Comparative analysis of four nutritional scores in predicting adverse outcomes in biopsy-confirmed diabetic kidney Disease.

Malnutrition is associated with adverse outcomes in patients with diabetic kidney disease (DKD). However, it is uncertain which nutritional assessment tools are most effective in predicting the adverse outcomes of DKD. This retrospective study was conducted at a single center and included 367 patients diagnosed with DKD based on biopsy results between August 2009 and December 2018. Four nutritional assessment indices, namely the Prognostic Nutritional Index (PNI), Geriatric Nutritional Risk Index (GNRI), Triglycerides (TG) × Total Cholesterol (TC) × Body Weight (BW) Index (TCBI), and Controlling Nutritional Status (CONUT) score, were selected and calculated. We aimed to assess the association between these nutritional scores and adverse outcomes, including progression to end-stage kidney disease (ESKD), cardiovascular diseases events (CVD), and all-cause mortality. Univariate and multivariate Cox regression analyses, Kaplan-Meier analysis, along with Restricted cubic spline analysis were used to examine the relationship between nutritional scores and adverse outcomes. Furthermore, the area under the curve (AUC) was calculated using time-dependent receiver operating characteristics to determine the predictive value of the four nutritional scores alone and some combinations. Lastly, ordered logistic regression analysis was conducted to explore the correlation between the four nutritional scores and different renal histologic changes. The incidence of ESKD, CVD, and all-cause mortality was significantly higher in patients with DKD who had a lower PNI, lower GNRI, and higher CONUT score. Additionally, The TCBI performed the worst in terms of grading and risk assessment. The PNI offer the highest predictive value for adverse outcomes and a stronger correlation with renal histologic changes compared to other nutritional scores. Patients diagnosed with DKD who have a worse nutritional status are more likely to experience higher rates of adverse outcomes. The PNI might offer more valuable predictive values and a stronger correlation with different renal histologic changes compared to other nutritional scores.

Computerized assessment of background parenchymal enhancement on breast dynamic contrast-enhanced-MRI including electronic lesion removal.

Purpose: Current clinical assessment qualitatively describes background parenchymal enhancement (BPE) as minimal, mild, moderate, or marked based on the visually perceived volume and intensity of enhancement in normal fibroglandular breast tissue in dynamic contrast-enhanced (DCE)-MRI. Tumor enhancement may be included within the visual assessment of BPE, thus inflating BPE estimation due to angiogenesis within the tumor. Using a dataset of 426 MRIs, we developed an automated method to segment breasts, electronically remove lesions, and calculate scores to estimate BPE levels. Approach: A U-Net was trained for breast segmentation from DCE-MRI maximum intensity projection (MIP) images. Fuzzy c-means clustering was used to segment lesions; the lesion volume was removed prior to creating projections. U-Net outputs were applied to create projection images of both, affected, and unaffected breasts before and after lesion removal. BPE scores were calculated from various projection images, including MIPs or average intensity projections of first- or second postcontrast subtraction MRIs, to evaluate the effect of varying image parameters on automatic BPE assessment. Receiver operating characteristic analysis was performed to determine the predictive value of computed scores in BPE level classification tasks relative to radiologist ratings. Results: Statistically significant trends were found between radiologist BPE ratings and calculated BPE scores for all breast regions (Kendall correlation, p<0.001). Scores from all breast regions performed significantly better than guessing (p<0.025 from the z-test). Results failed to show a statistically significant difference in performance with and without lesion removal. BPE scores of the affected breast in the second postcontrast subtraction MIP after lesion removal performed statistically greater than random guessing across various viewing projections and DCE time points. Conclusions: Results demonstrate the potential for automatic BPE scoring to serve as a quantitative value for objective BPE level classification from breast DCE-MR without the influence of lesion enhancement.

Development and validation of a deep learning-based microsatellite instability predictor from prostate cancer whole-slide images.

