RESUMEN
BACKGROUNDS: Few data are available for surveillance decisions focusing on factors related to mortality, as the primary outcome, in intraductal papillary mucinous neoplasm (IPMN) patients. AIMS: We aimed to identify imaging features and patient backgrounds associated with mortality risks by comparing pancreatic cancer (PC) and comorbidities. METHODS: We retrospectively conducted a multicenter long-term follow-up of 1864 IPMN patients. Competing risk analysis was performed for PC- and comorbidity-related mortality. RESULTS: During the median follow-up period of 5.5 years, 14.0% (261/1864) of patients died. Main pancreatic duct ≥5 mm and mural nodules were significantly related to all-cause and PC-related mortality, whereas cyst ≥30 mm did not relate. In 1730 patients without high-risk imaging features, 48 and 180 patients died of PC and comorbidity. In the derivation cohort, a prediction model for comorbidity-related mortality was created, comprising age, cancer history, diabetes mellitus complications, chronic heart failure, stroke, paralysis, peripheral artery disease, liver cirrhosis, and collagen disease in multivariate analysis. If a patient had a 5 score, 5- and 10-year comorbidity-related mortality is estimated at 18.9% and 50.2%, respectively, more than 7 times higher than PC-related mortality. The model score was also significantly associated with comorbidity-related mortality in a validation cohort. CONCLUSIONS: This study demonstrates main pancreatic duct dilation and mural nodules indicate risk of PC-related mortality, identifying patients who need periodic examination. A comorbidity-related mortality prediction model based on the patient's age and comorbidities can stratify patients who do not require regular tests, especially beyond 5 years, among IPMN patients without high-risk features. CLINICAL TRIAL REGISTRATION: T2022-0046.
Asunto(s)
Comorbilidad , Neoplasias Intraductales Pancreáticas , Neoplasias Pancreáticas , Humanos , Masculino , Femenino , Anciano , Estudios Retrospectivos , Neoplasias Pancreáticas/mortalidad , Neoplasias Pancreáticas/patología , Neoplasias Pancreáticas/complicaciones , Neoplasias Pancreáticas/epidemiología , Persona de Mediana Edad , Neoplasias Intraductales Pancreáticas/mortalidad , Neoplasias Intraductales Pancreáticas/patología , Neoplasias Intraductales Pancreáticas/epidemiología , Neoplasias Intraductales Pancreáticas/complicaciones , Factores de Riesgo , Estudios de Seguimiento , Carcinoma Ductal Pancreático/mortalidad , Carcinoma Ductal Pancreático/complicaciones , Carcinoma Ductal Pancreático/patología , Medición de Riesgo/métodos , Adenocarcinoma Mucinoso/mortalidad , Adenocarcinoma Mucinoso/patología , Adenocarcinoma Mucinoso/complicaciones , Conductos Pancreáticos/patología , Conductos Pancreáticos/diagnóstico por imagen , Anciano de 80 o más AñosRESUMEN
PURPOSE: Increased use of deep learning (DL) in medical imaging diagnoses has led to more frequent use of 10-fold cross-validation (10-CV) for the evaluation of the performance of DL. To eliminate some of the (10-fold) repetitive processing in 10-CV, we proposed a "generalized fitting method in conjunction with every possible coalition of N-combinations (G-EPOC)", to estimate the range of the mean accuracy of 10-CV using less than 10 results of 10-CV. MATERIAL AND METHODS: G-EPOC was executed as follows. We first provided (2N-1) coalition subsets using a specified N, which was 9 or less, out of 10 result datasets of 10-CV. We then obtained the estimation range of the accuracy by applying those subsets to the distribution fitting twice using a combination of normal, binominal, or Poisson distributions. Using datasets of 10-CVs acquired from the practical detection task of the appendicitis on CT by DL, we scored the estimation success rates if the range provided by G-EPOC included the true accuracy. RESULTS: G-EPOC successfully estimated the range of the mean accuracy by 10-CV at over 95% rates for datasets with N assigned as 2 to 9. CONCLUSIONS: G-EPOC will help lessen the consumption of time and computer resources in the development of computerbased diagnoses in medical imaging and could become an option for the selection of a reasonable K value in K-CV.
