Radiomics and deep learning models to differentiate lung adenosquamous carcinoma: A multicenter trial.
Ontology highlight
ABSTRACT:
SUBMITTER: Chu X
PROVIDER: S-EPMC10474462 | biostudies-literature | 2023 Sep
REPOSITORIES: biostudies-literature
Publications
Radiomics and deep learning models to differentiate lung adenosquamous carcinoma: A multicenter trial.
Chu Xianjing X Niu Lishui L Yang Xianghui X He Shiqi S Li Aixin A Chen Liu L Liang Zhan Z Jing Di D Zhou Rongrong R
iScience 20230816 9
Adenosquamous carcinoma (ASC) is frequently misdiagnosed or overlooked in clinical practice due to its dual histological components and potential transformation from either adenocarcinoma (ADC) or squamous cell carcinoma (SCC). Our study aimed to differentiate ASC from ADC and SCC by incorporating features of enhanced CTs and clinical characteristics to build radiomics and deep learning models. The classification models were trained in Xiangya Hospital and validated in two other independent hosp ...[more]
Similar Datasets
Project description:ObjectivesTo develop and validate radiomics and deep learning models based on contrast-enhanced MRI (CE-MRI) for differentiating dual-phenotype hepatocellular carcinoma (DPHCC) from HCC and intrahepatic cholangiocarcinoma (ICC).MethodsOur study consisted of 381 patients from four centers with 138 HCCs, 122 DPHCCs, and 121 ICCs (244 for training and 62 for internal tests, centers 1 and 2; 75 for external tests, centers 3 and 4). Radiomics, deep transfer learning (DTL), and fusion models based on CE-MRI were established for differential diagnosis, respectively, and their diagnostic performances were compared using the confusion matrix and area under the receiver operating characteristic (ROC) curve (AUC).ResultsThe radiomics model demonstrated competent diagnostic performance, with a macro-AUC exceeding 0.9, and both accuracy and F1-score above 0.75 in the internal and external validation sets. Notably, the vgg19-combined model outperformed the radiomics and other DTL models. The fusion model based on vgg19 further improved diagnostic performance, achieving a macro-AUC of 0.990 (95% CI: 0.965-1.000), an accuracy of 0.935, and an F1-score of 0.937 in the internal test set. In the external test set, it similarly performed well, with a macro-AUC of 0.988 (95% CI: 0.964-1.000), accuracy of 0.875, and an F1-score of 0.885.ConclusionsBoth the radiomics and the DTL models were able to differentiate DPHCC from HCC and ICC before surgery. The fusion models showed better diagnostic accuracy, which has important value in clinical application.Critical relevance statementMRI-based deep learning radiomics were able to differentiate DPHCC from HCC and ICC preoperatively, aiding clinicians in the identification and targeted treatment of these malignant hepatic tumors.Key pointsFusion models may yield an incremental value over radiomics models in differential diagnosis. Radiomics and deep learning effectively differentiate the three types of malignant hepatic tumors. The fusion models may enhance clinical decision-making for malignant hepatic tumors.
| S-EPMC11780023 | biostudies-literature
Project description:ObjectivesThe accurate assessment of lymph node metastasis (LNM) can facilitate clinical decision-making on radiotherapy or radical hysterectomy (RH) in cervical adenocarcinoma (AC)/adenosquamous carcinoma (ASC). This study aims to develop a deep learning radiomics nomogram (DLRN) to preoperatively evaluate LNM in cervical AC/ASC.Materials and methodsA total of 652 patients from a multicenter were enrolled and randomly allocated into primary, internal, and external validation cohorts. The radiomics features were extracted from axial T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted imaging (CE-T1WI). The DL features from T2WI, DWI, and CE-T1WI were exported from Resnet 34, which was pretrained by 14 million natural images of the ImageNet dataset. The radscore (RS) and DL score (DLS) were independently obtained after repeatability test, Pearson correlation coefficient (PCC), minimum redundancy maximum relevance (MRMR), and least absolute shrinkage and selection operator (LASSO) algorithm performed on the radiomics and DL feature sets. The DLRN was then developed by integrating the RS, DLS, and independent clinicopathological factors for evaluating the LNM in cervical AC/ASC.ResultsThe nomogram of DLRN-integrated FIGO stage, menopause, RS, and DLS achieved AUCs of 0.79 (95% CI, 0.74-0.83), 0.87 (95% CI, 0.81-0.92), and 0.86 (95% CI, 0.79-0.91) in the primary, internal, and external validation cohorts. Compared with the RS, DLS, and clinical models, DLRN had a significant higher AUC for evaluating LNM (all P < 0.005).ConclusionsThe nomogram of DLRN can accurately evaluate LNM in cervical AC/ASC.
