Dataset Information

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

ABSTRACT: The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

SUBMITTER: Ciompi F

PROVIDER: S-EPMC5395959 | biostudies-literature | 2017 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

Ciompi Francesco F Chung Kaman K van Riel Sarah J SJ Setio Arnaud Arindra Adiyoso AAA Gerke Paul K PK Jacobs Colin C Scholten Ernst Th ET Schaefer-Prokop Cornelia C Wille Mathilde M W MMW Marchianò Alfonso A Pastorino Ugo U Prokop Mathias M van Ginneken Bram B

Scientific reports 20170419

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevan ...[more]

PMID: 28422152

Similar Datasets

Project description:BackgroundLung cancer is the leading cause of cancer deaths worldwide. Clinical staging of lung cancer plays a crucial role in making treatment decisions and evaluating prognosis. However, in clinical practice, approximately one-half of the clinical stages of lung cancer patients are inconsistent with their pathological stages. As one of the most important diagnostic modalities for staging, chest computed tomography (CT) provides a wealth of information about cancer staging, but the free-text nature of the CT reports obstructs their computerization.ObjectiveWe aimed to automatically extract the staging-related information from CT reports to support accurate clinical staging of lung cancer.MethodsIn this study, we developed an information extraction (IE) system to extract the staging-related information from CT reports. The system consisted of the following three parts: named entity recognition (NER), relation classification (RC), and postprocessing (PP). We first summarized 22 questions about lung cancer staging based on the TNM staging guideline. Next, three state-of-the-art NER algorithms were implemented to recognize the entities of interest. Next, we designed a novel RC method using the relation sign constraint (RSC) to classify the relations between entities. Finally, a rule-based PP module was established to obtain the formatted answers using the results of NER and RC.ResultsWe evaluated the developed IE system on a clinical data set containing 392 chest CT reports collected from the Department of Thoracic Surgery II in the Peking University Cancer Hospital. The experimental results showed that the bidirectional encoder representation from transformers (BERT) model outperformed the iterated dilated convolutional neural networks-conditional random field (ID-CNN-CRF) and bidirectional long short-term memory networks-conditional random field (Bi-LSTM-CRF) for NER tasks with macro-F1 scores of 80.97% and 90.06% under the exact and inexact matching schemes, respectively. For the RC task, the proposed RSC showed better performance than the baseline methods. Further, the BERT-RSC model achieved the best performance with a macro-F1 score of 97.13% and a micro-F1 score of 98.37%. Moreover, the rule-based PP module could correctly obtain the formatted results using the extractions of NER and RC, achieving a macro-F1 score of 94.57% and a micro-F1 score of 96.74% for all the 22 questions.ConclusionsWe conclude that the developed IE system can effectively and accurately extract information about lung cancer staging from CT reports. Experimental results show that the extracted results have significant potential for further use in stage verification and prediction to facilitate accurate clinical staging.

Project description:ImportanceThe number of pulmonary nodules discovered incidentally or through screening programs has increased markedly. Multidisciplinary review and management are recommended, but the involvement of radiation oncologists in this context has not been defined.ObjectiveTo assess the role of stereotactic body radiation therapy among patients enrolled in a lung cancer screening program.Design, setting, and participantsThis prospective cohort study was performed at a pulmonary nodule and lung cancer screening clinic from October 1, 2012, to September 31, 2019. Referrals were based on chest computed tomography with Lung Imaging Reporting and Data System category 4 finding or an incidental nodule 6 mm or larger. A multidisciplinary team of practitioners from radiology, thoracic surgery, pulmonology, medical oncology, and radiation oncology reviewed all nodules and coordinated workup and treatment as indicated.ExposuresPatients referred to the pulmonary nodule and lung cancer screening clinic with an incidental or screen-detected pulmonary nodule.Main outcomes and measuresThe primary outcome was the proportion of patients undergoing therapeutic intervention with radiation therapy, stratified by the route of detection of their pulmonary nodules (incidental vs screen detected). Secondary outcomes were 2-year local control and metastasis-free survival.ResultsAmong 1150 total patients (median [IQR] age, 66.5 [59.3-73.7] years; 665 [57.8%] female; 1024 [89.0%] non-Hispanic White; 841 [73.1%] current or former smokers), 234 (20.3%) presented with screen-detected nodules and 916 (79.7%) with incidental nodules. For patients with screen-detected nodules requiring treatment, 41 (17.5%) received treatment, with 31 (75.6%) undergoing surgery and 10 (24.4%) receiving radiation therapy. Patients treated with radiation therapy were older (median [IQR] age, 73.8 [67.1 to 82.1] vs 67.6 [61.0 to 72.9] years; P < .001) and more likely to have history of tobacco use (67 [95.7%] vs 128 [76.6%]; P = .001) than those treated with surgery. Fifty-eight patients treated with radiation therapy (82.9%) were considered high risk for biopsy, and treatment recommendations were based on a clinical diagnosis of lung cancer after multidisciplinary review. All screened patients who received radiation therapy had stage I disease and were treated with stereotactic body radiation therapy. For all patients receiving stereotactic body radiation therapy, 2-year local control was 96.3% (95% CI, 91.1%-100%) and metastasis-free survival was 94.2% (95% CI, 87.7%-100%).Conclusions and relevanceIn this unique prospective cohort, 1 in 4 patients with screen-detected pulmonary nodules requiring intervention were treated with stereotactic body radiation therapy. This finding highlights the role of radiation therapy in a lung cancer screening population and the importance of including radiation oncologists in the multidisciplinary management of pulmonary nodules.

Dataset Information

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

Publications

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets