Automated selection of abdominal MRI series using a DICOM metadata classifier and selective use of a pixel-based classifier.

Accurate, automated MRI series identification is important for many applications, including display ("hanging") protocols, machine learning, and radiomics. The use of the series description or a pixel-based classifier each has limitations. We demonstrate a combined approach utilizing a DICOM metadata-based classifier and selective use of a pixel-based classifier to identify abdominal MRI series. The metadata classifier was assessed alone as Group metadata and combined with selective use of the pixel-based classifier for predictions with less than 70% certainty (Group combined). The overall accuracy (mean and 95% confidence intervals) for Groups metadata and combined on the test dataset were 0.870 CI (0.824,0.912) and 0.930 CI (0.893,0.963), respectively. With this combined metadata and pixel-based approach, we demonstrate accurate classification of 95% or greater for all pre-contrast MRI series and improved performance for some post-contrast series.

Using Augmented Reality Technology to Optimize Transfacet Lumbar Interbody Fusion: A Case Report.

The transfacet minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF) is a novel approach available for the management of lumbar spondylolisthesis. It avoids the need to manipulate either of the exiting or traversing nerve roots, both protected by the bony boundaries of the approach. With the advancement in operative technologies such as navigation, mapping, segmentation, and augmented reality (AR), surgeons are prompted to utilize these technologies to enhance their surgical outcomes. A 36-year-old male patient was complaining of chronic progressive lower back pain. He was found to have grade 2 L4/5 spondylolisthesis. We studied the feasibility of a trans-Kambin or a transfacet MIS-TLIF, and decided to proceed with the latter given the wider corridor it provides. Preoperative trajectory planning and level segmentation in addition to intraoperative navigation and image merging were all utilized to provide an AR model to guide us through the surgery. The use of AR can build on the safety and learning of novel surgical approaches to spine pathologies. However, larger high-quality studies are needed to further objectively analyze its impact on surgical outcomes and to expand on its application.

Incidence and imaging characteristics of difficult to detect retrospectively identified brain metastases in patients receiving repeat courses of stereotactic radiosurgery.

PURPOSE: During stereotactic radiosurgery (SRS) planning for brain metastases (BM), brain MRIs are reviewed to select appropriate targets based on radiographic characteristics. Some BM are difficult to detect and/or definitively identify and may go untreated initially, only to become apparent on future imaging. We hypothesized that in patients receiving multiple courses of SRS, reviewing the initial planning MRI would reveal early evidence of lesions that developed into metastases requiring SRS. METHODS: Patients undergoing two or more courses of SRS to BM within 6 months between 2016 and 2018 were included in this single-institution, retrospective study. Brain MRIs from the initial course were reviewed for lesions at the same location as subsequently treated metastases; if present, this lesion was classified as a "retrospectively identified metastasis" or RIM. RIMs were subcategorized as meeting or not meeting diagnostic imaging criteria for BM (+ DC or -DC, respectively). RESULTS: Among 683 patients undergoing 923 SRS courses, 98 patients met inclusion criteria. There were 115 repeat courses of SRS, with 345 treated metastases in the subsequent course, 128 of which were associated with RIMs found in a prior MRI. 58% of RIMs were + DC. 17 (15%) of subsequent courses consisted solely of metastases associated with + DC RIMs. CONCLUSION: Radiographic evidence of brain metastases requiring future treatment was occasionally present on brain MRIs from prior SRS treatments. Most RIMs were + DC, and some subsequent SRS courses treated only + DC RIMs. These findings suggest enhanced BM detection might enable earlier treatment and reduce the need for additional SRS.

Using Novel Segmentation Technology to Define Safe Corridors for Minimally Invasive Posterior Lumbar Interbody Fusion.