Microsatellite instability-high (MSI-H) is a tumor-agnostic biomarker for immune checkpoint inhibitor therapy. However, MSI status is not routinely tested in prostate cancer, in part due to low prevalence and assay cost. As such, prediction of MSI status from hematoxylin and eosin (H&E) stained whole-slide images (WSIs) could identify prostate cancer patients most likely to benefit from confirmatory testing to evaluate their eligibility for immunotherapy and need for Lynch syndrome testing. Prostate biopsies and surgical resections from prostate cancer patients referred to our institution were analyzed. MSI status was determined by next-generation sequencing. Patients sequenced before a cutoff date formed an algorithm development set (n = 4015, MSI-H 1.8%) and a paired validation set (n = 173, MSI-H 19.7%) that consisted of two serial sections from each sample, one stained and scanned internally and the other at an external site. Patients sequenced after the cutoff date formed a temporally independent validation set (n = 1350, MSI-H 2.3%). Attention-based multiple instance learning models were trained to predict MSI-H from H&E WSIs. The predictor achieved area under the receiver operating characteristic curve values of 0.78 (95% CI [0.69-0.86]), 0.72 (95% CI [0.63-0.81]), and 0.72 (95% CI [0.62-0.82]) on the internally prepared, externally prepared, and temporal validation sets, respectively, showing effective predictability and generalization to both external staining/scanning processes and temporally independent samples. While MSI-H status is significantly correlated with Gleason score, the model remained predictive within each Gleason score subgroup.

Predicting intensive care need for COVID-19 patients using deep learning on chest radiography.

Purpose: Image-based prediction of coronavirus disease 2019 (COVID-19) severity and resource needs can be an important means to address the COVID-19 pandemic. In this study, we propose an artificial intelligence/machine learning (AI/ML) COVID-19 prognosis method to predict patients' needs for intensive care by analyzing chest X-ray radiography (CXR) images using deep learning. Approach: The dataset consisted of 8357 CXR exams from 5046 COVID-19-positive patients as confirmed by reverse transcription polymerase chain reaction (RT-PCR) tests for the SARS-CoV-2 virus with a training/validation/test split of 64%/16%/20% on a by patient level. Our model involved a DenseNet121 network with a sequential transfer learning technique employed to train on a sequence of gradually more specific and complex tasks: (1) fine-tuning a model pretrained on ImageNet using a previously established CXR dataset with a broad spectrum of pathologies; (2) refining on another established dataset to detect pneumonia; and (3) fine-tuning using our in-house training/validation datasets to predict patients' needs for intensive care within 24, 48, 72, and 96 h following the CXR exams. The classification performances were evaluated on our independent test set (CXR exams of 1048 patients) using the area under the receiver operating characteristic curve (AUC) as the figure of merit in the task of distinguishing between those COVID-19-positive patients who required intensive care following the imaging exam and those who did not. Results: Our proposed AI/ML model achieved an AUC (95% confidence interval) of 0.78 (0.74, 0.81) when predicting the need for intensive care 24 h in advance, and at least 0.76 (0.73, 0.80) for 48 h or more in advance using predictions based on the AI prognostic marker derived from CXR images. Conclusions: This AI/ML prediction model for patients' needs for intensive care has the potential to support both clinical decision-making and resource management.

U-Net breast lesion segmentations for breast dynamic contrast-enhanced magnetic resonance imaging.

Purpose: Given the dependence of radiomic-based computer-aided diagnosis artificial intelligence on accurate lesion segmentation, we assessed the performances of 2D and 3D U-Nets in breast lesion segmentation on dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) relative to fuzzy c-means (FCM) and radiologist segmentations. Approach: Using 994 unique breast lesions imaged with DCE-MRI, three segmentation algorithms (FCM clustering, 2D and 3D U-Net convolutional neural networks) were investigated. Center slice segmentations produced by FCM, 2D U-Net, and 3D U-Net were evaluated using radiologist segmentations as truth, and volumetric segmentations produced by 2D U-Net slices and 3D U-Net were compared using FCM as a surrogate reference standard. Fivefold cross-validation by lesion was conducted on the U-Nets; Dice similarity coefficient (DSC) and Hausdorff distance (HD) served as performance metrics. Segmentation performances were compared across different input image and lesion types. Results: 2D U-Net outperformed 3D U-Net for center slice (DSC, HD p<0.001) and volume segmentations (DSC, HD p<0.001). 2D U-Net outperformed FCM in center slice segmentation (DSC p<0.001). The use of second postcontrast subtraction images showed greater performance than first postcontrast subtraction images using the 2D and 3D U-Net (DSC p<0.05). Additionally, mass segmentation outperformed nonmass segmentation from first and second postcontrast subtraction images using 2D and 3D U-Nets (DSC, HD p<0.001). Conclusions: Results suggest that 2D U-Net is promising in segmenting mass and nonmass enhancing breast lesions from first and second postcontrast subtraction MRIs and thus could be an effective alternative to FCM or 3D U-Net.

