Diagnosis Of Esophageal Cancer Research Articles

Pairwise machine learning-based automatic diagnostic platform utilizing CT images and clinical information for predicting radiotherapy locoregional recurrence in elderly esophageal cancer patients.

To investigate the feasibility and accuracy of predicting locoregional recurrence (LR) in elderly patients with esophageal squamous cell cancer (ESCC) who underwent radical radiotherapy using a pairwise machine learning algorithm. The 130 datasets enrolled were randomly divided into a training set and a testing set in a 7:3 ratio. Clinical factors were included and radiomics features were extracted from pretreatment CT scans using pyradiomics-based software, and a pairwise naive Bayes (NB) model was developed. The performance of the model was evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). To facilitate practical application, we attempted to construct an automated esophageal cancer diagnosis system based on trained models. To the follow-up date, 64 patients (49.23%) had experienced LR. Ten radiomics features and two clinical factors were selected for modeling. The model demonstrated good prediction performance, with area under the ROC curve of 0.903 (0.829-0.958) for the training cohort and 0.944 (0.849-1.000) for the testing cohort. The corresponding accuracies were 0.852 and 0.914, respectively. Calibration curves showed good agreement, and DCA curve confirmed the clinical validity of the model. The model accurately predicted LR in elderly patients, with a positive predictive value of 85.71% for the testing cohort. The pairwise NB model, based on pre-treatment enhanced chest CT-based radiomics and clinical factors, can accurately predict LR in elderly patients with ESCC. The esophageal cancer automated diagnostic system embedded with the pairwise NB model holds significant potential for application in clinical practice.

Chinese expert consensus on surgical continuous quality improvement goals in esophageal cancer and esophagogastric junction cancer (2024 edition)

Improving the quality and efficiency of surgical diagnosis and treatment guarantees the outcome for most patients with esophageal cancer and esophagogastric junction cancer, and the continuous quality improvement mechanism oriented to the "textbook outcome" is the best choice. To ensure the successful implementation of the "Quality Control Indicators for Standardized Diagnosis and Treatment of Esophageal Cancer in China (2022 Version)" aligning with it more effectively is crucial. The Expert Committee on Quality Control of Esophageal Cancer at the National Cancer Center leads work teams comprised of multidisciplinary experts, particularly those in thoracic surgery, to establish a consensus. The current consensus comprises eight "textbook outcomes" to standardize, promote, and consolidate surgical quality management and continuously improve the surgical quality of esophageal cancer and esophagogastric junction cancer.

Esophageal tuberculosis as a differential diagnosis of esophageal cancer.

The case of a patient in the eighth decade of life who begins with dysphagia and progressive weight loss is presented, who underwent contrast-enhanced tomography where a tumor was observed in the esophagus, endoscopy with biopsy and a report of esophageal tuberculosis.

Using Machine Learning and miRNA for the Diagnosis of Esophageal Cancer

Abstract Background Esophageal cancer (EC) remains a global health challenge, often diagnosed at advanced stages, leading to high mortality rates. Current diagnostic tools for EC are limited in their efficacy. This study aims to harness the potential of microRNAs (miRNAs) as novel, noninvasive diagnostic biomarkers for EC. Our objective was to determine the diagnostic accuracy of miRNAs, particularly in distinguishing miRNAs associated with EC from control miRNAs. Methods We applied machine learning (ML) techniques in WEKA (Waikato Environment for Knowledge Analysis) and TensorFlow Keras to a dataset of miRNA sequences and gene targets, assessing the predictive power of several classifiers: naïve Bayes, multilayer perceptron, Hoeffding tree, random forest, and random tree. The data were further subjected to InfoGain feature selection to identify the most informative miRNA sequence and gene target descriptors. The ML models’ abilities to distinguish between miRNA implicated in EC and control group miRNA was then tested. Results Of the tested WEKA classifiers, the top 3 performing ones were random forest, Hoeffding tree, and naïve Bayes. The TensorFlow Keras neural network model was subsequently trained and tested, the model’s predictive power was further validated using an independent dataset. The TensorFlow Keras gave an accuracy 0.91. The WEKA best algorithm (naïve Bayes) model yielded an accuracy of 0.94. Conclusions The results demonstrate the potential of ML-based miRNA classifiers in diagnosing EC. However, further studies are necessary to validate these findings and explore the full clinical potential of this approach.