BACKGROUND AND OBJECTIVES: There has been a rise in minimally invasive methods to access the intervertebral disk space posteriorly given their decreased tissue destruction, lower blood loss, and earlier return to work. Two such options include the percutaneous lumbar interbody fusion through the Kambin triangle and the endoscopic transfacet approach. However, without accurate preoperative visualization, these approaches carry risks of damaging surrounding structures, especially the nerve roots. Using novel segmentation technology, our goal was to analyze the anatomic borders and relative sizes of the safe triangle, trans-Kambin, and the transfacet corridors to assist surgeons in planning a safe approach and determining cannula diameters. METHODS: The areas of the safe triangle, Kambin, and transfacet corridors were measured using commercially available software (BrainLab, Munich, Germany). For each approach, the exiting nerve root, traversing nerve roots, theca, disk, and vertebrae were manually segmented on 3-dimensional T2-SPACE magnetic resonance imaging using a region-growing algorithm. The triangles' borders were delineated ensuring no overlap between the area and the nerves. RESULTS: A total of 11 patients (65.4 ± 12.5 years, 33.3% female) were retrospectively reviewed. The Kambin, safe, and transfacet corridors were measured bilaterally at the operative level. The mean area (124.1 ± 19.7 mm2 vs 83.0 ± 11.7 mm2 vs 49.5 ± 11.4 mm2) and maximum permissible cannula diameter (9.9 ± 0.7 mm vs 6.8 ± 0.5 mm vs 6.05 ± 0.7 mm) for the transfacet triangles were significantly larger than Kambin and the traditional safe triangles, respectively (P < .001). CONCLUSION: We identified, in 3-dimensional, the borders for the transfacet corridor: the traversing nerve root extending inferiorly until the caudal pedicle, the theca medially, and the exiting nerve root superiorly. These results illustrate the utility of preoperatively segmenting anatomic landmarks, specifically the nerve roots, to help guide decision-making when selecting the optimal operative approach.

Duke Liver Dataset: A Publicly Available Liver MRI Dataset with Liver Segmentation Masks and Series Labels.

The Duke Liver Dataset contains 2146 abdominal MRI series from 105 patients, including a majority with cirrhotic features, and 310 image series with corresponding manually segmented liver masks.

Two-Year Clinical and Radiographic Outcomes for Percutaneous Lumbar Interbody Fusion With an Expandable Titanium Cage Through Kambin's Triangle Without Facetectomy.

BACKGROUND: There has been heightened interest in performing percutaneous lumbar interbody fusions (percLIFs) through Kambin's triangle, an anatomic corridor allowing entrance into the disc space. However, due to its novelty, there are limited data regarding the long-term benefits of this procedure. Our objective was to determine the long-term efficacy and durability of the percutaneous insertion of an expandable titanium cage through Kambin's triangle without facetectomy. METHODS: A retrospective review of patients undergoing percLIF via Kambin's triangle using an expandable titanium cage was performed. Demographics, visual analog scale (VAS) scores, Oswestry Disability Index (ODI), radiographic measurements, perioperative variables, and complications were recorded. VAS, ODI, and radiographic measurements were compared with baseline using the generalized estimating equations assuming normally distributed data. Fusion was assessed with computed tomography (CT) at 1 and 2 years after the procedure. RESULTS: A total of 49 patients were included. Spondylolisthesis, lumbar lordosis (LL), sacral slope, pelvic tilt, and anterior/posterior disc space height were all significantly improved postoperatively at each time point of 3, 6, 12, and 24 months (P < 0.001). Pelvic incidence-LL mismatch decreased significantly at each follow-up (P < 0.001) with a mean reduction of 4° by 24 months. VAS back scores reduced by >2 points at the 6, 12, and 24 month follow-ups. ODI scores reduced by >15 points at the 12- and 24-month follow-ups. Of the patients who had 1- and 2-year CT images, fusion rates at those time points were 94.4% (17/18) and 87.5% (7/8), respectively. The mean annual rate of surgically significant adjacent segment disease was 2.74% through an average follow-up of 2.74 years. CONCLUSION: These results highlight that percLIF, a procedure done without an endoscope or facetectomy, can be performed using an expandable titanium cage through Kambin's triangle with excellent radiographic and clinical results. CLINICAL RELEVANCE: percLIF via Kambin's triangle is a safe and succesful procedure with long-term improvements in both clinical and radiographic outcomes.

Novel Approach to Percutaneous Lumbar Surgeries via Kambin's Triangle-Radiographic and Surgical Planning Analysis with Nerve Segmentation Technology.

