Piriformis syndrome is a pain syndrome originating in the buttock and is attributed to 6% – 8% of patients referred for the treatment of back and leg pain. The treatment for piriformis syndrome using fluoroscopy, computed tomography (CT), electromyography (EMG), and ultrasound (US) has become standard practice. The treatment of Piriformis Syndrome has evolved to include fluoroscopy and EMG with CT guidance. We present a case study of 5 successful piriformis injections using 3-D computer-assisted electromagnet needle tracking coupled with ultrasound. A 6-degree of freedom electromagnetic position tracker was attached to the ultrasound probe that allowed the system to detect the position and orientation of the probe in the magnetic field. The tracked ultrasound probe was used to find the posterior superior iliac spine. Subsequently, 3 points were captured to register the ultrasound image with the CT or magnetic resonance image scan. Moreover, after the registration was obtained, the navigation system visualized the tracked needle relative to the CT scan in real-time using 2 orthogonal multi-planar reconstructions centered at the tracked needle tip. Conversely, a recent study revealed that fluoroscopically guided injections had 30% accuracy compared to ultrasound guided injections, which tripled the accuracy percentage. This novel technique exhibited an accurate needle guidance injection precision of 98% while advancing to the piriformis muscle and avoiding the sciatic nerve. The mean (± SD) procedure time was 19.08 (± 4.9) minutes. This technique allows for electromagnetic instrument tip tracking with realtime 3-D guidance to the selected target. As with any new technique, a learning curve is expected; however, this technique could offer an alternative, minimizing radiation exposure. Key words: Piriformis, electromagnetic, ultrasound, fluoroscopy, injection, 3-D imaging.
Effective Use of Accessory Radiation Shielding Devices in Fluoroscopy
Abstract Background: Impact of recurrent pericarditis (RP) on patient health-related quality of life (HRQoL) was evaluated through qualitative patient interviews and as an exploratory endpoint in a Phase 2 trial evaluating the efficacy and safety of rilonacept (IL-1α/IL-1β blocker) to treat RP.Methods: Qualitative interviews were conducted with ten adults with RP to understand symptoms and HRQoL impacts, and the 10-item Patient-Reported Outcomes Measurement Information System Global Health (PROMIS Global) v1.2 was evaluated to determine questionnaire coverage of patient experience. The Phase 2 trial enrolled participants with active symptomatic RP (A-RP, n=16) and corticosteroid-dependent participants with no active recurrence at baseline (CSD-RP, n=9). All participants received rilonacept weekly for 6 weeks during a base treatment period (TP) plus an optional 18-week extension period (EP). Concomitant medications, including corticosteroids (CS), were tapered, if possible, during EP. HRQoL was assessed using the PROMIS Global, and patient-reported pain and blood levels of c-reactive protein (CRP) were also collected at Baseline and follow-up periods. Results: Information from qualitative interviews demonstrated that PROMIS GH concepts are relevant to adults with RP. From the Phase 2 trial, both participant groups showed impacted HRQoL at Baseline [mean PROMIS Global Physical Health (GPH) and Global Mental Health (GMH), were lower than population norm average]. In A-RP, GPH/MPH improved by end of base TP and were sustained through EP (similar trends were observed for pain and CRP). Similarly, in CSD-RP, GPH/MPH improved by end of TP and further improved at EP, during CS tapering or discontinuation, without disease recurrence (low pain scores and CRP levels continued during the TP and EP). Conclusion: This is the first study demonstrating impaired HRQoL in RP. Rilonacept treatment was associated with HRQoL improvements using PROMIS GH scores. Maintained/improved HRQoL during tapering/withdrawal of CS without recurrence suggests that rilonacept may provide an alternative to corticosteroids. Trial Registration: ClinicalTrials.Gov; NCT03980522; 5 June 2019, retrospectively registered; https://clinicaltrials.gov/ct2/show/NCT03980522
Randomized Phase II Trial of Polyphenon E versus Placebo in Patients at High Risk of Recurrent Colonic Neoplasia
Abstract Polyphenon E (Poly E) is a green tea polyphenol preparation whose most active component is epigallocatechin gallate (EGCG). We studied the cancer preventive efficacy and safety of Poly E in subjects with rectal aberrant crypt foci (ACF), which represent putative precursors of colorectal cancers. Eligible subjects had prior colorectal advanced adenomas or cancers, and had ≥5 rectal ACF at a preregistration chromoendoscopy. Subjects (N = 39) were randomized to 6 months of oral Poly E (780 mg EGCG) daily or placebo. Baseline characteristics were similar by treatment arm (all P >0.41); 32 of 39 (82%) subjects completed 6 months of treatment. The primary endpoint was percent reduction in rectal ACF at chromoendoscopy comparing before and after treatment. Among 32 subjects (15 Poly E, 17 