Patient Characteristics Impact Performance of AI Algorithm in Interpreting Negative Screening Digital Breast Tomosynthesis Studies.

Background Artificial intelligence (AI) is increasingly used to manage radiologists' workloads. The impact of patient characteristics on AI performance has not been well studied. Purpose To understand the impact of patient characteristics (race and ethnicity, age, and breast density) on the performance of an AI algorithm interpreting negative screening digital breast tomosynthesis (DBT) examinations. Materials and Methods This retrospective cohort study identified negative screening DBT examinations from an academic institution from January 1, 2016, to December 31, 2019. All examinations had 2 years of follow-up without a diagnosis of atypia or breast malignancy and were therefore considered true negatives. A subset of unique patients was randomly selected to provide a broad distribution of race and ethnicity. DBT studies in this final cohort were interpreted by a U.S. Food and Drug Administration-approved AI algorithm, which generated case scores (malignancy certainty) and risk scores (1-year subsequent malignancy risk) for each mammogram. Positive examinations were classified based on vendor-provided thresholds for both scores. Multivariable logistic regression was used to understand relationships between the scores and patient characteristics. Results A total of 4855 patients (median age, 54 years [IQR, 46-63 years]) were included: 27% (1316 of 4855) White, 26% (1261 of 4855) Black, 28% (1351 of 4855) Asian, and 19% (927 of 4855) Hispanic patients. False-positive case scores were significantly more likely in Black patients (odds ratio [OR] = 1.5 [95% CI: 1.2, 1.8]) and less likely in Asian patients (OR = 0.7 [95% CI: 0.5, 0.9]) compared with White patients, and more likely in older patients (71-80 years; OR = 1.9 [95% CI: 1.5, 2.5]) and less likely in younger patients (41-50 years; OR = 0.6 [95% CI: 0.5, 0.7]) compared with patients aged 51-60 years. False-positive risk scores were more likely in Black patients (OR = 1.5 [95% CI: 1.0, 2.0]), patients aged 61-70 years (OR = 3.5 [95% CI: 2.4, 5.1]), and patients with extremely dense breasts (OR = 2.8 [95% CI: 1.3, 5.8]) compared with White patients, patients aged 51-60 years, and patients with fatty density breasts, respectively. Conclusion Patient characteristics influenced the case and risk scores of a Food and Drug Administration-approved AI algorithm analyzing negative screening DBT examinations. © RSNA, 2024.

A new method to accurately identify single nucleotide variants using small FFPE breast samples.

Most tissue collections of neoplasms are composed of formalin-fixed and paraffin-embedded (FFPE) excised tumor samples used for routine diagnostics. DNA sequencing is becoming increasingly important in cancer research and clinical management; however it is difficult to accurately sequence DNA from FFPE samples. We developed and validated a new bioinformatic pipeline to use existing variant-calling strategies to robustly identify somatic single nucleotide variants (SNVs) from whole exome sequencing using small amounts of DNA extracted from archival FFPE samples of breast cancers. We optimized this strategy using 28 pairs of technical replicates. After optimization, the mean similarity between replicates increased 5-fold, reaching 88% (range 0-100%), with a mean of 21.4 SNVs (range 1-68) per sample, representing a markedly superior performance to existing tools. We found that the SNV-identification accuracy declined when there was less than 40 ng of DNA available and that insertion-deletion variant calls are less reliable than single base substitutions. As the first application of the new algorithm, we compared samples of ductal carcinoma in situ of the breast to their adjacent invasive ductal carcinoma samples. We observed an increased number of mutations (paired-samples sign test, P < 0.05), and a higher genetic divergence in the invasive samples (paired-samples sign test, P < 0.01). Our method provides a significant improvement in detecting SNVs in FFPE samples over previous approaches.

Prediction of Upstaging in Ductal Carcinoma in Situ Based on Mammographic Radiomic Features.