OBJECTIVE: While Kambin's Triangle has become an ever more important anatomic window given its proximity to the exiting nerve root, there have been limited studies examining the effect of disease on the corridor. Our goal was to better understand how pathology can affect Kambin's Triangle, thereby altering the laterality of approach for percutaneous lumbar interbody fusion (percLIF). METHODS: The authors performed a single-center retrospective review of patients evaluated for percLIF. The areas of Kambin's Triangle were measured without and with nerve segmentation. For the latter, the lumbosacral nerve roots on 3-dimensional T2 magnetic resonance imaging were manually segmented. Next, the borders of Kambin's Triangle were delineated, ensuring no overlap between the area and nerve above. RESULTS: Fifteen patients (67.5 ± 9.7 years, 46.7% female) were retrospectively reviewed. We measured 150 Kambin's Triangles. The mean areas from L1-S1 were 50.0 ± 12.3 mm2, 73.8 ± 12.5 mm2, 83.8 ± 12.2 mm2, 88.5 ± 19.0 mm2, and 116 ± 29.3 mm2, respectively. When pathology was present, the areas significantly decreased at L4-L5 (P = 0.046) and L5-S1 (P = 0.049). Higher spondylolisthesis and smaller posterior disk heights were linked with decreased areas via linear regression analysis (P < 0.05). When nerve segmentation was used, the areas were significantly smaller from L1-L5 (P < 0.05). Among 11 patients who underwent surgery, none suffered from postoperative neuropathies. CONCLUSIONS: These results illustrate the feasibility of preoperatively segmenting lumbosacral nerves and measuring Kambin's Triangle to help guide surgical planning and determine the ideal laterality of approach for percLIF.

Systematic Analysis of Common Factors Impacting Deep Learning Model Generalizability in Liver Segmentation.

Purpose: To investigate the effect of training data type on generalizability of deep learning liver segmentation models. Materials and Methods: This Health Insurance Portability and Accountability Act-compliant retrospective study included 860 MRI and CT abdominal scans obtained between February 2013 and March 2018 and 210 volumes from public datasets. Five single-source models were trained on 100 scans each of T1-weighted fat-suppressed portal venous (dynportal), T1-weighted fat-suppressed precontrast (dynpre), proton density opposed-phase (opposed), single-shot fast spin-echo (ssfse), and T1-weighted non-fat-suppressed (t1nfs) sequence types. A sixth multisource (DeepAll) model was trained on 100 scans consisting of 20 randomly selected scans from each of the five source domains. All models were tested against 18 target domains from unseen vendors, MRI types, and modality (CT). The Dice-Sørensen coefficient (DSC) was used to quantify similarity between manual and model segmentations. Results: Single-source model performance did not degrade significantly against unseen vendor data. Models trained on T1-weighted dynamic data generally performed well on other T1-weighted dynamic data (DSC = 0.848 ± 0.183 [SD]). The opposed model generalized moderately well to all unseen MRI types (DSC = 0.703 ± 0.229). The ssfse model failed to generalize well to any other MRI type (DSC = 0.089 ± 0.153). Dynamic and opposed models generalized moderately well to CT data (DSC = 0.744 ± 0.206), whereas other single-source models performed poorly (DSC = 0.181 ± 0.192). The DeepAll model generalized well across vendor, modality, and MRI type and against externally sourced data. Conclusion: Domain shift in liver segmentation appears to be tied to variations in soft-tissue contrast and can be effectively bridged with diversification of soft-tissue representation in training data.Keywords: Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Supervised Learning, CT, MRI, Liver Segmentation Supplemental material is available for this article. © RSNA, 2023.

Novel Merging of CT and MRI to Allow for Safe Navigation into Kambin's Triangle for Percutaneous Lumbar Interbody Fusion-Initial Case Series Investigating Safety and Efficacy.

