Radiology-Artificial Intelligence最新文献

Radiomics is a promising and fast-developing field within oncology that involves the mining of quantitative high-dimensional data from medical images. Radiomics has the potential to transform cancer management, whereby radiomics data can be used to aid early tumor characterization, prognosis, risk stratification, treatment planning, treatment response assessment, and surveillance. Nevertheless, certain challenges have delayed the clinical adoption and acceptability of radiomics in routine clinical practice. The objectives of this report are to (a) provide a perspective on the translational potential and potential impact of radiomics in oncology; (b) explore frequent challenges and mistakes in its derivation, encompassing study design, technical requirements, standardization, model reproducibility, transparency, data sharing, privacy concerns, quality control, as well as the complexity of multistep processes resulting in less radiologist-friendly interfaces; (c) discuss strategies to overcome these challenges and mistakes; and (d) propose measures to increase the clinical use and acceptability of radiomics, taking into account the different perspectives of patients, health care workers, and health care systems. Keywords: Radiomics, Oncology, Cancer Management, Artificial Intelligence © RSNA, 2024.

Supplemental material is available for this article.

Purpose To investigate the issues of generalizability and replication of deep learning models by assessing performance of a screening mammography deep learning system developed at New York University (NYU) on a local Australian dataset. Materials and Methods In this retrospective study, all individuals with biopsy or surgical pathology-proven lesions and age-matched controls were identified from a South Australian public mammography screening program (January 2010 to December 2016). The primary outcome was deep learning system performance-measured with area under the receiver operating characteristic curve (AUC)-in classifying invasive breast cancer or ductal carcinoma in situ (n = 425) versus no malignancy (n = 490) or benign lesions (n = 44). The NYU system, including models without (NYU1) and with (NYU2) heatmaps, was tested in its original form, after training from scratch (without transfer learning), and after retraining with transfer learning. Results The local test set comprised 959 individuals (mean age, 62.5 years ± 8.5 [SD]; all female). The original AUCs for the NYU1 and NYU2 models were 0.83 (95% CI: 0.82, 0.84) and 0.89 (95% CI: 0.88, 0.89), respectively. When NYU1 and NYU2 were applied in their original form to the local test set, the AUCs were 0.76 (95% CI: 0.73, 0.79) and 0.84 (95% CI: 0.82, 0.87), respectively. After local training without transfer learning, the AUCs were 0.66 (95% CI: 0.62, 0.69) and 0.86 (95% CI: 0.84, 0.88). After retraining with transfer learning, the AUCs were 0.82 (95% CI: 0.80, 0.85) and 0.86 (95% CI: 0.84, 0.88). Conclusion A deep learning system developed using a U.S. dataset showed reduced performance when applied "out of the box" to an Australian dataset. Local retraining with transfer learning using available model weights improved model performance. Keywords: Screening Mammography, Convolutional Neural Network (CNN), Deep Learning Algorithms, Breast Cancer Supplemental material is available for this article. © RSNA, 2024 See also commentary by Cadrin-Chênevert in this issue.

Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001 through December 2015) from a national brain tumor consortium (n = 184; median age, 7 years [range, 1-23 years]; 94 male patients) and a pediatric cancer center (n = 100; median age, 8 years [range, 1-19 years]; 47 male patients) to develop and evaluate deep learning neural networks for pediatric low-grade glioma segmentation using a stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally tested on an independent test set and subjected to randomized blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert- and artificial intelligence (AI)-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model used in-domain stepwise transfer learning (median Dice score coefficient, 0.88 [IQR, 0.72-0.91] vs 0.812 [IQR, 0.56-0.89] for baseline model; P = .049). With external testing, the AI model yielded excellent accuracy using reference standards from three clinical experts (median Dice similarity coefficients: expert 1, 0.83 [IQR, 0.75-0.90]; expert 2, 0.81 [IQR, 0.70-0.89]; expert 3, 0.81 [IQR, 0.68-0.88]; mean accuracy, 0.82). For clinical benchmarking (n = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score, 9 [IQR, 7-9] vs 7 [IQR 7-9]) and rated more AI segmentations as clinically acceptable (80.2% vs 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion Stepwise transfer learning enabled expert-level automated pediatric brain tumor autosegmentation and volumetric measurement with a high level of clinical acceptability. Keywords: Stepwise Transfer Learning, Pediatric Brain Tumors, MRI Segmentation, Deep Learning Supplemental material is available for this article. © RSNA, 2024.