Advanced polymer hydrogels that promote diabetic ulcer healing: mechanisms, classifications, and medical applications.

Diabetic ulcers (DUs) are one of the most serious complications of diabetes mellitus. The application of a functional dressing is a crucial step in DU treatment and is associated with the patient's recovery and prognosis. However, traditional dressings with a simple structure and a single function cannot meet clinical requirements. Therefore, researchers have turned their attention to advanced polymer dressings and hydrogels to solve the therapeutic bottleneck of DU treatment. Hydrogels are a class of gels with a three-dimensional network structure that have good moisturizing properties and permeability and promote autolytic debridement and material exchange. Moreover, hydrogels mimic the natural environment of the extracellular matrix, providing suitable surroundings for cell proliferation. Thus, hydrogels with different mechanical strengths and biological properties have been extensively explored as DU dressing platforms. In this review, we define different types of hydrogels and elaborate the mechanisms by which they repair DUs. Moreover, we summarize the pathological process of DUs and review various additives used for their treatment. Finally, we examine the limitations and obstacles that exist in the development of the clinically relevant applications of these appealing technologies. This review defines different types of hydrogels and carefully elaborate the mechanisms by which they repair diabetic ulcers (DUs), summarizes the pathological process of DUs, and reviews various bioactivators used for their treatment.

Causal effect of beta-blockers on the risk of lung cancer: a Mendelian randomization study.

Background: It remains uncertain whether there is a causal association of the use of beta-blockers (BBs) on lung cancer risk. We used a two-sample Mendelian randomization (MR) approach to identify the causal association of BBs and lung cancer risk. Methods: Twenty-two BB-related single-nucleotide polymorphisms (SNPs) were obtained from the UK Biobank as the instrumental variables (IVs). Genetic summary data information of lung cancer was extracted from the International Lung Cancer Consortium, with a total of 11,348 cases and 15,861 controls. We adopted the inverse-variance weighted (IVW) approach to conduct the MR analyses. Egger-intercept analysis was further performed as sensitivity analysis for pleiotropy evaluation. Additionally, we investigated whether BBs could causally affect the risk of lung cancer through their pharmacological effects. Results: The current IVW analysis suggested a decreased lung cancer risk in BB users [odds ratio (OR) =0.83; 95% confidence interval (CI): 0.73-0.95; P<0.01]. Results of Egger-intercept analysis demonstrated that no pleiotropy was found (P=0.94), which suggested the robustness of the causality. However, there was little evidence that pharmacological effects mediate the association between BBs and lung cancer. Conclusions: The current analysis suggested that BBs could decrease the risk of lung cancer but may be not via its pharmacological effects. Further research is in need for elucidating the underlying mechanisms.

A review of explainable and interpretable AI with applications in COVID-19 imaging.

The development of medical imaging artificial intelligence (AI) systems for evaluating COVID-19 patients has demonstrated potential for improving clinical decision making and assessing patient outcomes during the recent COVID-19 pandemic. These have been applied to many medical imaging tasks, including disease diagnosis and patient prognosis, as well as augmented other clinical measurements to better inform treatment decisions. Because these systems are used in life-or-death decisions, clinical implementation relies on user trust in the AI output. This has caused many developers to utilize explainability techniques in an attempt to help a user understand when an AI algorithm is likely to succeed as well as which cases may be problematic for automatic assessment, thus increasing the potential for rapid clinical translation. AI application to COVID-19 has been marred with controversy recently. This review discusses several aspects of explainable and interpretable AI as it pertains to the evaluation of COVID-19 disease and it can restore trust in AI application to this disease. This includes the identification of common tasks that are relevant to explainable medical imaging AI, an overview of several modern approaches for producing explainable output as appropriate for a given imaging scenario, a discussion of how to evaluate explainable AI, and recommendations for best practices in explainable/interpretable AI implementation. This review will allow developers of AI systems for COVID-19 to quickly understand the basics of several explainable AI techniques and assist in the selection of an approach that is both appropriate and effective for a given scenario.

