Deep Learning-Based Stage-Wise Risk Stratification for Early Lung Adenocarcinoma in CT Images: A Multi-Center Study

GMILT: A Novel Transformer Network That Can Noninvasively Predict EGFR Mutation Status

Noninvasively and accurately predicting the epidermal growth factor receptor (EGFR) mutation status is a clinically vital problem. Moreover, further identifying the most suspicious area related to the EGFR mutation status can guide the biopsy to avoid false negatives. Deep learning methods based on computed tomography (CT) images may improve the noninvasive prediction of EGFR mutation status and potentially help clinicians guide biopsies by visual methods. Inspired by the potential inherent links between EGFR mutation status and invasiveness information, we hypothesized that the predictive performance of a deep learning network can be improved through extra utilization of the invasiveness information. Here, we created a novel explainable transformer network for EGFR classification named gated multiple instance learning transformer (GMILT) by integrating multi-instance learning and discriminative weakly supervised feature learning. Pathological invasiveness information was first introduced into the multitask model as embeddings. GMILT was trained and validated on a total of 512 patients with adenocarcinoma and tested on three datasets (the internal test dataset, the external test dataset, and The Cancer Imaging Archive (TCIA) public dataset). The performance (area under the curve (AUC) =0.772 on the internal test dataset) of GMILT exceeded that of previously published methods and radiomics-based methods (i.e., random forest and support vector machine) and attained a preferable generalization ability (AUC =0.856 in the TCIA test dataset and AUC =0.756 in the external dataset). A diameter-based subgroup analysis further verified the efficiency of our model (most of the AUCs exceeded 0.772) to noninvasively predict EGFR mutation status from computed tomography (CT) images. In addition, because our method also identified the "core area" of the most suspicious area related to the EGFR mutation status, it has the potential ability to guide biopsies.

Standalone deep learning versus experts for diagnosis lung cancer on chest computed tomography: a systematic review

PURPOSE

To compare the diagnostic performance of standalone deep learning (DL) algorithms and human experts in lung cancer detection on chest computed tomography (CT) scans.

MATERIALS AND METHODS

This study searched for studies on PubMed, Embase, and Web of Science from their inception until November 2023. We focused on adult lung cancer patients and compared the efficacy of DL algorithms and expert radiologists in disease diagnosis on CT scans. Quality assessment was performed using QUADAS-2, QUADAS-C, and CLAIM. Bivariate random-effects and subgroup analyses were performed for tasks (malignancy classification vs invasiveness classification), imaging modalities (CT vs low-dose CT [LDCT] vs high-resolution CT), study region, software used, and publication year.

RESULTS

We included 20 studies on various aspects of lung cancer diagnosis on CT scans. Quantitatively, DL algorithms exhibited superior sensitivity (82%) and specificity (75%) compared to human experts (sensitivity 81%, specificity 69%). However, the difference in specificity was statistically significant, whereas the difference in sensitivity was not statistically significant. The DL algorithms' performance varied across different imaging modalities and tasks, demonstrating the need for tailored optimization of DL algorithms. Notably, DL algorithms matched experts in sensitivity on standard CT, surpassing them in specificity, but showed higher sensitivity with lower specificity on LDCT scans.

CONCLUSION

DL algorithms demonstrated improved accuracy over human readers in malignancy and invasiveness classification on CT scans. However, their performance varies by imaging modality, underlining the importance of continued research to fully assess DL algorithms' diagnostic effectiveness in lung cancer.

CLINICAL RELEVANCE STATEMENT

DL algorithms have the potential to refine lung cancer diagnosis on CT, matching human sensitivity and surpassing in specificity. These findings call for further DL optimization across imaging modalities, aiming to advance clinical diagnostics and patient outcomes.

KEY POINTS

Lung cancer diagnosis by CT is challenging and can be improved with AI integration. DL shows higher accuracy in lung cancer detection on CT than human experts. Enhanced DL accuracy could lead to improved lung cancer diagnosis and outcomes.

