A Prospective Study of the Diagnostic Performance of Photon-Counting CT Compared With MRI in the Characterization of Renal Masses.

OBJECTIVES: The aim of this study was to assess the interreader reliability and per-RCC sensitivity of high-resolution photon-counting computed tomography (PCCT) in the detection and characterization of renal masses in comparison to MRI. MATERIALS AND METHODS: This prospective study included 24 adult patients (mean age, 52 ± 14 years; 14 females) who underwent PCCT (using an investigational whole-body CT scanner) and abdominal MRI within a 3-month time interval and underwent surgical resection (partial or radical nephrectomy) with histopathology (n = 70 lesions). Of the 24 patients, 17 had a germline mutation and the remainder were sporadic cases. Two radiologists (R1 and R2) assessed the PCCT and corresponding MRI studies with a 3-week washout period between reviews. Readers recorded the number of lesions in each patient and graded each targeted lesion's characteristic features, dimensions, and location. Data were analyzed using a 2-sample t test, Fisher exact test, and weighted kappa. RESULTS: In patients with von Hippel-Lindau mutation, R1 identified a similar number of lesions suspicious for neoplasm on both modalities (51 vs 50, P = 0.94), whereas R2 identified more suspicious lesions on PCCT scans as compared with MRI studies (80 vs 56, P = 0.12). R1 and R2 characterized more lesions as predominantly solid in MRIs (R1: 58/70 in MRI vs 52/70 in PCCT, P < 0.001; R2: 60/70 in MRI vs 55/70 in PCCT, P < 0.001). R1 and R2 performed similarly in detecting neoplastic lesions on PCCT and MRI studies (R1: 94% vs 90%, P = 0.5; R2: 73% vs 79%, P = 0.13). CONCLUSIONS: The interreader reliability and per-RCC sensitivity of PCCT scans acquired on an investigational whole-body PCCT were comparable to MRI scans in detecting and characterizing renal masses. CLINICAL RELEVANCE STATEMENT: PCCT scans have comparable performance to MRI studies while allowing for improved characterization of the internal composition of lesions due to material decomposition analysis. Future generations of this imaging modality may reveal additional advantages of PCCT over MRI.

Preoperative Renal Parenchyma Volume as a Predictor of Kidney Function Following Nephrectomy of Complex Renal Masses.

Background: The von Hippel-Lindau disease (VHL) is a hereditary cancer syndrome with multifocal, bilateral cysts and solid tumors of the kidney. Surgical management may include multiple extirpative surgeries, which ultimately results in parenchymal volume loss and subsequent renal function decline. Recent studies have utilized parenchyma volume as an estimate of renal function prior to surgery for renal cell carcinoma; however, it is not yet validated for surgically altered kidneys with multifocal masses and complex cysts such as are present in VHL. Objective: We sought to validate a magnetic resonance imaging (MRI)-based volumetric analysis with mercaptoacetyltriglycine (MAG-3) renogram and postoperative renal function. Design setting and participants: We identified patients undergoing renal surgery at the National Cancer Institute from 2015 to 2020 with preoperative MRI. Renal tumors, cysts, and parenchyma of the operated kidney were segmented manually using ITK-SNAP software. Outcome measurements and statistical analysis: Serum creatinine and urinalysis were assessed preoperatively, and at 3- and 12-mo follow-up time points. Estimated glomerular filtration rate (eGFR) was calculated using serum creatinine-based CKD-EPI 2021 equation. A statistical analysis was conducted on R Studio version 4.1.1. Results and limitations: Preoperative MRI scans of 113 VHL patients (56% male, median age 48 yr) were evaluated between 2015 and 2021. Twelve (10.6%) patients had a solitary kidney at the time of surgery; 59 (52%) patients had at least one previous partial nephrectomy on the renal unit. Patients had a median of three (interquartile range [IQR]: 2-5) tumors and five (IQR: 0-13) cysts per kidney on imaging. The median preoperative GFR was 70 ml/min/1.73 m2 (IQR: 58-89). Preoperative split renal function derived from MAG-3 studies and MRI split renal volume were significantly correlated (r = 0.848, p < 0.001). On the multivariable analysis, total preoperative parenchymal volume, solitary kidney, and preoperative eGFR were significant independent predictors of 12-mo eGFR. When only considering patients with two kidneys undergoing partial nephrectomy, preoperative parenchymal volume and eGFR remained significant predictors of 12-mo eGFR. Conclusions: A parenchyma volume analysis on preoperative MRI correlates well with renogram split function and can predict long-term renal function with added benefit of anatomic detail and ease of application. Patient summary: Prior to kidney surgery, it is important to understand the contribution of each kidney to overall kidney function. Nuclear medicine scans are currently used to measure split kidney function. We demonstrated that kidney volumes on preoperative magnetic resonance imaging can also be used to estimate split kidney function before surgery, while also providing essential details of tumor and kidney anatomy.

