Automated full body tumor segmentation in DOTATATE PET/CT for neuroendocrine cancer patients.

PURPOSE: Neuroendocrine tumors (NETs) are a rare form of cancer that can occur anywhere in the body and commonly metastasizes. The large variance in location and aggressiveness of the tumors makes it a difficult cancer to treat. Assessments of the whole-body tumor burden in a patient image allow for better tracking of disease progression and inform better treatment decisions. Currently, radiologists rely on qualitative assessments of this metric since manual segmentation is unfeasible within a typical busy clinical workflow. METHODS: We address these challenges by extending the application of the nnU-net pipeline to produce automatic NET segmentation models. We utilize the ideal imaging type of 68Ga-DOTATATE PET/CT to produce segmentation masks from which to calculate total tumor burden metrics. We provide a human-level baseline for the task and perform ablation experiments of model inputs, architectures, and loss functions. RESULTS: Our dataset is comprised of 915 PET/CT scans and is divided into a held-out test set (87 cases) and 5 training subsets to perform cross-validation. The proposed models achieve test Dice scores of 0.644, on par with our inter-annotator Dice score on a subset 6 patients of 0.682. If we apply our modified Dice score to the predictions, the test performance reaches a score of 0.80. CONCLUSION: In this paper, we demonstrate the ability to automatically generate accurate NET segmentation masks given PET images through supervised learning. We publish the model for extended use and to support the treatment planning of this rare cancer.

Fast, light, and scalable: harnessing data-mined line annotations for automated tumor segmentation on brain MRI.

OBJECTIVES: While fully supervised learning can yield high-performing segmentation models, the effort required to manually segment large training sets limits practical utility. We investigate whether data mined line annotations can facilitate brain MRI tumor segmentation model development without requiring manually segmented training data. METHODS: In this retrospective study, a tumor detection model trained using clinical line annotations mined from PACS was leveraged with unsupervised segmentation to generate pseudo-masks of enhancing tumors on T1-weighted post-contrast images (9911 image slices; 3449 adult patients). Baseline segmentation models were trained and employed within a semi-supervised learning (SSL) framework to refine the pseudo-masks. Following each self-refinement cycle, a new model was trained and tested on a held-out set of 319 manually segmented image slices (93 adult patients), with the SSL cycles continuing until Dice score coefficient (DSC) peaked. DSCs were compared using bootstrap resampling. Utilizing the best-performing models, two inference methods were compared: (1) conventional full-image segmentation, and (2) a hybrid method augmenting full-image segmentation with detection plus image patch segmentation. RESULTS: Baseline segmentation models achieved DSC of 0.768 (U-Net), 0.831 (Mask R-CNN), and 0.838 (HRNet), improving with self-refinement to 0.798, 0.871, and 0.873 (each p < 0.001), respectively. Hybrid inference outperformed full image segmentation alone: DSC 0.884 (Mask R-CNN) vs. 0.873 (HRNet), p < 0.001. CONCLUSIONS: Line annotations mined from PACS can be harnessed within an automated pipeline to produce accurate brain MRI tumor segmentation models without manually segmented training data, providing a mechanism to rapidly establish tumor segmentation capabilities across radiology modalities. KEY POINTS: • A brain MRI tumor detection model trained using clinical line measurement annotations mined from PACS was leveraged to automatically generate tumor segmentation pseudo-masks. • An iterative self-refinement process automatically improved pseudo-mask quality, with the best-performing segmentation pipeline achieving a Dice score of 0.884 on a held-out test set. • Tumor line measurement annotations generated in routine clinical radiology practice can be harnessed to develop high-performing segmentation models without manually segmented training data, providing a mechanism to rapidly establish tumor segmentation capabilities across radiology modalities.

Report Automation.

A vascular lab procedure culminates in a diagnostic report that is a combination of the data generated on the vascular lab equipment, physician interpretations, and recommendations. The transcription process can be error prone and inefficient. Computerized capture of data from the equipment and transmission into a reporting system is the definition of "automation" in this article. In this article, we describe an organized approach to collecting data generated on vascular lab equipment and delivering to reporting systems to decrease error and improve efficiency.