Background Improving diagnosis of ductal carcinoma in situ (DCIS) before surgery is important in choosing optimal patient management strategies. However, patients may harbor occult invasive disease not detected until definitive surgery. Purpose To assess the performance and clinical utility of mammographic radiomic features in the prediction of occult invasive cancer among women diagnosed with DCIS on the basis of core biopsy findings. Materials and Methods In this Health Insurance Portability and Accountability Act-compliant retrospective study, digital magnification mammographic images were collected from women who underwent breast core-needle biopsy for calcifications that was performed at a single institution between September 2008 and April 2017 and yielded a diagnosis of DCIS. The database query was directed at asymptomatic women with calcifications without a mass, architectural distortion, asymmetric density, or palpable disease. Logistic regression with regularization was used. Differences across training and internal test set by upstaging rate, age, lesion size, and estrogen and progesterone receptor status were assessed by using the Kruskal-Wallis or χ2 test. Results The study consisted of 700 women with DCIS (age range, 40-89 years; mean age, 59 years ± 10 [standard deviation]), including 114 with lesions (16.3%) upstaged to invasive cancer at subsequent surgery. The sample was split randomly into 400 women for the training set and 300 for the testing set (mean ages: training set, 59 years ± 10; test set, 59 years ± 10; P = .85). A total of 109 radiomic and four clinical features were extracted. The best model on the test set by using all radiomic and clinical features helped predict upstaging with an area under the receiver operating characteristic curve of 0.71 (95% CI: 0.62, 0.79). For a fixed high sensitivity (90%), the model yielded a specificity of 22%, a negative predictive value of 92%, and an odds ratio of 2.4 (95% CI: 1.8, 3.2). High specificity (90%) corresponded to a sensitivity of 37%, positive predictive value of 41%, and odds ratio of 5.0 (95% CI: 2.8, 9.0). Conclusion Machine learning models that use radiomic features applied to mammographic calcifications may help predict upstaging of ductal carcinoma in situ, which can refine clinical decision making and treatment planning. © RSNA, 2022.

Multi-label annotation of text reports from computed tomography of the chest, abdomen, and pelvis using deep learning.

BACKGROUND: There is progress to be made in building artificially intelligent systems to detect abnormalities that are not only accurate but can handle the true breadth of findings that radiologists encounter in body (chest, abdomen, and pelvis) computed tomography (CT). Currently, the major bottleneck for developing multi-disease classifiers is a lack of manually annotated data. The purpose of this work was to develop high throughput multi-label annotators for body CT reports that can be applied across a variety of abnormalities, organs, and disease states thereby mitigating the need for human annotation. METHODS: We used a dictionary approach to develop rule-based algorithms (RBA) for extraction of disease labels from radiology text reports. We targeted three organ systems (lungs/pleura, liver/gallbladder, kidneys/ureters) with four diseases per system based on their prevalence in our dataset. To expand the algorithms beyond pre-defined keywords, attention-guided recurrent neural networks (RNN) were trained using the RBA-extracted labels to classify reports as being positive for one or more diseases or normal for each organ system. Alternative effects on disease classification performance were evaluated using random initialization or pre-trained embedding as well as different sizes of training datasets. The RBA was tested on a subset of 2158 manually labeled reports and performance was reported as accuracy and F-score. The RNN was tested against a test set of 48,758 reports labeled by RBA and performance was reported as area under the receiver operating characteristic curve (AUC), with 95% CIs calculated using the DeLong method. RESULTS: Manual validation of the RBA confirmed 91-99% accuracy across the 15 different labels. Our models extracted disease labels from 261,229 radiology reports of 112,501 unique subjects. Pre-trained models outperformed random initialization across all diseases. As the training dataset size was reduced, performance was robust except for a few diseases with a relatively small number of cases. Pre-trained classification AUCs reached > 0.95 for all four disease outcomes and normality across all three organ systems. CONCLUSIONS: Our label-extracting pipeline was able to encompass a variety of cases and diseases in body CT reports by generalizing beyond strict rules with exceptional accuracy. The method described can be easily adapted to enable automated labeling of hospital-scale medical data sets for training image-based disease classifiers.

Mixed-Methods Study to Predict Upstaging of DCIS to Invasive Disease on Mammography.