Role of ultra-high b-value DWI in the imaging of hereditary leiomyomatosis and renal cell carcinoma (HLRCC).

PURPOSE: Hereditary leiomyomatosis and renal cell carcinoma (HLRCC) syndrome is associated with an aggressive form of renal cell carcinoma with high risk of metastasis, even in small primary tumors with unequivocal imaging findings. In this study, we compare the performance of ultra-high b-value diffusion-weighted imaging (DWI) sequence (b = 2000 s/mm2) to standard DWI (b = 800 s/mm2) sequence in identifying malignant lesions in patients with HLRCC. METHODS: Twenty-eight patients (n = 18 HLRCC patients with 22 lesions, n = 10 controls) were independently evaluated by three abdominal radiologists with different levels of experience using four combinations of MRI sequences in two separate sessions (session 1: DWI with b-800, session 2: DWI with b-2000). T1 precontrast, T2-weighted (T2WI), and apparent diffusion coefficient (ADC) sequences were similar in both sessions. Each identified lesion was subjectively assessed using a six-point cancer likelihood score based on individual sequences and overall impression. RESULTS: The ability to distinguish benign versus malignant renal lesions improved with the use of b-2000 for more experienced radiologists (Reader 1 AUC: Session 1-0.649 and Session 2-0.938, p = 0.017; Reader 2 AUC: Session 1-0.781 and Session 2-0.921, p = 0.157); whereas no improvement was observed for the less experienced reader (AUC: Session 1-0.541 and Session 2-0.607, p = 0.699). CONCLUSION: The inclusion of ultra-high b-value DWI sequence improved the ability of classification of renal lesions in patients with HLRCC for experienced radiologists. Consideration should be given toward incorporation of DWI with b-2000 s/mm2 into existing renal MRI protocols.

Left Ventricular Structure, Tissue Composition, and Aortic Distensibility in the Diabetes Control and Complications Trial/Epidemiology of Diabetes Intervention and Complications.

Alterations in myocardial structure, function, tissue composition (e.g., fibrosis) may be associated with metabolic syndrome (MetS). This study aimed to determine the relation of MetS and its individual components to markers of cardiovascular disease in patients with type 1 Diabetes Mellitus (T1DM). A total of 978 subjects of the Diabetes Control and Complications Trial/Epidemiology of Diabetes Interventions and Complications T1DM cohort (age: 49 ± 7 years, 47% female, DM duration 28 ± 5 years) underwent cardiovascular magnetic resonance. In a subset of 200 patients, myocardial tissue composition was measured with cardiovascular magnetic resonance T1 mapping after contrast administration. MetS was defined as T1DM plus 2 other abnormalities based on the American Heart Association/National Cholesterol Education Program criteria. MetS was present in 34.1% of subjects. After adjustment for age, height, scanner, study cohort, gender, smoking, mean glycated hemoglobin levels, history of macroalbuminuria and end-stage renal disease, left ventricle mass was greater by 12.3 g, end-diastolic volume was higher by 5.4 ml, and mass to end-diastolic volume ratio was higher by 5% in patients with MetS versus those without MetS (p <0.001 for all). Myocardial T1 times were lower by 29 ms in patients with MetS than those without (p <0.001). Elevated waist circumference showed the strongest associations with left ventricle mass (+10.1 g), end-diastolic volume (+6.7 ml), and lower myocardial T1 times (+31 ms) in patients with MetS compared with those without (p <0.01). In conclusion, in a large cohort of patients with T1DM, 34.1% of subjects met MetS criteria. MetS was associated with adverse myocardial structural remodeling and change in myocardial tissue composition.

