Objective:To investigate the value of a preoperatively MRI-based deep learning (DL) radiomics machine learning model to distinguish low-grade and high-grade soft tissue sarcomas (STS).Methods:From November 2007 to May 2019, 151 patients with STS confirmed by pathology in the Affiliated Hospital of Qingdao University were enrolled as training sets, and 131 patients in the Affiliated Hospital of Shandong First Medical University and the Third Hospital of Hebei Medical University were enrolled as external validation sets. According to the French Federation Nationale des Centres de Lutte Contre le Cancer classification (FNCLCC) system, 161 patients with FNCLCC grades Ⅰ and Ⅱ were defined as low-grade and 121 patients with grade Ⅲ were defined as high-grade. The hand-crafted radiomic (HCR) and DL radiomic features of the lesions were extracted respectively. Based on HCR features, DL features, and HCR-DL combined features, respectively, three machine-learning models were established by decision tree, logistic regression, and support vector machine (SVM) classifiers. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of each machine learning model and choose the best one. The univariate and multivariate logistic regression were used to establish a clinical-imaging factors model based on demographics and MRI findings. The nomogram was established by combining the optimal radiomics model and the clinical-imaging model. The AUC was used to evaluate the performance of each model and the DeLong test was used for comparison of AUC between every two models. The Kaplan-Meier survival curve and log-rank test were used to evaluate the performance of the optimal machine learning model in the risk stratification of progression free survival (PFS) in STS patients.Results:The SVM radiomics model based on HCR-DL combined features had the optimal predicting power with AUC values of 0.931(95%CI 0.889-0.973) in the training set and 0.951 (95%CI 0.904-0.997) in the validation set. The AUC values of the clinical-imaging model were 0.795 (95%CI 0.724-0.867) and 0.615 (95%CI 0.510-0.720), and of the nomogram was 0.875 (95%CI 0.818-0.932) and 0.786 (95%CI 0.701-0.872) in the training and validation sets, respectively. In validation set, the performance of SVM radiomics model was better than those of the nomogram and clinical-imaging models ( Z=3.16, 6.07; P=0.002,<0.001). Using the optimal radiomics model, there was statistically significant in PFS between the high and low risk groups of STS patients (training sets: χ2=43.50, P<0.001; validation sets: χ2=70.50, P<0.001). Conclusion:Preoperative MRI-based DL radiomics machine learning model has accurate prediction performance in differentiating the histopathological grading of STS. The SVM radiomics model based on HCR-DL combined features has the optimal predicting power and was expected to undergo risk stratification of prognosis in STS patients.

Objective:To develop a prototype artificial intelligence immunofluorescence image recognition system for classification of antinuclear antibodies in order to meet the growing clinical requirements for an automatic readout and classification of immunof luorescence patterns for antinuclear antibody (ANA) images.Methods:Immunofluorescence images with positive results of ANA in Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine from April 2020 to December 2021 were collected. Three senior technicians independently and in parallel interpreted the Immunofluorescence images to determine the ANA results. Then the images were labeled according to the ANA International Consensus on Fluorescence Patterns (ICAP) classification criteria. There were 7 labeled groups: Fine speckled, Coarse speckled, Homogeneous, nucleolar, Centromere, Nuclear dots and Nuclear envelope. Each group was randomly divided into training dataset and validation dataset at a ratio of 9∶1 by using random number table. On the deep learning framework PyTORCH 1.7, the convolutional neural network (CNN) training platform was constructed based on ResNet-34 image classification network, and the automatic ANA recognition system was established. After the model was established, the test set was set up separately, the judgment results of the model were output by ranking the prediction probability, with the results of the 2 senior technicians was taken as "golden standard". Parameters such as accuracy, precision, recall and F1-score were used as indicators to evaluate the performance of the model.Results:A total of 23138 immunofluorescence images were obtained after segmentation and annotation. A total of 7 models were trained, and the effects of different algorithms, image processing and enhancement methods on the model were compared. The ResNet-34 model with the highest accuracy andswas selected as the final model, with the classification accuracy of 93.31%, precision rate of 91%, and recall rate of 90% and F1-score of 91% in the test set. The overall coincidence rate between the model and manual interpretation was 90.05%, and the accuracy of recognition of nucleolus was the highest, with the coincidence rate reaching 100% in the test set.Conclusion:The current AI system developed based on deep learning of the ANA immunofluorescence images in the present study showed the ability to recognize ANA pattern, especially in the common, typical, simple pattern.