BACKGROUND: For percutaneous lumbar fusion (percLIF), magnetic resonance imaging and computed tomography are critical to defining surgical corridors. Currently, these scans are performed separately, and surgeons then use fluoroscopy or neuromonitoring to guide instruments through Kambin's triangle. However, anatomic variations and intraoperative positional changes are possible, meaning that safely accessing Kambin's triangle remains a challenge because nerveroot visualization without endoscopes has not been thoroughly described. OBJECTIVE: To overcome the known challenges of percLIF and reduce the likelihood of iatrogenic injuries by showing real-time locations of neural and bony anatomy. METHODS: The authors demonstrate an intraoperative navigational platform that applies nerve root segmentation and image fusion to assist with percLIF. Five patients from a single institution were included. RESULTS: Of the 5 patients, the mean age was 71 ± 8 years and 3 patients (60%) were female. One patient had general anesthesia while the remaining 4 patients underwent awake surgery with spinal anesthesia. The mean area for the L4-L5 Kambin's triangle was 76.1 ± 14.5 mm 2 . A case example is shown where the side of approach was based on the fact that Kambin's triangle was larger on one side compared with the other. The mean operative time was 170 ± 17 minutes, the mean blood loss was 32 ± 16 mL, and the mean hospital length of stay was 19.6 ± 8.3 hours. No patients developed postoperative complications. CONCLUSION: This case series demonstrates the successful and safe application of nerve segmentation using magnetic resonance imaging/computed tomography fusion to perform percLIF and provide positive patient outcomes.

Head CT deep learning model is highly accurate for early infarct estimation.

Non-contrast head CT (NCCT) is extremely insensitive for early (< 3-6 h) acute infarct identification. We developed a deep learning model that detects and delineates suspected early acute infarcts on NCCT, using diffusion MRI as ground truth (3566 NCCT/MRI training patient pairs). The model substantially outperformed 3 expert neuroradiologists on a test set of 150 CT scans of patients who were potential candidates for thrombectomy (60 stroke-negative, 90 stroke-positive middle cerebral artery territory only infarcts), with sensitivity 96% (specificity 72%) for the model versus 61-66% (specificity 90-92%) for the experts; model infarct volume estimates also strongly correlated with those of diffusion MRI (r2 > 0.98). When this 150 CT test set was expanded to include a total of 364 CT scans with a more heterogeneous distribution of infarct locations (94 stroke-negative, 270 stroke-positive mixed territory infarcts), model sensitivity was 97%, specificity 99%, for detection of infarcts larger than the 70 mL volume threshold used for patient selection in several major randomized controlled trials of thrombectomy treatment.

How dimensions can guide surgical planning and training: a systematic review of Kambin's triangle.

OBJECTIVE: The authors sought to analyze the current literature to determine dimensional trends across the lumbar levels of Kambin's triangle, clarify the role of imaging techniques for preoperative planning, and understand the effect of inclusion of the superior articular process (SAP). This compiled knowledge of the triangle is needed to perform successful procedures, reduce nerve root injuries, and help guide surgeons in training. METHODS: The authors performed a search of multiple databases using combinations of keywords: Kambin's triangle, size, measurement, safe triangle, and bony triangle. Articles were included if their main findings included measurement of Kambin's triangle. The PubMed, Scopus, Ovid, Cochrane, Embase, and Medline databases were systematically searched for English-language articles with no time frame restrictions through July 2022. RESULTS: Eight studies comprising 132 patients or cadavers were included in the study. The mean ± SD age was 66.69 ± 9.6 years, and 53% of patients were male. Overall, the size of Kambin's triangle increased in area moving down vertebral levels, with L5-S1 being the largest (133.59 ± 4.36 mm2). This trend followed a linear regression model when SAP was kept (p = 0.008) and removed (p = 0.003). There was also a considerable increase in the size of Kambin's triangle if the SAP was removed. CONCLUSIONS: Here, the authors have provided the first reported systematic review of the literature of Kambin's triangle, its measurements at each lumbar level, and key areas of debate related to the definition of the working safe zone. These findings indicate that CT is heavily utilized for imaging of the safe zone, the area of Kambin's triangle tends to increase caudally, and variation exists between patients. Future studies should focus on using advanced imaging techniques for preoperative planning and establishing guidelines for surgeons.

A Deep Learning-Based Computer Aided Detection (CAD) System for Difficult-to-Detect Brain Metastases.