BACKGROUND. The incidence of ductal carcinoma in situ (DCIS) has steadily increased, as have concerns regarding overtreatment. Active surveillance is a novel treatment strategy that avoids surgical excision, but identifying patients with occult invasive disease who should be excluded from active surveillance is challenging. Radiologists are not typically expected to predict the upstaging of DCIS to invasive disease, though they might be trained to perform this task. OBJECTIVE. The purpose of this study was to determine whether a mixed-methods two-stage observer study can improve radiologists' ability to predict upstaging of DCIS to invasive disease on mammography. METHODS. All cases of DCIS calcifications that underwent stereotactic biopsy between 2010 and 2015 were identified. Two cohorts were randomly generated, each containing 150 cases (120 pure DCIS cases and 30 DCIS cases upstaged to invasive disease at surgery). Nine breast radiologists reviewed the mammograms in the first cohort in a blinded fashion and scored the probability of upstaging to invasive disease. The radiologists then reviewed the cases and results collectively in a focus group to develop consensus criteria that could improve their ability to predict upstaging. The radiologists reviewed the mammograms from the second cohort in a blinded fashion and again scored the probability of upstaging. Statistical analysis compared the performances between rounds 1 and 2. RESULTS. The mean AUC for reader performance in predicting upstaging in round 1 was 0.623 (range, 0.514-0.684). In the focus group, radiologists agreed that upstaging was better predicted when an associated mass, asymmetry, or architectural distortion was present; when densely packed calcifications extended over a larger area; and when the most suspicious features were focused on rather than the most common features. Additionally, radiologists agreed that BI-RADS descriptors do not adequately characterize risk of invasion, and that microinvasive disease and smaller areas of DCIS will have poor prediction estimates. Reader performance significantly improved in round 2 (mean AUC, 0.765; range, 0.617-0.852; p = .045). CONCLUSION. A mixed-methods two-stage observer study identified factors that helped radiologists significantly improve their ability to predict upstaging of DCIS to invasive disease. CLINICAL IMPACT. Breast radiologists can be trained to better predict upstaging of DCIS to invasive disease, which may facilitate discussions with patients and referring providers.

Growth Dynamics of Mammographic Calcifications: Differentiating Ductal Carcinoma in Situ from Benign Breast Disease.

Background Most ductal carcinoma in situ (DCIS) lesions are first detected on screening mammograms as calcifications. However, false-positive biopsy rates for calcifications range from 30% to 87%. Improved methods to differentiate benign from malignant calcifications are thus needed. Purpose To quantify the growth rates of DCIS and benign breast disease that manifest as mammographic calcifications. Materials and Methods All calcifications (n = 2359) for which a stereotactic biopsy was performed from 2008 through 2015 at Duke University Medical Center were retrospectively identified. Mammograms from all cases of DCIS (n = 404) were reviewed for calcifications that were visible on mammograms taken at least 6 months before biopsy. Women with at least one prior mammogram with visible calcifications were age- and race-matched 1:2 to women with a benign breast biopsy and calcifications visible on prior mammograms. The long axis of the calcifications was measured on all mammograms. Multivariable adjusted linear mixed-effects models estimated the association of calcification growth rates with patholo findings. Hierarchical clustering accounted for matching benign and DCIS groups. Results A total of 74 DCIS calcifications and 148 benign calcifications were included for final analysis. The median patient age was 62 years (interquartile range, 51-71 years). No significant difference in breast density (P > .05) or number of available mammograms (P > .05) was detected between groups. Calcifications associated with DCIS were larger than those associated with benign breast disease at biopsy (median, 10 mm vs 6 mm, respectively; P < .001). After adjustment, the relative annual increase in the long-axis length of DCIS calcifications was greater than that of benign breast calcifications (96% [95% confidence interval: 72%, 224%] vs 68% [95% confidence interval: 56%, 80%] per year, respectively; P < .001). Conclusion Ductal carcinoma in situ calcifications are more extensive at diagnosis and grow faster in extent than those associated with benign breast disease. The rate of calcification change may help to discriminate benign from malignant calcifications. © RSNA, 2019 Online supplemental material is available for this article.

Can Digital Breast Tomosynthesis Replace Full-Field Digital Mammography? A Multireader, Multicase Study of Wide-Angle Tomosynthesis.