Modern radiographic imaging in multiple myeloma, what is the minimum requirement?

Imaging innovations offer useful techniques applicable to many oncology specialties. Treatment advances in the field of multiple myeloma (MM) have increased the need for accurate diagnosis, particularly in the bone marrow, which is an essential component in myeloma-defining criteria. Modern imaging identifies osteolytic lesions, distinguishes solitary plasmacytoma from MM, and evaluates the presence of extramedullary disease. Furthermore, imaging is increasingly valuable in post-treatment response assessment. Detection of minimal residual disease after therapy carries prognostic implications and influences subsequent treatment planning. Whole-body low-dose Computed Tomography is now recommended over the conventional skeletal survey, and more sophisticated functional imaging methods, such as 18F-Fluorodeoxyglucose Positron Emission Tomography , and diffusion-weighted Magnetic Resonance Imaging are proving effective in the assessment and monitoring of MM disease. This review focuses on understanding indications and advantages of these imaging modalities for diagnosing and managing myeloma.

A deep learning system for automated kidney stone detection and volumetric segmentation on noncontrast CT scans.

PURPOSE: Early detection and size quantification of renal calculi are important for optimizing treatment and preventing severe kidney stone disease. Prior work has shown that volumetric measurements of kidney stones are more informative and reproducible than linear measurements. Deep learning-based systems that use abdominal noncontrast computed tomography (CT) scans may assist in detection and reduce workload by removing the need for manual stone volume measurement. Prior to this work, no such system had been developed for use on noisy low-dose CT or tested on a large-scale external dataset. METHODS: We used a dataset of 91 CT colonography (CTC) scans with manually marked kidney stones combined with 89 CTC scans without kidney stones. To compare with a prior work half the data was used for training and half for testing. A set of CTC scans from 6185 patients from a separate institution with patient-level labels were used as an external validation set. A 3D U-Net model was employed to segment the kidneys, followed by gradient-based anisotropic denoising, thresholding, and region growing. A 13 layer convolutional neural network classifier was then applied to distinguish kidney stones from false positive regions. RESULTS: The system achieved a sensitivity of 0.86 at 0.5 false positives per scan on a challenging test set of low-dose CT with many small stones, an improvement over an earlier work that obtained a sensitivity of 0.52. The stone volume measurements correlated well with manual measurements ( r 2 = 0.95 $r^2 = 0.95$ ). For patient-level classification, the system achieved an area under the receiver-operating characteristic of 0.95 on an external validation set (sensitivity = 0.88, specificity = 0.91 at the Youden point). A common cause of false positives were small atherosclerotic plaques in the renal sinus that simulated kidney stones. CONCLUSIONS: Our deep-learning-based system showed improvements over a previously developed system that did not use deep learning, with even higher performance on an external validation set.

Generalized chest CT and lab curves throughout the course of COVID-19.

A better understanding of temporal relationships between chest CT and labs may provide a reference for disease severity over the disease course. Generalized curves of lung opacity volume and density over time can be used as standardized references from well before symptoms develop to over a month after recovery, when residual lung opacities remain. 739 patients with COVID-19 underwent CT and RT-PCR in an outbreak setting between January 21st and April 12th, 2020. 29 of 739 patients had serial exams (121 CTs and 279 laboratory measurements) over 50 ± 16 days, with an average of 4.2 sequential CTs each. Sequential volumes of total lung, overall opacity and opacity subtypes (ground glass opacity [GGO] and consolidation) were extracted using deep learning and manual segmentation. Generalized temporal curves of CT and laboratory measurements were correlated. Lung opacities appeared 3.4 ± 2.2 days prior to symptom onset. Opacity peaked 1 day after symptom onset. GGO onset was earlier and resolved later than consolidation. Lactate dehydrogenase, and C-reactive protein peaked earlier than procalcitonin and leukopenia. The temporal relationships of quantitative CT features and clinical labs have distinctive patterns and peaks in relation to symptom onset, which may inform early clinical course in patients with mild COVID-19 pneumonia, or may shed light upon chronic lung effects or mechanisms of medical countermeasures in clinical trials.