Quantitative analysis of lung lesions using unenhanced chest computed tomography images

INTRODUCTION

Chest radiograph and computed tomography (CT) scans can accidentally reveal pulmonary nodules. Malignant and benign pulmonary nodules can be difficult to distinguish without specific imaging features, such as calcification, necrosis, and contrast enhancement. However, these lesions may exhibit different image texture characteristics which cannot be assessed visually. Thus, a computer-assisted quantitative method like histogram analysis (HA) of Hounsfield unit (HU) values can improve diagnostic accuracy, reducing the need for invasive biopsy.

METHODS

In this exploratory control study, nonenhanced chest CT images of 20 patients with benign (10) and cancerous (10) lesion were selected retrospectively. The appearances of benign and malignant lesions were very similar in chest CT images, and only pathology report was used to discriminate them. Free hand region of interest (ROI) was inserted inside the lesion for all slices of each lesion. Mean, minimum, maximum, and standard deviations of HU values were recorded and used to make HA.

RESULTS

HA showed that the most malignant lesions have a mean HU value between 30 and 50, a maximum HU less than 150, and a minimum HU between -30 and 20. Lesions outside these ranges were mostly benign.

CONCLUSION

Quantitative CT analysis may differentiate malignant from benign lesions without specific malignancy patterns on unenhanced chest CT image.

Predicting Invasiveness of Lung Adenocarcinoma at Chest CT with Deep Learning Ternary Classification Models

Background Preoperative discrimination of preinvasive, minimally invasive, and invasive adenocarcinoma at CT informs clinical management decisions but may be challenging for classifying pure ground-glass nodules (pGGNs). Deep learning (DL) may improve ternary classification. Purpose To determine whether a strategy that includes an adjudication approach can enhance the performance of DL ternary classification models in predicting the invasiveness of adenocarcinoma at chest CT and maintain performance in classifying pGGNs. Materials and Methods In this retrospective study, six ternary models for classifying preinvasive, minimally invasive, and invasive adenocarcinoma were developed using a multicenter data set of lung nodules. The DL-based models were progressively modified through framework optimization, joint learning, and an adjudication strategy (simulating a multireader approach to resolving discordant nodule classifications), integrating two binary classification models with a ternary classification model to resolve discordant classifications sequentially. The six ternary models were then tested on an external data set of pGGNs imaged between December 2019 and January 2021. Diagnostic performance including accuracy, specificity, and sensitivity was assessed. The χ2 test was used to compare model performance in different subgroups stratified by clinical confounders. Results A total of 4929 nodules from 4483 patients (mean age, 50.1 years ± 9.5 [SD]; 2806 female) were divided into training (n = 3384), validation (n = 579), and internal (n = 966) test sets. A total of 361 pGGNs from 281 patients (mean age, 55.2 years ± 11.1 [SD]; 186 female) formed the external test set. The proposed strategy improved DL model performance in external testing (P < .001). For classifying minimally invasive adenocarcinoma, the accuracy was 85% and 79%, sensitivity was 75% and 63%, and specificity was 89% and 85% for the model with adjudication (model 6) and the model without (model 3), respectively. Model 6 showed a relatively narrow range (maximum minus minimum) across diagnostic indexes (accuracy, 1.7%; sensitivity, 7.3%; specificity, 0.9%) compared with the other models (accuracy, 0.6%-10.8%; sensitivity, 14%-39.1%; specificity, 5.5%-17.9%). Conclusion Combining framework optimization, joint learning, and an adjudication approach improved DL classification of adenocarcinoma invasiveness at chest CT. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Sohn and Fields in this issue.

Enhancing brain metastasis prediction in non-small cell lung cancer: a deep learning-based segmentation and CT radiomics-based ensemble learning model

BACKGROUND

Brain metastasis (BM) is most common in non-small cell lung cancer (NSCLC) patients. This study aims to enhance BM risk prediction within three years for advanced NSCLC patients by using a deep learning-based segmentation and computed tomography (CT) radiomics-based ensemble learning model.