OBJECTIVE. The purpose of this study was to test the hypothesis whether two-view wide-angle digital breast tomosynthesis (DBT) can replace full-field digital mammography (FFDM) for breast cancer detection. SUBJECTS AND METHODS. In a multireader multicase study, bilateral two-view FFDM and bilateral two-view wide-angle DBT images were independently viewed for breast cancer detection in two reading sessions separated by more than 1 month. From a pool of 764 patients undergoing screening and diagnostic mammography, 330 patient-cases were selected. The endpoints were the mean ROC AUC for the reader per breast (breast level), ROC AUC per patient (subject level), noncancer recall rates, sensitivity, and specificity. RESULTS. Twenty-nine of 31 readers performed better with DBT than FFDM regardless of breast density. There was a statistically significant improvement in readers' mean diagnostic accuracy with DBT. The subject-level AUC increased from 0.765 (standard error [SE], 0.027) for FFDM to 0.835 (SE, 0.027) for DBT (p = 0.002). Breast-level AUC increased from 0.818 (SE, 0.019) for FFDM to 0.861 (SE, 0.019) for DBT (p = 0.011). The noncancer recall rate per patient was reduced by 19% with DBT (p < 0.001). Masses and architectural distortions were detected more with DBT (p < 0.001); calcifications trended lower (p = 0.136). Accuracy for detection of invasive cancers was significantly greater with DBT (p < 0.001). CONCLUSION. Reader performance in breast cancer detection is significantly higher with wide-angle two-view DBT independent of FFDM, verifying the robustness of DBT as a sole view. However, results of perception studies in the vision sciences support the inclusion of an overview image.

Classification performance bias between training and test sets in a limited mammography dataset.

OBJECTIVES: To assess the performance bias caused by sampling data into training and test sets in a mammography radiomics study. METHODS: Mammograms from 700 women were used to study upstaging of ductal carcinoma in situ. The dataset was repeatedly shuffled and split into training (n = 400) and test cases (n = 300) forty times. For each split, cross-validation was used for training, followed by an assessment of the test set. Logistic regression with regularization and support vector machine were used as the machine learning classifiers. For each split and classifier type, multiple models were created based on radiomics and/or clinical features. RESULTS: Area under the curve (AUC) performances varied considerably across the different data splits (e.g., radiomics regression model: train 0.58-0.70, test 0.59-0.73). Performances for regression models showed a tradeoff where better training led to worse testing and vice versa. Cross-validation over all cases reduced this variability, but required samples of 500+ cases to yield representative estimates of performance. CONCLUSIONS: In medical imaging, clinical datasets are often limited to relatively small size. Models built from different training sets may not be representative of the whole dataset. Depending on the selected data split and model, performance bias could lead to inappropriate conclusions that might influence the clinical significance of the findings. ADVANCES IN KNOWLEDGE: Performance bias can result from model testing when using limited datasets. Optimal strategies for test set selection should be developed to ensure study conclusions are appropriate.

A Method for Efficient De-identification of DICOM Metadata and Burned-in Pixel Text.

De-identification of DICOM images is an essential component of medical image research. While many established methods exist for the safe removal of protected health information (PHI) in DICOM metadata, approaches for the removal of PHI "burned-in" to image pixel data are typically manual, and automated high-throughput approaches are not well validated. Emerging optical character recognition (OCR) models can potentially detect and remove PHI-bearing text from medical images but are very time-consuming to run on the high volume of images found in typical research studies. We present a data processing method that performs metadata de-identification for all images combined with a targeted approach to only apply OCR to images with a high likelihood of burned-in text. The method was validated on a dataset of 415,182 images across ten modalities representative of the de-identification requests submitted at our institution over a 20-year span. Of the 12,578 images in this dataset with burned-in text of any kind, only 10 passed undetected with the method. OCR was only required for 6050 images (1.5% of the dataset).

Application of deep learning on mammographies to discriminate between low and high-risk DCIS for patient participation in active surveillance trials.