Cardiothoracic imaging findings of Proteus syndrome.

In this work, we sought to delineate the prevalence of cardiothoracic imaging findings of Proteus syndrome in a large cohort at our institution. Of 53 individuals with a confirmed diagnosis of Proteus syndrome at our institution from 10/2001 to 10/2019, 38 individuals (men, n = 23; average age = 24 years) underwent cardiothoracic imaging (routine chest CT, CT pulmonary angiography and/or cardiac MRI). All studies were retrospectively and independently reviewed by two fellowship-trained cardiothoracic readers. Disagreements were resolved by consensus. Differences between variables were analyzed via parametric and nonparametric tests based on the normality of the distribution. The cardiothoracic findings of Proteus syndrome were diverse, but several were much more common and included: scoliosis from bony overgrowth (94%), pulmonary venous dilation (62%), band-like areas of lung scarring (56%), and hyperlucent lung parenchyma (50%). In addition, of 20 individuals who underwent cardiac MRI, 9/20 (45%) had intramyocardial fat, mostly involving the endocardial surface of the left ventricular septal wall. There was no statistically significant difference among the functional cardiac parameters between individuals with and without intramyocardial fat. Only one individual with intramyocardial fat had mildly decreased function (LVEF = 53%), while all others had normal ejection fraction.

Quality of Prostate MRI: Is the PI-RADS Standard Sufficient?

RATIONALE AND OBJECTIVE: The Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) published a set of minimum technical standards (MTS) to improve image quality and reduce variability in multiparametric prostate MRI. The effect of PIRADSv2 MTS on image quality has not been validated. We aimed to determine whether adherence to PI-RADSv2 MTS improves study adequacy and perceived quality. MATERIALS AND METHODS: Sixty-two prostate MRI examinations including T2 weighted (T2W) and diffusion weighted image (DWI) consecutively referred to our center from 62 different institutions within a 12-month period (September 2017 to September 2018) were included. Six readers assessed images as adequate or inadequate for use in PCa detection and a numerical image quality ranking was given using a 1-5 scale. The PI-RADSv2 MTS were synthesized into sets of seven and 10 rules for T2W and DWI, respectively. Image adherence was assessed using Digital Imaging and Communications in Medicine (DICOM) metadata. Statistical analysis of survey results and image adherence was performed based on reader quality scoring (Kendall Rank tau-b) and reader adequate scoring (Wilcoxon test for association) for T2 and DWI quality assessment. RESULTS: Out of 62 images, 52 (83%) T2W and 38 (61%) DWIs were rated to be adequate by a majority of readers. Reader adequacy scores showed no significant association with adherence to PI-RADSv2. There was a weak (tau-b = 0.22) but significant (p value = 0.01) correlation between adherence to PIRADSv2 MTS and image quality for T2W. Studies following all PI-RADSv2 T2W rules achieved a higher median average quality score (3.58 for 7/7 vs. 3.0 for <7/7, p = 0.012). No statistical relationship with PI-RADSv2 MTS adherence and DWI quality was found. CONCLUSION: Among 62 sites performing prostate MRI, few were considered of high quality, but the majority were considered adequate. DWI showed considerably lower rates of adequate studies in the sample. Adherence to PI-RADSv2 MTS did not increase the likelihood of having a qualitatively adequate T2W or DWI.

CT and clinical assessment in asymptomatic and pre-symptomatic patients with early SARS-CoV-2 in outbreak settings.

