A novel strategy to develop deep learning for image super-resolution using original ultra-high-resolution computed tomography images of lung as training dataset.

PURPOSE: To improve the image quality of inflated fixed cadaveric human lungs by utilizing ultra-high-resolution computed tomography (U-HRCT) as a training dataset for super-resolution processing using deep learning (SR-DL). MATERIALS AND METHODS: Image data of nine cadaveric human lungs were acquired using U-HRCT. Three different matrix images of U-HRCT images were obtained with two acquisition modes: normal mode (512-matrix image) and super-high-resolution mode (1024- and 2048-matrix image). SR-DL used 512- and 1024-matrix images as training data for deep learning. The virtual 2048-matrix images were acquired by applying SR-DL to the 1024-matrix images. Three independent observers scored normal anatomical structures and abnormal computed tomography (CT) findings of both types of 2048-matrix images on a 3-point scale compared to 1024-matrix images. The image noise values were quantitatively calculated. Moreover, the edge rise distance (ERD) and edge rise slope (ERS) were also calculated using the CT attenuation profile to evaluate margin sharpness. RESULTS: The virtual 2048-matrix images significantly improved visualization of normal anatomical structures and abnormal CT findings, except for consolidation and nodules, compared with the conventional 2048-matrix images (p < 0.01). Quantitative noise values were significantly lower in the virtual 2048-matrix images than in the conventional 2048-matrix images (p < 0.001). ERD was significantly shorter in the virtual 2048-matrix images than in the conventional 2048-matrix images (p < 0.01). ERS was significantly higher in the virtual 2048-matrix images than in the conventional 2048-matrix images (p < 0.01). CONCLUSION: SR-DL using original U-HRCT images as a training dataset might be a promising tool for image enhancement in terms of margin sharpness and image noise reduction. By applying trained SR-DL to U-HRCT SHR mode images, virtual ultra-high-resolution images were obtained which surpassed the image quality of unmodified SHR mode images.

Imaging findings of vitamin deficiencies: are they forgotten diseases?

Vitamin deficiency is rare in modern industrialised countries; however, it still occurs in patients with specific backgrounds, such as those with extremely unbalanced diets, those with alcoholism and those who have undergone gastrointestinal surgery. Imaging examinations that demonstrate classic findings confirm the clinical diagnosis of vitamin deficiency and help monitor response to treatment. Because vitamin deficiencies are not prevalent, the diagnosis might not be straightforward. Therefore, imaging should be performed in cases of suspected vitamin deficiency. Radiologists should be familiar with characteristic imaging findings of vitamin deficiency and should survey an affected patient's background and blood vitamin levels. Because symptoms of vitamin deficiency are quickly improved by vitamin replacement, early diagnosis is essential. This pictorial review provides imaging findings for deficiencies in vitamins B1 (Wernicke encephalopathy and wet beriberi), B12 (subacute combined degeneration), C (scurvy), D (rickets) and K (bleeding tendency).

Machine Learning for Diagnosis of AD and Prediction of MCI Progression From Brain MRI Using Brain Anatomical Analysis Using Diffeomorphic Deformation.

Background: With the growing momentum for the adoption of machine learning (ML) in medical field, it is likely that reliance on ML for imaging will become routine over the next few years. We have developed a software named BAAD, which uses ML algorithms for the diagnosis of Alzheimer's disease (AD) and prediction of mild cognitive impairment (MCI) progression. Methods: We constructed an algorithm by combining a support vector machine (SVM) to classify and a voxel-based morphometry (VBM) to reduce concerned variables. We grouped progressive MCI and AD as an AD spectrum and trained SVM according to this classification. We randomly selected half from the total 1,314 subjects of AD neuroimaging Initiative (ADNI) from North America for SVM training, and the remaining half were used for validation to fine-tune the model hyperparameters. We created two types of SVMs, one based solely on the brain structure (SVMst), and the other based on both the brain structure and Mini-Mental State Examination score (SVMcog). We compared the model performance with two expert neuroradiologists, and further evaluated it in test datasets involving 519, 592, 69, and 128 subjects from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Aging (AIBL), Japanese ADNI, the Minimal Interval Resonance Imaging in AD (MIDIAD) and the Open Access Series of Imaging Studies (OASIS), respectively. Results: BAAD's SVMs outperformed radiologists for AD diagnosis in a structural magnetic resonance imaging review. The accuracy of the two radiologists was 57.5 and 70.0%, respectively, whereas, that of the SVMst was 90.5%. The diagnostic accuracy of the SVMst and SVMcog in the test datasets ranged from 88.0 to 97.1% and 92.5 to 100%, respectively. The prediction accuracy for MCI progression was 83.0% in SVMst and 85.0% in SVMcog. In the AD spectrum classified by SVMst, 87.1% of the subjects were Aß positive according to an AV-45 positron emission tomography. Similarly, among MCI patients classified for the AD spectrum, 89.5% of the subjects progressed to AD. Conclusion: Our ML has shown high performance in AD diagnosis and prediction of MCI progression. It outperformed expert radiologists, and is expected to provide support in clinical practice.

