3D CT Radiomic Analysis Improves Detection of Axillary Lymph Node Metastases Compared to Conventional Features in Patients With Locally Advanced Breast Cancer.

OBJECTIVE: Preoperative detection of axillary lymph node metastases (ALNMs) from breast cancer is suboptimal; however, recent work suggests radiomics may improve detection of ALNMs. This study aims to develop a 3D CT radiomics model to improve detection of ALNMs compared to conventional imaging features in patients with locally advanced breast cancer. METHODS: Retrospective chart review was performed on patients referred to a specialty breast cancer center between 2015 and 2020 with US-guided biopsy-proven ALNMs and pretreatment chest CT. One hundred and twelve patients (224 lymph nodes) met inclusion and exclusion criteria and were assigned to discovery (n = 150 nodes) and testing (n = 74 nodes) cohorts. US-biopsy images were referenced in identifying ALNMs on CT, with contralateral nodes taken as negative controls. Positive and negative nodes were assessed for conventional features of lymphadenopathy as well as for 107 radiomic features extracted following 3D segmentation. Diagnostic performance of individual and combined radiomic features was evaluated. RESULTS: The strongest conventional imaging feature of ALNMs was short axis diameter ≥10 mm with a sensitivity of 64%, specificity of 95%, and area under the curve (AUC) of 0.89 (95% CI, 0.84-0.94). Several radiomic features outperformed conventional features, most notably energy, a measure of voxel density magnitude. This feature demonstrated a sensitivity, specificity, and AUC of 91%, 79%, and 0.94 (95% CI, 0.91-0.98) for the discovery cohort. On the testing cohort, energy scored 92%, 81%, and 0.94 (95% CI, 0.89-0.99) for sensitivity, specificity, and AUC, respectively. Combining radiomic features did not improve AUC compared to energy alone (P = .08). CONCLUSION: 3D radiomic analysis represents a promising approach for noninvasive and accurate detection of ALNMs.

Automated screening of computed tomography using weakly supervised anomaly detection.

BACKGROUND: Current artificial intelligence studies for supporting CT screening tasks depend on either supervised learning or detecting anomalies. However, the former involves a heavy annotation workload owing to requiring many slice-wise annotations (ground truth labels); the latter is promising, but while it reduces the annotation workload, it often suffers from lower performance. This study presents a novel weakly supervised anomaly detection (WSAD) algorithm trained based on scan-wise normal and anomalous annotations to provide better performance than conventional methods while reducing annotation workload. METHODS: Based on surveillance video anomaly detection methodology, feature vectors representing each CT slice were trained on an AR-Net-based convolutional network using a dynamic multiple-instance learning loss and a center loss function. The following two publicly available CT datasets were retrospectively analyzed: the RSNA brain hemorrhage dataset (normal scans: 12,862; scans with intracranial hematoma: 8882) and COVID-CT set (normal scans: 282; scans with COVID-19: 95). RESULTS: Anomaly scores of each slice were successfully predicted despite inaccessibility to any slice-wise annotations. Slice-level area under the curve (AUC), sensitivity, specificity, and accuracy from the brain CT dataset were 0.89, 0.85, 0.78, and 0.79, respectively. The proposed method reduced the number of annotations in the brain dataset by 97.1% compared to an ordinary slice-level supervised learning method. CONCLUSION: This study demonstrated a significant annotation reduction in identifying anomalous CT slices compared to a supervised learning approach. The effectiveness of the proposed WSAD algorithm was verified through higher AUC than existing anomaly detection techniques.

Quantifying uncertainty in machine learning classifiers for medical imaging.

PURPOSE: Machine learning (ML) models in medical imaging (MI) can be of great value in computer aided diagnostic systems, but little attention is given to the confidence (alternatively, uncertainty) of such models, which may have significant clinical implications. This paper applied, validated, and explored a technique for assessing uncertainty in convolutional neural networks (CNNs) in the context of MI. MATERIALS AND METHODS: We used two publicly accessible imaging datasets: a chest x-ray dataset (pneumonia vs. control) and a skin cancer imaging dataset (malignant vs. benign) to explore the proposed measure of uncertainty based on experiments with different class imbalance-sample sizes, and experiments with images close to the classification boundary. We also further verified our hypothesis by examining the relationship with other performance metrics and cross-checking CNN predictions and confidence scores with an expert radiologist (available in the Supplementary Information). Additionally, bounds were derived on the uncertainty metric, and recommendations for interpretability were made. RESULTS: With respect to training set class imbalance for the pneumonia MI dataset, the uncertainty metric was minimized when both classes were nearly equal in size (regardless of training set size) and was approximately 17% smaller than the maximum uncertainty resulting from greater imbalance. We found that less-obvious test images (those closer to the classification boundary) produced higher classification uncertainty, about 10-15 times greater than images further from the boundary. Relevant MI performance metrics like accuracy, sensitivity, and sensibility showed seemingly negative linear correlations, though none were statistically significant (p [Formula: see text] 0.05). The expert radiologist and CNN expressed agreement on a small sample of test images, though this finding is only preliminary. CONCLUSIONS: This paper demonstrated the importance of uncertainty reporting alongside predictions in medical imaging. Results demonstrate considerable potential from automatically assessing classifier reliability on each prediction with the proposed uncertainty metric.

Artificial intelligence and radiomics in pediatric molecular imaging.

In the past decade, a new approach for quantitative analysis of medical images and prognostic modelling has emerged. Defined as the extraction and analysis of a large number of quantitative parameters from medical images, radiomics is an evolving field in precision medicine with the ultimate goal of the discovery of new imaging biomarkers for disease. Radiomics has already shown promising results in extracting diagnostic, prognostic, and molecular information latent in medical images. After acquisition of the medical images as part of the standard of care, a region of interest is defined often via a manual or semi-automatic approach. An algorithm then extracts and computes quantitative radiomics parameters from the region of interest. Whereas radiomics captures quantitative values of shape and texture based on predefined mathematical terms, neural networks have recently been used to directly learn and identify predictive features from medical images. Thereby, neural networks largely forego the need for so called "hand-engineered" features, which appears to result in significantly improved performance and reliability. Opportunities for radiomics and neural networks in pediatric nuclear medicine/radiology/molecular imaging are broad and can be thought of in three categories: automating well-defined administrative or clinical tasks, augmenting broader administrative or clinical tasks, and unlocking new methods of generating value. Specific applications include intelligent order sets, automated protocoling, improved image acquisition, computer aided triage and detection of abnormalities, next generation voice dictation systems, biomarker development, and therapy planning.