RESUMO
Objective: To evaluate the performance of 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET/CT) radiomic features to predict overall survival (OS) in patients with locally advanced uterine cervical carcinoma. Methods: Longitudinal and retrospective study that evaluated 50 patients with cervical epidermoid carcinoma (clinical stage IB2 to IVA according to FIGO). Segmentation of the 18F-FDG PET/CT tumors was performed using the LIFEx software, generating the radiomic features. We used the Mann-Whitney test to select radiomic features associated with the clinical outcome (death), excluding the features highly correlated with each other with Spearman correlation. Subsequently, ROC curves and a Kaplan-Meier analysis were performed. A p-value < 0.05 were considered significant. Results: The median follow-up was 23.5 months and longer than 24 months in all surviving patients. Independent predictors for OS were found-SUVpeak with an AUC of 0.74, sensitivity of 77.8%, and specificity of 72.7% (p = 0.006); and the textural feature gray-level run-length matrix GLRLM_LRLGE, with AUC of 0.74, sensitivity of 72.2%, and specificity of 81.8% (p = 0.005). When we used the derived cut-off points from these ROC curves (12.76 for SUVpeak and 0.001 for GLRLM_LRLGE) in a Kaplan-Meier analysis, we can see two different groups (one with an overall survival probability of approximately 90% and the other with 30%). These biomarkers are independent of FIGO staging. Conclusion: By radiomic 18F-FDG PET/CT data analysis, SUVpeak and GLRLM_LRLGE textural feature presented the best performance to predict OS in patients with cervical cancer undergoing chemo-radiotherapy and brachytherapy.
RESUMO
The disease caused by the new type of coronavirus, Covid-19, has posed major public health challenges for many countries. With its rapid spread, since the beginning of the outbreak in December 2019, the disease transmitted by SARS-CoV-2 has already caused over 2 million deaths to date. In this work, we propose a web solution, called Heg.IA, to optimize the diagnosis of Covid-19 through the use of artificial intelligence. Our system aims to support decision-making regarding to diagnosis of Covid-19 and to the indication of hospitalization on regular ward, semi-ICU or ICU based on decision a Random Forest architecture with 90 trees. The main idea is that healthcare professionals can insert 41 hematological parameters from common blood tests and arterial gasometry into the system. Then, Heg.IA will provide a diagnostic report. The system reached good results for both Covid-19 diagnosis and to recommend hospitalization. For the first scenario we found average results of accuracy of 92.891%±0.851, kappa index of 0.858 ± 0.017, sensitivity of 0.936 ± 0.011, precision of 0.923 ± 0.011, specificity of 0.921 ± 0.012 and area under ROC of 0.984 ± 0.003. As for the indication of hospitalization, we achieved excellent performance of accuracies above 99% and more than 0.99 for the other metrics in all situations. By using a computationally simple method, based on the classical decision trees, we were able to achieve high diagnosis performance. Heg.IA system may be a way to overcome the testing unavailability in the context of Covid-19.Communicated by Ramaswamy H. Sarma.