Programmatic Implementation of a Custom Subspecialized Oncologic Imaging Workflow Manager at a Tertiary Cancer Center.

PURPOSE: To evaluate whether a custom programmatic workflow manager reduces reporting turnaround times (TATs) from a body oncologic imaging workflow at a tertiary cancer center. METHODS: A custom software program was developed and implemented in the programming language R. Other aspects of the workflow were left unchanged. TATs were measured over a 12-month period (June-May). The same prior 12-month period served as a historical control. Median TATs of magnetic resonance imaging (MRI) and computed tomography (CT) examinations were compared with a Wilcoxon test. A chi-square test was used to compare the numbers of examinations reported within 24 hours and after 72 hours as well as the proportions of examinations assigned according to individual radiologist preferences. RESULTS: For all MRI and CT examinations (124,507 in 2019/2020 and 138,601 in 2020/2021), the median TAT decreased from 4 (interquartile range: 1-22 hours) to 3 hours (1-17 hours). Reports completed within 24 hours increased from 78% (124,127) to 89% (138,601). For MRI, TAT decreased from 22 (5-49 hours) to 8 hours (2-21 hours), and reports completed within 24 hours increased from 55% (14,211) to 80% (23,744). For CT, TAT decreased from 3 (1-19 hours) to 2 hours (1-13 hours), and reports completed within 24 hours increased from 84% (82,342) to 92% (99,922). Delayed reports (with a TAT > 72 hours) decreased from 17.0% (4,176) to 2.2% (649) for MRI and from 2.5% (2,500) to 0.7% (745) for CT. All differences were statistically significant (P < .001). CONCLUSION: The custom workflow management software program significantly decreased MRI and CT report TATs.

Radiologist-Level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans.

PURPOSE: To develop a deep network architecture that would achieve fully automated radiologist-level segmentation of cancers at breast MRI. MATERIALS AND METHODS: In this retrospective study, 38 229 examinations (composed of 64 063 individual breast scans from 14 475 patients) were performed in female patients (age range, 12-94 years; mean age, 52 years ± 10 [standard deviation]) who presented between 2002 and 2014 at a single clinical site. A total of 2555 breast cancers were selected that had been segmented on two-dimensional (2D) images by radiologists, as well as 60 108 benign breasts that served as examples of noncancerous tissue; all these were used for model training. For testing, an additional 250 breast cancers were segmented independently on 2D images by four radiologists. Authors selected among several three-dimensional (3D) deep convolutional neural network architectures, input modalities, and harmonization methods. The outcome measure was the Dice score for 2D segmentation, which was compared between the network and radiologists by using the Wilcoxon signed rank test and the two one-sided test procedure. RESULTS: The highest-performing network on the training set was a 3D U-Net with dynamic contrast-enhanced MRI as input and with intensity normalized for each examination. In the test set, the median Dice score of this network was 0.77 (interquartile range, 0.26). The performance of the network was equivalent to that of the radiologists (two one-sided test procedures with radiologist performance of 0.69-0.84 as equivalence bounds, P < .001 for both; n = 250). CONCLUSION: When trained on a sufficiently large dataset, the developed 3D U-Net performed as well as fellowship-trained radiologists in detailed 2D segmentation of breast cancers at routine clinical MRI.Keywords: MRI, Breast, Segmentation, Supervised Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning AlgorithmsPublished under a CC BY 4.0 license. Supplemental material is available for this article.

Automatic Forecasting of Radiology Examination Volume Trends for Optimal Resource Planning and Allocation.