Efficiency of endoscopic artificial intelligence in the diagnosis of early esophageal cancer.

The accuracy of artificial intelligence (AI) and experts in diagnosing early esophageal cancer (EC) and its infiltration depth was summarized and analyzed, thus identifying the advantages of AI over traditional manual diagnosis, with a view to more accurately assisting doctors in evaluating the patients' conditions and improving their cure and survival rates. The PubMed, EMBASE, Cochrane, Google, and CNKI databases were searched for relevant literature related to AI diagnosis of early EC and its invasion depth published before August 2023. Summary analysis of pooled sensitivity, specificity, summary receiver operating characteristics (SROC) and area under the curve (AUC) of AI in diagnosing early EC were performed, and Review Manager and Stata were adopted for data analysis. A total of 19 studies were enrolled with a low to moderate total risk of bias. The pooled sensitivity of AI for diagnosing early EC was markedly higher than that of novices and comparable to that of endoscopists. Moreover, AI predicted early EC with markedly higher AUCs than novices and experts (0.93 vs. 0.74 vs. 0.89). In addition, pooled sensitivity and specificity in the diagnosis of invasion depth in early EC were higher than that of experts, with AUCs of 0.97 and 0.92, respectively. AI-assistance can diagnose early EC and its infiltration depth more accurately, which can help in its early intervention and the customization of personalized treatment plans. Therefore, AI systems have great potential in the early diagnosis of EC.

Exploring Potential Biomarkers in Oesophageal Cancer: A Comprehensive Analysis.

Oesophageal cancer (OC) is the sixth leading cause of cancer-related death worldwide. OC is highly aggressive, primarily due to its late stage of diagnosis and poor prognosis for patients' survival. Therefore, the establishment of new biomarkers that will be measured with non-invasive techniques at low cost is a critical issue in improving the diagnosis of OC. In this review, we summarize several original studies concerning the potential significance of selected chemokines and their receptors, including inflammatory proteins such as interleukin-6 (IL-6) and C-reactive protein (CRP), hematopoietic growth factors (HGFs), claudins (CLDNs), matrix metalloproteinases (MMPs) and their tissue inhibitors (TIMPs), adamalysines (ADAMs), as well as DNA- and RNA-based biomarkers, in OC. The presented results indicate the significant correlation between the CXCL12, CXCR4, CXCL8/CXCR2, M-CSF, MMP-2, MMP-9 ADAM17, ADAMTS-6, and CLDN7 levels and tumor stage, as well as the clinicopathological parameters of OC, such as the presence of lymph node and/or distant metastases. CXCL12, CXCL8/CXCR2, IL-6, TIMP-2, ADAM9, and ADAMTS-6 were prognostic factors for the overall survival of OC patients. Furthermore, IL-6, CXCR4, CXCL8, and MMP-9 indicate higher diagnostic utility based on the area under the ROC curve (AUC) than well-established OC tumor markers, whereas CLDN18.2 can be used in novel targeted therapies for OC patients.

Endoscopic diagnosis of gastric and oesophageal cancer in Lusaka, Zambia: a retrospective analysis