Cancer risks in rheumatoid arthritis patients who received immunosuppressive therapies: Will immunosuppressants work?

Background: Exploring the cancer risks of rheumatoid arthritis (RA) patients with disease-modifying anti-rheumatic drugs (DMARDs) can help detect, evaluate, and treat malignancies at an early stage for these patients. Thus, a comprehensive analysis was conducted to determine the cancer risk of RA patients using different types of DMARDs and analyze their relationship with tumor mutational burdens (TMBs) reflecting immunogenicity. Methods: A thorough search of PubMed, EMBASE, Web of Science, and Medline was conducted up to 20 August 2022. Standardized incidence ratios (SIRs) were constructed with a random-effect model to determine risks for different types of malignancies in comparison with the general population. We also analyzed the correlation between SIRs and TMBs using linear regression (LR). Results: From a total of 22 studies, data on 371,311 RA patients receiving different types of DMARDs, 36 kinds of malignancies, and four regions were available. Overall cancer risks were 1.15 (SIR 1.15; 1.09-1.22; p < 0.001) and 0.91 (SIR 0.91; 0.72-1.14; p = 0.402) in RA populations using conventional synthetic DMARDs (csDMARDs) and biologic DMARDs (bDMARDs), respectively. RA patients taking csDMARDs displayed a 1.77-fold lung cancer risk (SIR 1.77; 1.50-2.09; p < 0.001), a 2.15-fold lymphoma risk (SIR 2.15; 1.78-2.59; p < 0.001), and a 1.72-fold melanoma risk (SIR 1.72; 1.26-2.36; p = 0.001). Correlation coefficients between TMBs and SIRs were 0.22 and 0.29 from those taking csDMARDs and bDMARDs, respectively. Conclusion: We demonstrated a cancer risk spectrum of RA populations using DMARDs. Additionally, TMBs were not associated with elevated cancer risks in RA patients following immunosuppressive therapy, which confirmed that iatrogenic immunosuppression might not increase cancer risks in patients with RA. Interpretation: Changes were similar in cancer risk after different immunosuppressive treatments, and there was a lack of correlation between SIRs and TMBs. These suggest that we should look for causes of increased risks from the RA disease itself, rather than using different types of DMARDs.

Evaluation of Clinical and Safety Outcomes of Neoadjuvant Immunotherapy Combined With Chemotherapy for Patients With Resectable Esophageal Cancer: A Systematic Review and Meta-analysis.

Importance: A considerable number of clinical trials of neoadjuvant immunotherapy for patients with resectable esophageal cancer are emerging. However, systematic evaluations of these studies are lacking. Objective: To provide state-of-the-art evidence and normative theoretical support for neoadjuvant immunotherapy for locally advanced resectable esophageal cancer. Data Sources: PubMed, Embase, Cochrane Library, and ClinicalTrials.gov databases were searched for relevant original articles and conference proceedings that were published in English through April 1, 2022. Study Selection: Published phase 2 or 3 clinical trials that included patients with resectable stage I to IV esophageal cancer who received immune checkpoint inhibitors (ICIs) before surgery as monotherapy or in combination with other therapies. Data Extraction and Synthesis: The Preferred Reporting Items for Systematic Reviews and Meta-analyses and the Meta-analysis of Observational Studies in Epidemiology guidelines for meta-analysis were followed to extract data. A random-effects model was adopted if the heterogeneity was significant (I2 statistic >50%); otherwise, the common-effects model was used. Data analyses were conducted from April 2 to 8, 2022. Main Outcomes and Measures: Pathological complete response (pCR) rate and major pathological response (MPR) rate were considered to be the primary outcomes calculated for the clinical outcomes of neoadjuvant immunotherapy. Incidence of treatment-related severe adverse events was set as the major measure for the safety outcome. The rate of R0 surgical resection was summarized. Subgroup analyses were conducted according to histologic subtype and ICI types. Results: A total of 27 clinical trials with 815 patients were included. Pooled rates were 31.4% (95% CI, 27.6%-35.3%) for pCR and 48.9% (95% CI, 42.0-55.9%) for MCR in patients with esophageal cancer. In terms of safety, the pooled incidence of treatment-related severe adverse events was 26.9% (95% CI, 16.7%-38.3%). Most patients achieved R0 surgical resection (98.6%; 95% CI, 97.1%-99.6%). Regarding histologic subtypes, the pooled pCR rates were 32.4% (95% CI, 28.2%-36.8%) in esophageal squamous cell carcinoma and 25.2% (95% CI, 16.3%-35.1%) in esophageal adenocarcinoma. The pooled MPR rate was 49.4% (95% CI, 42.1%-56.7%) in esophageal squamous cell carcinoma. Conclusions and Relevance: This study found that neoadjuvant immunotherapy with chemotherapy had promising clinical and safety outcomes for patients with resectable esophageal cancer. Randomized clinical trials with long-term follow-up are warranted to validate the findings and benefits of ICIs.