placebo), percent change in rectal ACF number (baseline vs. 6 months) did not differ significantly between study arms (3.7% difference of means; P = 0.28); total ACF burden was also similar (−2.3% difference of means; P = 0.83). Adenoma recurrence rates at 6 months were similar by arm (P > 0.35). Total drug received did not differ significantly by study arm; 31 (79%) subjects received ≥70% of prescribed Poly E. Poly E was well tolerated and adverse events (AE) did not differ significantly by arm. One subject on placebo had two grade 3 AEs; one subject had grade 2 hepatic transaminase elevations attributed to treatment. In conclusion, Poly E for 6 months did not significantly reduce rectal ACF number relative to placebo. Poly E was well tolerated and without significant toxicity at the dose studied. Prevention Relevance: We report a chemoprevention trial of polyphenon E in subjects at high risk of colorectal cancer. The results show that polyphenon E was well tolerated, but did not significantly reduce the number of rectal aberrant crypt foci, a surrogate endpoint biomarker of colorectal cancer.
Aneurysmal Bone Cysts of the Paranasal Sinuses: The Mayo Clinic Experience and Review of the Literature
Objective/HypothesisAneurysmal bone cysts (ABCs) are benign, lytic bone lesions, which rarely present in the paranasal sinuses. There is no published consensus on the appropriate diagnostic or treatment approach. Our objective was to elucidate the clinical behavior, treatment, and outcomes for patients with ABCs of the paranasal sinuses (psABCs).Study DesignRetrospective case series and system review of the literature.MethodsA retrospective chart review was performed to identify patients evaluated at the authors' institution with psABC and consolidated with literature reports of psABC.ResultsEighty‐nine patients met inclusion criteria. The most common presenting symptom was painless facial swelling (n = 35, 39%). The ethmoid sinuses were the most common site involved (n = 55, 62%). Surgical approach was reported in 74 cases including 20 endoscopic and 54 with an open or combined approach. Fifty‐nine patients (71%) underwent gross total resection. Follow up data was reported for 67 patients. Fifteen patients (22%) were found to have recurrence or progression at follow up; 10/15 (66%) patients within the first 12 months, 14/15 (93%) within the first 24 months, and 1/15 (7%) greater than 24 months after treatment. Patients were more likely to have recurrence/progression if they presented with nasal discharge (P = .05), proptosis (P = .01), or orbital involvement (P = .03).ConclusionspsABCs typically present with painless swelling or nasal obstruction. Orbital involvement is a negative prognostic indicator with these patients more likely to have recurrence after treatment. Recurrence or progression of disease is most likely to occur within 2 years after treatment. Therefore, patients should be monitored closely during this time.Level of Evidence4 Laryngoscope, 131:E2525–E2533, 2021
Racial Disparities in Diagnosis of Attention-Deficit/Hyperactivity Disorder in a US National Birth Cohort
Abstract PO-084: Automated detection of pancreatic ductal adenocarcinoma (PDAC) on CT scans using artificial intelligence (AI): Impact of inclusion of automated pancreas segmentation on the accuracy of 3D-convolutional neural network (CNN)
Abstract Purpose: Around 30% of PDAC less than 2-cm tend to go undetected on CT due to their subtle imaging signatures. Automated detection of PDAC using AI represents an opportunity to augment physician expertise and to improve outcomes through early detection of PDAC. Our purpose was to develop a 3D-CNN for fully automated detection of PDAC and to further evaluate the impact of inclusion of pancreas segmentation on the accuracy of this 3D-CNN. Methods: A Medical Imaging Data Readiness Scale (MIDaR) level A dataset (portal venous phase CTs, slice thickness ≤ 3.75 mm) of 466 treatment-naïve biopsy-proven PDAC and 1994 subjects with normal pancreas was created after exclusion of CTs with suboptimal image quality or biliary stents. Volumetric pancreas and tumor segmentations on CTs were done by two radiologists using 3D Slicer. A total of 370 CTs with PDAC and 370 CTs with normal pancreas were randomly selected for separate training and validation sets, and 396 CTs (96 CTs with PDAC and 300 CTs with normal pancreas) were utilized for testing. Two separate 3D-CNNs were trained. A three-stage bounding-box-only model (A): stage 1 was based on a UNET-like architecture and localized the pancreas on CT with a bounding box; stage 2 utilized an Inception ResNet architecture and classified each slice through the pancreas into PDAC vs. normal; and stage 3 utilized the output of stage 2 to generate final classification for a given CT. Conversely, a four-stage pancreas segmentation-based model (B) included stage 1 of model A followed by an additional stage of automated pancreas and tumor segmentation (stage 2), classification of each slice through the pancreas into PDAC vs. normal (stage 3) and, finally, generation of final classification score (stage 4) for a given