BACKGROUND: Ductal Carcinoma In Situ (DCIS) can progress to invasive breast cancer, but most DCIS lesions never will. Therefore, four clinical trials (COMET, LORIS, LORETTA, AND LORD) test whether active surveillance for women with low-risk Ductal carcinoma In Situ is safe (E. S. Hwang et al., BMJ Open, 9: e026797, 2019, A. Francis et al., Eur J Cancer. 51: 2296-2303, 2015, Chizuko Kanbayashi et al. The international collaboration of active surveillance trials for low-risk DCIS (LORIS, LORD, COMET, LORETTA),  L. E. Elshof et al., Eur J Cancer, 51, 1497-510, 2015). Low-risk is defined as grade I or II DCIS. Because DCIS grade is a major eligibility criteria in these trials, it would be very helpful to assess DCIS grade on mammography, informed by grade assessed on DCIS histopathology in pre-surgery biopsies, since surgery will not be performed on a significant number of patients participating in these trials. OBJECTIVE: To assess the performance and clinical utility of a convolutional neural network (CNN) in discriminating high-risk (grade III) DCIS and/or Invasive Breast Cancer (IBC) from low-risk (grade I/II) DCIS based on mammographic features. We explored whether the CNN could be used as a decision support tool, from excluding high-risk patients for active surveillance. METHODS: In this single centre retrospective study, 464 patients diagnosed with DCIS based on pre-surgery biopsy between 2000 and 2014 were included. The collection of mammography images was partitioned on a patient-level into two subsets, one for training containing 80% of cases (371 cases, 681 images) and 20% (93 cases, 173 images) for testing. A deep learning model based on the U-Net CNN was trained and validated on 681 two-dimensional mammograms. Classification performance was assessed with the Area Under the Curve (AUC) receiver operating characteristic and predictive values on the test set for predicting high risk DCIS-and high-risk DCIS and/ or IBC from low-risk DCIS. RESULTS: When classifying DCIS as high-risk, the deep learning network achieved a Positive Predictive Value (PPV) of 0.40, Negative Predictive Value (NPV) of 0.91 and an AUC of 0.72 on the test dataset. For distinguishing high-risk and/or upstaged DCIS (occult invasive breast cancer) from low-risk DCIS a PPV of 0.80, a NPV of 0.84 and an AUC of 0.76 were achieved. CONCLUSION: For both scenarios (DCIS grade I/II vs. III, DCIS grade I/II vs. III and/or IBC) AUCs were high, 0.72 and 0.76, respectively, concluding that our convolutional neural network can discriminate low-grade from high-grade DCIS.

VLST: Virtual Lung Screening Trial for Lung Cancer Detection Using Virtual Imaging Trial.

Importance: The efficacy of lung cancer screening can be significantly impacted by the imaging modality used. This Virtual Lung Screening Trial (VLST) addresses the critical need for precision in lung cancer diagnostics and the potential for reducing unnecessary radiation exposure in clinical settings. Objectives: To establish a virtual imaging trial (VIT) platform that accurately simulates real-world lung screening trials (LSTs) to assess the diagnostic accuracy of CT and CXR modalities. Design Setting and Participants: Utilizing computational models and machine learning algorithms, we created a diverse virtual patient population. The cohort, designed to mirror real-world demographics, was assessed using virtual imaging techniques that reflect historical imaging technologies. Main Outcomes and Measures: The primary outcome was the difference in the Area Under the Curve (AUC) for CT and CXR modalities across lesion types and sizes. Results: The study analyzed 298 CT and 313 CXR simulated images from 313 virtual patients, with a lesion-level AUC of 0.81 (95% CI: 0.78-0.84) for CT and 0.55 (95% CI: 0.53-0.56) for CXR. At the patient level, CT demonstrated an AUC of 0.85 (95% CI: 0.80-0.89), compared to 0.53 (95% CI: 0.47-0.60) for CXR. Subgroup analyses indicated CT's superior performance in detecting homogeneous lesions (AUC of 0.97 for lesion-level) and heterogeneous lesions (AUC of 0.71 for lesion-level) as well as in identifying larger nodules (AUC of 0.98 for nodules > 8 mm). Conclusion and Relevance: The VIT platform validated the superior diagnostic accuracy of CT over CXR, especially for smaller nodules, underscoring its potential to replicate real clinical imaging trials. These findings advocate for the integration of virtual trials in the evaluation and improvement of imaging-based diagnostic tools.

Classification performance bias between training and test sets in a limited mammography dataset.