OBJECTIVES: The early infection dynamics of patients with SARS-CoV-2 are not well understood. We aimed to investigate and characterize associations between clinical, laboratory, and imaging features of asymptomatic and pre-symptomatic patients with SARS-CoV-2. METHODS: Seventy-four patients with RT-PCR-proven SARS-CoV-2 infection were asymptomatic at presentation. All were retrospectively identified from 825 patients with chest CT scans and positive RT-PCR following exposure or travel risks in outbreak settings in Japan and China. CTs were obtained for every patient within a day of admission and were reviewed for infiltrate subtypes and percent with assistance from a deep learning tool. Correlations of clinical, laboratory, and imaging features were analyzed and comparisons were performed using univariate and multivariate logistic regression. RESULTS: Forty-eight of 74 (65%) initially asymptomatic patients had CT infiltrates that pre-dated symptom onset by 3.8 days. The most common CT infiltrates were ground glass opacities (45/48; 94%) and consolidation (22/48; 46%). Patient body temperature (p < 0.01), CRP (p < 0.01), and KL-6 (p = 0.02) were associated with the presence of CT infiltrates. Infiltrate volume (p = 0.01), percent lung involvement (p = 0.01), and consolidation (p = 0.043) were associated with subsequent development of symptoms. CONCLUSIONS: COVID-19 CT infiltrates pre-dated symptoms in two-thirds of patients. Body temperature elevation and laboratory evaluations may identify asymptomatic patients with SARS-CoV-2 CT infiltrates at presentation, and the characteristics of CT infiltrates could help identify asymptomatic SARS-CoV-2 patients who subsequently develop symptoms. The role of chest CT in COVID-19 may be illuminated by a better understanding of CT infiltrates in patients with early disease or SARS-CoV-2 exposure. KEY POINTS: • Forty-eight of 74 (65%) pre-selected asymptomatic patients with SARS-CoV-2 had abnormal chest CT findings. • CT infiltrates pre-dated symptom onset by 3.8 days (range 1-5). • KL-6, CRP, and elevated body temperature identified patients with CT infiltrates. Higher infiltrate volume, percent lung involvement, and pulmonary consolidation identified patients who developed symptoms.

Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets.

Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8% accuracy, with 84% sensitivity and 93% specificity, as evaluated in an independent test set (not included in training and validation) of 1337 patients. Normal controls included chest CTs from oncology, emergency, and pneumonia-related indications. The false positive rate in 140 patients with laboratory confirmed other (non COVID-19) pneumonias was 10%. AI-based algorithms can readily identify CT scans with COVID-19 associated pneumonia, as well as distinguish non-COVID related pneumonias with high specificity in diverse patient populations.

Coronary CT Angiography and Carotid MRI Improve Phenotyping of Disease Extent Compared with ACC/AHA Risk Score Alone.

PURPOSE: To determine the relationship between the American College of Cardiology/American Heart Association (ACC/AHA) risk score and plaque phenotype of the coronary and carotid arteries assessed directly using CT angiography and MRI. MATERIALS AND METHODS: Asymptomatic subjects eligible for statin therapy by risk score were enrolled in a prospective study of disease burden using coronary artery calcium (CAC) scoring, coronary CT angiography, and MRI of the carotid arteries. Quartiles were calculated for noncalcified plaque, CAC, and average carotid wall volume and were compared with ACC/AHA risk quartiles. RESULTS: Two hundred three subjects were studied (60% men; mean age, 65 years). There were weak correlations between risk and carotid wall volume (Kendall tau = 0.29), noncalcified plaque (tau = 0.16), and CAC (tau = 0.33). ACC/AHA risk alone misclassified plaque extent compared with measurement by carotid wall volume, CAC, and noncalcified plaque in 22.1%, 24.1%, and 29.6% of subjects, respectively. On average, 13% of the subjects were underclassified, and 12.5% were overclassified. CONCLUSION: Approximately 25% of subjects had large discrepancies between ACC/AHA risk and plaque burden at imaging. These results suggest that clinical risk score models alone do not fully reflect the amount of atherosclerotic disease present.© RSNA, 2020See also the commentary by Truong and Villines in this issue.

Preparation of a radiology department in an Italian hospital dedicated to COVID-19 patients.

