Using Radiomics to Detect Subtle Architecture Changes of Cartilage and Subchondral Bone in Chronic Lateral Ankle Instability Patients Based on MRI PD-FS Images.

RATIONALE AND OBJECTIVES: To use radiomics to detect the subtle changes of cartilage and subchondral bone in chronic lateral ankle instability (CLAI) patients based on MRI PD-FS images. MATERIALS AND METHODS: A total of 215 CLAI patients and 186 healthy controls were included and randomly split into a training set (n=281, patients/controls=151/130) and an independent test set (n=120, patients/controls=64/56). They underwent ankle MRI examinations. On sagittal PD-FS images, eight cartilage regions and their corresponding subchondral bone regions were drawn. Radiomics models of cartilage, subchondral bone and combined cartilage and subchondral bone were built to differentiate CLAI patients from controls. A receiver operating characteristic curve (ROC) was used to assess the model's performance. RESULTS: In the test dataset, the cartilage model yielded an area under the curve (AUC) of 0.0.912 (95% confidence interval (CI): 0.858-0.965, p<0.001), a sensitivity of 0.859, a specificity of 0.893, a negative predictive value (NPV) of 0.848, and a positive predictive value (PPV) of 0.902. The subchondral bone model yielded an AUC of 0.837 (95% CI: 0.766-0.907, p<0.001), a sensitivity of 0.875, a specificity of 0.714, an NPV of 0.833, and a PPV of 0.778. For the combined model, the AUC was 0.921 (95% CI: 0.863-0.972, p<0.001), sensitivity was 0.844, specificity was 0.911, NPV was 0.836, and PPV was 0.915, whose AUC was higher than those of both the cartilage model and the subchondral bone model. CONCLUSION: The combined radiomics model achieved satisfying performance in detecting potential early architectural changes in cartilage and subchondral bone for CLAI patients.

Self-supervised learning for multi-center magnetic resonance imaging harmonization without traveling phantoms.

Objective.With the progress of artificial intelligence (AI) in magnetic resonance imaging (MRI), large-scale multi-center MRI datasets have a great influence on diagnosis accuracy and model performance. However, multi-center images are highly variable due to the variety of scanners or scanning parameters in use, which has a negative effect on the generality of AI-based diagnosis models. To address this problem, we propose a self-supervised harmonization (SSH) method.Approach.Mapping the style of images between centers allows harmonization without traveling phantoms to be formalized as an unpaired image-to-image translation problem between two domains. The mapping is a two-stage transform, consisting of a modified cycle generative adversarial network (cycleGAN) for style transfer and a histogram matching module for structure fidelity. The proposed algorithm is demonstrated using female pelvic MRI images from two 3 T systems and compared with three state-of-the-art methods and one conventional method. In the absence of traveling phantoms, we evaluate harmonization from three perspectives: image fidelity, ability to remove inter-center differences, and influence on the downstream model.Main results.The improved image sharpness and structure fidelity are observed using the proposed harmonization pipeline. It largely decreases the number of features with a significant difference between two systems (from 64 to 45, lower than dualGAN: 57, cycleGAN: 59, ComBat: 64, and CLAHE: 54). In the downstream cervical cancer classification, it yields an area under the receiver operating characteristic curve of 0.894 (higher than dualGAN: 0.828, cycleGAN: 0.812, ComBat: 0.685, and CLAHE: 0.770).Significance.Our SSH method yields superior generality of downstream cervical cancer classification models by significantly decreasing the difference in radiomics features, and it achieves greater image fidelity.

Hydrogel modification of 3D printing hybrid tracheal scaffold to construct an orthotopic transplantation.

OBJECTIVE: To evaluate the biological properties of modified 3D printing scaffold (PTS) and applied the hybrid graft for in situ transplantation. METHODS: PTS was prepared via 3D printing and modified by Pluronic F-127. Biocompatibility of the scaffold was examined in vitro to ascertain its benefit in attachment and proliferation of bone marrow mesenchymal stem cells (BMSCs). Moreover, a hybrid trachea was constructed by combining the modified PTS with decellularized matrix. Finally, two animal models of in situ transplantation were established, one for repairing tracheal local window-shape defects and the other for tracheal segmental replacement. RESULTS: The rough surface and chemical elements of the scaffold were improved after modification by Pluronic F-127. Results of BMSCs inoculation showed that the modified scaffold was beneficial to attachment and proliferation. The epithelial cells were seen crawling on and attaching to the patch, 30 days following prothetic surgery of the local tracheal defects. Furthermore, the advantages of the modified PTS and decellularized matrix were combined to generate a hybrid graft, which was subsequently applied to a tracheal segmental replacement model. CONCLUSION: Pluronic F-127-based modification generated a PTS with excellent biocompatibility. The modified scaffold has great potential in development of future therapies for tracheal replacement and reconstruction.

Radiomics Feature Analysis of Cartilage and Subchondral Bone in Differentiating Knees Predisposed to Posttraumatic Osteoarthritis after Anterior Cruciate Ligament Reconstruction from Healthy Knees.