IntroductionThere are uncertainties surrounding the spectrum of upper gastrointestinal (UGI) diseases in sub-Saharan Africa. This is mainly due to the limitations of data collection and recording. We previously reported an audit of UGI endoscopic diagnoses in Zambia spanning from 1977 to 2014. We now have extended this analysis to include subsequent years, in order to provide a more comprehensive picture of how the diagnoses have evolved over 4 decades.MethodsWe combined data collected from the endoscopy unit at the University Teaching Hospital (UTH) in Lusaka during a previous review with that collected from the beginning of 2015 to the end of 2021. Since 2015, an electronic data base of endoscopy reports at the UTH was kept. The electronic data base was composed of drop-down menus that allowed for standardised reporting of findings. Collected data were coded by two experienced endoscopists and analysed.ResultsIn total, the analysis included 25,849 endoscopic records covering 43 years. The number of endoscopic procedures performed per year increased drastically in 2010. With the exception of the last 2 years, the proportion of normal endoscopies also increased during the time under review. In total, the number of gastric cancer (GC) cases was 658 (3%) while that of oesophageal cancer (OC) was 1168 (5%). The number of GC and OC diagnoses increased significantly over the period under review, (p < 0.001 for both). For OC the increase remained significant when analysed as a percentage of all procedures performed (p < 0.001). Gastric ulcers (GU) were diagnosed in 2095 (8%) cases, duodenal ulcers (DU) in 2276 (9%) cases and 239 (1%) had both ulcer types. DU diagnosis showed a significantly decreasing trend over each decade (p < 0.001) while GU followed an increasing trend (p < 0.001).ConclusionsUGI endoscopic findings in Lusaka, Zambia, have evolved over the past four decades with a significant increase of OC and GU diagnoses. Reasons for these observations are yet to be established.

Computer-aided diagnostic system with automated deep learning method based on the AutoGluon framework improved the diagnostic accuracy of early esophageal cancer.

There have been studies on the application of computer-aided diagnosis (CAD) in the endoscopic diagnosis of early esophageal cancer (EEC), but there is still a significant gap from clinical application. We developed an endoscopic CAD system for EEC based on the AutoGluon framework, aiming to explore the feasibility of automatic deep learning (DL) in clinical application. The endoscopic pictures of normal esophagus, esophagitis, and EEC were collected from The First Affiliated Hospital of Soochow University (September 2015 to December 2021) and the Norwegian HyperKvasir database. All images of non-cancerous esophageal lesions and EEC in this study were pathologically examined. There were three tasks: task A was normal vs. lesion classification under non-magnifying endoscopy (n=932 vs. 1,092); task B was non-cancer lesion vs. EEC classification under non-magnifying endoscopy (n=594 vs. 429); and task C was non-cancer lesion vs. EEC classification under magnifying endoscopy (n=505 vs. 824). In all classification tasks, we took 100 pictures as the verification set, and the rest comprised as the training set. The CAD system was established based on the AutoGluon framework. Diagnostic performance of the model was compared with that of endoscopists grouped according to years of experience (senior >15 years; junior <5 years). Model evaluation indicators included accuracy, recall rate, precision, F1 value, interpretation time, and the area under the receiver operating characteristic (ROC) curve (AUC). In tasks A and B, the accuracies of medium-performance CAD and high-performance CAD were lower than those of junior doctors and senior doctors. In task C, the medium-performance and high-performance CAD accuracies were close to those of junior doctors and senior doctors. The high-performance CAD model outperformed the junior doctors in both task A (0.850 vs. 0.830) and task C (0.840 vs. 0.830) in sensitivity comparison, but there was still a large gap between high-performance CAD models and doctors in sensitivity comparison. In task A, with the aid of CAD pre-interpretation, the accuracy of junior and senior physicians were significantly improved (from 0.880 to 0.915 and from 0.920 to 0.945, respectively); the time spent on film reading was significantly shortened (junior: from 11.3 to 8.7 s; senior: from 6.7 to 5.5 s). In task C, with the aid of CAD pre-interpretation, the accuracy of junior and senior physicians were significantly improved (from 0.850 to 0.865 and from 0.915 to 0.935, respectively); the reading time was significantly shortened (junior: from 9.5 to 7.7 s; senior: from 5.6 to 3.0 s). The CAD system based on the AutoGluon framework can assist doctors to improve the diagnostic accuracy and reading time of EEC under endoscopy. This study reveals that automatic DL methods are promising in clinical application.

