RESUMO
Background Multiparametric MRI can help identify clinically significant prostate cancer (csPCa) (Gleason score ≥7) but is limited by reader experience and interobserver variability. In contrast, deep learning (DL) produces deterministic outputs. Purpose To develop a DL model to predict the presence of csPCa by using patient-level labels without information about tumor location and to compare its performance with that of radiologists. Materials and Methods Data from patients without known csPCa who underwent MRI from January 2017 to December 2019 at one of multiple sites of a single academic institution were retrospectively reviewed. A convolutional neural network was trained to predict csPCa from T2-weighted images, diffusion-weighted images, apparent diffusion coefficient maps, and T1-weighted contrast-enhanced images. The reference standard was pathologic diagnosis. Radiologist performance was evaluated as follows: Radiology reports were used for the internal test set, and four radiologists' PI-RADS ratings were used for the external (ProstateX) test set. The performance was compared using areas under the receiver operating characteristic curves (AUCs) and the DeLong test. Gradient-weighted class activation maps (Grad-CAMs) were used to show tumor localization. Results Among 5735 examinations in 5215 patients (mean age, 66 years ± 8 [SD]; all male), 1514 examinations (1454 patients) showed csPCa. In the internal test set (400 examinations), the AUC was 0.89 and 0.89 for the DL classifier and radiologists, respectively (P = .88). In the external test set (204 examinations), the AUC was 0.86 and 0.84 for the DL classifier and radiologists, respectively (P = .68). DL classifier plus radiologists had an AUC of 0.89 (P < .001). Grad-CAMs demonstrated activation over the csPCa lesion in 35 of 38 and 56 of 58 true-positive examinations in internal and external test sets, respectively. Conclusion The performance of a DL model was not different from that of radiologists in the detection of csPCa at MRI, and Grad-CAMs localized the tumor. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Johnson and Chandarana in this issue.
Assuntos
Aprendizado Profundo , Imageamento por Ressonância Magnética , Neoplasias da Próstata , Masculino , Humanos , Neoplasias da Próstata/diagnóstico por imagem , Estudos Retrospectivos , Idoso , Pessoa de Meia-Idade , Imageamento por Ressonância Magnética/métodos , Interpretação de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética Multiparamétrica/métodos , Próstata/diagnóstico por imagem , Próstata/patologiaRESUMO
OBJECTIVES: To evaluate the impact of susceptibility artifacts from hip prosthesis on cancer detection rate (CDR) in prostate MRI. MATERIALS AND METHODS: This three-center retrospective study included prostate MRI studies for patients without known prostate cancer between 2017 and 2021. Exams with hip prosthesis were searched on MRI reports. The degree of susceptibility artifact on diffusion-weighted images was retrospectively categorized into mild, moderate, and severe (> 66%, 33-66%, and < 33% of the prostate volume are evaluable) by blind reviewers. CDR was defined as the number of exams with Gleason score ≥7 detected by MRI (PI-RADS ≥3) divided by the total number of exams. For each artifact grade, control exams without hip prosthesis were matched (1:6 match), and CDR was compared. The degree of CDR reduction was evaluated with ratio, and influential factors were evaluated by expanding the equation. RESULTS: Hip arthroplasty was present in 548 (4.8%) of the 11,319 MRI exams. CDR of the cases and matched control exams for each artifact grade were as follows: mild (n = 238), 0.27 vs 0.25, CDR ratio = 1.09 [95% CI: 0.87-1.37]; moderate (n = 143), 0.18 vs 0.27, CDR ratio = 0.67 [95% CI: 0.46-0.96]; severe (n = 167), 0.22 vs 0.28, CDR ratio = 0.80 [95% CI: 0.59-1.08]. When moderate and severe artifact grades were combined, CDR ratio was 0.74 [95% CI: 0.58-0.93]. CDR reduction was mostly attributed to the increased frequency of PI-RADS 1-2. CONCLUSION: With moderate to severe susceptibility artifacts from hip prosthesis, CDR was decreased to 74% compared to the matched control. CLINICAL RELEVANCE STATEMENT: Moderate to severe susceptibility artifacts from hip prosthesis may cause a non-negligible CDR reduction in prostate MRI. Expanding indications for systematic prostate biopsy may be considered when PI-RADS 1-2 was assigned. KEY POINTS: ⢠We proposed cancer detection rate as a diagnostic performance metric in prostate MRI. ⢠With moderate to severe susceptibility artifacts secondary to hip arthroplasty, cancer detection rate decreased to 74% compared to the matched control. ⢠Expanding indications for systematic prostate biopsy may be considered when PI-RADS 1-2 is assigned.