Preparedness for the ongoing coronavirus disease 2019 (COVID-19) and its spread in Italy called for setting up of adequately equipped and dedicated health facilities to manage sick patients while protecting healthcare workers, uninfected patients, and the community. In our country, in a short time span, the demand for critical care beds exceeded supply. A new sequestered hospital completely dedicated to intensive care (IC) for isolated COVID-19 patients needed to be designed, constructed, and deployed. Along with this new initiative, the new concept of "Pandemic Radiology Unit" was implemented as a practical solution to the emerging crisis, born out of a critical and urgent acute need. The present article describes logistics, planning, and practical design issues for such a pandemic radiology and critical care unit (e.g., space, infection control, safety of healthcare workers, etc.) adopted in the IC Hospital Unit for the care and management of COVID-19 patients.

Deep-Learning-Based Artificial Intelligence for PI-RADS Classification to Assist Multiparametric Prostate MRI Interpretation: A Development Study.

BACKGROUND: The Prostate Imaging Reporting and Data System (PI-RADS) provides guidelines for risk stratification of lesions detected on multiparametric MRI (mpMRI) of the prostate but suffers from high intra/interreader variability. PURPOSE: To develop an artificial intelligence (AI) solution for PI-RADS classification and compare its performance with an expert radiologist using targeted biopsy results. STUDY TYPE: Retrospective study including data from our institution and the publicly available ProstateX dataset. POPULATION: In all, 687 patients who underwent mpMRI of the prostate and had one or more detectable lesions (PI-RADS score >1) according to PI-RADSv2. FIELD STRENGTH/SEQUENCE: T2 -weighted, diffusion-weighted imaging (DWI; five evenly spaced b values between b = 0-750 s/mm2 ) for apparent diffusion coefficient (ADC) mapping, high b-value DWI (b = 1500 or 2000 s/mm2 ), and dynamic contrast-enhanced T1 -weighted series were obtained at 3.0T. ASSESSMENT: PI-RADS lesions were segmented by a radiologist. Bounding boxes around the T2 /ADC/high-b value segmentations were stacked and saved as JPEGs. These images were used to train a convolutional neural network (CNN). The PI-RADS scores obtained by the CNN were compared with radiologist scores. The cancer detection rate was measured from a subset of patients who underwent biopsy. STATISTICAL TESTS: Agreement between the AI and the radiologist-driven PI-RADS scores was assessed using a kappa score, and differences between categorical variables were assessed with a Wald test. RESULTS: For the 1034 detection lesions, the kappa score for the AI system vs. the expert radiologist was moderate, at 0.40. However, there was no significant difference in the rates of detection of clinically significant cancer for any PI-RADS score in 86 patients undergoing targeted biopsy (P = 0.4-0.6). DATA CONCLUSION: We developed an AI system for assignment of a PI-RADS score on segmented lesions on mpMRI with moderate agreement with an expert radiologist and a similar ability to detect clinically significant cancer. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 2.

Radiomics, Radiogenomics, and Next-Generation Molecular Imaging to Augment Diagnosis of Hepatocellular Carcinoma.

Ultrasound, computed tomography, magnetic resonance imaging, and [F]F-fluorodeoxyglucose positron emission tomography are invaluable in the clinical evaluation of human cancers. Radiomics and radiogenomics tools may allow clinicians to standardize interpretation of these conventional imaging modalities, while better linking radiographic hallmarks to disease biology and prognosis. These advances, coupled with next-generation positron emission tomography imaging tracers capable of providing biologically relevant tumor information, may further expand the tools available in our armamentarium against human cancers. We present current imaging methods and explore emerging research that may improve diagnosis and monitoring of local, oligometastatic, and disseminated cancers exhibiting heterogeneous uptake of [F]F-fluorodeoxyglucose, using hepatocellular carcinoma as an example.

Impact of DAT-SPECT on Management of Patients Suspected of Parkinsonism.