OBJECTIVES: To introduce a new implementation of radiomics analysis for cartilage and subchondral bone of the knee and to compare the performance of the proposed models to classic T2 relaxation time in distinguishing knees predisposed to posttraumatic osteoarthritis (PTOA) after anterior cruciate ligament reconstruction (ACLR) and healthy controls. METHODS: 114 patients following ACLR after at least 2 years and 43 healthy controls were reviewed and allocated to training (n = 110) and testing (n = 47) cohorts. Radiomics models are built for cartilage and subchondral bone regions of different compartments: lateral femur (LF), lateral tibia (LT), medial femur (MF), and medial tibia (MT) and combined models of four compartments on T2 mapping images. The model performance of discrimination between patients and controls was illustrated with the receiver operating characteristic curve and compared with a classic T2 value-based model. RESULTS: The T2 value model of cartilage yielded moderate predictive performance in discerning patients and controls, with an AUC of 0.731 (95% confidence interval, 0.556-0.875) in the testing cohort, while the radiomics signature of cartilage and subchondral bone of different compartments demonstrated excellent performance, with AUCs of 0.864-0.979. Furthermore, the combined model reported an even better performance, with AUCs of 0.977 (95% confidence interval, 0.919-1.000) for the cartilage and 0.934 (95% confidence interval, 0.865-0.994) for the subchondral bone in the testing cohort. CONCLUSION: The radiomics features of the cartilage and subchondral bone may be able to provide powerful tools with more sensitive detection than T2 values in differentiating knees at risk for PTOA after ACLR from healthy knees.

Evaluating Solid Lung Adenocarcinoma Anaplastic Lymphoma Kinase Gene Rearrangement Using Noninvasive Radiomics Biomarkers.

PURPOSE: To develop a radiogenomics classifier to assess anaplastic lymphoma kinase (ALK) gene rearrangement status in pretreated solid lung adenocarcinoma noninvasively. MATERIALS AND METHODS: This study consisted of 140 consecutive pretreated solid lung adenocarcinoma patients with complete enhanced CT scans who were tested for both EGFR mutations and ALK status. Pre-contrast CT and standard post-contrast CT radiogenomics machine learning classifiers were designed as two separate classifiers. In each classifier, dataset was randomly split into training and independent testing group on a 7:3 ratio, accordingly subjected to a 5-fold cross-validation. After normalization, best feature subsets were selected by Pearson correlation coefficient (PCC) and analysis of variance (ANOVA) or recursive feature elimination (RFE), whereupon a radiomics classifier was built with support vector machine (SVM). The discriminating performance was assessed with the area under receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: In classifier one, 98 cases were selected as training data set, 42 cases as independent testing data set. In classifier two, 87 cases were selected as training data set, 37 cases as independent testing data set. Both classifiers extracted 851 radiomics features. The top 25 pre-contrast features and top 19 post-contrast features were selected to build optimal ALK+ radiogenomics classifiers accordingly. The accuracies, AUCs, sensitivity, specificity, PPV, and NPV of pre-contrast CT classifier were 78.57%, 80.10% (CI: 0.6538-0.9222), 71.43%, 82.14%, 66.67%, and 85.19%, respectively. Those results of standard post-contrast CT classifier were 81.08%, 82.85% (CI: 0.6630-0.9567), 76.92%, 83.33%, 71.43%, and 86.96%. CONCLUSION: Solid lung adenocarcinoma ALK+ radiogenomics classifier of standard post-contrast CT radiomics biomarkers produced superior performance compared with that of pre-contrast one, suggesting that post-contrast CT radiomics should be recommended in the context of solid lung adenocarcinoma radiogenomics AI. Standard post-contrast CT machine learning radiogenomics classifier could help precisely identify solid adenocarcinoma ALK rearrangement status, which may act as a pragmatic and cost-efficient substitute for traditional invasive ALK status test.

A clinical-radiomics nomogram for the preoperative prediction of lymph node metastasis in colorectal cancer.

BACKGROUND: Accurate lymph node metastasis (LNM) prediction in colorectal cancer (CRC) patients is of great significance for treatment decision making and prognostic evaluation. We aimed to develop and validate a clinical-radiomics nomogram for the individual preoperative prediction of LNM in CRC patients. METHODS: We enrolled 766 patients (458 in the training set and 308 in the validation set) with clinicopathologically confirmed CRC. We included nine significant clinical risk factors (age, sex, preoperative carbohydrate antigen 19-9 (CA19-9) level, preoperative carcinoembryonic antigen (CEA) level, tumor size, tumor location, histotype, differentiation and M stage) to build the clinical model. We used analysis of variance (ANOVA), relief and recursive feature elimination (RFE) for feature selection (including clinical risk factors and the imaging features of primary lesions and peripheral lymph nodes), established classification models with logistic regression analysis and selected the respective candidate models by fivefold cross-validation. Then, we combined the clinical risk factors, primary lesion radiomics features and peripheral lymph node radiomics features of the candidate models to establish combined predictive models. Model performance was assessed by the area under the receiver operating characteristic (ROC) curve (AUC). Finally, decision curve analysis (DCA) and a nomogram were used to evaluate the clinical usefulness of the model. RESULTS: The clinical-primary lesion radiomics-peripheral lymph node radiomics model, with the highest AUC value (0.7606), was regarded as the candidate model and had good discrimination and calibration in both the training and validation sets. DCA demonstrated that the clinical-radiomics nomogram was useful for preoperative prediction in the clinical environment. CONCLUSION: The present study proposed a clinical-radiomics nomogram with a combination of clinical risk factors and radiomics features that can potentially be applied in the individualized preoperative prediction of LNM in CRC patients.