even in maximally treated patients; adjuvant therapies are unable to entirely mitigate this risk. Incorporation of adverse features into future editions of TNM can improve precision in staging and identify candidates for treatment escalation.
Asunto(s)
Carcinoma de Células Escamosas , Neoplasias de Cabeza y Cuello , Neoplasias de la Boca , Carcinoma de Células Escamosas/patología , Neoplasias de Cabeza y Cuello/patología , Humanos , Neoplasias de la Boca/patología , Invasividad Neoplásica/patología , Estadificación de Neoplasias , Pronóstico , Estudios RetrospectivosRESUMEN
Significance: Oral cancer is one of the most prevalent cancers, especially in middle- and low-income countries such as India. Automatic segmentation of oral cancer images can improve the diagnostic workflow, which is a significant task in oral cancer image analysis. Despite the remarkable success of deep-learning networks in medical segmentation, they rarely provide uncertainty quantification for their output. Aim: We aim to estimate uncertainty in a deep-learning approach to semantic segmentation of oral cancer images and to improve the accuracy and reliability of predictions. Approach: This work introduced a UNet-based Bayesian deep-learning (BDL) model to segment potentially malignant and malignant lesion areas in the oral cavity. The model can quantify uncertainty in predictions. We also developed an efficient model that increased the inference speed, which is almost six times smaller and two times faster (inference speed) than the original UNet. The dataset in this study was collected using our customized screening platform and was annotated by oral oncology specialists. Results: The proposed approach achieved good segmentation performance as well as good uncertainty estimation performance. In the experiments, we observed an improvement in pixel accuracy and mean intersection over union by removing uncertain pixels. This result reflects that the model provided less accurate predictions in uncertain areas that may need more attention and further inspection. The experiments also showed that with some performance compromises, the efficient model reduced computation time and model size, which expands the potential for implementation on portable devices used in resource-limited settings. Conclusions: Our study demonstrates the UNet-based BDL model not only can perform potentially malignant and malignant oral lesion segmentation, but also can provide informative pixel-level uncertainty estimation. With this extra uncertainty information, the accuracy and reliability of the model's prediction can be improved.
Asunto(s)
Neoplasias de la Boca , Semántica , Humanos , Incertidumbre , Teorema de Bayes , Reproducibilidad de los Resultados , Redes Neurales de la Computación , Procesamiento de Imagen Asistido por Computador/métodos , Neoplasias de la Boca/diagnóstico por imagenRESUMEN
Background: Oral squamous cell carcinoma (OSCC) is a common head and neck cancer with high morbidity and mortality. Currently, treatment decisions are guided by TNM staging, which omits important negative prognosticators such as lymphovascular invasion, perineural invasion (PNI), and histologic differentiation. We proposed nomogram models based on adverse pathological features to identify candidates suitable for treatment escalation within each risk group according to the National Comprehensive Cancer Network (NCCN) guidelines. Methods: Anonymized clinicopathologic data of OSCC patients from 5 tertiary healthcare institutions in Asia were divided into 3 risk groups according to the NCCN guidelines. Within each risk group, nomograms were built to predict overall survival based on histologic differentiation, histologic margin involvement, depth of invasion (DOI), extranodal extension, PNI, lymphovascular, and bone invasion. Nomograms were internally validated with precision-recall analysis and the Kaplan-Meier survival analysis. Results: Low-risk patients with positive pathological nodal involvement and/or positive PNI should be considered for adjuvant radiotherapy. Intermediate-risk patients with gross bone invasion may benefit from concurrent chemotherapy. High-risk patients with positive margins, high DOI, and a high composite score of histologic differentiation, PNI, and the American Joint Committee on Cancer (AJCC) 8th edition T staging should be considered for treatment escalation to experimental therapies in clinical trials. Conclusion: Nomograms built based on prognostic adverse pathological features can be used within each NCCN risk group to fine-tune treatment decisions for OSCC patients.