SIMULTANEOUS CORONARY BYPASS AND ESOPHAGECTOMY IN PATIENTS WITH ESOPHAGEAL TUMOR

HighlightsThe article presents data on international practices regarding simultaneous coronary bypass surgery and esophagectomy. There are very few works devoted to this topic in the literature, whereas such patients can show up unexpectedly but cannot safely undergo multiple procedures. Studying the international practices will allow specialists to make the right decision in each individual case. AbstractCoronary heart disease (CHD) remains the leading cause of death from cardiovascular disease, accounting for nearly 50% of deaths. However, recent data show a significant change in the composition of patients with CHD: patients with a concomitant diagnosis of esophageal cancer, a disease for which a new generation of novel immune and targeted therapies has altered and significantly increased life expectancy, predominate. However, the treatment algorithm for such patients is not fully known. If myocardial revascularization is performed first, radical surgery regarding the tumor will be delayed. If first to perform surgical intervention on the esophagus, then the number of complications increases, which according to some authors is 30–40 times higher than in patients without cardiac disease. One-stage intervention and simultaneous surgery allows to avoid such problems. This article summarizes the world experience of such interventions.

National clinical and financial outcomes associated with acute kidney injury following esophagectomy for cancer.

Esophagectomy is a complex oncologic operation associated with high rates of postoperative complications. While respiratory and septic complications have been well-defined, the implications of acute kidney injury (AKI) remain unclear. Using a nationally representative database, we aimed to characterize the association of AKI with mortality, resource use, and 30-day readmission. All adults undergoing elective esophagectomy with a diagnosis of esophageal or gastric cancer were identified in the 2010-2019 Nationwide Readmissions Database. Study cohorts were stratified based on presence of AKI. Multivariable regressions and Royston-Parmar survival analysis were used to evaluate the independent association between AKI and outcomes of interest. Of an estimated 40,438 patients, 3,210 (7.9%) developed AKI. Over the 10-year study period, the incidence of AKI increased from 6.4% to 9.7%. Prior radiation/chemotherapy and minimally invasive operations were associated with reduced odds of AKI, whereas public insurance coverage and concurrent infectious and respiratory complications had greater risk of AKI. After risk adjustment, AKI remained independently associated with greater odds of in-hospital mortality (AOR: 4.59, 95% CI: 3.62-5.83) and had significantly increased attributable costs ($112,000 vs $54,000) and length of stay (25.7 vs 13.3 days) compared to patients without AKI. Furthermore, AKI demonstrated significantly increased hazard of 30-day readmission (hazard ratio: 1.16, 95% CI: 1.01-1.32). AKI after esophagectomy is associated with greater risk of mortality, hospitalization costs, and 30-day readmission. Given the significant adverse consequences of AKI, careful perioperative management to mitigate this complication may improve quality of esophageal surgical care at the national level.

Esophageal cancer: current status and new insights from inflammatory markers – a brief review

Esophageal cancer (EC) poses a significant challenge to the healthcare system due to its profound impact on cancer-related morbidity and mortality worldwide. This malignancy ranks among the most arduous conditions confronting the surgeon. EC arises from a complex interplay of genetic predispositions and environmental factors. While the incidence of esophageal adenocarcinoma (EAC) is on the rise in the West, esophageal squamous cell carcinoma (ESCC) remains prevalent in the East. Chronic inflammation plays a pivotal role in the initiation and progression of EC. Accordingly, serum inflammatory markers, growth factors, and cytokines have been shown to be clinically useful. Thus, evaluating serum cytokine levels for EC prediction is a safe and feasible screening method. Given the aggressive nature and poor prognosis of the disease, innovative approaches to diagnosis, prognosis, and management of EC are indispensable. This review discusses the major risk factors and the current landscape of EC, with a specific focus on the potential contributions of new inflammatory markers to enhance disease management and improve patient outcomes.

Endoscopic Diagnosis and Treatment of Early Mucosal Neoplasms in the Oesophagus

Endoscopy is the gold standard for diagnosis of oesophageal cancer and its precursor lesions. Besides this, endoscopy treatment of these precursor lesions and early oesophageal cancer has been well evaluated and established. This includes dysplastic lesions associated with Barrett's oesophagus and early adenocarcinoma, as well as early squamous cell cancer of the oesophagus. The role of endoscopy for diagnosis and treatment of these lesions is summarised.

