Search

State-of-the-art thoracic magnetic resonance imaging (MRI) plays a complementary role in the assessment of pulmonary nodules/masses which potentially indicate to cancer. We aimed to evaluate the sensitivity and specificity of MRI in diagnosis of pulmonary nodules/masses.Sixty-eight patients with computed tomography (CT)-detected pulmonary nodules/masses underwent 3T MRI (T1-VIBE, T1-starVIBE, T2-fBLADE turbo spin-echo, and T2-SPACE). The detection rate was calculated for each of the different subgroups of pulmonary nodules according to lung imaging reporting and data system (Lung-RADS). The four MRI sequences were compared in terms of detection rate and image quality-signal to noise ratio (SNR), contrast to noise ratio (CNR) and 5-point scoring scale. Agreement of lesion size measurement between CT and MRI was assessed by intraclass correlation coefficient (ICC). The picture-SNR, lesion-SNR and CNR of each sequence were analyzed by Mann-Whitney U test.In total, 232 pulmonary lesions were detected by CT. The CT showed 86 solid nodules (SNs)6 mm, 15 SNs between 6-8 mm, 35 SNs between 8-15 mm, and 52 SNs between 15-30 mm. The T1-VIBE, T1-starVIBE, T2-fBLADE TSE and T2-SPACE sequences accurately detected 141 SNs (141/188, 75%/83.3%), 150 SNs (150/188, 79.8%/100%), 166 SNs (166/188, 88.3%/66.7%) and 169 SNs (169/188, 89.9%/53.3%), respectively. Four ground glass nodules (GGNs) (4/6) were detected by T2-fBLADE TSE. Twelve part-solid nodules (PSNs) (12/22) were detected by T1-VIBE and 20 PSNs (20/22) by T2-SPACE. A total of 100 lesions (2.2±1.4 cm, 0.8-7.3 cm) were accurately detected and measured by the four MRI sequences with ICC0.96. The picture-SNR, lesion-SNR and CNR by T1-starVIBE were higher than those by T1-VIBE (P0.001). The lesion-SNR and CNR by T2-fBLADE TSE were higher than those by T2-SPACE (P=0.006, 0.038). 86% of images by T1-starVIBE, 92% by T2-fBLADE TSE, 90% by T2-SPACE and 93% by T1-VIBE were scored 3 or more.MRI achieves high sensitivity and specificity for different type of pulmonary nodules detection and is an effective alternative to CT as a diagnostic tool for pulmonary nodules.

BACKGROUND: The efficient and accurate diagnosis of pulmonary adenocarcinoma before surgery is of considerable significance to clinicians. Although computed tomography (CT) examinations are widely used in practice, it is still challenging and time-consuming for radiologists to distinguish between different types of subcentimeter pulmonary nodules. Although there have been many deep learning algorithms proposed, their performance largely depends on vast amounts of data, which is difficult to collect in the medical imaging area. Therefore, we propose an automatic classification system for subcentimeter pulmonary adenocarcinoma, combining a convolutional neural network (CNN) and a generative adversarial network (GAN) to optimize clinical decision-making and to provide small dataset algorithm design ideas. METHODS: A total of 206 nodules with postoperative pathological labels were analyzed. Among them were 30 adenocarcinomas in situ (AISs), 119 minimally invasive adenocarcinomas (MIAs), and 57 invasive adenocarcinomas (IACs). Our system consisted of two parts, a GAN-based image synthesis, and a CNN classification. First, several popular existing GAN techniques were employed to augment the datasets, and comprehensive experiments were conducted to evaluate the quality of the GAN synthesis. Additionally, our classification system processes were based on two-dimensional (2D) nodule-centered CT patches without the need of manual labeling information. RESULTS: For GAN-based image synthesis, the visual Turing test showed that even radiologists could not tell the GAN-synthesized from the raw images (accuracy: primary radiologist 56%, senior radiologist 65%). For CNN classification, our progressive growing wGAN improved the performance of CNN most effectively (area under the curve =0.83). The experiments indicated that the proposed GAN augmentation method improved the classification accuracy by 23.5% (from 37.0% to 60.5%) and 7.3% (from 53.2% to 60.5%) in comparison with training methods using raw and common augmented images respectively. The performance of this combined GAN and CNN method (accuracy: 60.5%±2.6%) was comparable to the state-of-the-art methods, and our CNN was also more lightweight. CONCLUSIONS: The experiments revealed that GAN synthesis techniques could effectively alleviate the problem of insufficient data in medical imaging. The proposed GAN plus CNN framework can be generalized for use in building other computer-aided detection (CADx) algorithms and thus assist in diagnosis.

BACKGROUND: The assessment of the severity of coronavirus disease 2019 (COVID-19) by clinical presentation has not met the urgent clinical need so far. We aimed to establish a deep learning (DL) model based on quantitative computed tomography (CT) and initial clinical features to predict the severity of COVID-19. METHODS: One hundred ninety-six hospitalized patients with confirmed COVID-19 were enrolled from January 20 to February 10, 2020 in our centre, and were divided into severe and non-severe groups. The clinico-radiological data on admission were retrospectively collected and compared between the two groups. The optimal clinico-radiological features were determined based on least absolute shrinkage and selection operator (LASSO) logistic regression analysis, and a predictive nomogram model was established by five-fold cross-validation. Receiver operating characteristic (ROC) analyses were conducted, and the areas under the receiver operating characteristic curve (AUCs) of the nomogram model, quantitative CT parameters that were significant in univariate analysis, and pneumonia severity index (PSI) were compared. RESULTS: In comparison with the non-severe group (151 patients), the severe group (45 patients) had a higher PSI (P

BACKGROUND: To evaluate the diagnostic efficacy of Densely Connected Convolutional Networks (DenseNet) for detection of COVID-19 features on high resolution computed tomography (HRCT). METHODS: The Ethic Committee of our institution approved the protocol of this study and waived the requirement for patient informed consent. Two hundreds and ninety-five patients were enrolled in this study (healthy person: 149; COVID-19 patients: 146), which were divided into three separate non-overlapping cohorts (training set, n=135, healthy person, n=69, patients, n=66; validation set, n=20, healthy person, n=10, patients, n=10; test set, n=140, healthy person, n=70, patients, n=70). The DenseNet was trained and tested to classify the images as having manifestation of COVID-19 or as healthy. A radiologist also blindly evaluated all the test images and rechecked the misdiagnosed cases by DenseNet. Receiver operating characteristic curves (ROC) and areas under the curve (AUCs) were used to assess the model performance. The sensitivity, specificity and accuracy of DenseNet model and radiologist were also calculated. RESULTS: The DenseNet algorithm model yielded an AUC of 0.99 (95% CI: 0.958–1.0) in the validation set and 0.98 (95% CI: 0.972–0.995) in the test set. The threshold value was selected as 0.8, while for validation and test sets, the accuracies were 95% and 92%, the sensitivities were 100% and 97%, the specificities were 90% and 87%, and the F1 values were 95% and 93%, respectively. The sensitivity of radiologist was 94%, the specificity was 96%, while the accuracy was 95%. CONCLUSIONS: Deep learning (DL) with DenseNet can accurately classify COVID-19 on HRCT with an AUC of 0.98, which can reduce the miss diagnosis rate (combined with radiologists’ evaluation) and radiologists’ workload.