Purpose To explore the value of three-dimensions densely connected convolutional networks(3D-DenseNet)in the differential diagnosis of high-grade gliomas(HGGs)and single brain metastases(BMs)via MRI,and to compare the diagnostic performance of models built with different sequences.Materials and Methods T2WI and T1WI contra-enhanced(T1C)imaging data of 230 cases of HGGs and 111 cases of BMs confirmed by surgical pathology in Lanzhou University Second Hospital from June 2016 to June 2021 were retrospectively collected,and the volume of interest under the 3D model was delineated in advance as the input data.All data were randomly divided into a training set(n=254)and a validation set(n=87)in a ratio of 7∶3.Based on the 3D-DenseNet,T2WI,T1C and two sequence fusion prediction models(T2-net,T1C-net and TS-net)were constructed respectively.The predictive efficiency of each model was evaluated and compared by the receiver operating characteristic curve,and the predictive performance of models built with different sequences were compared.Results The area under curve(AUC)of T1C-net,T2-net and TS-net in the training and validation sets were 0.852,0.853,0.802,0.721,0.856 and 0.745,respectively.The AUC and accuracy of the validation set of T1C-net were significantly higher than those of T2-net and TS-net,respectively,and the AUC and accuracy of the validation set of TS-net were significantly higher than those of T2-net.There was a significant difference between T1C-net and T2-net models(P<0.05),while there were no statistical differences between the models of TS-net and T2-net,T1C-net and TS-net(P>0.05).The T1C-net model based on 3D-DenseNet had the best performance,the accuracy of the validation set was 80.5%,the sensitivity was 90.9%,the specificity was 62.5%.Conclusion The 3D-DenseNet model based on MRI conventional sequence has better diagnostic performance,and the model built by T1C-net sequence has better performance in differentiating HGGs and BMs.Deep learning models can be a potential tool to identify HGGs and BMs and to guide the clinical formulation of precise treatment plans.

BACKGROUND: Pneumonia-like primary pulmonary lymphoma (PPL) was commonly misdiagnosed as infectious pneumonia, leading to delayed treatment. The purpose of this study was to establish a computed tomography (CT)-based radiomics model to differentiate pneumonia-like PPL from infectious pneumonia. METHODS: In this retrospective study, 79 patients with pneumonia-like PPL and 176 patients with infectious pneumonia from 12 medical centers were enrolled. Patients from center 1 to center 7 were assigned to the training or validation cohort, and the remaining patients from other centers were used as the external test cohort. Radiomics features were extracted from CT images. A three-step procedure was applied for radiomics feature selection and radiomics signature building, including the inter- and intra-class correlation coefficients (ICCs), a one-way analysis of variance (ANOVA), and least absolute shrinkage and selection operator (LASSO). Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and construct a clinical factor model. Two radiologists reviewed the CT images for the external test set. Performance of the radiomics model, clinical factor model, and each radiologist were assessed by receiver operating characteristic, and area under the curve (AUC) was compared. RESULTS: A total of 144 patients (44 with pneumonia-like PPL and 100 infectious pneumonia) were in the training cohort, 38 patients (12 with pneumonia-like PPL and 26 infectious pneumonia) were in the validation cohort, and 73 patients (23 with pneumonia-like PPL and 50 infectious pneumonia) were in the external test cohort. Twenty-three radiomics features were selected to build the radiomics model, which yielded AUCs of 0.95 (95% confidence interval [CI]: 0.94-0.99), 0.93 (95% CI: 0.85-0.98), and 0.94 (95% CI: 0.87-0.99) in the training, validation, and external test cohort, respectively. The AUCs for the two readers and clinical factor model were 0.74 (95% CI: 0.63-0.83), 0.72 (95% CI: 0.62-0.82), and 0.73 (95% CI: 0.62-0.84) in the external test cohort, respectively. The radiomics model outperformed both the readers' interpretation and clinical factor model ( P <0.05). CONCLUSIONS The CT-based radiomics model may provide an effective and non-invasive tool to differentiate pneumonia-like PPL from infectious pneumonia, which might provide assistance for clinicians in tailoring precise therapy.
Humans ; Retrospective Studies ; Pneumonia/diagnostic imaging* ; Analysis of Variance ; Tomography, X-Ray Computed ; Lymphoma/diagnostic imaging*