METHODS

This retrospective study included 602 stage IIIA-IVB NSCLC patients, 309 BM patients and 293 non-BM patients, from two centers. Patients were divided into a training cohort (N = 376), an internal validation cohort (N = 161) and an external validation cohort (N = 65). Lung tumors were first segmented by using a three-dimensional (3D) deep residual U-Net network. Then, a total of 1106 radiomics features were computed by using pretreatment lung CT images to decode the imaging phenotypes of primary lung cancer. To reduce the dimensionality of the radiomics features, recursive feature elimination configured with the least absolute shrinkage and selection operator (LASSO) regularization method was applied to select the optimal image features after removing the low-variance features. An ensemble learning algorithm of the extreme gradient boosting (XGBoost) classifier was used to train and build a prediction model by fusing radiomics features and clinical features. Finally, Kaplan‒Meier (KM) survival analysis was used to evaluate the prognostic value of the prediction score generated by the radiomics-clinical model.

RESULTS

The fused model achieved area under the receiver operating characteristic curve values of 0.91 ± 0.01, 0.89 ± 0.02 and 0.85 ± 0.05 on the training and two validation cohorts, respectively. Through KM survival analysis, the risk score generated by our model achieved a significant prognostic value for BM-free survival (BMFS) and overall survival (OS) in the two cohorts (P < 0.05).

CONCLUSIONS

Our results demonstrated that (1) the fusion of radiomics and clinical features can improve the prediction performance in predicting BM risk, (2) the radiomics model generates higher performance than the clinical model, and (3) the radiomics-clinical fusion model has prognostic value in predicting the BMFS and OS of NSCLC patients.

Hybrid deep multi-task learning radiomics approach for predicting EGFR mutation status of non-small cell lung cancer in CT images

Objective.Epidermal growth factor receptor (EGFR) mutation genotyping plays a pivotal role in targeted therapy for non-small cell lung cancer (NSCLC). We aimed to develop a computed tomography (CT) image-based hybrid deep radiomics model to predict EGFR mutation status in NSCLC and investigate the correlations between deep image and quantitative radiomics features.Approach.First, we retrospectively enrolled 818 patients from our centre and 131 patients from The Cancer Imaging Archive database to establish a training cohort (N= 654), an independent internal validation cohort (N= 164) and an external validation cohort (N= 131). Second, to predict EGFR mutation status, we developed three CT image-based models, namely, a multi-task deep neural network (DNN), a radiomics model and a feature fusion model. Third, we proposed a hybrid loss function to train the DNN model. Finally, to evaluate the model performance, we computed the areas under the receiver operating characteristic curves (AUCs) and decision curve analysis curves of the models.Main results.For the two validation cohorts, the feature fusion model achieved AUC values of 0.86 ± 0.03 and 0.80 ± 0.05, which were significantly higher than those of the single-task DNN and radiomics models (allP< 0.05). There was no significant difference between the feature fusion and the multi-task DNN models (P> 0.8). The binary prediction scores showed excellent prognostic value in predicting disease-free survival (P= 0.02) and overall survival (P< 0.005) for validation cohort 2.Significance.The results demonstrate that (1) the feature fusion and multi-task DNN models achieve significantly higher performance than that of the conventional radiomics and single-task DNN models, (2) the feature fusion model can decode the imaging phenotypes representing NSCLC heterogeneity related to both EGFR mutation and patient NSCLC prognosis, and (3) high correlations exist between some deep image and radiomics features.

End-to-end deep learning radiomics: development and validation of a novel attention-based aggregate convolutional neural network to distinguish breast diffuse large B-cell lymphoma from breast invasive ductal carcinoma

Background

Apart from invasive pathological examination, there is no effective method to differentiate breast diffuse large B-cell lymphoma (DLBCL) from breast invasive ductal carcinoma (IDC). In this study, we aimed to develop and validate an effective deep learning radiomics model to discriminate between DLBCL and IDC.