The aim of the study was to evaluate the performance of the Prophet forecasting procedure, part of the Facebook open-source Artificial Intelligence portfolio, for forecasting variations in radiological examination volumes. Daily CT and MRI examination volumes from our institution were extracted from the radiology information system (RIS) database. Data from January 1, 2015, to December 31, 2019, was used for training the Prophet algorithm, and data from January 2020 was used for validation. Algorithm performance was then evaluated prospectively in February and August 2020. Total error and mean error per day were evaluated, and computational time was logged using different Markov chain Monte Carlo (MCMC) samples. Data from 610,570 examinations were used for training; the majority were CTs (82.3%). During retrospective testing, prediction error was reduced from 19 to < 1 per day in CT (total 589 to 17) and from 5 to < 1 per day (total 144 to 27) in MRI by fine-tuning the Prophet procedure. Prospective prediction error in February was 11 per day in CT (9934 predicted, 9667 actual) and 1 per day in MRI (2484 predicted, 2457 actual) and was significantly better than manual weekly predictions (p = 0.001). Inference with MCMC added no substantial improvements while vastly increasing computational time. Prophet accurately models weekly, seasonal, and overall trends paving the way for optimal resource allocation for radiology exam acquisition and interpretation.

Integrating Al Algorithms into the Clinical Workflow.

Integration of artificial intelligence (AI) applications within clinical workflows is an important step for leveraging developed AI algorithms. In this report, generalizable components for deploying AI systems into clinical practice are described that were implemented in a clinical pilot study using lymphoscintigraphy examinations as a prospective use case (July 1, 2019-October 31, 2020). Deployment of the AI algorithm consisted of seven software components, as follows: (a) image delivery, (b) quality control, (c) a results database, (d) results processing, (e) results presentation and delivery, (f) error correction, and (g) a dashboard for performance monitoring. A total of 14 users used the system (faculty radiologists and trainees) to assess the degree of satisfaction with the components and overall workflow. Analyses included the assessment of the number of examinations processed, error rates, and corrections. The AI system processed 1748 lymphoscintigraphy examinations. The system enabled radiologists to correct 146 AI results, generating real-time corrections to the radiology report. All AI results and corrections were successfully stored in a database for downstream use by the various integration components. A dashboard allowed monitoring of the AI system performance in real time. All 14 survey respondents "somewhat agreed" or "strongly agreed" that the AI system was well integrated into the clinical workflow. In all, a framework of processes and components for integrating AI algorithms into clinical workflows was developed. The implementation described could be helpful for assessing and monitoring AI performance in clinical practice. Keywords: PACS, Computer Applications-General (Informatics), Diagnosis © RSNA, 2021.

Bag-of-Words Technique in Natural Language Processing: A Primer for Radiologists.

Natural language processing (NLP) is a methodology designed to extract concepts and meaning from human-generated unstructured (free-form) text. It is intended to be implemented by using computer algorithms so that it can be run on a corpus of documents quickly and reliably. To enable machine learning (ML) techniques in NLP, free-form text must be converted to a numerical representation. After several stages of preprocessing including tokenization, removal of stop words, token normalization, and creation of a master dictionary, the bag-of-words (BOW) technique can be used to represent each remaining word as a feature of the document. The preprocessing steps simplify the documents but also potentially degrade meaning. The values of the features in BOW can be modified by using techniques such as term count, term frequency, and term frequency-inverse document frequency. Experience and experimentation will guide decisions on which specific techniques will optimize ML performance. These and other NLP techniques are being applied in radiology. Radiologists' understanding of the strengths and limitations of these techniques will help in communication with data scientists and in implementation for specific tasks. Online supplemental material is available for this article. ©RSNA, 2021.

Application of Deep Learning Techniques for Characterization of 3D Radiological Datasets - A Pilot Study for Detection of Intravenous Contrast in Breast MRI.