| S-EPMC11671353 | biostudies-literature
Project description:BackgroundBrain metastases are common brain tumors in adults. Brain metastases from different primary tumors have special magnetic resonance imaging (MRI) features. As a new technology that can extract and quantify medical image data, and with the rapid development of artificial intelligence, the machine learning model based on radiology has been successfully applied to the diagnosis and differentiation of tumors. This study aimed to develop radiomics models from post-contrast T1-weighted images using machine learning algorithms to differentiate lung cancer from breast cancer brain metastases.MethodsA retrospective analysis was conducted on 118 lung cancer brain metastases patients and 62 breast cancer brain metastases patients confirmed by surgery pathology or combined clinical and imaging diagnosis at The Fifth Affiliated Hospital of Sun Yat-sen University from August 2015 to September 2023. Patients were randomly divided into a training set (126 cases) and a validation set (54 cases) at a 7:3 ratio. Enhanced T1-weighted images of all patients were imported into ITK-SNAP software to manually delineate the region of interest (ROI). Radiomic features were extracted based on the ROI and feature selection was performed using the least absolute shrinkage and selection operator. Significant features were used to develop models using logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), multilayer perceptron (MLP), and light gradient boosting machine (LightGBM). The diagnostic performance of the models was assessed using the receiver operating characteristic (ROC) curve.ResultsThe LightGBM radiomics model exhibited the best diagnostic performance, with an area under the curve (AUC) of 0.875 [95% confidence interval (CI): 0.819-0.931] in the training set and 0.866 (95% CI: 0.740-0.993) in the validation set.ConclusionsThe enhanced MRI radiomics model, especially the LightGBM model, can accurately predict the primary lesion types of brain metastases from lung cancer and breast cancer origins.
| S-EPMC11912090 | biostudies-literature
Project description:BackgroundPreoperative prediction models for histologic subtype and grade of stage IA lung adenocarcinoma (LUAD) according to the update of the WHO Classification of Tumors of the Lung in 2021 and the 2020 new grade system are yet to be explored. We aim to develop the noninvasive pathology and grade evaluation approach for patients with stage IA LUAD via CT-based radiomics approach and evaluate their performance in clinical practice.MethodsChest CT scans were retrospectively collected from patients who were diagnosed with stage IA LUAD and underwent complete resection at two hospitals. A deep learning segmentation algorithm was first applied to assist lesion delineation. Expansion strategies such as bounding-box annotations were further applied. Radiomics features were then extracted and selected followed by radiomics modeling based on four classic machine learning algorithms for histologic subtype classification and grade stratification. The area under the receiver operating characteristic curve (AUC) was used to evaluate model performance.ResultsThe study included 294 and 145 patients with stage IA LUAD from two hospitals for radiomics analysis, respectively. For classification of four histological subtypes, multilayer perceptron (MLP) algorithm presented no annotation strategy preference and achieved the average AUC of 0.855, 0.922, and 0.720 on internal, independent, and external test sets with 1-pixel expansion annotation. Bounding-box annotation strategy also enabled MLP an acceptable and stable accuracy among test sets. Meanwhile, logistic regression was selected for grade stratification and achieved the average AUC of 0.928, 0.837, and 0.748 on internal, independent, and external test sets with optimal annotation strategies.ConclusionsDL-enhanced radiomics models had great potential to predict the fine histological subtypes and grades of early-stage LUADs based on CT images, which might serve as a promising noninvasive approach for the diagnosis and management of early LUADs.
| S-EPMC10400286 | biostudies-literature
Project description:Cross-sectional X-ray imaging has become the standard for staging most solid organ malignancies. However, for some malignancies such as urinary bladder cancer, the ability to accurately assess local extent of the disease and understand response to systemic chemotherapy is limited with current imaging approaches. In this study, we explored the feasibility that radiomics-based predictive models using pre- and post-treatment computed tomography (CT) images might be able to distinguish between bladder cancers with and without complete chemotherapy responses. We assessed three unique radiomics-based predictive models, each of which employed different fundamental design principles ranging from a pattern recognition method via deep-learning convolution neural network (DL-CNN), to a more deterministic radiomics feature-based approach and then a bridging method between the two, utilizing a system which extracts radiomics features from the image patterns. Our study indicates that the computerized assessment using radiomics information from the pre- and post-treatment CT of bladder cancer patients has the potential to assist in assessment of treatment response.