Objectives: To assess the performance bias caused by sampling data into training and test sets in a mammography radiomics study. Methods: Mammograms from 700 women were used to study upstaging of ductal carcinoma in situ. The dataset was repeatedly shuffled and split into training (n=400) and test cases (n=300) forty times. For each split, cross-validation was used for training, followed by an assessment of the test set. Logistic regression with regularization and support vector machine were used as the machine learning classifiers. For each split and classifier type, multiple models were created based on radiomics and/or clinical features. Results: Area under the curve (AUC) performances varied considerably across the different data splits (e.g., radiomics regression model: train 0.58-0.70, test 0.59-0.73). Performances for regression models showed a tradeoff where better training led to worse testing and vice versa. Cross-validation over all cases reduced this variability, but required samples of 500+ cases to yield representative estimates of performance. Conclusions: In medical imaging, clinical datasets are often limited to relatively small size. Models built from different training sets may not be representative of the whole dataset. Depending on the selected data split and model, performance bias could lead to inappropriate conclusions that might influence the clinical significance of the findings. Optimal strategies for test set selection should be developed to ensure study conclusions are appropriate.

Utility of a Rule-Based Algorithm in the Assessment of Standardized Reporting in PI-RADS.

RATIONALE AND OBJECTIVES: Adoption of the Prostate Imaging Reporting & Data System (PI-RADS) has been shown to increase detection of clinically significant prostate cancer on prostate mpMRI. We propose that a rule-based algorithm based on Regular Expression (RegEx) matching can be used to automatically categorize prostate mpMRI reports into categories as a means by which to assess for opportunities for quality improvement. MATERIALS AND METHODS: All prostate mpMRIs performed in the Duke University Health System from January 2, 2015, to January 29, 2021, were analyzed. Exclusion criteria were applied, for a total of 5343 male patients and 6264 prostate mpMRI reports. These reports were then analyzed by our RegEx algorithm to be categorized as PI-RADS 1 through PI-RADS 5, Recurrent Disease, or "No Information Available." A stratified, random sample of 502 mpMRI reports was reviewed by a blinded clinical team to assess performance of the RegEx algorithm. RESULTS: Compared to manual review, the RegEx algorithm achieved overall accuracy of 92.6%, average precision of 88.8%, average recall of 85.6%, and F1 score of 0.871. The clinical team also reviewed 344 cases that were classified as "No Information Available," and found that in 150 instances, no numerical PI-RADS score for any lesion was included in the impression section of the mpMRI report. CONCLUSION: Rule-based processing is an accurate method for the large-scale, automated extraction of PI-RADS scores from the text of radiology reports. These natural language processing approaches can be used for future initiatives in quality improvement in prostate mpMRI reporting with PI-RADS.

Ipsilateral Lesion Detection Refinement for Tomosynthesis.

Computer-aided detection (CAD) frameworks for breast cancer screening have been researched for several decades. Early adoption of deep-learning models in CAD frameworks has shown greatly improved detection performance compared to traditional CAD on single-view images. Recently, studies have improved performance by merging information from multiple views within each screening exam. Clinically, the integration of lesion correspondence during screening is a complicated decision process that depends on the correct execution of several referencing steps. However, most multi-view CAD frameworks are deep-learning-based black-box techniques. Fully end-to-end designs make it very difficult to analyze model behaviors and fine-tune performance. More importantly, the black-box nature of the techniques discourages clinical adoption due to the lack of explicit reasoning for each multi-view referencing step. Therefore, there is a need for a multi-view detection framework that can not only detect cancers accurately but also provide step-by-step, multi-view reasoning. In this work, we present Ipsilateral-Matching-Refinement Networks (IMR-Net) for digital breast tomosynthesis (DBT) lesion detection across multiple views. Our proposed framework adaptively refines the single-view detection scores based on explicit ipsilateral lesion matching. IMR-Net is built on a robust, single-view detection CAD pipeline with a commercial development DBT dataset of 24675 DBT volumetric views from 8034 exams. Performance is measured using location-based, case-level receiver operating characteristic (ROC) and case-level free-response ROC (FROC) analysis.

Technical note: Controlling the attenuation of 3D-printed physical phantoms for computed tomography with a single material.