Clinical Artificial Intelligence Applications: Breast Imaging.

This article gives a brief overview of the development of artificial intelligence in clinical breast imaging. For multiple decades, artificial intelligence (AI) methods have been developed and translated for breast imaging tasks such as detection, diagnosis, and assessing response to therapy. As imaging modalities arise to support breast cancer screening programs and diagnostic examinations, including full-field digital mammography, breast tomosynthesis, ultrasound, and MRI, AI techniques parallel the efforts with more complex algorithms, faster computers, and larger data sets. AI methods include human-engineered radiomics algorithms and deep learning methods. Examples of these AI-supported clinical tasks are given along with commentary on the future.

Role of standard and soft tissue chest radiography images in deep-learning-based early diagnosis of COVID-19.

Purpose: We propose a deep learning method for the automatic diagnosis of COVID-19 at patient presentation on chest radiography (CXR) images and investigates the role of standard and soft tissue CXR in this task. Approach: The dataset consisted of the first CXR exams of 9860 patients acquired within 2 days after their initial reverse transcription polymerase chain reaction tests for the SARS-CoV-2 virus, 1523 (15.5%) of whom tested positive and 8337 (84.5%) of whom tested negative for COVID-19. A sequential transfer learning strategy was employed to fine-tune a convolutional neural network in phases on increasingly specific and complex tasks. The COVID-19 positive/negative classification was performed on standard images, soft tissue images, and both combined via feature fusion. A U-Net variant was used to segment and crop the lung region from each image prior to performing classification. Classification performances were evaluated and compared on a held-out test set of 1972 patients using the area under the receiver operating characteristic curve (AUC) and the DeLong test. Results: Using full standard, cropped standard, cropped, soft tissue, and both types of cropped CXR yielded AUC values of 0.74 [0.70, 0.77], 0.76 [0.73, 0.79], 0.73 [0.70, 0.76], and 0.78 [0.74, 0.81], respectively. Using soft tissue images significantly underperformed standard images, and using both types of CXR failed to significantly outperform using standard images alone. Conclusions: The proposed method was able to automatically diagnose COVID-19 at patient presentation with promising performance, and the inclusion of soft tissue images did not result in a significant performance improvement.

Improved Classification of Benign and Malignant Breast Lesions Using Deep Feature Maximum Intensity Projection MRI in Breast Cancer Diagnosis Using Dynamic Contrast-enhanced MRI.