| S-EPMC5562694 | biostudies-other
Project description:ObjectiveThe neglect of occult lymph nodes metastasis (OLNM) is one of the pivotal causes of early non-small cell lung cancer (NSCLC) recurrence after local treatments such as stereotactic body radiotherapy (SBRT) or surgery. This study aimed to develop and validate a computed tomography (CT)-based radiomics and deep learning (DL) fusion model for predicting non-invasive OLNM.MethodsPatients with radiologically node-negative lung adenocarcinoma from two centers were retrospectively analyzed. We developed clinical, radiomics, and radiomics-clinical models using logistic regression. A DL model was established using a three-dimensional squeeze-and-excitation residual network-34 (3D SE-ResNet34) and a fusion model was created by integrating seleted clinical, radiomics features and DL features. Model performance was assessed using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, calibration curves, and decision curve analysis (DCA). Five predictive models were compared; SHapley Additive exPlanations (SHAP) and Gradient-weighted Class Activation Mapping (Grad-CAM) were employed for visualization and interpretation.ResultsOverall, 358 patients were included: 186 in the training cohort, 48 in the internal validation cohort, and 124 in the external testing cohort. The DL fusion model incorporating 3D SE-Resnet34 achieved the highest AUC of 0.947 in the training dataset, with strong performance in internal and external cohorts (AUCs of 0.903 and 0.907, respectively), outperforming single-modal DL models, clinical models, radiomics models, and radiomics-clinical combined models (DeLong test: P<0.05). DCA confirmed its clinical utility, and calibration curves demonstrated excellent agreement between predicted and observed OLNM probabilities. Features interpretation highlighted the importance of textural characteristics and the surrounding tumor regions in stratifying OLNM risk.ConclusionsThe DL fusion model reliably and accurately predicts OLNM in early-stage lung adenocarcinoma, offering a non-invasive tool to refine staging and guide personalized treatment decisions. These results may aid clinicians in optimizing surgical and radiotherapy strategies.
| S-EPMC11893343 | biostudies-literature
Project description:BackgroundPreoperative prediction of pancreatic cystic neoplasm (PCN) differentiation has significant value for the implementation of personalized diagnosis and treatment plans. This study aimed to build radiomics deep learning (DL) models using computed tomography (CT) data for the preoperative differential diagnosis of common cystic tumors of the pancreas.MethodsClinical and CT data of 193 patients with PCN were collected for this study. Among these patients, 99 were pathologically diagnosed with pancreatic serous cystadenoma (SCA), 55 were diagnosed with mucinous cystadenoma (MCA) and 39 were diagnosed with intraductal papillary mucinous neoplasm (IPMN). The regions of interest (ROIs) were obtained based on manual image segmentation of CT slices. The radiomics and radiomics-DL models were constructed using support vector machines (SVMs). Moreover, based on the fusion of clinical and radiological features, the best combined feature set was obtained according to the Akaike information criterion (AIC) analysis. Then the fused model was constructed using logistic regression.ResultsFor the SCA differential diagnosis, the fused model performed the best and obtained an average area under the curve (AUC) of 0.916. It had a best feature set including position, polycystic features (ā„6), cystic wall calcification, pancreatic duct dilatation and radiomics-DL score. For the MCA and IPMN differential diagnosis, the fused model with AUC of 0.973 had a best feature set including age, communication with the pancreatic duct and radiomics score.ConclusionsThe radiomics, radiomics-DL and fused models based on CT images have a favorable differential diagnostic performance for SCA, MCA and IPMN. These findings may be beneficial for the exploration of individualized management strategies.