PURPOSE: The purpose of this work was to characterize and improve the ability of fused filament fabrication to create anthropomorphic physical phantoms for CT research. Specifically, we sought to develop the ability to create multiple levels of X-ray attenuation with a single material. METHODS: CT images of 3D printed cylinders with different infill angles and printing patterns were assessed by comparing their 2D noise power spectra to determine the conditions that produced minimal and uniform noise. A backfilling approach in which additional polymer was extruded into an existing 3D printed background layer was developed to create multiple levels of image contrast. RESULTS: A print with nine infill angles and a rectilinear infill pattern was found to have the best uniformity, but the printed objects were not as uniform as a commercial phantom. An HU dynamic range of 600 was achieved by changing the infill percentage from 40% to 100%. The backfilling technique enabled control of up to eight levels of contrast within one object across a range of 200 HU, similar to the range of soft tissue. A contrast detail phantom with six levels of contrast and an anthropomorphic liver phantom with four levels of contrast were printed with a single material. CONCLUSION: This work improves the uniformity and levels of contrast that can be achieved with fused filament fabrication, thereby enabling researchers to easily create more detailed physical phantoms, including realistic, anthropomorphic textures.

Classification of Multiple Diseases on Body CT Scans Using Weakly Supervised Deep Learning.

PURPOSE: To design multidisease classifiers for body CT scans for three different organ systems using automatically extracted labels from radiology text reports. MATERIALS AND METHODS: This retrospective study included a total of 12 092 patients (mean age, 57 years ± 18 [standard deviation]; 6172 women) for model development and testing. Rule-based algorithms were used to extract 19 225 disease labels from 13 667 body CT scans performed between 2012 and 2017. Using a three-dimensional DenseVNet, three organ systems were segmented: lungs and pleura, liver and gallbladder, and kidneys and ureters. For each organ system, a three-dimensional convolutional neural network classified each as no apparent disease or for the presence of four common diseases, for a total of 15 different labels across all three models. Testing was performed on a subset of 2158 CT volumes relative to 2875 manually derived reference labels from 2133 patients (mean age, 58 years ± 18; 1079 women). Performance was reported as area under the receiver operating characteristic curve (AUC), with 95% CIs calculated using the DeLong method. RESULTS: Manual validation of the extracted labels confirmed 91%-99% accuracy across the 15 different labels. AUCs for lungs and pleura labels were as follows: atelectasis, 0.77 (95% CI: 0.74, 0.81); nodule, 0.65 (95% CI: 0.61, 0.69); emphysema, 0.89 (95% CI: 0.86, 0.92); effusion, 0.97 (95% CI: 0.96, 0.98); and no apparent disease, 0.89 (95% CI: 0.87, 0.91). AUCs for liver and gallbladder were as follows: hepatobiliary calcification, 0.62 (95% CI: 0.56, 0.67); lesion, 0.73 (95% CI: 0.69, 0.77); dilation, 0.87 (95% CI: 0.84, 0.90); fatty, 0.89 (95% CI: 0.86, 0.92); and no apparent disease, 0.82 (95% CI: 0.78, 0.85). AUCs for kidneys and ureters were as follows: stone, 0.83 (95% CI: 0.79, 0.87); atrophy, 0.92 (95% CI: 0.89, 0.94); lesion, 0.68 (95% CI: 0.64, 0.72); cyst, 0.70 (95% CI: 0.66, 0.73); and no apparent disease, 0.79 (95% CI: 0.75, 0.83). CONCLUSION: Weakly supervised deep learning models were able to classify diverse diseases in multiple organ systems from CT scans.Keywords: CT, Diagnosis/Classification/Application Domain, Semisupervised Learning, Whole-Body Imaging© RSNA, 2022.

Corrections to "iPhantom: A Framework for Automated Creation of Individualized Computational Phantoms and its Application to CT Organ Dosimetry".

In [1], the dose estimation accuracy using the alternative baseline method under modulated tube current was not correctly calculated due to an unintentional simulation error.

Anomaly Detection of Calcifications in Mammography Based on 11,000 Negative Cases.

In mammography, calcifications are one of the most common signs of breast cancer. Detection of such lesions is an active area of research for computer-aided diagnosis and machine learning algorithms. Due to limited numbers of positive cases, many supervised detection models suffer from overfitting and fail to generalize. We present a one-class, semi-supervised framework using a deep convolutional autoencoder trained with over 50,000 images from 11,000 negative-only cases. Since the model learned from only normal breast parenchymal features, calcifications produced large signals when comparing the residuals between input and reconstruction output images. As a key advancement, a structural dissimilarity index was used to suppress non-structural noises. Our selected model achieved pixel-based AUROC of 0.959 and AUPRC of 0.676 during validation, where calcification masks were defined in a semi-automated process. Although not trained directly on any cancers, detection performance of calcification lesions on 1,883 testing images (645 malignant and 1238 negative) achieved 75% sensitivity at 2.5 false positives per image. Performance plateaued early when trained with only a fraction of the cases, and greater model complexity or a larger dataset did not improve performance. This study demonstrates the potential of this anomaly detection approach to detect mammographic calcifications in a semi-supervised manner with efficient use of a small number of labeled images, and may facilitate new clinical applications such as computer-aided triage and quality improvement.