Methods

A total of 324 breast nodules from 236 patients with baseline 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) were retrospectively analyzed. After grouping breast DLBCL and breast IDC patients, external and internal datasets were divided according to the data collected by different centers. Preprocessing was then used to process the original PET/CT images and an attention-based aggregate convolutional neural network (AACNN) model was designed. The AACNN model was trained using patches of CT or PET tumor images and optimized with an improved loss function. The final ensemble predictive model was built using distance weight voting. Finally, the model performance was evaluated and statistically verified.

Results

A total of 249 breast nodules from Fudan University Shanghai Cancer Center (FUSCC) and 75 breast nodules from Shanghai Proton and Heavy Ion Center (SPHIC) were selected as internal and external datasets, respectively. On the internal testing, our method yielded an area under the curve (AUC), accuracy (ACC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), and harmonic mean of precision and sensitivity (F1) of 0.886, 83.0%, 80.9%, 85.0%, 84.8%, 81.2%, and 0.828, respectively. Meanwhile on the external testing, the results were 0.788, 71.6%, 61.4%, 84.7%, 84.0%, 62.6%, and 0.709, respectively.

Conclusions

Our study outlines a deep learning radiomics method which can automatically, noninvasively, and accurately differentiate breast DLBCL from breast IDC, which will be more in line with the needs and strategies of precision medicine, individualized diagnosis, and treatment.

Novel method for predicting nonvisible symptoms using machine learning in cancer palliative care

End-of-life patients with cancer may find expressing their symptoms difficult if they can no longer communicate verbally because of deteriorating health. In this study, we assessed these symptoms using machine learning, which has excellent predictive capabilities and has recently been applied in healthcare. We performed a retrospective clinical survey involving 213 patients with cancer from August 2015 to August 2016. We divided the reported symptoms into two groups-visible and nonvisible symptoms. We used decision tree analysis, an analytical machine learning method that organizes and analyzes information in the form of a tree diagram to visually represent the information structure. Our machine learning model used patient background data and visible symptoms to predict nonvisible symptoms: pain, dyspnea, fatigue, drowsiness, anxiety, delirium, inadequate informed consent, and spiritual issues. The highest and/or lowest values for prediction accuracy, sensitivity, and specificity were 88.0%/55.5%, 84.9%/3.3%, and 96.7%/24.1%, respectively. This work will facilitate better assessment and management of symptoms in patients with cancer. This study was the first to predict nonvisible symptoms using decision tree analyses for patients with cancer receiving palliative care. Notably, applications based on our results may assess symptoms to the same extent as healthcare professionals.

An ensemble deep learning model for risk stratification of invasive lung adenocarcinoma using thin-slice CT

Lung cancer screening using computed tomography (CT) has increased the detection rate of small pulmonary nodules and early-stage lung adenocarcinoma. It would be clinically meaningful to accurate assessment of the nodule histology by CT scans with advanced deep learning algorithms. However, recent studies mainly focus on predicting benign and malignant nodules, lacking of model for the risk stratification of invasive adenocarcinoma. We propose an ensemble multi-view 3D convolutional neural network (EMV-3D-CNN) model to study the risk stratification of lung adenocarcinoma. We include 1075 lung nodules (≤30 mm and ≥4 mm) with preoperative thin-section CT scans and definite pathology confirmed by surgery. Our model achieves a state-of-art performance of 91.3% and 92.9% AUC for diagnosis of benign/malignant and pre-invasive/invasive nodules, respectively. Importantly, our model outperforms senior doctors in risk stratification of invasive adenocarcinoma with 77.6% accuracy [i.e., Grades 1, 2, 3]). It provides detailed predictive histological information for the surgical management of pulmonary nodules. Finally, for user-friendly access, the proposed model is implemented as a web-based system ( https://seeyourlung.com.cn ).