RESUMEN
Breast positron emission tomography (PET) has had insurance coverage when performed with conventional whole-body PET in Japan since 2013. Together with whole-body PET, accurate examination of breast cancer and diagnosis of metastatic disease are possible, and are expected to contribute significantly to its treatment planning. To facilitate a safer, smoother, and more appropriate examination, the Japanese Society of Nuclear Medicine published the first edition of practice guidelines for high-resolution breast PET in 2013. Subsequently, new types of breast PET have been developed and their clinical usefulness clarified. Therefore, the guidelines for breast PET were revised in 2019. This article updates readers as to what is new in the second edition. This edition supports two different types of breast PET depending on the placement of the detector: the opposite-type (positron emission mammography; PEM) and the ring-shaped type (dedicated breast PET; dbPET), providing an overview of these scanners and appropriate imaging methods, their clinical applications, and future prospects. The name "dedicated breast PET" from the first edition is widely used to refer to ring-shaped type breast PET. In this edition, "breast PET" has been defined as a term that refers to both opposite- and ring-shaped devices. Up-to-date breast PET practice guidelines would help provide useful information for evidence-based breast imaging.
Asunto(s)
Neoplasias de la Mama/diagnóstico por imagen , Tomografía de Emisión de Positrones , Guías de Práctica Clínica como Asunto , Relación Señal-Ruido , HumanosRESUMEN
The original article can be found online.
RESUMEN
PURPOSE: To reveal that a computed tomography surveillance program (CT-surveillance) could demonstrate the epidemiologic features of COVID-19 infection and simultaneously investigate the type and frequency of CT findings using clinical CT data. MATERIALS AND METHODS: We targeted individuals with possible CT findings of viral pneumonia. Using an online questionnaire, we asked Japanese board-certified radiologists to register their patients' information including patient age and sex, the CT examination date, the results of PCR test for COVID-19 infection, CT findings, and the postal code of the medical institution that performed the CT. We compared the diurnal patient number and the cumulative regional distribution map of registrations in CT-surveillance to those of the PCR-positive patient surveillance (PCR-surveillance). RESULTS: A total of 637 patients was registered from January 1 to April 17, 2020 for CT-surveillance. Their PCR test results were positive (n = 62.5-398%), negative (n = 8.9-57%), unknown (n = 26.2-167%), and other disease (n = 2.4-15%). An age peak at 60-69 years and male dominance were observed in CT-surveillance. The most common CT finding was bilaterally distributed ground-glass opacities. The diurnal number and the cumulative regional distribution map by CT-surveillance showed tendencies that were similar to those revealed by PCR-surveillance. CONCLUSION: Using clinical CT data, CT-surveillance program delineated the epidemiologic features of COVID-19 infection.
Asunto(s)
COVID-19/diagnóstico por imagen , COVID-19/epidemiología , Tomografía Computarizada por Rayos X/métodos , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Niño , Preescolar , Monitoreo Epidemiológico , Femenino , Humanos , Lactante , Japón/epidemiología , Pulmón/diagnóstico por imagen , Masculino , Persona de Mediana Edad , Pandemias , SARS-CoV-2 , Encuestas y Cuestionarios , Adulto JovenRESUMEN
PURPOSE: Increased use of deep convolutional neural networks (DCNNs) in medical imaging diagnosis requires determinate evaluation of diagnostic performance. We performed the fundamental investigation of diagnostic performance of DCNNs using the detection task of brain metastasis. METHODS: We retrospectively investigated AlexNet and GoogLeNet using 3117 positive and 37961 negative MRI images with and without metastasis regarding (1) diagnostic biases, (2) the optimal K number of K-fold cross validations (K-CVs), (3) the optimal positive versus negative image ratio, (4) the accuracy improvement curves, (5) the accuracy range prediction by the bootstrap method, and (6) metastatic lesion detection by regions with CNNs (R-CNNs). RESULTS: Respectively, AlexNet and GoogLeNet had (1) 50 ± 4.6% and 50 ± 4.9% of the maximal mean ± 95% confidence intervals (95% CIs) measured with equal-sized negative versus negative image datasets and positive versus positive image datasets, (2) no less than 10 and 4 of K number in K-CVs fell within the respective maximum biases of 4.6% or 4.9%, (3) 74% of the highest accuracy with equal positive versus negative image ratio dataset and 91% of that with four times of negative-to-positive image ratio dataset, (4) the accuracy improvement curves increasing from 69% to 74% and 73% to 88% as positive versus negative pairs of the training images increased from 500 to 2495, (5) at least nine and six out of 10-CV result sets essential to predict the accuracy ranges by the bootstrap method, and (6) 50% and 45% of metastatic lesion detection accuracies by R-CNNs. CONCLUSIONS: Our research presented methodological fundamentals to evaluate diagnostic features in the visual recognition of DCNNs. Our series will help to conduct the accuracy investigation of computer diagnosis in medical imaging.