PURPOSE: We sought to develop a computer-aided detection (CAD) system that optimally augments human performance, excelling especially at identifying small inconspicuous brain metastases (BMs), by training a convolutional neural network on a unique magnetic resonance imaging (MRI) data set containing subtle BMs that were not detected prospectively during routine clinical care. METHODS AND MATERIALS: Patients receiving stereotactic radiosurgery (SRS) for BMs at our institution from 2016 to 2018 without prior brain-directed therapy or small cell histology were eligible. For patients who underwent 2 consecutive courses of SRS, treatment planning MRIs from their initial course were reviewed for radiographic evidence of an emerging metastasis at the same location as metastases treated in their second SRS course. If present, these previously unidentified lesions were contoured and categorized as retrospectively identified metastases (RIMs). RIMs were further subcategorized according to whether they did (+DC) or did not (-DC) meet diagnostic imaging-based criteria to definitively classify them as metastases based upon their appearance in the initial MRI alone. Prospectively identified metastases (PIMs) from these patients, and from patients who only underwent a single course of SRS, were also included. An open-source convolutional neural network architecture was adapted and trained to detect both RIMs and PIMs on thin-slice, contrast-enhanced, spoiled gradient echo MRIs. Patients were randomized into 5 groups: 4 for training/cross-validation and 1 for testing. RESULTS: One hundred thirty-five patients with 563 metastases, including 72 RIMS, met criteria. For the test group, CAD sensitivity was 94% for PIMs, 80% for +DC RIMs, and 79% for PIMs and +DC RIMs with diameter <3 mm, with a median of 2 false positives per patient and a Dice coefficient of 0.79. CONCLUSIONS: Our CAD model, trained on a novel data set and using a single common MR sequence, demonstrated high sensitivity and specificity overall, outperforming published CAD results for small metastases and RIMs - the lesion types most in need of human performance augmentation.

Implementation of Clinical Artificial Intelligence in Radiology: Who Decides and How?

As the role of artificial intelligence (AI) in clinical practice evolves, governance structures oversee the implementation, maintenance, and monitoring of clinical AI algorithms to enhance quality, manage resources, and ensure patient safety. In this article, a framework is established for the infrastructure required for clinical AI implementation and presents a road map for governance. The road map answers four key questions: Who decides which tools to implement? What factors should be considered when assessing an application for implementation? How should applications be implemented in clinical practice? Finally, how should tools be monitored and maintained after clinical implementation? Among the many challenges for the implementation of AI in clinical practice, devising flexible governance structures that can quickly adapt to a changing environment will be essential to ensure quality patient care and practice improvement objectives.

Imaging AI in Practice: A Demonstration of Future Workflow Using Integration Standards.

Artificial intelligence (AI) tools are rapidly being developed for radiology and other clinical areas. These tools have the potential to dramatically change clinical practice; however, for these tools to be usable and function as intended, they must be integrated into existing radiology systems. In a collaborative effort between the Radiological Society of North America, radiologists, and imaging-focused vendors, the Imaging AI in Practice (IAIP) demonstrations were developed to show how AI tools can generate, consume, and present results throughout the radiology workflow in a simulated clinical environment. The IAIP demonstrations highlight the critical importance of semantic and interoperability standards, as well as orchestration profiles for successful clinical integration of radiology AI tools. Keywords: Computer Applications-General (Informatics), Technology Assessment © RSNA, 2021.

Robotic-Assisted Trajectory Into Kambin's Triangle During Percutaneous Transforaminal Lumbar Interbody Fusion-Initial Case Series Investigating Safety and Efficacy.

BACKGROUND: Minimally invasive spine surgery (MISS) has the potential to further advance with the use of robot-assisted (RA) techniques. While RA pedicle screw placement has been extensively investigated, there is a lack of literature on the use of the robot for other tasks, such as accessing Kambin's triangle in percutaneous lumbar interbody fusion (percLIF). OBJECTIVE: To characterize the surgical feasibility and preliminary outcomes of an initial case series of 10 patients receiving percLIF with RA cage placement via Kambin's triangle. METHODS: We performed a single-center, retrospective review of patients undergoing RA percLIF using robot-guided trajectory to access Kambin's triangle for cage placement. Patients undergoing RA percLIF were eligible for enrollment. Baseline health and demographic information in addition to peri- and postoperative data was collected. The dimensions of each patient's Kambin's triangle were measured. RESULTS: Ten patients and 11 levels with spondylolisthesis were retrospectively reviewed. All patients successfully underwent the planned procedure without perioperative complications. Four patients underwent their procedure with awake anesthesia. The average dimension of Kambin's triangle was 66.3 m2. With the exception of 1 patient who stayed in the hospital for 7 d, the average length of stay was 1.2 d, with 2 patients discharged the day of surgery. No patients suffered postoperative motor or sensory deficits. Spinopelvic parameters and anterior and posterior disc heights were improved with surgery. CONCLUSION: As MISS continues to evolve, further exploration of robot-guided surgical practice, such as our technique, will lead to creative solutions to challenging anatomical variation and overall improved patient care.

