Prediction of tuberous sclerosis-associated neurocognitive disorders and seizures via machine learning of structural magnetic resonance imaging.

PURPOSE: Tuberous sclerosis complex (TSC) is a genetic disorder characterized by multiorgan hamartomas, including cerebral lesions, with seizures as a common presentation. Most TSC patients will also experience neurocognitive comorbidities. Our objective was to use machine learning techniques incorporating clinical and imaging data to predict the occurrence of major neurocognitive disorders and seizures in TSC patients. METHODS: A cohort of TSC patients were enrolled in this retrospective study. Clinical data included genetic, demographic, and seizure characteristics. Imaging parameters included the number, characteristics, and location of cortical tubers and the presence of subependymal nodules, SEGAs, and cerebellar tubers. A random forest machine learning scheme was used to predict seizures and neurodevelopmental delay or intellectual developmental disability. Prediction ability was assessed by the area-under-the-curve of receiver-operating-characteristics (AUC-ROC) of ten-fold cross-validation training set and an independent validation set. RESULTS: The study population included 77 patients, 55% male (17.1 ± 11.7 years old). The model achieved AUC-ROC of 0.72 ± 0.1 and 0.68 in the training and internal validation datasets, respectively, for predicting neurocognitive comorbidity. Performance was limited in predicting seizures (AUC-ROC of 0.54 ± 0.19 and 0.71 in the training and internal validation datasets, respectively). The integration of seizure characteristics into the model improved the prediction of neurocognitive comorbidity with AUC-ROC of 0.84 ± 0.07 and 0.75 in the training and internal validation datasets, respectively. CONCLUSIONS: This proof of concept study shows that it is possible to achieve a reasonable prediction of major neurocognitive morbidity in TSC patients using structural brain imaging and machine learning techniques. These tools can help clinicians identify subgroups of TSC patients with an increased risk of developing neurocognitive comorbidities.

Breast MRI during lactation: effects on tumor conspicuity using dynamic contrast-enhanced (DCE) in comparison with diffusion tensor imaging (DTI) parametric maps.

PURPOSE: To investigate the effect of lactation on breast cancer conspicuity on dynamic contrast-enhanced (DCE) MRI in comparison with diffusion tensor imaging (DTI) parametric maps. MATERIALS AND METHODS: Eleven lactating patients with 16 biopsy-confirmed pregnancy-associated breast cancer (PABC) lesions were prospectively evaluated by DCE and DTI on a 1.5-T MRI for pre-treatment evaluation. Additionally, DCE datasets of 16 non-lactating age-matched breast cancer patients were retrospectively reviewed, as control. Contrast-to-noise ratio (CNR) comprising two regions of interests of the normal parenchyma was used to assess the differences in the tumor conspicuity on DCE subtraction images between lactating and non-lactating patients, as well as in comparison against DTI parametric maps of λ1, λ2, λ3, mean diffusivity (MD), fractional anisotropy (FA), and maximal anisotropy index, λ1-λ3. RESULTS: CNR values of breast cancer on DCE MRI among lactating patients were reduced by 62% and 58% (p < 0.001) in comparison with those in non-lactating patients, when taking into account the normal contralateral parenchyma and an area of marked background parenchymal enhancement (BPE), respectively. Among the lactating patients, DTI parameters of λ1, λ2, λ3, MD, and λ1-λ3 were significantly decreased, and FA was significantly increased in PABC, relative to the normal lactating parenchyma ROIs. When compared against DCE in the lactating cohort, the CNR on λ1, λ2, λ3, and MD was significantly superior, providing up to 138% more tumor conspicuity, on average. CONCLUSION: Breast cancer conspicuity on DCE MRI is markedly reduced during lactation owing to the marked BPE. However, the additional application of DTI can improve the visualization and quantitative characterization of PABC, therefore possibly suggesting an additive value in the diagnostic workup of PABC. KEY POINTS: • Breast cancer conspicuity on DCE MRI has decreased by approximately 60% among lactating patients compared with non-lactating controls. • DTI-derived diffusion coefficients and the anisotropy indices of PABC lesions were significantly different than those of the normal lactating fibroglandular tissue. • Among lactating patients, breast cancer conspicuity on DTI-derived parametric maps provided up to 138% increase in contrast-to-noise ratio compared with DCE imaging.

Trends in Imaging Workup of the Male Breast: Experience from a Single Center.

BACKGROUND: Male breast cancer (MBC) is a rare disease representing less than 1% of breast cancers. In the absence of a screening program, such as for females, the diagnostic workup is critical for early detection of MBC. OBJECTIVES: To summarize our institutional experience in the workup of male patients referred for breast imaging, emphasizing the clinical, imaging, and histopathological characteristics of the MBC cohort. METHODS: All male patients who underwent breast imaging between 2011 and 2016 in our institution were retrospectively reviewed. Clinical, radiological, and histopathological data were collected and statistically evaluated. All images were reviewed using the American College of Radiology Breast Imaging Reporting and Data System. RESULTS: 178 male patients (average age 61 years, median age 64), underwent breast imaging in our institution. The most common indication for referral was palpable mass (49%) followed by gynecomastia (16%). Imaging included mostly mammography or ultrasound. Biopsies were performed on 56 patients, 38 (68%) were benign and 18 (32%) were malignant. In all, 13 patients had primary breast cancer and 5 had metastatic disease to the breast. Palpable mass at presentation was strongly associated with malignancy (P = 0.007). CONCLUSIONS: Mammography and ultrasound remain the leading modalities in breast imaging among males for diagnostic workup of palpable mass, with gynecomastia being the predominant diagnosis. However, presentation with palpable mass was also associated with malignancy. Despite a notable MBC rate in our cohort, the likelihood of cancer is low in young patients and in cases of gynecomastia.

Incidental pulmonary embolism in CT scans of oncological patients with metastatic disease undergoing clinical trials: frequency and linkage with onset of disease progression (PE-PD association).

OBJECTIVES: We aimed to analyze the association between the onsets of PE and of progressive disease (PD) in CT scans of oncological patients undergoing clinical trials. METHODS: We retrospectively searched our oncological clinical trials database (1/2012 - 6/2017). We retrieved patients who underwent protocol baseline and follow-up CT scans. RECIST 1.1 categories of response were calculated for each scan at interpretation. The entire dataset was searched for reports with incidental PE.For patients with incidental PE, we collected all the scans conducted up to and including the scan with PE. For each scan, we retrieved the recorded RECIST 1.1 category. We excluded patients with PE at baseline.The frequency of incidental PE in oncological clinical trial patients was calculated. For patients with incidental PE, we evaluated the association between PE and PD. RESULTS: During the study period, 1,070 patients underwent 3,818 CTs. The total number of follow-up months was 7,292 months. 18 patients developed incidental PE during follow-up. Thus, the frequency of incidental PE in oncological clinical trial patients was 3% per year of follow-up. Patients with incidental PE underwent 60 scans up to development of PE. Of 42 non-baseline scans, 6/6 (100%) PD showed PE, and 5/36 (13.9%) non-PD showed PE, making PE onset associated with PD onset (p < 0.001). CONCLUSION: In oncological clinical trials, the frequency of incidental PE is 3% per year of follow-up. The onset of incidental PE is linked to the onset of PD. ADVANCES IN KNOWLEDGE: Incidental PE is associated with the onset of disease progression. Radiologists interpret oncological scans should be aware of the association between PE and PD.