Deep-learning algorithm to detect fibrosing interstitial lung disease on chest radiographs.

BACKGROUND: Antifibrotic therapies are available to treat chronic fibrosing interstitial lung diseases (CF-ILDs), including idiopathic pulmonary fibrosis. Early use of these treatments is recommended to slow deterioration of respiratory function and to prevent acute exacerbation. However, identifying patients in the early stages of CF-ILD using chest radiographs is challenging. In this study, we developed and tested a deep-learning algorithm to detect CF-ILD using chest radiograph images. METHOD: From the image archive of Sapporo Medical University Hospital, 653 chest radiographs from 263 patients with CF-ILDs and 506 from 506 patients without CF-ILD were identified; 921 were used for deep learning and 238 were used for algorithm testing. The algorithm was designed to output a numerical score ranging from 0 to 1, representing the probability of CF-ILD. Using the testing dataset, the algorithm's capability to identify CF-ILD was compared with that of doctors. A second dataset, in which CF-ILD was confirmed using computed tomography images, was used to further evaluate the algorithm's performance. RESULTS: The area under the receiver operating characteristic curve, which indicates the algorithm's detection capability, was 0.979. Using a score cut-off of 0.267, the sensitivity and specificity of detection were 0.896 and 1.000, respectively. These data showed that the algorithm's performance was noninferior to that of doctors, including pulmonologists and radiologists; performance was verified using the second dataset. CONCLUSIONS: We developed a deep-learning algorithm to detect CF-ILDs using chest radiograph images. The algorithm's detection capability was noninferior to that of doctors.

Lateral Position With Gantry Tilt Further Improves Computed Tomography Image Quality Reconstructed Using Single-Energy Metal Artifact Reduction Algorithm in the Oral Cavity.

OBJECTIVE: To assess the limitations of single-energy metal artifact reduction algorithm in the oral cavity and evaluate the availability of a solution by setting the patient in a lateral position (LP) with the use of a gantry tilt (GT). METHODS: We analyzed 88 patients with dental metals retrospectively in study 1, and 74 patients prospectively in study 2. Patients were classified: metal I with dental metals in 1 region, metal II in 2 regions, and metal III in 3 regions. Patients underwent neck computed tomography examinations in a supine position (SP) in study 1, and 2 positions, an LP with a GT and an SP, in study 2. All images were reconstructed with this algorithm. Image quality was scored using a 4-point scale: 1 = severe artifact, 2 = moderate artifact, 3 = slight artifact, 4 = no artifact. The scores were compared between metal I, metal II, and metal III using the Mann-Whitney U test in study 1, and between an LP with a GT and an SP using the Wilcoxon signed ranks test in study 2. RESULTS: The scores outside the dental arch were significantly higher in metal I than in metal II and metal III (3.0 ± 0.6 vs 2.3 ± 0.5 vs 2.2 ± 0.4; P < 0.0001 for metal I vs metal II and for metal I vs metal III) and significantly higher in an LP with a GT than an SP (3.2 ± 0.4 vs 2.3 ± 0.4; P < 0.0001). CONCLUSIONS: Single-energy metal artifact reduction algorithm could reduce metal artifacts adequately in patients with dental metals in 1 region, but not in 2 or more regions. However, even for the latter, combination of this algorithm and an LP with a GT could further improve the image quality.

Repeatability analysis of ADC histogram metrics of the uterus.