Flat-panel detector computed tomography imaging: observer performance in detecting pulmonary nodules in comparison with conventional chest radiography and multidetector computed tomography.

PURPOSE: The aim of this study was to compare the detectability of lung nodules on images obtained with a flat-panel detector computed tomography (FPD-CT) system and by chest radiographs (CXRs) using receiver-operating characteristic (ROC) analysis. MATERIALS AND METHODS: FPD-CT was conducted with the patients in the sitting position. For the CXR study, the patients stood erect. Our study population consisted of 26 individuals ranging in age from 50 to 83 years. The reference standard was based on the interpretations obtained by consensus of 2 radiologists on multidetector CT images for the presence or absence of nodules. Four other radiologists independently assessed and recorded the absence or presence of lung nodules and their location on FPD-CT and CXR images. ROC analysis was used to evaluate lung nodule detectability by both imaging modalities. RESULTS: Two radiologists identified 34 nodules whose diameter was 5 to 42 mm (mean, 19.3 mm) in 23 of the 26 study participants on the multidetector CT images. Overall, analysis of variance for ROC analysis showed that FPD-CT was significantly better in detecting nodules than CXR (P=0.02). The estimated mean Az value was 0.9818±0.0083 with FPD-CT and 0.7610±0.0908 with CXR. The sensitivity for nodule detection on FPD-CT and CXR images was 79.4% and 33.8%, respectively. CONCLUSION: The detectability of pulmonary nodules was better on images of FPD-CT than on CXRs.

Three-dimensional computed tomography combined with hysterosalpingography is useful for both diagnosis and treatment of iatrogenic diverticulum of the uterus.

A woman presented with vaginal bleeding after myomectomy. Ultrasonography, magnetic resonance imaging (MRI), and three-dimensional computed tomography (CT) combined with hysterosalpingography (HSG) revealed an iatrogenic diverticulum of the uterus. The three-dimensional CT combined with HSG images were very useful for subsequent surgery.

Ability of chest X-ray to detect faint shadows documented as ground-glass attenuation in images of computed tomography: a comparison between flat-panel detector radiography and film-screen radiography.

PURPOSE: To compare flat-panel detector (FPD) radiography and film-screen (FS) radiography in detectability of faint shadows documented as ground-glass attenuation (GGA) areas in images of computed tomography (CT). MATERIALS AND METHODS: Study population was comprised of 50 patients who underwent FS and another 50 patients who underwent FPD. Standard of reference (SOR) was determined on the basis of area of GGA in all cross-sections of CT, in terms of GGA extent and presence or absence of GGA in each trisected lung fields (GGA distribution). Eight radiologists assessed the GGA extent with the 5-grade scale and the GGA distribution. Inter-observer variances of the GGA extents and distributions, degree of divergences and correspondence in the GGA extent and distributions with SOR, were compared between the FS and FPD by the jackknife method and Fisher's exact test. RESULTS: Inter-observer variance in the GGA extent and distribution were slightly larger in the FS than in the FPD. The GGA extent scale corresponded with SOR in the FS statistically significantly better (p=0.001), as the correct ratio was 0.428 in the FS and 0.310 in the FPD. Divergence in the GGA extent scale with SOR was smaller in the FS, as average kappa pseudo-value of Kendall's rank correlation coefficient was 0.474 in the FS and 0.433 in the FPD. CONCLUSION: These results indicate that some lesions of GGA documented in CT may not be reflected and are difficult to be detected in chest X-ray radiographs with the FPD.

Diagnosis of cerebral cortical vein thrombosis with T2* weighted magnetic resonance imaging.

A 47-year-old woman presented with paresthesia in her left arm and trunk. She was diagnosed as having an arterial pure sensory stroke at first presentation. On the second hospital day, left hemiparesis developed after convulsions. Magnetic resonance (MR) imaging revealed a hyperintense lesion involving the right parietal lobe on diffusion weighted image. The T2* weighted image disclosed a linear hypointense lesion in the same area. Progressive feature of her symptoms and T2* weighted MR image prompted us to perform MR venography. MR venography confirmed the diagnosis of cortical vein and sagittal sinus thrombosis. Her symptoms attenuated gradually after anticoagulation therapy. Gene analysis showed type I anti-thrombin III (ATIII) deficiency due to the novel mutation of AT III gene. T2* weighted imaging may be much more sensitive than other imaging to detect thrombosed cortical vein during the first week after onset. Rapid diagnosis induced appropriate treatment and monitoring of the patient.