CT. Area under the receiver operating characteristic curve (AUROC) of the two models were compared on the test set. Results: Mean (SD) PDAC diameter in the test set was 1.1 (0.43) cm. Model A (three-stage bounding-box-only) correctly classified 305 (77%) out of 396 CTs from the test set into PDAC vs. normal. It incorrectly classified 12/96 (12.5%) CTs with PDAC as normal and 79/300 (26%) normal CTs as PDAC. AUROC for model A was 0.85. Model B (four-stage pancreas segmentation-based) correctly classified 351 (88%) out of 396 CTs. It incorrectly classified 13/96 (13.5%) CTs with PDAC as normal and 32/300 (10.7%) normal CTs as PDAC. AUROC for model B was 0.94. AUROC for model B was significantly higher than model A (p<0.005). Conclusion: A 3D-CNN can detect small PDAC with high accuracy using automated localization of pancreas with a bounding box without relying on separate pancreas segmentation. Inclusion of an additional automated pancreas segmentation step reduced false positives with consequent incremental gain in the model’s accuracy. Prospective validation and subsequent integration of such models into clinical workflows has the potential to reduce inadvertent errors in detection of subtle or small PDAC on standard-of-care CT scans. Citation Format: Anurima Patra, Korfiatis Panagiotis, Garima Suman, Ananya Panda, Sushil Kumar Garg, Ajit Goenka. Automated detection of pancreatic ductal adenocarcinoma (PDAC) on CT scans using artificial intelligence (AI): Impact of inclusion of automated pancreas segmentation on the accuracy of 3D-convolutional neural network (CNN) [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-084.
Abstract PO-050: Identifying de novo stage IV breast cancer (DNIV) cases in Electronic Health Records (EHR) using natural language processing
Abstract Background: DNIV accounts for 6%–10% of newly diagnosed breast cancer cases. Despite widespread mammography screening, its incidence is increasing in the United States and survival of this disease has only modestly improved since the late 1970s. As patient data accumulates in EHR, it’s promising to generate practice-based evidence through utilization of observational data sources. However, assembly of a DNIV cohort based on EHR data is challenging, as key pathologic and staging information are stored in unstructured clinical narratives and not available as structured data. In this study, we developed a rule-based algorithm to phenotype DNIV using natural language processing (NLP) techniques, and implemented the algorithm on our institutional EHR to extract potential DNIV cases. Methods and Results: We defined DNIV as those with either (1) M1 disease identified at time of initial presentation or M1 disease identified within 4 months after definitive surgery. We first developed a reference case list of DNIV verified by physician chart review of the EHR. We next refined the algorithm on a training dataset containing 51 positive and 38 negative reference cases. Next we tested the performance on the testing data containing 23 positive and 55 negative cases. The phenotyping algorithm identified key data elements using NLP, i.e., stage IV breast cancer, definitive surgery, stage 0-III, recurrent breast cancer and associated dates. To identify DNIV cases, phenotyping algorithm integrated temporal relations among the key data elements. The following steps were conducted in the following sequential order: (1) Identification of patients with breast cancer diagnosis using ICD-9 and ICD-10 codes. (2) Patients are positive cases if there are explicit mentions that delineate DNIV from recurrent metastatic breast cancer, such as “de novo stage IV” or “primary intact” detected by NLP at time of diagnosis. (3) Otherwise, patients with definitive surgery are selected if stage IV was within 5 years before definitive surgery or within 4 months after definitive surgery, along with patients with stage IV but without definitive surgery. (4) We further excluded patients with stage 0-III detected within 5 years after stage IV. (5) We further excluded patients with recurrent breast cancer detected before or at time of detection of stage IV. The remaining patients were left as positive cases. Precision of the algorithm was 70%, recall was 87% and F1, the weighted average of precision and recall, was 77%. We implemented our algorithm to interrogate 10 million clinical documents in a cohort of 56,548 patients with breast cancer diagnosis codes who presented to our institution between 2004 and 2018 and had research authorization. We identified 1918 potential DNIV cases. Conclusion: Our future focus is on algorithm refinement. An algorithm-generated cohort could serve as a data source for further study on outcomes related to DNIV and ideally as automated data abstractor and staging process. Citation Format: Liwei Wang, Karthik Giridhar, Kimberly Corbin, Brenda Ernst, Sadia Choudhery, Emmanuel Gabriel, Feichen Shen, Hongfang Liu, James Jakub. Identifying de novo stage IV breast cancer (DNIV) cases in Electronic Health Records (EHR) using natural language processing [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-050.