Pretreatment Multiparametric MRI-Based Radiomics Analysis for the Diagnosis of Breast Phyllodes Tumors

BACKGROUND

Preoperative pathological grading assessment is important for patients with breast phyllodes tumors (PTs).

PURPOSE

To develop and validate a clinical-radiomics model based on multiparametric MRI and clinical information for the pretreatment differential diagnosis of PTs.

STUDY TYPE

Retrospective.

POPULATION

A total of 216 patients with PTs, 133 in the training cohort (55 benign PTs [BPTs] and 78 borderline/malignant PTs [BMPTs]) and 83 in the validation cohort (28 BPTs and 55 BMPTs).

FIELD STRENGTH/SEQUENCE

1.5 T and 3 T; T2-weighted imaging (T2WI), precontrast T1-weighted imaging (T1WI) and dynamic contrast-enhanced T1-weighted imaging (DCE-T1WI).

ASSESSMENT

A total of 3138 radiomics features were computed to decode the imaging phenotypes of PTs. To build the classification models, the following workflow was followed: minimum-maximum scaling normalization method, recursive feature elimination based on ridge regression (Ridge-RFE), synthetic minority oversampling technique, and support vector machine classifier. We established several models based on the statistically significant features (Ridge-RFE selected) of each sequence to distinguish BPTs from BMPTs, including precontrast T1WI model, DCE-T1WI phase 1 model, T1WI feature fusion model, T2WI model, T1WI + T2WI model, clinical feature model, conventional MRI characteristics model, and combined clinical-radiomics model.

STATISTICAL TESTS

Univariate analysis was utilized to compare variables between the BPT and BMPT groups. The receiver operating characteristic curve (ROC) analysis was used to evaluate the diagnostic performance of these models.

RESULTS

In the training cohort, the clinical-radiomics model had excellent diagnostic efficiency, with an area under ROC (AUC) of 0.91 ± 0.02 (95% CI: 0.87-0.94). In the validation cohort, the AUCs were 0.79 ± 0.05 (95% CI: 0.70-0.87) for the combined model and 0.77 ± 0.05 (95% CI: 0.67-0.85) for the radiomics model.

DATA CONCLUSION

Compared with conventional MRI characteristics, radiomics features extracted from multiparametric MRI are helpful for improving the accuracy of differentiating the pathological grades of PTs preoperatively. The model based on radiomics and clinical information is expected to become a potential noninvasive tool for the assessment of PTs grades.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Artificial intelligence: A critical review of applications for lung nodule and lung cancer

Artificial intelligence (AI) is a broad concept that usually refers to computer programs that can learn from data and perform certain specific tasks. In the recent years, the growth of deep learning, a successful technique for computer vision tasks that does not require explicit programming, coupled with the availability of large imaging databases fostered the development of multiple applications in the medical imaging field, especially for lung nodules and lung cancer, mostly through convolutional neural networks (CNN). Some of the first applications of AI is this field were dedicated to automated detection of lung nodules on X-ray and computed tomography (CT) examinations, with performances now reaching or exceeding those of radiologists. For lung nodule segmentation, CNN-based algorithms applied to CT images show excellent spatial overlap index with manual segmentation, even for irregular and ground glass nodules. A third application of AI is the classification of lung nodules between malignant and benign, which could limit the number of follow-up CT examinations for less suspicious lesions. Several algorithms have demonstrated excellent capabilities for the prediction of the malignancy risk when a nodule is discovered. These different applications of AI for lung nodules are particularly appealing in the context of lung cancer screening. In the field of lung cancer, AI tools applied to lung imaging have been investigated for distinct aims. First, they could play a role for the non-invasive characterization of tumors, especially for histological subtype and somatic mutation predictions, with a potential therapeutic impact. Additionally, they could help predict the patient prognosis, in combination to clinical data. Despite these encouraging perspectives, clinical implementation of AI tools is only beginning because of the lack of generalizability of published studies, of an inner obscure working and because of limited data about the impact of such tools on the radiologists' decision and on the patient outcome. Radiologists must be active participants in the process of evaluating AI tools, as such tools could support their daily work and offer them more time for high added value tasks.