BACKGROUND: Recently, histogram analysis based on voxel-wise apparent diffusion coefficient (ADC) value distribution has been increasingly performed. However, few studies have been reported regarding its repeatability. PURPOSE: To evaluate the repeatability of ADC histogram metrics of the uterus in clinical magnetic resonance imaging (MRI). MATERIAL AND METHODS: Thirty-three female patients who underwent pelvic MRI including diffusion-weighted imaging (DWI) were prospectively included after providing informed consent. Two sequential DWI acquisitions with identical parameters and position were obtained. Regions of interest (ROIs) for histologically confirmed uterine lesions (five cervical and three endometrial cancers, and one endometrial hyperplasia) and normal appearing tissues (21 endometrium and 33 myometrium) were assigned on the first DWI dataset and then pasted onto the second DWI dataset. ADC histogram metrics within the ROIs were calculated and repeatability was evaluated by calculating within-subject coefficient of variance (%) (wCV (%)) and Bland-Altman plot (%). RESULTS: ADC 10%, 25%, median, 75%, 90%, maximum, mean, and entropy showed high repeatability (wCV (%) < 7, 95% limit of agreement in Bland-Altman plot (%) < ±20), followed by ADC minimum (wCV (%) = 8.12, 95% limit of agreement in Bland-Altman plot (%) < ±30). However, ADC skewness and kurtosis showed very low repeatability in all evaluations. CONCLUSION: ADC histogram metrics like ADC 10%, 25%, median, 75%, 90%, maximum, mean, and entropy are robust biomarkers and could be applicable to clinical use. However, ADC skewness and kurtosis lack robustness. Radiologists should keep these characteristics and limitations in mind when interpreting quantitative DWI.

Three cases of implantation of a SureScan® system and MRI for investigating causes of pain.

We report three cases of implantation of the SureScan® system and magnetic resonance imaging (MRI) for investigating causes of pain. Although there were metal-induced artifacts on the MR images of 2 patients, the artifacts did not affect the images of structures that needed to be assessed to make the diagnosis. The SureScan® system enabled patients implanted with spinal cord stimulation devices to undergo MRI.

The signal intensity ratio of the optic nerve to ipsilateral frontal white matter is of value in the diagnosis of acute optic neuritis.

OBJECTIVES: To evaluate the usefulness of the signal intensity ratio (SIR) of the optic nerve to the white matter (WM) on short tau inversion recovery (STIR) images to diagnose acute optic neuritis (AON). METHODS: The 405 consecutive patients with suspected orbital diseases underwent orbital magnetic resonance imaging (MRI) using a 3-T scanner between June 2008 and August 2011. Among them, 108 optic nerves (33 AON and 75 control) were retrospectively analysed. The averaged SIR (SIRave) and maximum SIR (SIRmax) were defined as the averaged signal intensity (SI) of the optic nerve divided by that of WM, and the maximum SI of the optic nerve divided by averaged SI of WM, respectively. These values were compared between AON and control using the Mann-Whitney U test. A P < 0.05 was considered statistically significant. RESULTS: SIRave and SIRmax were significantly (P < 0.001) higher in the AON compared to the control. At a cut-off SIRave value of 1.119, the sensitivity, specificity and accuracy were 0.939, 0.840, and 0.870; and at a cut-off SIRmax value of 1.281, these were 1.000, 0.720 and 0.806, respectively. CONCLUSION: The SIR of the optic nerve to WM on STIR images is of value in diagnosing AON. KEY POINTS: • We propose a method of diagnosing acute optic neuritis using 3-T MRI. • Our method is simple and objective and requires no novel imaging techniques. • Our method shows high diagnostic accuracy.

Imprint cytology of biphenotypic sinonasal sarcoma of the paranasal sinus: A case report.

Biphenotypic sinonasal sarcoma (BSNS) is a rare low-grade spindle cell sarcoma that predominantly affects middle-aged women with multiple tumors in the sinonasal tract. BSNS shows biphenotypic expression of neural and myogenic markers on immunohistochemistry (IHC) with a specific chimeric PAX3-MAML3 fusion. The cytological features of BSNS have so far not been reported. Here, we describe a case of BSNS including findings of imprint cytology, histology, IHC, and genetic analysis. A 30-year-old woman presented with a nodular tumor that completely occupied the ethmoid sinus. The tumor was resected and submitted for imprint cytology, which revealed relatively bland spindle tumor cells that had mildly enlarged oval to spindle-shaped nuclei with fine nuclear chromatin and a thin nuclear rim in a clear background. Nucleoli were inconspicuous and there was no significant nuclear atypia and pleomorphism. These cytological findings were consistent with the histology of low-grade spindle cell sarcoma in BSNS. On IHC, the tumor cells were focally positive for S-100 protein and α-smooth muscle actin; nuclear ß-catenin expression was also seen. PAX3 split signals were detected in 52% of tumor cells by fluorescence in situ hybridization. Reverse transcriptase-polymerase chain reaction also identified a chimeric PAX3-MAML3 fusion gene. Based on these findings, we diagnosed the tumor as BSNS. Our findings revealed that a relatively bland spindle cell cytology with a clear background is a characteristic feature of BSNS. BSNS should therefore be differentiated from benign and bland-appearing malignant spindle cell tumors and the combination of cytology, histology, IHC, and genetic analysis facilitates the diagnosis of BSNS.