Secondary Esophageal Cancer After Hematopoietic Stem Cell Transplant: An Institutional Case Series

BackgroundDevelopment of secondary esophageal cancer after hematopoietic stem cell transplantation has been described; however, there is little consensus on treatment and surveillance for these patients. The objective of this study was to describe our experience treating patients with secondary esophageal cancer. MethodsA retrospective chart review of prospectively collected data was performed to identify patients who underwent hematopoietic stem cell transplantation from 1997 to 2012 and in whom esophageal cancer developed later. ResultsA total of 5066 patients underwent hematopoietic stem cell transplantation, and esophageal cancer developed in 11 (0.2%) of these patients. The median time to diagnosis of esophageal cancer after hematopoietic stem cell transplantation was 11 years (interquartile range, 8.5 to 14 years). Four patients received a diagnosis of stage III or IV disease. Seven patients underwent esophagectomy, 6 patients after neoadjuvant treatment. Three patients experienced adverse events postoperatively, all grades II and IIIa. Two surgical patients died of distant recurrence 2 years and 3 years, respectively, after their esophageal cancer diagnosis. The other 5 surgical patients have not experienced recurrence of their esophageal cancer. ConclusionsFor patients with secondary esophageal cancer, esophagectomy after neoadjuvant treatment has acceptable morbidity and may be a viable option for this cohort.

Causal relationship between gut microbiota and risk of esophageal cancer: evidence from Mendelian randomization study.

The causative implications remain ambiguous. Consequently, this study aims to evaluate the putative causal relationship between gut microbiota and Esophageal cancer (EC). The genome-wide association study (GWAS) pertaining to the microbiome, derived from the MiBioGen consortium-which consolidates 18,340 samples across 24 population-based cohorts-was utilized as the exposure dataset. Employing the GWAS summary statistics specific to EC patients sourced from the GWAS Catalog and leveraging the two-sample Mendelian randomization (MR) methodology, the principal analytical method applied was the inverse variance weighted (IVW) technique. Cochran's Q statistic was utilized to discern heterogeneity inherent in the data set. Subsequently, a reverse MR analysis was executed. Findings derived from the IVW technique elucidated that the Family Porphyromonadaceae (P = 0.048) and Genus Candidatus Soleaferrea (P = 0.048) function as deterrents against EC development. In contrast, the Genus Catenibacterium (P = 0.044), Genus Eubacterium coprostanoligenes group (P = 0.038), Genus Marvinbryantia (P = 0.049), Genus Ruminococcaceae UCG010 (P = 0.034), Genus Ruminococcus1 (P = 0.047), and Genus Sutterella (P = 0.012) emerged as prospective risk contributors for EC. To assess reverse causal effect, we used EC as the exposure and the gut microbiota as the outcome, and this analysis revealed associations between EC and seven different types of gut microbiota. The robustness of the MR findings was substantiated through comprehensive heterogeneity and pleiotropy evaluations. This research identified certain microbial taxa as either protective or detrimental elements for EC, potentially offering valuable biomarkers for asymptomatic diagnosis and prospective therapeutic interventions for EC.

Ensembled CNN with artificial bee colony optimization method for esophageal cancer stage classification using SVM classifier.

Esophageal cancer (EC) is aggressive cancer with a high fatality rate and a rapid rise of the incidence globally. However, early diagnosis of EC remains a challenging task for clinicians. To help address and overcome this challenge, this study aims to develop and test a new computer-aided diagnosis (CAD) network that combines several machine learning models and optimization methods to detect EC and classify cancer stages. The study develops a new deep learning network for the classification of the various stages of EC and the premalignant stage, Barrett's Esophagus from endoscopic images. The proposed model uses a multi-convolution neural network (CNN) model combined with Xception, Mobilenetv2, GoogLeNet, and Darknet53 for feature extraction. The extracted features are blended and are then applied on to wrapper based Artificial Bee Colony (ABC) optimization technique to grade the most accurate and relevant attributes. A multi-class support vector machine (SVM) classifies the selected feature set into the various stages. A study dataset involving 523 Barrett's Esophagus images, 217 ESCC images and 288 EAC images is used to train the proposed network and test its classification performance. The proposed network combining Xception, mobilenetv2, GoogLeNet, and Darknet53 outperforms all the existing methods with an overall classification accuracy of 97.76% using a 3-fold cross-validation method. This study demonstrates that a new deep learning network that combines a multi-CNN model with ABC and a multi-SVM is more efficient than those with individual pre-trained networks for the EC analysis and stage classification.

