Dataset Information

Deep learning for predicting subtype classification and survival of lung adenocarcinoma on computed tomography.

ABSTRACT:

Objectives

The subtype classification of lung adenocarcinoma is important for treatment decision. This study aimed to investigate the deep learning and radiomics networks for predicting histologic subtype classification and survival of lung adenocarcinoma diagnosed through computed tomography (CT) images.

Methods

A dataset of 1222 patients with lung adenocarcinoma were retrospectively enrolled from three medical institutions. The anonymised preoperative CT images and pathological labels of atypical adenomatous hyperplasia, adenocarcinoma in situ, minimally invasive adenocarcinoma, invasive adenocarcinoma (IAC) with five predominant components were obtained. These pathological labels were divided into 2-category classification (IAC; non-IAC), 3-category and 8-category. We modeled the classification task of histological subtypes based on modified ResNet-34 deep learning network, radiomics strategies and deep radiomics combined algorithm. Then we established the prognostic models in lung adenocarcinoma patients with survival outcomes. The accuracy (ACC), area under ROC curves (AUCs) and C-index were primarily performed to evaluate the algorithms.

Results

This study included a training set (n = 802) and two validation cohorts (internal, n = 196; external, n = 224). The ACC of deep radiomics algorithm in internal validation achieved 0.8776, 0.8061 in the 2-category, 3-category classification, respectively. Even in 8 classifications, the AUC ranged from 0.739 to 0.940 in internal set. Further, we constructed a prognosis model that C-index was 0.892(95% CI: 0.846-0.937) in internal validation set.

Conclusions

The automated deep radiomics based triage system has achieved the great performance in the subtype classification and survival predictability in patients with CT-detected lung adenocarcinoma nodules, providing the clinical guide for treatment strategies.

SUBMITTER: Wang C

PROVIDER: S-EPMC8184655 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:UnlabelledIn this study we developed 25 computed tomography descriptors among 117 patients with lung adenocarcinoma to semiquantitatively assess their association with overall survival. Pleural attachment was significantly associated with an increased risk of death and texture was most important for distinguishing histological subtypes. This approach has the potential to support automated analyses and develop decision-support clinical tools.BackgroundComputed tomography (CT) characteristics derived from noninvasive images that represent the entire tumor might have diagnostic and prognostic value. The purpose of this study was to assess the association of a standardized set of semiquantitative CT characteristics of lung adenocarcinoma with overall survival.Patients and methodsAn initial set of CT descriptors was developed to semiquantitatively assess lung adenocarcinoma in patients (n = 117) who underwent resection. Survival analyses were used to determine the association between each characteristic and overall survival. Principle component analysis (PCA) was used to determine characteristics that might differentiate histological subtypes.ResultsCharacteristics significantly associated with overall survival included pleural attachment (P < .001), air bronchogram (P = .03), and lymphadenopathy (P = .02). Multivariate analyses revealed pleural attachment was significantly associated with an increased risk of death overall (hazard ratio [HR], 3.21; 95% confidence interval [CI], 1.53-6.70) and among patients with lepidic predominant adenocarcinomas (HR, 5.85; 95% CI, 1.75-19.59), and lymphadenopathy was significantly associated with an increased risk of death among patients with adenocarcinomas without a predominant lepidic component (HR, 3.07; 95% CI, 1.09-8.70). A PCA model showed that texture (ground-glass opacity component) was most important for separating the 2 subtypes.ConclusionA subset of the semiquantitative characteristics described herein has prognostic importance and provides the ability to distinguish between different histological subtypes of lung adenocarcinoma.

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.