Radiology 2019; 290:187-194 • https://doi.org/10.1148/radiol.2018180901 • Content code:Purpose: To develop and evaluate a supportive algorithm using deep learning for detecting cerebral aneurysms at time-of-flight MR angiography to provide a second assessment of images already interpreted by radiologists. Materials and Methods:MR images reported by radiologists to contain aneurysms were extracted from four institutions for the period from November 2006 through October 2017. The images were divided into three data sets: training data set, internal test data set, and external test data set. The algorithm was constructed by deep learning with the training data set, and its sensitivity to detect aneurysms in the test data sets was evaluated. To find aneurysms that had been overlooked in the initial reports, two radiologists independently performed a blinded interpretation of aneurysm candidates detected by the algorithm. When there was disagreement, the final diagnosis was made in consensus. The number of newly detected aneurysms was also evaluated. Results:The training data set, which provided training and validation data, included 748 aneurysms (mean size, 3.1 mm 6 2.0 [standard deviation]) from 683 examinations; 318 of these examinations were on male patients (mean age, 63 years 6 13) and 365 were on female patients (mean age, 64 years 6 13). Test data were provided by the internal test data set (649 aneurysms [mean size, 4.1 mm 6 3.2] in 521 examinations, including 177 male patients and 344 female patients with mean age of 66 years 6 12 and 67 years 6 13, respectively) and the external test data set (80 aneurysms [mean size, 4.1 mm 6 2.1] in 67 examinations, including 19 male patients and 48 female patients with mean age of 63 years 6 12 and 68 years 6 12, respectively). The sensitivity was 91% (592 of 649) and 93% (74 of 80) for the internal and external test data sets, respectively. The algorithm improved aneurysm detection in the internal and external test data sets by 4.8% (31 of 649) and 13% (10 of 80), respectively, compared with the initial reports. Conclusion:A deep learning algorithm detected cerebral aneurysms in radiologic reports with high sensitivity and improved aneurysm detection compared with the initial reports.

The authors examined two Japanese siblings with a recessive hereditary spastic paraplegia (HSP) with dementia and a thin corpus callosum. Both showed thalamic glucose hypometabolism on PET. Recessive HSP with a thin corpus callosum is a rare disorder, with less than 20 reported patients, that may be a Japanese subtype of HSP.

We followed-up a Japanese man suffering from hereditary spastic paraplegia with a thin corpus callosum (HSP-TCC) by single photon emission computed tomography (SPECT) using 123IN-isopropyl-piodoamphetamine (123I-IMP) over 4 years (25 to 29 years old). Besides the initial symptoms of lower limb spasticity, mental deterioration slightly progressed and upper limb spasticity and slight cerebellar ataxia were developed, during the period. Cranial magnetic resonance imaging (MRI) revealed an extremely thin corpus callosum and medial frontal atrophy, which remained essentially unchanged during the period. 123I-IMP SPECT demonstrated that cerebral blood flow was decreased in the thalamus and the medial frontal, temporal and parietal cortices at the first examination, and that the thalamus showed further reduction but the other involved regions presented essentially no progression during the follow-up period. This is the first report referring to the longitudinal clinical and neuroradiological changes in HSP-TCC.

Recent advances in deep learning (DL) (4,5) have led to several radiologic applications (6), specifically Background: Digital subtraction angiography (DSA) generates an image by subtracting a mask image from a dynamic angiogram. However, patient movement-caused misregistration artifacts can result in unclear DSA images that interrupt procedures. Purpose:To train and to validate a deep learning (DL)-based model to produce DSA-like cerebral angiograms directly from dynamic angiograms and then quantitatively and visually evaluate these angiograms for clinical usefulness. Materials and Methods:A retrospective model development and validation study was conducted on dynamic and DSA image pairs consecutively collected from January 2019 through April 2019. Angiograms showing misregistration were first separated per patient by two radiologists and sorted into the misregistration test data set. Nonmisregistration angiograms were divided into development and external test data sets at a ratio of 8:1 per patient. The development data set was divided into training and validation data sets at ratio of 3:1 per patient. The DL model was created by using the training data set, tuned with the validation data set, and then evaluated quantitatively with the external test data set and visually with the misregistration test data set. Quantitative evaluations used the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) with mixed liner models. Visual evaluation was conducted by using a numerical rating scale. Results:The training, validation, nonmisregistration test, and misregistration test data sets included 10 751, 2784, 1346, and 711 paired images collected from 40 patients (mean age, 62 years  11 [standard deviation]; 33 women). In the quantitative evaluation, DL-generated angiograms showed a mean PSNR value of 40.2 dB  4.05 and a mean SSIM value of 0.97  0.02, indicating high coincidence with the paired DSA images. In the visual evaluation, the median ratings of the DL-generated angiograms were similar to or better than those of the original DSA images for all 24 sequences. Conclusion:The deep learning-based model provided clinically useful cerebral angiograms free from clinically significant artifacts directly from dynamic angiograms.

GI bleeding scintigraphy in combination with SPECT/CT is a noninvasive and useful tool for the examination of GI bleeding.