PURPOSE: To develop a deep transfer learning method that incorporates four-dimensional (4D) information in dynamic contrast-enhanced (DCE) MRI to classify benign and malignant breast lesions. MATERIALS AND METHODS: The retrospective dataset is composed of 1990 distinct lesions (1494 malignant and 496 benign) from 1979 women (mean age, 47 years ± 10). Lesions were split into a training and validation set of 1455 lesions (acquired in 2015-2016) and an independent test set of 535 lesions (acquired in 2017). Features were extracted from a convolutional neural network (CNN), and lesions were classified as benign or malignant using support vector machines. Volumetric information was collapsed into two dimensions by taking the maximum intensity projection (MIP) at the image level or feature level within the CNN architecture. Performances were evaluated using the area under the receiver operating characteristic curve (AUC) as the figure of merit and were compared using the DeLong test. RESULTS: The image MIP and feature MIP methods yielded AUCs of 0.91 (95% CI: 0.87, 0.94) and 0.93 (95% CI: 0.91, 0.96), respectively, for the independent test set. The feature MIP method achieved higher performance than the image MIP method (∆AUC 95% CI: 0.003, 0.051; P = .03). CONCLUSION: Incorporating 4D information in DCE MRI by MIP of features in deep transfer learning demonstrated superior classification performance compared with using MIP images as input in the task of distinguishing between benign and malignant breast lesions.Keywords: Breast, Computer Aided Diagnosis (CAD), Convolutional Neural Network (CNN), MR-Dynamic Contrast Enhanced, Supervised learning, Support vector machines (SVM), Transfer learning, Volume Analysis © RSNA, 2021.

Lessons learned in transitioning to AI in the medical imaging of COVID-19.

The coronavirus disease 2019 (COVID-19) pandemic has wreaked havoc across the world. It also created a need for the urgent development of efficacious predictive diagnostics, specifically, artificial intelligence (AI) methods applied to medical imaging. This has led to the convergence of experts from multiple disciplines to solve this global pandemic including clinicians, medical physicists, imaging scientists, computer scientists, and informatics experts to bring to bear the best of these fields for solving the challenges of the COVID-19 pandemic. However, such a convergence over a very brief period of time has had unintended consequences and created its own challenges. As part of Medical Imaging Data and Resource Center initiative, we discuss the lessons learned from career transitions across the three involved disciplines (radiology, medical imaging physics, and computer science) and draw recommendations based on these experiences by analyzing the challenges associated with each of the three associated transition types: (1) AI of non-imaging data to AI of medical imaging data, (2) medical imaging clinician to AI of medical imaging, and (3) AI of medical imaging to AI of COVID-19 imaging. The lessons learned from these career transitions and the diffusion of knowledge among them could be accomplished more effectively by recognizing their associated intricacies. These lessons learned in the transitioning to AI in the medical imaging of COVID-19 can inform and enhance future AI applications, making the whole of the transitions more than the sum of each discipline, for confronting an emergency like the COVID-19 pandemic or solving emerging problems in biomedicine.

Radiomics methodology for breast cancer diagnosis using multiparametric magnetic resonance imaging.

Purpose: This study aims to develop and compare human-engineered radiomics methodologies that use multiparametric magnetic resonance imaging (mpMRI) to diagnose breast cancer. Approach: The dataset comprises clinical multiparametric MR images of 852 unique lesions from 612 patients. Each MR study included a dynamic contrast-enhanced (DCE)-MRI sequence and a T2-weighted (T2w) MRI sequence, and a subset of 389 lesions were also imaged with a diffusion-weighted imaging (DWI) sequence. Lesions were automatically segmented using the fuzzy C-means algorithm. Radiomic features were extracted from each MRI sequence. Two approaches, feature fusion and classifier fusion, to utilizing multiparametric information were investigated. A support vector machine classifier was trained for each method to differentiate between benign and malignant lesions. Area under the receiver operating characteristic curve (AUC) was used to evaluate and compare diagnostic performance. Analyses were first performed on the entire dataset and then on the subset that was imaged using the three-sequence protocol. Results: When using the full dataset, the single-parametric classifiers yielded the following AUCs and 95% confidence intervals: AUC DCE = 0.84 [0.82, 0.87], AUC T 2 w = 0.83 [0.80, 0.86], and AUC DWI = 0.69 [0.62, 0.75]. The two multiparametric classifiers both yielded AUCs of 0.87 [0.84, 0.89] and significantly outperformed all single-parametric methods classifiers. When using the three-sequence subset, the mpMRI classifiers' performances significantly decreased. Conclusions: The proposed mpMRI radiomics methods can improve the performance of computer-aided diagnostics for breast cancer and handle missing sequences in the imaging protocol.