| S-EPMC9710154 | biostudies-literature
Project description:BackgroundNon-small-cell lung cancer (NSCLC) patients often demonstrate varying clinical courses and outcomes, even within the same tumor stage. This study explores deep learning applications in medical imaging allowing for the automated quantification of radiographic characteristics and potentially improving patient stratification.Methods and findingsWe performed an integrative analysis on 7 independent datasets across 5 institutions totaling 1,194 NSCLC patients (age median = 68.3 years [range 32.5-93.3], survival median = 1.7 years [range 0.0-11.7]). Using external validation in computed tomography (CT) data, we identified prognostic signatures using a 3D convolutional neural network (CNN) for patients treated with radiotherapy (n = 771, age median = 68.0 years [range 32.5-93.3], survival median = 1.3 years [range 0.0-11.7]). We then employed a transfer learning approach to achieve the same for surgery patients (n = 391, age median = 69.1 years [range 37.2-88.0], survival median = 3.1 years [range 0.0-8.8]). We found that the CNN predictions were significantly associated with 2-year overall survival from the start of respective treatment for radiotherapy (area under the receiver operating characteristic curve [AUC] = 0.70 [95% CI 0.63-0.78], p < 0.001) and surgery (AUC = 0.71 [95% CI 0.60-0.82], p < 0.001) patients. The CNN was also able to significantly stratify patients into low and high mortality risk groups in both the radiotherapy (p < 0.001) and surgery (p = 0.03) datasets. Additionally, the CNN was found to significantly outperform random forest models built on clinical parameters-including age, sex, and tumor node metastasis stage-as well as demonstrate high robustness against test-retest (intraclass correlation coefficient = 0.91) and inter-reader (Spearman's rank-order correlation = 0.88) variations. To gain a better understanding of the characteristics captured by the CNN, we identified regions with the most contribution towards predictions and highlighted the importance of tumor-surrounding tissue in patient stratification. We also present preliminary findings on the biological basis of the captured phenotypes as being linked to cell cycle and transcriptional processes. Limitations include the retrospective nature of this study as well as the opaque black box nature of deep learning networks.ConclusionsOur results provide evidence that deep learning networks may be used for mortality risk stratification based on standard-of-care CT images from NSCLC patients. This evidence motivates future research into better deciphering the clinical and biological basis of deep learning networks as well as validation in prospective data.
| S-EPMC6269088 | biostudies-literature
Project description:BackgroundEarly diagnosis of lung cancer is a key intervention for the treatment of lung cancer in which computer-aided diagnosis (CAD) can play a crucial role. Most published CAD methods perform lung cancer diagnosis by classifying each lung nodule in isolation. However, this does not reflect clinical practice, where clinicians diagnose a patient based on a set of images of nodules, instead of looking at one nodule at a time. Besides, the low interpretability of the output provided by these methods presents an important barrier for their adoption.MethodIn this article, we treat lung cancer diagnosis as a multiple instance learning (MIL) problem, which better reflects the diagnosis process in the clinical setting and provides higher interpretability of the output. We selected radiomics as the source of input features and deep attention-based MIL as the classification algorithm. The attention mechanism provides higher interpretability by estimating the importance of each instance in the set for the final diagnosis. To improve the model's performance in a small imbalanced dataset, we propose a new bag simulation method for MIL.Results and conclusionThe results show that our method can achieve a mean accuracy of 0.807 with a standard error of the mean (SEM) of 0.069, a recall of 0.870 (SEM 0.061), a positive predictive value of 0.928 (SEM 0.078), a negative predictive value of 0.591$0.591$ (SEM 0.155), and an area under the curve (AUC) of 0.842 (SEM 0.074), outperforming other MIL methods. Additional experiments show that the proposed oversampling strategy significantly improves the model's performance. In addition, experiments show that our method provides a good indication of the importance of each nodule in determining the diagnosis, which combined with the well-defined radiomic features, to make the results more interpretable and acceptable for doctors and patients.
| S-EPMC9310706 | biostudies-literature
Project description:The main challenge in the management of indeterminate incidentally discovered adrenal tumours is to differentiate benign from malignant lesions. In the absence of clear signs of invasion or metastases, imaging techniques do not always precisely define the nature of the mass. The present pilot study aimed to determine whether radiomics may predict malignancy in adrenocortical tumours. CT images in unenhanced, arterial, and venous phases from 19 patients who had undergone resection of adrenocortical tumours and a cohort who had undergone surveillance for at least 5 years for incidentalomas were reviewed. A volume of interest was drawn for each lesion using dedicated software, and, for each phase, first-order (histogram) and second-order (grey-level colour matrix and run-length matrix) radiological features were extracted. Data were revised by an unsupervised machine learning approach using the K-means clustering technique. Of operated patients, nine had non-functional adenoma and 10 carcinoma. There were 11 patients in the surveillance group. Two first-order features in unenhanced CT and one in arterial CT, and 14 second-order parameters in unenhanced and venous CT and 10 second-order features in arterial CT, were able to differentiate adrenocortical carcinoma from adenoma (Pā<ā0.050). After excluding two malignant outliers, the unsupervised machine learning approach correctly predicted malignancy in seven of eight adrenocortical carcinomas in all phases. Radiomics with CT texture analysis was able to discriminate malignant from benign adrenocortical tumours, even by an unsupervised machine learning approach, in nearly all patients.
| S-EPMC7937424 | biostudies-literature