Impact of the COVID-19 pandemic on esophageal cancer resource allocation: a systematic review.

The coronavirus disease 2019 (COVID-19) pandemic challenged global infrastructure. Healthcare systems were forced to reallocate resources toward the frontlines. In this systematic review, we analyze the impact of resource reallocation during the COVID-19 pandemic on the diagnosis, management, and outcomes of esophageal cancer (EC) patients. PubMed and Embase were systematically searched for articles investigating the impact of the COVID-19 pandemic on EC patients. Of the 1,722 manuscripts initially screened, 23 met the inclusion criteria. Heterogeneity of data and outcomes reporting prohibited aggregate analysis. Reduced detection of EC and considerable variability in disease stage at presentation were noted during the COVID-19 pandemic. EC patients experienced delays in diagnostic and preoperative staging investigations but surgical resection was not associated with greater short-term morbidity or mortality. Modeling the impact of pandemic-related delays in EC care predicts significant reductions in survival with associated economic losses in the coming years. Amidst resource scarcity during the COVID-19 pandemic, the multidisciplinary management of patients with EC was affected at multiple stages in the care pathway. Although the complete ramifications of reductions in EC diagnosis and delays in care remain unclear, EC surgery was able to safely continue as a result of collaboration between centers, strict adherence to COVID-19 protective measures, and reallocation of healthcare resources towards the same. Ultimately, when healthcare systems are pushed to the brink, the downstream consequences of resource reallocation require judicious analysis to optimize overall patient outcomes.

Updated German guideline on diagnosis and treatment of squamous cell carcinoma and adenocarcinoma of the esophagus.

Diagnosis and therapy of esophageal carcinoma is challenging and requires a multidisciplinary approach. The purpose of the updated German guideline "Diagnosis and Treatment of Squamous Cell Carcinoma and Adenocarcinoma of the Esophagus-version 3.1" is to provide practical and evidence-based advice for the management of patients with esophageal cancer. Recommendations were developed by a multidisciplinary expert panel based on an extensive and systematic evaluation of the published medical literature and the application of well-established methodologies (e.g. Oxford evidence grading scheme, grading of recommendations). Accurate diagnostic evaluation of the primary tumor as well as lymph node and distant metastases is required in order to guide patients to a stage-appropriate therapy after the initial diagnosis of esophageal cancer. In high-grade intraepithelial neoplasia or mucosal carcinoma endoscopic resection shall be performed. Whether endoscopic resection is the definitive therapeutic measure depends on the histopathological evaluation of the resection specimen. Esophagectomy should be performed minimally invasive or in combination with open procedures (hybrid technique). Because the prognosis in locally advanced esophageal carcinoma is poorwith surgery alone, multimodality therapy is recommended. In locally advancedadenocarcinomas of the esophagus or esophagogastric junction, perioperative chemotherapy or preoperative radiochemotherapy should be administered. In locally advanced squamous cell carcinomas of the esophagus, preoperative radiochemotherapy followed by complete resection or definitive radiochemotherapy without surgery should be performed. In the case of residual tumor in the resection specimen after neoadjuvant radiochemotherapy and R0 resection of squamous cell carcinoma or adenocarcinoma, adjuvant immunotherapy with nivolumab should be given. Systemic palliative treatment options (chemotherapy, chemotherapy plus immunotherapy, immunotherapy alone) in unresectable or metastastic esophageal cancer depend on histology and are stratified according to PD-L1 and/or Her2 expression.