Abstract PO-023: Differentiation of tumefactive multiple sclerosis and glioblastoma using radiomics features extracted from magnetic resonance imaging and machine learning
Abstract Introduction Tumefactive multiple sclerosis (MS) and glioblastoma (GBM) can be difficult to differentiate. Clinical presentations are nonspecific and may occur in patients with both diseases. Magnetic resonance imaging (MRI) scans are routinely used to generate an initial differential diagnosis. Although imaging features can help distinguish these entities, there are no pathognomonic signs, neither on traditional nor advanced MRI. Moreover, the ability to differentiate these entities depends on the radiologists’ experience. Ensuring the correct diagnosis has important therapeutic and prognostic implications, as the management of these diseases is very different. To date, a brain biopsy often represents the only option to obtain a diagnosis, but it may be inconclusive and could add unnecessary morbidity. We hypothesize that a machine-learning tool based on routinely performed MRI scans could guarantee a more reliable, fast, and reproducible diagnosis. Methods Only patients with a histological diagnosis were included in the study. Patients that underwent any form of radiation therapy before the surgery were excluded to avoid confounding factors due to treatment-related effects. A total of 99 MS and 257 GBMs were included, and preoperative T2-weighted images were collected. For each patient, the lesions' segmentation was performed, including both the contrast-enhancing and non-enhancing areas of the lesions. The segmentation masks were used to extract radiomic features from the T2-weighted sequences. All MRI images were standardized to the same mean and standard deviation before feature extraction and resampled to a voxel size of 1.0 × 1.0 × 1.0 mm. Features extraction was performed using Pyradiomics (v. 3.0.1) and included first order, shape, and texture features, totaling 100 features. The classifier consisted of a support vector machine (SVM) model. Patients were randomly assigned to the training and test sets with an 80-20% proportion for each class. To select the best hyperparameters for the SVM classifier, a grid-search analysis was performed on the training set using a nested cross-validation scheme (k=5). All experiments were performed using Python (v. 3.5) and the Scikit-learn library (v. 0.23.1). Results The mean accuracy and area under the ROC curve for the best set of hyperparameters on the validation set were 0.83 and 0.86, respectively. The weighted-average precision, recall, and F1 scores on the test set were 0.78, 0.76, and 0.77, respectively. Conclusions Radiomic features extracted from a routinely acquired MRI sequence showed promising results in differentiating tumefactive multiple sclerosis from glioblastoma, opening the possibility to obtain a reliable diagnosis without the need for a brain biopsy. Future experiments Future experiments will focus on using post-contrast T1-weighted images for the radiomic features extractions, testing multiple machine learning models and features selection algorithms, and including more diagnostic classes (i.e., metastasis, lymphomas). Citation Format: Gian Marco Conte, Jeanette E. Eckel-Passow, W. Oliver Tobin, Paul Decker, Daniel H. Lachance, Robert B. Jenkins, Bradley J. Erickson. Differentiation of tumefactive multiple sclerosis and glioblastoma using radiomics features extracted from magnetic resonance imaging and machine learning [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-023.