Predicting Mental Decline Rates in Mild Cognitive Impairment From Baseline MRI Volumetric Data.

PURPOSE: In mild cognitive impairment (MCI), identifying individuals at high risk for progressive cognitive deterioration can be useful for prognostication and intervention. This study quantitatively characterizes cognitive decline rates in MCI and tests whether volumetric data from baseline magnetic resonance imaging (MRI) can predict accelerated cognitive decline. METHODS: The authors retrospectively examined Alzheimer Disease Neuroimaging Initiative data to obtain serial Mini-Mental Status Exam (MMSE) scores, diagnoses, and the following baseline MRI volumes: total intracranial volume, whole-brain and ventricular volumes, and volumes of the hippocampus, entorhinal cortex, fusiform gyrus, and medial temporal lobe. Subjects with <24 months or <4 measurements of MMSE data were excluded. Predictive modeling of fast cognitive decline (defined as >0.6/year) from baseline volumetric data was performed on subjects with MCI using a single hidden layer neural network. RESULTS: Among 698 baseline MCI subjects, the median annual decline in the MMSE score was 1.3 for converters to dementia versus 0.11 for stable MCI (P<0.001). A 0.6/year threshold captured dementia conversion with 82% accuracy (sensitivity 79%, specificity 85%, area under the receiver operating characteristic curve 0.88). Regional volumes on baseline MRI predicted fast cognitive decline with a test accuracy of 71%. DISCUSSION: An MMSE score decrease of >0.6/year is associated with MCI-to-dementia conversion and can be predicted from baseline MRI.

Pre-deployment assessment of an AI model to assist radiologists in chest X-ray detection and identification of lead-less implanted electronic devices for pre-MRI safety screening: realized implementation needs and proposed operational solutions.

Purpose: Chest X-ray (CXR) use in pre-MRI safety screening, such as for lead-less implanted electronic device (LLIED) recognition, is common. To assist CXR interpretation, we "pre-deployed" an artificial intelligence (AI) model to assess (1) accuracies in LLIED-type (and consequently safety-level) identification, (2) safety implications of LLIED nondetections or misidentifications, (3) infrastructural or workflow requirements, and (4) demands related to model adaptation to real-world conditions. Approach: A two-tier cascading methodology for LLIED detection/localization and identification on a frontal CXR was applied to evaluate the performance of the original nine-class AI model. With the unexpected early appearance of LLIED types during simulated real-world trialing, retraining of a newer 12-class version preceded retrialing. A zero footprint (ZF) graphical user interface (GUI)/viewer with DICOM-based output was developed for inference-result display and adjudication, supporting end-user engagement and model continuous learning and/or modernization. Results: During model testing or trialing using both the nine-class and 12-class models, robust detection/localization was consistently 100%, with mAP 0.99 from fivefold cross-validation. Safety-level categorization was high during both testing ( AUC ≥ 0.98 and ≥ 0.99 , respectively) and trialing (accuracy 98% and 97%, respectively). LLIED-type identifications by the two models during testing (1) were 98.9% and 99.5% overall correct and (2) consistently showed AUC ≥ 0.92 (1.00 for 8/9 and 9/12 LLIED-types, respectively). Pre-deployment trialing of both models demonstrated overall type-identification accuracies of 94.5% and 95%, respectively. Of the small number of misidentifications, none involved MRI-stringently conditional or MRI-unsafe types of LLIEDs. Optimized ZF GUI/viewer operations led to greater user-friendliness for radiologist engagement. Conclusions: Our LLIED-related AI methodology supports (1) 100% detection sensitivity, (2) high identification (including MRI-safety) accuracy, and (3) future model deployment with facilitated inference-result display and adjudication for ongoing model adaptation to future real-world experiences.

A Pilot Randomized Trial of Transdermal Nicotine for Pulmonary Sarcoidosis.

BACKGROUND: Tobacco smoking is associated with a reduced risk of developing sarcoidosis, and we previously reported that nicotine normalizes immune responses to environmental antigens in patients with active pulmonary sarcoidosis. The effects of nicotine on the progression of pulmonary sarcoidosis are unknown. RESEARCH QUESTION: Is nicotine treatment well tolerated, and will it improve lung function in patients with active pulmonary sarcoidosis? STUDY DESIGN AND METHODS: With local institutional review board approval, a randomized, double-blind, controlled pilot trial was conducted of daily nicotine transdermal patch treatment (21 mg daily) or placebo patch use for 24 weeks. The Ohio State University Wexner Medical Center and Cleveland Clinic enrolled 50 consecutive subjects aged ≥ 18 years with active pulmonary sarcoidosis, based on symptoms (ie, dyspnea, cough) and objective radiographic evidence of infiltrates consistent with nonfibrotic lung disease. Each study group was compared at 26 weeks based on repeated measures of FVC, FEV1, quantitative lung texture score based on CT texture analysis, Fatigue Assessment Score (FAS), St. George's Respiratory Questionnaire (SGRQ), and the Sarcoidosis Assessment Tool. RESULTS: Nicotine treatment was associated with a clinically significant, approximately 2.1% (70 mL) improvement in FVC from baseline to 26 weeks. FVC decreased by a similar amount (2.2%) in the placebo group, with a net increase of 140 mL (95% CI, 10-260) when comparing nicotine vs placebo groups at 26 weeks. FEV1 and FAS improved marginally in the nicotine-treated group, compared with those on placebo. No improvement was observed in lung texture score, FAS, St. George's Respiratory Questionnaire score, or the Sarcoidosis Assessment Tool. There were no reported serious adverse events or evidence of nicotine addiction. INTERPRETATION: Nicotine treatment was well tolerated in patients with active pulmonary sarcoidosis, and the preliminary findings of this pilot study suggest that it may reduce disease progression, based on FVC. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov; No.: NCT02265874; URL: www.clinicaltrials.gov.