The Difference in Gender Affects the Pathogenesis of Ligamentum Flavum Hypertrophy.

INTRODUCTION: Gender differences may play a role in the pathogenesis of lumbar spinal stenosis. However, few reports that discuss the effects of gender differences in ligamentum flavum (LF) hypertrophy have been published, and no study has investigated the relationship between LF thickness and the quantitative value of intervertebral disc (IVD) degeneration. This study aimed to investigate the impact of gender on the pathomechanisms underlying LF hypertrophy, focusing on the relationship among LF thickness, IVD degeneration, and age. METHODS: The subjects include 100 patients with low back pain and leg numbness, tingling, or pain. We measured LF thickness and the T2 values of IVDs using MR imaging and analyzed the relationship among LF thickness, T2 values of IVDs, and age. The interclass correlation coefficient (ICC) was calculated as the inter-rater reliability between the LF thickness values measured by two investigators. RESULTS: ICC was calculated for the two measurements of LF thickness (r = 0.923, 95% CI: 0.907-0.936). No statistically significant difference in the T2 values of IVDs was observed between females and males from L2/3 to L5/S. There were significantly negative linear correlations between LF thickness and the T2 values of IVDs at all levels, but this correlation was not observed in females at L4/5. There were significantly negative linear correlations between age and the T2 values of IVDs from L2/3 to L5/S for all patients, females, and males (r = 0.422-0.756). In addition, there were significantly positive linear correlations between age and LF thickness from L2/3 to L4/5 for all patients (r = 0.329-0.361) and females (r = 0.411-0.481). Correlations were not observed for males at all levels or for all patients at L5/S. CONCLUSIONS: The relationships identified among LF thickness, age, and IVD degeneration suggest that gender differences play a role in the pathogenesis of LF hypertrophy.

Differentiating spinal intradural-extramedullary schwannoma from meningioma using MRI T2 weighted images.

OBJECTIVE:: Prior studies advocate the subjective visual differences between meningioma and schwannoma on T2 weighted images, however objective measurement of signal intensity differences may be useful in certain cases. The aim of this study was to investigate whether an objective evaluation of SIs on T2 weighted images would be useful to differentiate spinal schwannomas from meningiomas. METHODS:: The patients with spinal MRIs demonstrating path proven and subsequently treated intradural extramedullary spinal tumors were selected between April 2008 and May 2017. Regions of interest (ROIs) were measured in the tumor and subcutaneous fat on the same image, and we calculated the SI ratio between tumor and fat ROIs. RESULTS:: Twenty patients each with meningioma and schwannoma were enrolled. The SI ratios of schwannomas were significantly higher than those of meningiomas (both researcher 1 and 2: p = 0.002). The areas under the curve by researchers 1 and 2 were 0.780. The cutoff value of SI ratio by both of researchers 1 and 2 to differentiate between schwannomas from meningiomas was 0.420 (sensitivity: 80.0%, specificity: 70.0-75.0%). CONCLUSION:: The SI ratio, calculated from the SIs of the tumor and fat on T2 weighted images, is useful for differentiating spinal schwannomas from meningiomas to obtain an accurate diagnosis. ADVANCES IN KNOWLEDGE:: Signal intensity ratio of the spinal tumor and fat on T2 weighted images is useful for differentiating schwannomas from meningiomas to obtain an accurate diagnosis.

Vascular measurement changes observed using postmortem computed tomography.