RESUMEN
Early detection of oral cancer in low-resource settings necessitates a Point-of-Care screening tool that empowers Frontline-Health-Workers (FHW). This study was conducted to validate the accuracy of Convolutional-Neural-Network (CNN) enabled m(mobile)-Health device deployed with FHWs for delineation of suspicious oral lesions (malignant/potentially-malignant disorders). The effectiveness of the device was tested in tertiary-care hospitals and low-resource settings in India. The subjects were screened independently, either by FHWs alone or along with specialists. All the subjects were also remotely evaluated by oral cancer specialist/s. The program screened 5025 subjects (Images: 32,128) with 95% (n = 4728) having telediagnosis. Among the 16% (n = 752) assessed by onsite specialists, 20% (n = 102) underwent biopsy. Simple and complex CNN were integrated into the mobile phone and cloud respectively. The onsite specialist diagnosis showed a high sensitivity (94%), when compared to histology, while telediagnosis showed high accuracy in comparison with onsite specialists (sensitivity: 95%; specificity: 84%). FHWs, however, when compared with telediagnosis, identified suspicious lesions with less sensitivity (60%). Phone integrated, CNN (MobileNet) accurately delineated lesions (n = 1416; sensitivity: 82%) and Cloud-based CNN (VGG19) had higher accuracy (sensitivity: 87%) with tele-diagnosis as reference standard. The results of the study suggest that an automated mHealth-enabled, dual-image system is a useful triaging tool and empowers FHWs for oral cancer screening in low-resource settings.
Asunto(s)
Teléfono Celular , Aprendizaje Profundo , Neoplasias de la Boca , Telemedicina , Detección Precoz del Cáncer/métodos , Humanos , Neoplasias de la Boca/diagnóstico , Neoplasias de la Boca/patología , Sistemas de Atención de Punto , Telemedicina/métodosRESUMEN
SIGNIFICANCE: Convolutional neural networks (CNNs) show the potential for automated classification of different cancer lesions. However, their lack of interpretability and explainability makes CNNs less than understandable. Furthermore, CNNs may incorrectly concentrate on other areas surrounding the salient object, rather than the network's attention focusing directly on the object to be recognized, as the network has no incentive to focus solely on the correct subjects to be detected. This inhibits the reliability of CNNs, especially for biomedical applications. AIM: Develop a deep learning training approach that could provide understandability to its predictions and directly guide the network to concentrate its attention and accurately delineate cancerous regions of the image. APPROACH: We utilized Selvaraju et al.'s gradient-weighted class activation mapping to inject interpretability and explainability into CNNs. We adopted a two-stage training process with data augmentation techniques and Li et al.'s guided attention inference network (GAIN) to train images captured using our customized mobile oral screening devices. The GAIN architecture consists of three streams of network training: classification stream, attention mining stream, and bounding box stream. By adopting the GAIN training architecture, we jointly optimized the classification and segmentation accuracy of our CNN by treating these attention maps as reliable priors to develop attention maps with more complete and accurate segmentation. RESULTS: The network's attention map will help us to actively understand what the network is focusing on and looking at during its decision-making process. The results also show that the proposed method could guide the trained neural network to highlight and focus its attention on the correct lesion areas in the images when making a decision, rather than focusing its attention on relevant yet incorrect regions. CONCLUSIONS: We demonstrate the effectiveness of our approach for more interpretable and reliable oral potentially malignant lesion and malignant lesion classification.
Asunto(s)
Aprendizaje Profundo , Neoplasias de la Boca , Atención , Humanos , Neoplasias de la Boca/diagnóstico por imagen , Redes Neurales de la Computación , Reproducibilidad de los ResultadosRESUMEN
OBJECTIVES: The AJCC 8th edition (AJCC 8) has introduced depth of invasion (DOI) and extranodal extension (ENE) into staging for oral squamous cell carcinoma (OSCC). Although validations have been performed on institutional datasets have shown a good performance, particularly in early OSCC, there have been no studies on diverse patient populations that determine the impact on prognostic heterogeneity. MATERIALS AND METHODS: Retrospective analysis of 4710 patients with oral squamous cell carcinoma (OSCC) treated with surgery +/- adjuvant therapy in 8 institutions in Australia, North America and Asia. With overall survival (OS) as endpoint, the prognostic performance of AJCC 7th and 8th editions were compared using Akaike Information Criterion (AIC), Bayesian Information Criteria (BIC), Harrell's concordance index (C-index). RESULTS: When comparing AJCC 8 to AJCC 7, the heterogeneity in prediction of OS increased for T-category and N-category while remaining unchanged for TNM staging, suggesting AJCC 8 increased complexity with no improvement in predictive value. There were significant differences in median DOI and incidence of ENE between geographical regions, resulting in dissimilar rates of stage-migration when adopting AJCC 8. CONCLUSION: In an attempt to improve prognostic performance, AJCC 8 introduced more variables; however heterogeneity in these results in significant geographical differences in model discrimination and performance. Caution should be applied as this may result in inaccurate and unreliable prognostic predictions that may impact treatment recommendations.