A deep learning methodology for improved breast cancer diagnosis using multiparametric MRI.

Multiparametric magnetic resonance imaging (mpMRI) has been shown to improve radiologists' performance in the clinical diagnosis of breast cancer. This machine learning study develops a deep transfer learning computer-aided diagnosis (CADx) methodology to diagnose breast cancer using mpMRI. The retrospective study included clinical MR images of 927 unique lesions from 616 women. Each MR study included a dynamic contrast-enhanced (DCE)-MRI sequence and a T2-weighted (T2w) MRI sequence. A pretrained convolutional neural network (CNN) was used to extract features from the DCE and T2w sequences, and support vector machine classifiers were trained on the CNN features to distinguish between benign and malignant lesions. Three methods that integrate the sequences at different levels (image fusion, feature fusion, and classifier fusion) were investigated. Classification performance was evaluated using the receiver operating characteristic (ROC) curve and compared using the DeLong test. The single-sequence classifiers yielded areas under the ROC curves (AUCs) [95% confidence intervals] of AUCDCE = 0.85 [0.82, 0.88] and AUCT2w = 0.78 [0.75, 0.81]. The multiparametric schemes yielded AUCImageFusion = 0.85 [0.82, 0.88], AUCFeatureFusion = 0.87 [0.84, 0.89], and AUCClassifierFusion = 0.86 [0.83, 0.88]. The feature fusion method statistically significantly outperformed using DCE alone (P < 0.001). In conclusion, the proposed deep transfer learning CADx method for mpMRI may improve diagnostic performance by reducing the false positive rate and improving the positive predictive value in breast imaging interpretation.

Deep-learning-based model observer for a lung nodule detection task in computed tomography.

Purpose: Task-based image quality assessment using model observers (MOs) is an effective approach to radiation dose and scanning protocol optimization in computed tomography (CT) imaging, once the correlation between MOs and radiologists can be established in well-defined clinically relevant tasks. Conventional MO studies were typically simplified to detection, classification, or localization tasks using tissue-mimicking phantoms, as traditional MOs cannot be readily used in complex anatomical background. However, anatomical variability can affect human diagnostic performance. Approach: To address this challenge, we developed a deep-learning-based MO (DL-MO) for localization tasks and validated in a lung nodule detection task, using previously validated projection-based lesion-/noise-insertion techniques. The DL-MO performance was compared with 4 radiologist readers over 12 experimental conditions, involving varying radiation dose levels, nodule sizes, nodule types, and reconstruction types. Each condition consisted of 100 trials (i.e., 30 images per trial) generated from a patient cohort of 50 cases. DL-MO was trained using small image volume-of-interests extracted across the entire volume of training cases. For each testing trial, the nodule searching of DL-MO was confined to a 3-mm thick volume to improve computational efficiency, and radiologist readers were tasked to review the entire volume. Results: A strong correlation between DL-MO and human readers was observed (Pearson's correlation coefficient: 0.980 with a 95% confidence interval of [0.924, 0.994]). The averaged performance bias between DL-MO and human readers was 0.57%. Conclusion: The experimental results indicated the potential of using the proposed DL-MO for diagnostic image quality assessment in realistic chest CT tasks.

A virtual clinical trial using projection-based nodule insertion to determine radiologist reader performance in lung cancer screening CT.

Task-based image quality assessment using model observers is promising to provide an efficient, quantitative, and objective approach to CT dose optimization. Before this approach can be reliably used in practice, its correlation with radiologist performance for the same clinical task needs to be established. Determining human observer performance for a well-defined clinical task, however, has always been a challenge due to the tremendous amount of efforts needed to collect a large number of positive cases. To overcome this challenge, we developed an accurate projection-based insertion technique. In this study, we present a virtual clinical trial using this tool and a low-dose simulation tool to determine radiologist performance on lung-nodule detection as a function of radiation dose, nodule type, nodule size, and reconstruction methods. The lesion insertion and low-dose simulation tools together were demonstrated to provide flexibility to generate realistically-appearing clinical cases under well-defined conditions. The reader performance data obtained in this virtual clinical trial can be used as the basis to develop model observers for lung nodule detection, as well as for dose and protocol optimization in lung cancer screening CT.