Small low-risk pulmonary nodules on chest digital radiography: can we predict whether the nodule is benign?

Missrie, Israel; Hochhegger, Bruno; Zanon, Matheus; Capobianco, Júlia; Neto, Augusto Cesar de Macedo; Maciel, Raquel; Antunes, Viviane Baptista; Figueiredo, Elisabete; Szarf, Gilberto; Meirelles, Gustavo de Souza Portes

doi:10.1016/j.crad.2018.06.002

Cited by 4 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quantitative results of notably higher accuracies than the original RNN are reported, using several metrics on predicting the future tumor volumes. Compared with the most recent 2D + time deep learning–based tumor growth prediction models ( Missrie et al, 2018 ; Audrey et al, 2019 ), our new approach directly works on 3D imaging space and incorporates clinical factors in an end-to-end trainable manner. This method can also detect the benign and malignant pulmonary nodules.…”

Section: Discussionmentioning

confidence: 99%

Study on the Prediction Method of Long-term Benign and Malignant Pulmonary Lesions Based on LSTM

Liu

Wang

Aftab

2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

In order to more accurately and comprehensively characterize the changes and development rules of lesion characteristics in pulmonary medical images in different periods, the study was conducted to predict the evolution of pulmonary nodules in the longitudinal dimension of time, and a benign and malignant prediction model of pulmonary lesions in different periods was constructed under multiscale three-dimensional (3D) feature fusion. According to the sequence of computed tomography (CT) images of patients at different stages, 3D interpolation was conducted to generate 3D lung CT images. The 3D features of different size lesions in the lungs were extracted using 3D convolutional neural networks for fusion features. A time-modulated long short-term memory was constructed to predict the benign and malignant lesions by using the improved time-length memory method to learn the feature vectors of lung lesions with temporal and spatial characteristics in different periods. The experiment shows that the area under the curve of the proposed method is 92.71%, which is higher than that of the traditional method.

show abstract

Section: Discussionmentioning

confidence: 99%

Study on the Prediction Method of Long-term Benign and Malignant Pulmonary Lesions Based on LSTM

Liu

Wang

Aftab

2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…During the time frame of our study, protocol dictated performance of a routine chest radiography as recommended by the national guideline. A chest CT was advised in patients with tumours >4 cm, multifocal tumours, clinically or histologically confirmed groin metastases or abnormalities at chest radiography 14,15 . (Figure S1).…”

Section: Methodsmentioning

confidence: 99%

“…A chest CT was advised in patients with tumours >4 cm, multifocal tumours, clinically or histologically confirmed groin metastases or abnormalities at chest radiography. 14 , 15 (Figure S1 ).…”

Section: Methodsmentioning

confidence: 99%

Low incidence of pulmonary metastases in vulvar cancer patients: limited value of routine chest imaging based on a cohort study

Pleunis

Pouwer

Ploegmakers

et al. 2021

BJOG

View full text Add to dashboard Cite

Objective To evaluate the incidence of pulmonary metastases in the preoperative work-up of patients with primary vulvar squamous cell carcinoma (SCC).Design Retrospective cohort study.Setting Tertiary referral centre.Population Patients treated for primary vulvar SCC from 2000 to 2018.Methods The pre-operative chest imaging of 452 consecutively treated patients was documented with a minimal follow-up period of 2 years.Mean outcome measures Incidence of pulmonary metastases, frequency of chest imaging and subsequent coincidental findings.Results In total, 80.8% of patients underwent pre-operative chest imaging. Seven patients (1.9%), with a median tumour size of 80 mm, presented with pulmonary metastases. None of the patients with early stage disease and tumour size <40 mm who underwent radical local excision (RLE) with sentinel node (SN)procedure, was diagnosed with pulmonary metastasis. Chest imaging was performed by radiography (58.9%) and computerised tomography (CT) (41.1%). Coincidental findings were reported in 40.7% of patients who underwent CT, compared with 15.8% of patients undergoing radiography, resulting in additional diagnostics in 14.7 and 19.7% and being of limited consequence for outcome in 2.9 and 3.3%, respectively.Conclusions The incidence of pulmonary metastases in patients with primary vulvar SCC is extremely low, and none in patients with early stage disease undergoing the SN procedure. Chest imaging was performed in the majority of patients and was associated with frequent coincidental findings leading to clinically irrelevant diagnostic procedures. Therefore, we recommend omitting chest imaging in patients with early stage disease and tumours <40 mm, considering chest CT only in patients with large tumours and/or advanced stage disease.

show abstract

“…With the wide use of multi-detector low dose CT scanners, more small pulmonary nodules can be detected. Most pulmonary nodules, in both non-oncological and oncological patients, were detected to be less than 10 mm in diameter [31].…”

Section: Location Of Ipns Lung Nodule Location Has Been Provenmentioning

confidence: 95%

Colorectal cancer with indeterminate pulmonary nodules

Jiang

Xie

Jing

et al. 2020

neo

View full text Add to dashboard Cite

Colorectal cancer (CRC) is one of the most common malignancies with a dismal prognosis. Indeterminate pulmonary nodules (IPNs) are lung nodules with uncertain nature, generally defined as a noncalcified nodule smaller than 10 mm in diameter or solid nodule no greater than 20 mm at maximum diameter without malignant character. With the widespread use of preoperative staging computed tomography (CT) of the chest and follow-up CT, IPNs are frequently detected in patients with CRC, which makes diagnosis more controversial. Generally, progression to pulmonary metastasis from IPNs is rare. Thus, no further interventions were needed for IPNs in CRC patients. A second reviewing of scans with IPNs by both clinicians and experienced thoracic radiologists may help to obtain a more accurate diagnosis.

show abstract

Small low-risk pulmonary nodules on chest digital radiography: can we predict whether the nodule is benign?

Cited by 4 publications

References 13 publications

Study on the Prediction Method of Long-term Benign and Malignant Pulmonary Lesions Based on LSTM

Study on the Prediction Method of Long-term Benign and Malignant Pulmonary Lesions Based on LSTM

Low incidence of pulmonary metastases in vulvar cancer patients: limited value of routine chest imaging based on a cohort study

Colorectal cancer with indeterminate pulmonary nodules

Contact Info

Product

Resources

About