Asunto(s)
Neoplasias Encefálicas/diagnóstico por imagen , Aprendizaje Profundo , Interpretación de Imagen Asistida por Computador/métodos , Encéfalo/diagnóstico por imagen , Humanos , Imagen por Resonancia Magnética , Estudios RetrospectivosRESUMEN
PURPOSE: The confusion of MRI sequence names could be solved if MR images were automatically identified after image data acquisition. We revealed the ability of deep learning to classify head MRI sequences. MATERIALS AND METHODS: Seventy-eight patients with mild cognitive impairment (MCI) having apparently normal head MR images and 78 intracranial hemorrhage (ICH) patients with morphologically deformed head MR images were enrolled. Six imaging protocols were selected to be performed: T2-weighted imaging, fluid attenuated inversion recovery imaging, T2-star-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient mapping, and source images of time-of-flight magnetic resonance angiography. The proximal first image slices and middle image slices having ambiguous and distinctive contrast patterns, respectively, were classified by two deep learning imaging classifiers, AlexNet and GoogLeNet. RESULTS: AlexNet had accuracies of 73.3%, 73.6%, 73.1%, and 60.7% in the middle slices of MCI group, middle slices of ICH group, first slices of MCI group, and first slices of ICH group, while GoogLeNet had accuracies of 100%, 98.1%, 93.1%, and 94.8%, respectively. AlexNet significantly had lower classification ability than GoogLeNet for all datasets. CONCLUSIONS: GoogLeNet could judge the types of head MRI sequences with a small amount of training data, irrespective of morphological or contrast conditions.
Asunto(s)
Inteligencia Artificial , Encéfalo/diagnóstico por imagen , Encéfalo/fisiopatología , Disfunción Cognitiva/fisiopatología , Imagen por Resonancia Magnética/métodos , Redes Neurales de la Computación , Anciano , Anciano de 80 o más Años , Imagen de Difusión por Resonancia Magnética , Femenino , Humanos , Angiografía por Resonancia Magnética , Masculino , Persona de Mediana Edad , Reproducibilidad de los Resultados , Estudios RetrospectivosRESUMEN
In Results of Abstract, the first sentence should read as: The radiologist potential workload in Japan was 2.78-4.17 times higher than those in other countries.
RESUMEN
PURPOSE: To investigate the global variation in radiologist potential workload for CT and MRI examinations, and the regional variation in potential workload and extent of radiologists' involvement in CT and MRI examinations in Japan. METHODS: "Radiologist potential workload" was defined as the annual number of CT plus MRI examinations divided by the total number of diagnostic radiologists. The extent of radiologists' involvement was measured as the proportion of CT and MRI examinations to which "Added-fees for Radiological Managements on Imaging-studies (ARMIs)" were applied among eligible examinations. Maximum variation was computed as the ratio of the highest-to-lowest values among the countries or Japanese prefectures. RESULTS: The radiologist potential workload in Japan was 2.78-4.17 times higher than those in other countries. A maximum prefecture-to-prefecture variation was 3.88. The average percentage of CT plus MRI examinations with ARMI applied was 43.3%, with a maximum prefecture-to-prefecture variation of 3.97. Prefectures with more radiologists tended to have a higher extent of radiologists' involvement. CONCLUSIONS: Japan had a far greater radiologist potential workload compared with other countries, with a large regional variation among prefectures. Prefectures with more radiologists tended to have a higher extent of radiologists' involvement in CT and MRI examinations.