OBJECTIVE: To evaluate the value of I-2ß-carbomethoxy-3ß-(4-iodophenyl)-N-(3-fluoropropyl) nortropane (I-FP-CIT) dopamine transporter single photon emission computed tomography (DAT-SPECT) to change management strategies of patients suspected of parkinsonism. METHOD: This was an institutional review board-approved, retrospective study. DAT-SPECT scans ordered by movement disorder specialist and neurologists from 2011-2014 were reviewed. Clinical data and radiological reports of 173 patients suspected of parkinsonism were reviewed. The DAT-SPECT scan results were correlated with clinical assessment and treatment changes. RESULTS: A total of 173 patients (104 male and 69 female subjects; age, 64.4 ± 12.6 years) suspected of parkinsonism were included. Median duration of symptoms was 36 months (range, 1-480 months). Scans were most often requested when there was diagnostic uncertainty in clinical features (59.6%, 103/173) or to differentiate one other disease from parkinsonism such as Parkinson disease (PD) versus essential tremor (23.7%, 41/173), PD versus drug-induced parkinsonism (8.7%, 15/173), or PD versus psychogenic (6.4%, 11/173) or vascular (1.7%, 3/173) disorders. Patients were classified, according to the DAT-SPECT scanning results, as those with abnormal DAT-SPECT findings (59%, 102/173) and those with normal DAT-SPECT findings (41%, 71/173). In patients with normal DAT-SPECT findings, follow-up management data were available in 76.1% (54/71). The management changed in 39.4% (28/54) after DAT scan with starting a new appropriate medications or supportive therapy in 4.2% (3/28), withholding inappropriate dopaminergic treatment in 11.3% (8/28), or continuing observation in 23.9% (17/28). In patients with abnormal DAT-SPECT findings, follow-up management data were available in 78.4% (80/102). There was change in management of 37.3% (38/80), a new PD treatment was started in 89.5% (34/38). The dose of medication was adjusted in 5.3% (2/38), although the original treatment was not changed. Parkinson disease treatment was stopped in 2.6% (1/38) and discontinued in 2.6% (1/38) based on clinical decision of neurologists despite abnormal DAT-SPECT findings. CONCLUSIONS: DAT-SPECT findings impacted treatment decisions in 44.7% of patients suspected of Parkinsonism.

Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks.

PURPOSE: Colitis refers to inflammation of the inner lining of the colon that is frequently associated with infection and allergic reactions. In this paper, we propose deep convolutional neural networks methods for lesion-level colitis detection and a support vector machine (SVM) classifier for patient-level colitis diagnosis on routine abdominal CT scans. METHODS: The recently developed Faster Region-based Convolutional Neural Network (Faster RCNN) is utilized for lesion-level colitis detection. For each 2D slice, rectangular region proposals are generated by region proposal networks (RPN). Then, each region proposal is jointly classified and refined by a softmax classifier and bounding-box regressor. Two convolutional neural networks, eight layers of ZF net and 16 layers of VGG net are compared for colitis detection. Finally, for each patient, the detections on all 2D slices are collected and a SVM classifier is applied to develop a patient-level diagnosis. We trained and evaluated our method with 80 colitis patients and 80 normal cases using 4 × 4-fold cross validation. RESULTS: For lesion-level colitis detection, with ZF net, the mean of average precisions (mAP) were 48.7% and 50.9% for RCNN and Faster RCNN, respectively. The detection system achieved sensitivities of 51.4% and 54.0% at two false positives per patient for RCNN and Faster RCNN, respectively. With VGG net, Faster RCNN increased the mAP to 56.9% and increased the sensitivity to 58.4% at two false positive per patient. For patient-level colitis diagnosis, with ZF net, the average areas under the ROC curve (AUC) were 0.978 ± 0.009 and 0.984 ± 0.008 for RCNN and Faster RCNN method, respectively. The difference was not statistically significant with P = 0.18. At the optimal operating point, the RCNN method correctly identified 90.4% (72.3/80) of the colitis patients and 94.0% (75.2/80) of normal cases. The sensitivity improved to 91.6% (73.3/80) and the specificity improved to 95.0% (76.0/80) for the Faster RCNN method. With VGG net, Faster RCNN increased the AUC to 0.986 ± 0.007 and increased the diagnosis sensitivity to 93.7% (75.0/80) and specificity was unchanged at 95.0% (76.0/80). CONCLUSION: Colitis detection and diagnosis by deep convolutional neural networks is accurate and promising for future clinical application.