Purpose To evaluate the reproducibility of radiomics features extracted from T2-weighted MR images in patients with neuroblastoma. Materials and Methods A retrospective study included 419 patients (mean age, 29 months ± 34 [SD]; 220 male, 199 female) with neuroblastic tumors diagnosed between 2002 and 2023, within the scope of the PRedictive In-silico Multiscale Analytics to support cancer personalized diaGnosis and prognosis, Empowered by imaging biomarkers (ie, PRIMAGE) project, involving 746 T2/T2*-weighted MRI sequences at diagnosis and/or after initial chemotherapy. Images underwent processing steps (denoising, inhomogeneity bias field correction, normalization, and resampling). Tumors were automatically segmented, and 107 shape, first-order, and second-order radiomics features were extracted, considered as the reference standard. Subsequently, the previous image processing settings were modified, and volumetric masks were applied. New radiomics features were extracted and compared with the reference standard. Reproducibility was assessed using the concordance correlation coefficient (CCC); intrasubject repeatability was measured using the coefficient of variation (CoV). Results When normalization was omitted, only 5% of the radiomics features demonstrated high reproducibility. Statistical analysis revealed significant changes in the normalization and resampling processes (P < .001). Inhomogeneities removal had the least impact on radiomics (83% of parameters remained stable). Shape features remained stable after mask modifications, with a CCC greater than 0.90. Mask modifications were the most favorable changes for achieving high CCC values, with a radiomics features stability of 70%. Only 7% of second-order radiomics features showed an excellent CoV of less than 0.10. Conclusion Modifications in the T2-weighted MRI preparation process in patients with neuroblastoma resulted in changes in radiomics features, with normalization identified as the most influential factor for reproducibility. Inhomogeneities removal had the least impact on radiomics features. Keywords: Pediatrics, MR Imaging, Oncology, Radiomics, Reproducibility, Repeatability, Neuroblastic Tumors Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Safdar and Galaria in this issue.

Purpose To investigate the accuracy and robustness of prostate segmentation using deep learning across various training data sizes, MRI vendors, prostate zones, and testing methods relative to fellowship-trained diagnostic radiologists. Materials and Methods In this systematic review, Embase, PubMed, Scopus, and Web of Science databases were queried for English-language articles using keywords and related terms for prostate MRI segmentation and deep learning algorithms dated to July 31, 2022. A total of 691 articles from the search query were collected and subsequently filtered to 48 on the basis of predefined inclusion and exclusion criteria. Multiple characteristics were extracted from selected studies, such as deep learning algorithm performance, MRI vendor, and training dataset features. The primary outcome was comparison of mean Dice similarity coefficient (DSC) for prostate segmentation for deep learning algorithms versus diagnostic radiologists. Results Forty-eight studies were included. Most published deep learning algorithms for whole prostate gland segmentation (39 of 42 [93%]) had a DSC at or above expert level (DSC ≥ 0.86). The mean DSC was 0.79 ± 0.06 (SD) for peripheral zone, 0.87 ± 0.05 for transition zone, and 0.90 ± 0.04 for whole prostate gland segmentation. For selected studies that used one major MRI vendor, the mean DSCs of each were as follows: General Electric (three of 48 studies), 0.92 ± 0.03; Philips (four of 48 studies), 0.92 ± 0.02; and Siemens (six of 48 studies), 0.91 ± 0.03. Conclusion Deep learning algorithms for prostate MRI segmentation demonstrated accuracy similar to that of expert radiologists despite varying parameters; therefore, future research should shift toward evaluating segmentation robustness and patient outcomes across diverse clinical settings. Keywords: MRI, Genital/Reproductive, Prostate Segmentation, Deep Learning Systematic review registration link: osf.io/nxaev © RSNA, 2024.

Purpose To explore the potential benefits of deep learning-based artifact reduction in sparse-view cranial CT scans and its impact on automated hemorrhage detection. Materials and Methods In this retrospective study, a U-Net was trained for artifact reduction on simulated sparse-view cranial CT scans in 3000 patients, obtained from a public dataset and reconstructed with varying sparse-view levels. Additionally, EfficientNet-B2 was trained on full-view CT data from 17 545 patients for automated hemorrhage detection. Detection performance was evaluated using the area under the receiver operating characteristic curve (AUC), with differences assessed using the DeLong test, along with confusion matrices. A total variation (TV) postprocessing approach, commonly applied to sparse-view CT, served as the basis for comparison. A Bonferroni-corrected significance level of .001/6 = .00017 was used to accommodate for multiple hypotheses testing. Results Images with U-Net postprocessing were better than unprocessed and TV-processed images with respect to image quality and automated hemorrhage detection. With U-Net postprocessing, the number of views could be reduced from 4096 (AUC: 0.97 [95% CI: 0.97, 0.98]) to 512 (0.97 [95% CI: 0.97, 0.98], P < .00017) and to 256 views (0.97 [95% CI: 0.96, 0.97], P < .00017) with a minimal decrease in hemorrhage detection performance. This was accompanied by mean structural similarity index measure increases of 0.0210 (95% CI: 0.0210, 0.0211) and 0.0560 (95% CI: 0.0559, 0.0560) relative to unprocessed images. Conclusion U-Net-based artifact reduction substantially enhanced automated hemorrhage detection in sparse-view cranial CT scans. Keywords: CT, Head/Neck, Hemorrhage, Diagnosis, Supervised Learning Supplemental material is available for this article. © RSNA, 2024.