Natural Language Processing of Radiology Text Reports: Interactive Text Classification.

This report presents a hands-on introduction to natural language processing (NLP) of radiology reports with deep neural networks in Google Colaboratory (Colab) to introduce readers to the rapidly evolving field of NLP. The implementation of the Google Colab notebook was designed with code hidden to facilitate learning for noncoders (ie, individuals with little or no computer programming experience). The data used for this module are the corpus of radiology reports from the Indiana University chest x-ray collection available from the National Library of Medicine's Open-I service. The module guides learners through the process of exploring the data, splitting the data for model training and testing, preparing the data for NLP analysis, and training a deep NLP model to classify the reports as normal or abnormal. Concepts in NLP, such as tokenization, numericalization, language modeling, and word embeddings, are demonstrated in the module. The module is implemented in a guided fashion with the authors presenting the material and explaining concepts. Interactive features and extensive text commentary are provided directly in the notebook to facilitate self-guided learning and experimentation with the module. Keywords: Neural Networks, Negative Expression Recognition, Natural Language Processing, Computer Applications, Informatics © RSNA, 2021.

A Conference-Friendly, Hands-on Introduction to Deep Learning for Radiology Trainees.

Artificial or augmented intelligence, machine learning, and deep learning will be an increasingly important part of clinical practice for the next generation of radiologists. It is therefore critical that radiology residents develop a practical understanding of deep learning in medical imaging. Certain aspects of deep learning are not intuitive and may be better understood through hands-on experience; however, the technical requirements for setting up a programming and computing environment for deep learning can pose a high barrier to entry for individuals with limited experience in computer programming and limited access to GPU-accelerated computing. To address these concerns, we implemented an introductory module for deep learning in medical imaging within a self-contained, web-hosted development environment. Our initial experience established the feasibility of guiding radiology trainees through the module within a 45-min period typical of educational conferences.

The Composite Severity Score for Lumbar Spine MRI: a Metric of Cumulative Degenerative Disease Predicts Time Spent on Interpretation and Reporting.

Conventional measures of radiologist efficiency, such as the relative value unit, fail to account for variations in the complexity and difficulty of a given study. For lumbar spine MRI (LMRI), an ideal performance metric should account for the global severity of lumbar degenerative disease (LSDD) which may influence reporting time (RT), thereby affecting clinical productivity. This study aims to derive a global LSDD metric and estimate its effect on RT. A 10-year archive of LMRI reports comprising 13,388 exams was reviewed. Objective reporting timestamps were used to calculate RT. A natural language processing (NLP) tool was used to extract radiologist-assigned stenosis severity using a 6-point scale (0 = "normal" to 5 = "severe") at each lumbar level. The composite severity score (CSS) was calculated as the sum of each of 18 stenosis grades. The predictive values of CSS, sex, age, radiologist identity, and referring service on RT were examined with multiple regression models. The NLP tool accurately classified LSDD in 94.8% of cases in a validation set. The CSS increased with patient age and differed between men and women. In a univariable model, CSS was a significant predictor of mean RT (R2 = 0.38, p < 0.001) and independent predictor of mean RT (p < 0.001) controlling for patient sex, patient age, service location, and interpreting radiologist. The predictive strength of CSS was stronger for the low CSS range (CSS = 0-25, R2 = 0.83, p < 0.001) compared to higher CSS values (CSS > 25, R2 = 0.15, p = 0.05). Individual radiologist study volume was negatively correlated with mean RT (Pearson's R = - 0.35, p < 0.001). The composite severity score predicts radiologist reporting efficiency in LMRI, providing a quantitative measure of case complexity which may be useful for workflow planning and performance evaluation.