Automated Brain Metastases Detection Framework for T1-Weighted Contrast-Enhanced 3D MRI.

Brain Metastases (BM) complicate 20-40% of cancer cases. BM lesions can present as punctate (1 mm) foci, requiring high-precision Magnetic Resonance Imaging (MRI) in order to prevent inadequate or delayed BM treatment. However, BM lesion detection remains challenging partly due to their structural similarities to normal structures (e.g., vasculature). We propose a BM-detection framework using a single-sequence gadolinium-enhanced T1-weighted 3D MRI dataset. The framework focuses on the detection of smaller (<15 mm) BM lesions and consists of: (1) candidate-selection stage, using Laplacian of Gaussian approach for highlighting parts of an MRI volume holding higher BM occurrence probabilities, and (2) detection stage that iteratively processes cropped region-of-interest volumes centered by candidates using a custom-built 3D convolutional neural network ("CropNet"). Data is augmented extensively during training via a pipeline consisting of random ga mma correction and elastic deformation stages; the framework thereby maintains its invariance for a plausible range of BM shape and intensity representations. This approach is tested using five-fold cross-validation on 217 datasets from 158 patients, with training and testing groups randomized per patient to eliminate learning bias. The BM database included lesions with a mean diameter of ∼5.4 mm and a mean volume of ∼160 mm3. For 90% BM-detection sensitivity, the framework produced on average 9.12 false-positive BM detections per patient (standard deviation of 3.49); for 85% sensitivity, the average number of false-positives declined to 5.85. Comparative analysis showed that the framework produces comparable BM-detection accuracy with the state-of-art approaches validated for significantly larger lesions.

Outcomes of benign breast papillomas diagnosed at image-guided vacuum-assisted core needle biopsy.

PURPOSE: To determine the upgrade rate of benign papillomas diagnosed at image-guided vacuum-assisted core needle biopsy (VACNB) and to compare our results with the summarized literature. MATERIALS AND METHODS: A database search was performed to identify patients older than 18 years of age with benign papillomas diagnosed at VACNB between 2004 and 2013. A total of 199 papillomas in 184 patients were identified. Clinical, imaging, and pathological features for each were analyzed. Patients who were subsequently diagnosed with malignancy at the site of papilloma, either at surgical excision or upon imaging follow-up, were compared with those not upgraded. Upgrade was defined as a diagnosis of invasive carcinoma or ductal carcinoma in situ (DCIS). RESULTS: Of 199 papillomas, 110 (55.3%) were diagnosed at ultrasound-guided VACNB, 78 (39.2%) were diagnosed at stereotactic-guided VACNB, and 11 (5.5%) were diagnosed at magnetic resonance imaging-guided VACNB. Surgical excision was performed for 89 (44.7%), and the remaining 110 (55.3%) underwent imaging follow-up. Two patients were subsequently diagnosed with invasive carcinoma and 4 were found with DCIS. The upgrade rate across both groups was 3% (6 of 199). Masses with calcifications (P=.001) and smaller needle gauge at VACNB (P=.02) had a significant association with upgrade. CONCLUSION: Benign papillomas diagnosed with VACNB demonstrated a 3% upgrade rate to malignancy, which is similar to the 2.9% upgrade rate calculated by compiling applicable published literature. Conservative management with imaging follow-up as opposed to surgical excision may be appropriate in cases where an initial diagnosis of benign papilloma is made with VACNB. Benign papillomas associated with calcifications on imaging should be considered for surgical excision given their increased association with malignancy.

Quantitative computerized two-point correlation analysis of lung CT scans correlates with pulmonary function in pulmonary sarcoidosis.

BACKGROUND: Chest CT scans are commonly used to clinically assess disease severity in patients presenting with pulmonary sarcoidosis. Despite their ability to reliably detect subtle changes in lung disease, the utility of chest CT scans for guiding therapy is limited by the fact that image interpretation by radiologists is qualitative and highly variable. We sought to create a computerized CT image analysis tool that would provide quantitative and clinically relevant information. METHODS: We established that a two-point correlation analysis approach reduced the background signal attendant to normal lung structures, such as blood vessels, airways, and lymphatics while highlighting diseased tissue. This approach was applied to multiple lung fields to generate an overall lung texture score (LTS) representing the quantity of diseased lung parenchyma. Using deidentified lung CT scan and pulmonary function test (PFT) data from The Ohio State University Medical Center's Information Warehouse, we analyzed 71 consecutive CT scans from patients with sarcoidosis for whom simultaneous matching PFTs were available to determine whether the LTS correlated with standard PFT results. RESULTS: We found a high correlation between LTS and FVC, total lung capacity, and diffusing capacity of the lung for carbon monoxide (P < .0001 for all comparisons). Moreover, LTS was equivalent to PFTs for the detection of active lung disease. The image analysis protocol was conducted quickly (< 1 min per study) on a standard laptop computer connected to a publicly available National Institutes of Health ImageJ toolkit. CONCLUSIONS: The two-point image analysis tool is highly practical and appears to reliably assess lung disease severity. We predict that this tool will be useful for clinical and research applications.