How Many Private Data Are Needed for Deep Learning in Lung Nodule Detection on CT Scans? A Retrospective Multicenter Study

Simple Summary

The early detection of lung nodules is important for patient treatment and follow-up. Many researchers are investigating deep-learning-based lung nodule detection to ease the burden of lung nodule detection by radiologists. The purpose of this paper is to provide guidelines for collecting lung nodule data to facilitate research. We collected chest computed tomography scans reviewed by radiologists at three hospitals. In addition, several experiments were conducted using the large-scale open dataset, LUNA16. As a result of the experiment, it was possible to prove the value of using the collected data compared to using LUNA16. We also demonstrated the effectiveness of transfer learning from pre-trained learning weights in LUNA16. Finally, our study provides information on the amount of lung nodule data that must be collected to stabilize lung nodule detection performance.

Abstract

Early detection of lung nodules is essential for preventing lung cancer. However, the number of radiologists who can diagnose lung nodules is limited, and considerable effort and time are required. To address this problem, researchers are investigating the automation of deep-learning-based lung nodule detection. However, deep learning requires large amounts of data, which can be difficult to collect. Therefore, data collection should be optimized to facilitate experiments at the beginning of lung nodule detection studies. We collected chest computed tomography scans from 515 patients with lung nodules from three hospitals and high-quality lung nodule annotations reviewed by radiologists. We conducted several experiments using the collected datasets and publicly available data from LUNA16. The object detection model, YOLOX was used in the lung nodule detection experiment. Similar or better performance was obtained when training the model with the collected data rather than LUNA16 with large amounts of data. We also show that weight transfer learning from pre-trained open data is very useful when it is difficult to collect large amounts of data. Good performance can otherwise be expected when reaching more than 100 patients. This study offers valuable insights for guiding data collection in lung nodules studies in the future.

Artificial Intelligence and the diagnosis of lung cancer in early stage: scoping review. (Preprint).. [DOI: 10.2196/preprints.38773] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Lung cancer is considered to be the most fatal out of all diagnoseable cancers. This is, in part, due to the difficulty in detecting lung cancer at an early stage. Moreover, approximately one in five individuals who will develop lung cancer will pass away due to a misdiagnosis. Fortunately, Machine Learning (ML) and Deep Learning (DL) is considered to be a promising solution for detection of lung cancer through developments in radiology.

OBJECTIVE

The purpose of this paper is to is to review how AI can assist identifying and diagnosing of lung cancer in an early stage.

METHODS

PRISMA was utilized and were retrieved from 4 databases: Google Scholar, PubMed, EMBASE, and Institute of Electrical and Electronics Engineers (IEEE). In addition, two phases of screening were implemented in order to determine relevant literature. The first phase was reading the title and abstract, and the second stage was reading the full text. These two steps were independently conducted by three reviewers. Finally, the three authors use a narrative synthesis to present the data.

RESULTS

Overall, 543 potential studies were extracted from four databases. After screening, 26 articles that met the inclusion criteria were included in this scoping review. Several articles utilized privet data including patients’ data and other public sources. 15 articles used data from UCI repository dataset (58%). However, CT scan images was utilized on 9 studies (normal CT was mentioned in 5 articles (19%), two studies used CT scan with PET (7.7%), and two articles used FDG with CT (7.7%). While two articles used demographic data such as age, sex, and educational background (7.7%).

CONCLUSIONS

This scoping review illustrates recent studies that utilize AI models to diagnose lung cancer. The literature currently relies on private and public databases and compare models with physicians or other machine learning technology. Additional studies should be conducted to explore the efficacy of these technologies in clinical settings.