Three novel rare TP53 fusion mutations in a patient with multiple primary cancers: a case report

Abstract As survival rates improve and detection technologies advance, the occurrence of multiple primary cancers (MPCs) has been increasing. Approximately 16% of cancer survivors develop a subsequent malignancy, with lung cancer often developing after esophageal cancer due to potential “field cancerization” effects. Despite this observation, the genetic heterogeneity underlying MPCs remains understudied. However, the recent emergence of genetic testing has expanded the scope of investigations into MPCs to investigate signatures underlying cancer predisposition. This report reveals 3 unprecedented TP53 fusion mutations in a Chinese patient afflicted by MPCs, namely, AP1M2–TP53 (A1;T11) fusion, TP53–ILF3 (T10;I13) fusion, and SLC44A2–TP53 (S5;T11) fusion. This patient exhibited an extended period of survival after diagnosis of extensive-stage small cell lung cancer, which occurred 6 years after the diagnosis of esophageal squamous cell cancer. This unique report may provide supplementary data that enhance our understanding of the genetic landscape of MPCs.

Thime Between the diagnosis and treatment of esophagus cancer

INTRODUCTION: Esophagus cancer is the fifth most frequent tumor in the gastrointestinal tract, responsible for 358 thousand deaths per year (1). Because most of the patients are asymptomatics, clinical suspicion is usually low. As it is a rapidly progressive cancer, it needs a fast intervention. This is guaranteed by the law n° 127232/2012, in which an oncologic patient must start treatment at least 60 days after diagnosis. This research aims to analyze if this right was guaranteed in Brazil between 2018 and 2021, considering the COVID-19 pandemic period. OBJECTIVES: To establish a comparison in the time between the diagnosis and the treatment of esophagus cancer in Brazil, during the biennia 2018-2019 and 2020-2021, considering the impact of COVID-19 pandemic. METHODS: This research is an ecologic study with secondary data, about the consequences of the pandemic in the time to start the treatment of malignant esophagus neoplasm in Brazil, between 2020-2021 and 2018 and 2019. The data was obtained from the “PAINEL – oncologia do Departamento de Informática do Sistema Único de Saúde (DATASUS)”, considering the variables' time to start the treatment and year of treatment. The data was analyzed and categorized utilizing the program Microsoft Excel (2019). RESULTS: Between 2018 and 2021 there were 19186 patients diagnosed and treated, the number of treated people in at least 60 days after the diagnosis being 9713 (50,62%), while the ones in which the beginning in less than 60 days was 9473 (49,37%), a difference of 240 (2,5%). There was a non-linear increase in the number of patients treated in more than 60 days, with a decay of 0,98% in 2020 and, right after, an increase of 2,18% in 2021. However, from 2019, the cases with more than 60 days to treat stand out in relation to the less than 60 days. Still, it was observed a discreet increase of 328 cases (6,46%) with less than 60 days to treat in the whole period. CONCLUSION: This study showed that the treatment in more than 60 days after the diagnosis of esophagus cancer has increased quantitatively in a non linear form, while the treatment in less than 60 days increased discreetly in percentage value. Considering these findings, it is suggested that treatment made in more than 60 days has increased during the COVID-19 pandemic, evidencing a possible delay in the start of the treatment in Brazil during this period. Keywords: Esophagus cancer, comparative study, Brazil, cancer, esophagus, diagnosi

Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions.

Accurate segmentation of lesions is crucial for diagnosis and treatment of early esophageal cancer (EEC). However, neither traditional nor deep learning-based methods up to today can meet the clinical requirements, with the mean Dice score - the most important metric in medical image analysis - hardly exceeding 0.75. In this paper, we present a novel deep learning approach for segmenting EEC lesions. Our method stands out for its uniqueness, as it relies solely on a single input image from a patient, forming the so-called "You-Only-Have-One" (YOHO) framework. On one hand, this "one-image-one-network" learning ensures complete patient privacy as it does not use any images from other patients as the training data. On the other hand, it avoids nearly all generalization-related problems since each trained network is applied only to the same input image itself. In particular, we can push the training to "over-fitting" as much as possible to increase the segmentation accuracy. Our technical details include an interaction with clinical doctors to utilize their expertise, a geometry-based data augmentation over a single lesion image to generate the training dataset (the biggest novelty), and an edge-enhanced UNet. We have evaluated YOHO over an EEC dataset collected by ourselves and achieved a mean Dice score of 0.888, which is much higher as compared to the existing deep-learning methods, thus representing a significant advance toward clinical applications. The code and dataset are available at: https://github.com/lhaippp/YOHO.