PURPOSE: Postmortem vascular changes were quantitatively analyzed in the aorta and vena cava and compared with antemortem findings as a basis for distinguishing between normal postmortem changes and pathological changes. MATERIALS AND METHODS: Whole-body computed tomography (CT) was performed on 12 individuals before and after death. The scans, performed at seven levels (five for the aorta, two for the vena cava) within the vasculature, allowed various measurements to be made on the same individual before and after death. RESULTS: Postmortem long-axis diameter, short-axis diameter, and the square of the radius of the aorta were 79.2-85.0 % (mean 81.3 %), 55.6-80.0 % (68.0 %), and 48.5-71.4 % (60.8 %) of the antemortem measurements, respectively. The ante- and postmortem measurements of the long and short axes and the caliber of the aorta were statistically different (p < 0.05). The superior vena cava (SVC) was increased in size: the short-axis diameter and the square of the radius were both statistically different after death. None of the measured parameters of the inferior vena cava (IVC) changed significantly following death. CONCLUSION: In postmortem images, the aortic diameter decreased and changes in the size and shape of the SVC were noted. The IVC did not exhibit significant postmortem changes.

MR angiography for detecting the artery of Adamkiewicz and its branching level from the aorta.

PURPOSE: We evaluated the efficacy of magnetic resonance angiography (MRA) for detecting the artery of Adamkiewicz (AKA) and the vertebral level of its feeding arteries branching from the aorta. MATERIALS AND METHODS: Eighty-two patients (67 men, 15 women; aged 34 to 86 years, mean age 68.6 years) with thoracic descending and thoracoabdominal aortic lesions (aneurysm in 55, dissection in 25, coarctation in 2) underwent MRA to detect AKA. MRA was performed using 6-phase, dynamic-enhanced, 3-dimensional, fast spoiled gradient recalled acquisition in steady state (GRASS) on a 1.5-tesla (T) system, with double-dose bolus contrast injection. The vertebral levels of AKA branching and the AKA feeder artery branching from the aorta were determined. RESULTS: The AKA was detected in 67 patients (81.7%). Branching of AKA occurred at levels T7 to T12 on the left side (n=52) and on the right (n=15). Vascular continuity from the aorta to the anterior spinal artery was demonstrated in 55 patients (67.1%). Comparing the vertebral level of arterial branching from the aorta to that of the AKA at the intervertebral foramen, the AKA branched at the same vertebral level in 44 patients (80.0%), one vertebral level above/below in 10 (18.2%), and 2 vertebral levels above in one (1.8%). CONCLUSION: MRA can be useful in the preoperative work-up of patients with thoracoabdominal aortic lesions to localize AKA and the segmental trajectories of vessels supplying blood to the AKA.

[Neonatal cystic structure adjacent to frontal horn--MRI features].

PURPOSE: To evaluate the incidence and features of cystic structures adjacent to the frontal horns of neonates using MRI, and to assess the clinical features of the neonates. MATERIALS AND METHODS: Between April 2001 and January 2005, MRI examinations were performed at our hospital in 352 neonates and infants whose postconceptional age was less than 48 weeks. We retrospectively evaluated the MRI findings and the clinical records. RESULTS: Seventeen babies (8 males and 9 females) showed cystic structures adjacent to frontal horns, hemilaterally or bilaterally. The incidence of the cysts was 4.8% in total, and was 1.4% (1/74), 9.2% (6/65), and 4.7% (10/213)in term infants, preterm infants born at 33-36 weeks of gestational age, and at less than 32 weeks, respectively. The cysts ranged from 1 to 8 mm in diameter, and were located in the white matter adjacent to ventricular walls and in the portion cephalad to the frontal horns. The cysts resolved in 5 cases (with follow-up ranging from 3 months to 2 years of age), causing slight dilatation of the frontal horn. Developmental disturbances were not observed in patients without other abnormalities. CONCLUSION: Cystic structures near the frontal horns in neonates are detected by MRI at a rate of 4.8%. They will resolve spontaneously without causing developmental abnormalities.