Categorization of radiological images according to characteristics such as modality, scanner parameters, body part etc, is important for quality control, clinical efficiency and research. The metadata associated with images stored in the DICOM format reliably captures scanner settings such as tube current in CT or echo time (TE) in MRI. Other parameters such as image orientation, body part examined and presence of intravenous contrast, however, are not inherent to the scanner settings, and therefore require user input which is prone to human error. There is a general need for automated approaches that will appropriately categorize images, even with parameters that are not inherent to the scanner settings. These approaches should be able to process both planar 2D images and full 3D scans. In this work, we present a deep learning based approach for automatically detecting one such parameter: the presence or absence of intravenous contrast in 3D MRI scans. Contrast is manually injected by radiology staff during the imaging examination, and its presence cannot be automatically recorded in the DICOM header by the scanner. Our classifier is a convolutional neural network (CNN) based on the ResNet architecture. Our data consisted of 1000 breast MRI scans (500 scans with and 500 scans without intravenous contrast), used for training and testing a CNN on 80%/20% split, respectively. The labels for the scans were obtained from the series descriptions created by certified radiological technologists. Preliminary results of our classifier are very promising with an area under the ROC curve (AUC) of 0.98, sensitivity and specificity of 1.0 and 0.9 respectively (at the optimal ROC cut-off point), demonstrating potential usefulness in both clinical as well as research settings.

An Informatics Approach to Facilitate Clinical Management of Patients With Retrievable Inferior Vena Cava Filters.

OBJECTIVE: Long indwelling times for inferior vena cava (IVC) filters that are used to prevent venous thromboembolism can result in complications. To improve care for patients receiving retrievable IVC filters, we developed and evaluated an informatics-based initiative to facilitate patient tracking, clinical decision-making, and care coordination. MATERIALS AND METHODS: A semiautomated filter-tracking application was custom-built to query our radiology information system to extract and transfer key data elements related to IVC filter insertion procedures into a database. A web-based interface displayed key information and facilitated communication between the interventional radiology clinical team and referring physicians. A set of filter management options was provided depending on each patient's clinical condition. The system was launched in April 2016. Using retrospective observational cohort methods, we compared filter retrieval rates during a test period from July through December 2016 with a control period of the same 6 months in 2015. RESULTS: System development required approximately 100 hours of development time. Two hundred ninety-three IVC filter placements and 83 filter retrievals were tracked during the study periods. The overall filter retrieval rate was 23% in the control period and 34% in the test period. Mean times from filter placement to retrieval in the control and test periods were not significantly different (88.9 and 102.7 days, respectively; p = 0.32). CONCLUSION: A semiautomated approach to tracking patients with IVC filters can facilitate care coordination and clinical decision-making for a device with known potential complications. Similar applications designed to improve provider communication and documentation of filter management plans, including appropriateness for retrieval, can be replicated.

Implementation of a Point-of-Care Radiologist-Technologist Communication Tool in a Quality Assurance Program.

OBJECTIVE: We implemented an Image Quality Reporting and Tracking Solution (IQuaRTS), directly linked from the PACS, to improve communication between radiologists and technologists. MATERIALS AND METHODS: IQuaRTS launched in May 2015. We compared MRI issues filed in the period before IQuaRTS implementation (May-September 2014) using a manual system with MRI issues filed in the IQuaRTS period (May-September 2015). The unpaired t test was used for analysis. For assessment of overall results in the IQuaRTS period alone, all issues filed across all modalities were included. Summary statistics and charts were generated using Excel and Tableau. RESULTS: For MRI issues, the number of issues filed during the IQuaRTS period was 498 (2.5% of overall MRI examination volume) compared with 78 issues filed during the period before IQuaRTS implementation (0.4% of total examination volume) (p = 0.0001), representing a 625% relative increase. Tickets that documented excellent work were 8%. Other issues included images not pushed to PACS (20%), film library issues (19%), and documentation or labeling (8%). Of the issues filed, 55% were MRI-related and 25% were CT-related. The issues were stratified across six sites within our institution. Staff requiring additional training could be readily identified, and 80% of the issues were resolved within 72 hours. CONCLUSION: IQuaRTS is a cost-effective online issue reporting tool that enables robust data collection and analytics to be incorporated into quality improvement programs. One limitation of the system is that it must be implemented in an environment where staff are receptive to quality improvement.