RESUMO
Since 2000, there have been more than 8000 publications on radiology artificial intelligence (AI). AI breakthroughs allow complex tasks to be automated and even performed beyond human capabilities. However, the lack of details on the methods and algorithm code undercuts its scientific value. Many science subfields have recently faced a reproducibility crisis, eroding trust in processes and results, and influencing the rise in retractions of scientific papers. For the same reasons, conducting research in deep learning (DL) also requires reproducibility. Although several valuable manuscript checklists for AI in medical imaging exist, they are not focused specifically on reproducibility. In this study, we conducted a systematic review of recently published papers in the field of DL to evaluate if the description of their methodology could allow the reproducibility of their findings. We focused on the Journal of Digital Imaging (JDI), a specialized journal that publishes papers on AI and medical imaging. We used the keyword "Deep Learning" and collected the articles published between January 2020 and January 2022. We screened all the articles and included the ones which reported the development of a DL tool in medical imaging. We extracted the reported details about the dataset, data handling steps, data splitting, model details, and performance metrics of each included article. We found 148 articles. Eighty were included after screening for articles that reported developing a DL model for medical image analysis. Five studies have made their code publicly available, and 35 studies have utilized publicly available datasets. We provided figures to show the ratio and absolute count of reported items from included studies. According to our cross-sectional study, in JDI publications on DL in medical imaging, authors infrequently report the key elements of their study to make it reproducible.
Assuntos
Inteligência Artificial , Diagnóstico por Imagem , Humanos , Estudos Transversais , Reprodutibilidade dos Testes , AlgoritmosRESUMO
PURPOSE: To develop a deep learning (DL) zonal segmentation model of prostate MR from T2-weighted images and evaluate TZ-PSAD for prediction of the presence of csPCa (Gleason score of 7 or higher) compared to PSAD. METHODS: 1020 patients with a prostate MRI were randomly selected to develop a DL zonal segmentation model. Test dataset included 20 cases in which 2 radiologists manually segmented both the peripheral zone (PZ) and TZ. Pair-wise Dice index was calculated for each zone. For the prediction of csPCa using PSAD and TZ-PSAD, we used 3461 consecutive MRI exams performed in patients without a history of prostate cancer, with pathological confirmation and available PSA values, but not used in the development of the segmentation model as internal test set and 1460 MRI exams from PI-CAI challenge as external test set. PSAD and TZ-PSAD were calculated from the segmentation model output. The area under the receiver operating curve (AUC) was compared between PSAD and TZ-PSAD using univariate and multivariate analysis (adjusts age) with the DeLong test. RESULTS: Dice scores of the model against two radiologists were 0.87/0.87 and 0.74/0.72 for TZ and PZ, while those between the two radiologists were 0.88 for TZ and 0.75 for PZ. For the prediction of csPCa, the AUCs of TZPSAD were significantly higher than those of PSAD in both internal test set (univariate analysis, 0.75 vs. 0.73, p < 0.001; multivariate analysis, 0.80 vs. 0.78, p < 0.001) and external test set (univariate analysis, 0.76 vs. 0.74, p < 0.001; multivariate analysis, 0.77 vs. 0.75, p < 0.001 in external test set). CONCLUSION: DL model-derived zonal segmentation facilitates the practical measurement of TZ-PSAD and shows it to be a slightly better predictor of csPCa compared to the conventional PSAD. Use of TZ-PSAD may increase the sensitivity of detecting csPCa by 2-5% for a commonly used specificity level.
RESUMO
Oropharyngeal Squamous Cell Carcinoma (OPSCC) is one of the common forms of heterogeneity in head and neck cancer. Infection with human papillomavirus (HPV) has been identified as a major risk factor for OPSCC. Therefore, differentiating the HPV-positive and negative cases in OPSCC patients is an essential diagnostic factor influencing future treatment decisions. In this study, we investigated the accuracy of a deep learning-based method for image interpretation and automatically detected the HPV status of OPSCC in routinely acquired Computed Tomography (CT) and Positron Emission Tomography (PET) images. We introduce a 3D CNN-based multi-modal feature fusion architecture for HPV status prediction in primary tumor lesions. The architecture is composed of an ensemble of CNN networks and merges image features in a softmax classification layer. The pipeline separately learns the intensity, contrast variation, shape, texture heterogeneity, and metabolic assessment from CT and PET tumor volume regions and fuses those multi-modal features for final HPV status classification. The precision, recall, and AUC scores of the proposed method are computed, and the results are compared with other existing models. The experimental results demonstrate that the multi-modal ensemble model with soft voting outperformed single-modality PET/CT, with an AUC of 0.76 and F1 score of 0.746 on publicly available TCGA and MAASTRO datasets. In the MAASTRO dataset, our model achieved an AUC score of 0.74 over primary tumor volumes of interest (VOIs). In the future, more extensive cohort validation may suffice for better diagnostic accuracy and provide preliminary assessment before the biopsy.
RESUMO
The increasing use of machine learning (ML) algorithms in clinical settings raises concerns about bias in ML models. Bias can arise at any step of ML creation, including data handling, model development, and performance evaluation. Potential biases in the ML model can be minimized by implementing these steps correctly. This report focuses on performance evaluation and discusses model fitness, as well as a set of performance evaluation toolboxes: namely, performance metrics, performance interpretation maps, and uncertainty quantification. By discussing the strengths and limitations of each toolbox, our report highlights strategies and considerations to mitigate and detect biases during performance evaluations of radiology artificial intelligence models. Keywords: Segmentation, Diagnosis, Convolutional Neural Network (CNN) © RSNA, 2022.