Assuntos
COVID-19 , Humanos , COVID-19/diagnóstico , SARS-CoV-2 , Teste para COVID-19 , Algoritmo Florestas Aleatórias , Inteligência Artificial , Testes HematológicosRESUMO
O carcinoma bronquioloalveolar (CBA) de pulmão é um subtipo de adenocarcinoma que apresenta características clínicas e radiológicas peculiares com evolução distinta dos outros tumores de pulmão. Nos últimos anos, essa doença vem despertando interesse da comunidade científica face sua relação com determinados alvos moleculares. No Brasil, os dados clínicos, epidemiológicos e relacionados ao tratamento desses pacientes são escassos. O objetivo principal do estudo é analisar retrospectivamente os fatores prognósticos do CBA de pacientes tratados em centros oncológicos brasileiros e avaliar as respostas aos tratamentos instituídos. Trata-se de um estudo retrospectivo, colaborativo, multicêntrico que analisou os dados clínicos de pacientes admitidos entre 1990 e 2006. Foram incluídos pacientes com idade entre 18 e 84 anos, com confirmação histológica de CBA em estágios I ao IV. O tipo histológico foi obtido através da análise de relatório da anatomia patológica incluída no prontuário. Foram excluídos da análise os casos de Câncer de Pulmão de pequenas células. Foram utilizados para análise e determinação da PS os critérios do ECOG. Os dados foram obtidos por um mesmo oncologista em fichas padronizadas e após revisão os dados foram tabulados em banco de dados para análise posterior. Foram calculados o tempo de sobrevida global e a curva de sobrevida actuarial foi construída pelo método de Kaplan e Meier e a comparação das curvas através dos testes long-rang e Breslow. O modelo de regressão de Cox foi utilizado para o cálculo das "hazard ratio" para óbito (HR). A técnica "stepwise foward" foi utilizada para construção do modelo multivariado de Cox. Foram utilizadas para análise univariada e multivariada as seguintes variáveis: Centro de tratamento de câncer, gênero, idade, PS, estadiamento, histologia, e tratamento. As análises estatísticas foram realizadas utilizando o programa estatístico SPSS 10.0 for Windows. Um valor de p<0,05 foi considerado estatisticamente significativo. Foram analisados 237 pacientes com CBA em 4 centros médicos brasileiros. A idade mediana dos pacientes foi de 63 anos (29-84 anos), sendo 47.5% do sexo masculino e 52.5% do sexo feminino. Referiam tabagismo 60.6% dos pacientes e 34.7% negavam este hábito. A maioria dos pacientes (70.7%) apresentava PS 0 ou 1. O estadiamento mais prevalente se concentrou entre T1-2, N0, M0. Dentre as variáveis estudadas da análise univariada apresentaram valor de P significativo em relação á sobrevida Global as seguintes: sexo, PS, Tabagismo, estadiamento, forma de apresentação radiológica, realização de cirurgia. Os fatores associados com pior prognóstico através da análise multivariada foram tamanho tumoral, realização de cirurgia, idade e tabagismo. Gênero, PS, tabagismo, estadiamento radiologia, cirurgia, estadiamento TNM estão associados a maior sobrevida. Além disso, variáveis como tamanho tumoral, idade, tabagismo e cirurgia são fatores prognósticos independentes no CBA. Sendo o CBA uma neoplasia com comportamento clínico distinto dos demais subtipos histológicos do carcinoma de pulmão de não pequenas células, sua abordagem clínica, diagnóstica e terapêutica deve ser individualizada, considerando os diversos fatores prognósticos a ele relacionados.
Bronchioloalveolar carcinoma (CBA) is a subtype of lung adenocarcinoma that presents unique clinical and radiological features with distinct outcome. In recent years, this disease is attracting interest from the scientific community mainly for its association with certain molecular targets. In Brazil, data related to clinical and epidemiological characteristics, as well as response to treatment in patients with CBA are scarce. The main objective of the present study is to analyze the prognostic factors of CBA in patients treated at Brazilian cancer centers and to evaluate response to the treatment and outcome. This is a retrospective study, collaborative, multicenter which analyzed clinical data of patients admitted between 1990 and 2006. Patients aged between 18 and 84 years, with histological confirmation of CBA in stages I to IV, were included. Histological type was obtained through analysis of the pathology report included in the records. Data were collected by the same oncologist and registered in a database for further analysis. Overall survival was calculated by the method of Kaplan and Meier, and the survival curves were compared by log-Rang and Breslow tests. The model of the Cox regression was used to calculate the "hazard ratio" for death (HR). The technique "stepwise foward" was used to build the Cox multivariate model, including the following variables: Center for treatment of cancer, gender, age, PS, staging, histology, and treatment, and p<0.05 was considered statistically significant. We analyzed 237 patients with CBA at four institutions. Median age of patients was 63 years (29-84y), with 47.5% of males and 52.5% of females. Most patients (60.6%) were smokers, and 70.7% of patients presented with PS 0 or 1. On univariate analysis the following factors had significant impact on overall survival: sex, PS, smoking, staging, radiological form of presentation, surgical resection. Multivariate analysis identified the following significant independent prognostic factors: tumor size, performance of surgery, age and smoking. Gender, PS, smoking, staging radiology, surgery, TNM staging are associated with higher survival. Also, tumor size, age, smoking and surgery are independent prognostic factors in the CBA. As a histologic subtype with clinic features distinct from other types of non-small cell lung cancer, its diagnostic and therapeutic approach should be individualized, considering the prognostic factors related to it.