Computer-aided classification of breast masses: performance and interobserver variability of expert radiologists versus residents.

PURPOSE: To evaluate the interobserver variability in descriptions of breast masses by dedicated breast imagers and radiology residents and determine how any differences in lesion description affect the performance of a computer-aided diagnosis (CAD) computer classification system. MATERIALS AND METHODS: Institutional review board approval was obtained for this HIPAA-compliant study, and the requirement to obtain informed consent was waived. Images of 50 breast lesions were individually interpreted by seven dedicated breast imagers and 10 radiology residents, yielding 850 lesion interpretations. Lesions were described with use of 11 descriptors from the Breast Imaging Reporting and Data System, and interobserver variability was calculated with the Cohen κ statistic. Those 11 features were selected, along with patient age, and merged together by a linear discriminant analysis (LDA) classification model trained by using 1005 previously existing cases. Variability in the recommendations of the computer model for different observers was also calculated with the Cohen κ statistic. RESULTS: A significant difference was observed for six lesion features, and radiology residents had greater interobserver variability in their selection of five of the six features than did dedicated breast imagers. The LDA model accurately classified lesions for both sets of observers (area under the receiver operating characteristic curve = 0.94 for residents and 0.96 for dedicated imagers). Sensitivity was maintained at 100% for residents and improved from 98% to 100% for dedicated breast imagers. For residents, the computer model could potentially improve the specificity from 20% to 40% (P < .01) and the κ value from 0.09 to 0.53 (P < .001). For dedicated breast imagers, the computer model could increase the specificity from 34% to 43% (P = .16) and the κ value from 0.21 to 0.61 (P < .001). CONCLUSION: Among findings showing a significant difference, there was greater interobserver variability in lesion descriptions among residents; however, an LDA model using data from either dedicated breast imagers or residents yielded a consistently high performance in the differentiation of benign from malignant breast lesions, demonstrating potential for improving specificity and decreasing interobserver variability in biopsy recommendations.

Knowledge-based IMRT treatment planning for prostate cancer.

PURPOSE: To demonstrate the feasibility of using a knowledge base of prior treatment plans to generate new prostate intensity modulated radiation therapy (IMRT) plans. Each new case would be matched against others in the knowledge base. Once the best match is identified, that clinically approved plan is used to generate the new plan. METHODS: A database of 100 prostate IMRT treatment plans was assembled into an information-theoretic system. An algorithm based on mutual information was implemented to identify similar patient cases by matching 2D beam's eye view projections of contours. Ten randomly selected query cases were each matched with the most similar case from the database of prior clinically approved plans. Treatment parameters from the matched case were used to develop new treatment plans. A comparison of the differences in the dose-volume histograms between the new and the original treatment plans were analyzed. RESULTS: On average, the new knowledge-based plan is capable of achieving very comparable planning target volume coverage as the original plan, to within 2% as evaluated for D98, D95, and D1. Similarly, the dose to the rectum and dose to the bladder are also comparable to the original plan. For the rectum, the mean and standard deviation of the dose percentage differences for D20, D30, and D50 are 1.8% +/- 8.5%, -2.5% +/- 13.9%, and -13.9% +/- 23.6%, respectively. For the bladder, the mean and standard deviation of the dose percentage differences for D20, D30, and D50 are -5.9% +/- 10.8%, -12.2% +/- 14.6%, and -24.9% +/- 21.2%, respectively. A negative percentage difference indicates that the new plan has greater dose sparing as compared to the original plan. CONCLUSIONS: The authors demonstrate a knowledge-based approach of using prior clinically approved treatment plans to generate clinically acceptable treatment plans of high quality. This semiautomated approach has the potential to improve the efficiency of the treatment planning process while ensuring that high quality plans are developed.