Identifying key factors for predicting O6-Methylguanine-DNA methyltransferase status in adult patients with diffuse glioma: a multimodal analysis of demographics, radiomics, and MRI by variable Vision Transformer.

PURPOSE: This study aimed to perform multimodal analysis by vision transformer (vViT) in predicting O6-methylguanine-DNA methyl transferase (MGMT) promoter status among adult patients with diffuse glioma using demographics (sex and age), radiomic features, and MRI. METHODS: The training and test datasets contained 122 patients with 1,570 images and 30 patients with 484 images, respectively. The radiomic features were extracted from enhancing tumors (ET), necrotic tumor cores (NCR), and the peritumoral edematous/infiltrated tissues (ED) using contrast-enhanced T1-weighted images (CE-T1WI) and T2-weighted images (T2WI). The vViT had 9 sectors; 1 demographic sector, 6 radiomic sectors (CE-T1WI ET, CE-T1WI NCR, CE-T1WI ED, T2WI ET, T2WI NCR, and T2WI ED), 2 image sectors (CE-T1WI, and T2WI). Accuracy and area under the curve of receiver-operating characteristics (AUC-ROC) were calculated for the test dataset. The performance of vViT was compared with AlexNet, GoogleNet, VGG16, and ResNet by McNemar and Delong test. Permutation importance (PI) analysis with the Mann-Whitney U test was performed. RESULTS: The accuracy was 0.833 (95% confidence interval [95%CI]: 0.714-0.877) and the area under the curve of receiver-operating characteristics was 0.840 (0.650-0.995) in the patient-based analysis. The vViT had higher accuracy than VGG16 and ResNet, and had higher AUC-ROC than GoogleNet (p<0.05). The ED radiomic features extracted from the T2-weighted image demonstrated the highest importance (PI=0.239, 95%CI: 0.237-0.240) among all other sectors (p<0.0001). CONCLUSION: The vViT is a competent deep learning model in predicting MGMT status. The ED radiomic features of the T2-weighted image demonstrated the most dominant contribution.

Altered structural connectivity of pain-related brain network in burning mouth syndrome-investigation by graph analysis of probabilistic tractography.

PURPOSE: Burning mouth syndrome (BMS) is a chronic intraoral pain syndrome featuring idiopathic oral pain and burning discomfort despite clinically normal oral mucosa. The etiology of chronic pain syndrome is unclear, but preliminary neuroimaging research has suggested the alteration of volume, metabolism, blood flow, and diffusion at multiple brain regions. According to the neuromatrix theory of Melzack, pain sense is generated in the brain by the network of multiple pain-related brain regions. Therefore, the alteration of pain-related network is also assumed as an etiology of chronic pain. In this study, we investigated the brain network of BMS brain by using probabilistic tractography and graph analysis. METHODS: Fourteen BMS patients and 14 age-matched healthy controls underwent 1.5T MRI. Structural connectivity was calculated in 83 anatomically defined regions with probabilistic tractography of 60-axis diffusion tensor imaging and 3D T1-weighted imaging. Graph theory network analysis was used to evaluate the brain network at local and global connectivity. RESULTS: In BMS brain, a significant difference of local brain connectivity was recognized at the bilateral rostral anterior cingulate cortex, right medial orbitofrontal cortex, and left pars orbitalis which belong to the medial pain system; however, no significant difference was recognized at the lateral system including the somatic sensory cortex. A strengthened connection of the anterior cingulate cortex and medial prefrontal cortex with the basal ganglia, thalamus, and brain stem was revealed. CONCLUSION: Structural brain network analysis revealed the alteration of the medial system of the pain-related brain network in chronic pain syndrome.

Predicting isocitrate dehydrogenase status among adult patients with diffuse glioma using patient characteristics, radiomic features, and magnetic resonance imaging: Multi-modal analysis by variable vision transformer.

OBJECTIVES: To evaluate the performance of the multimodal model, termed variable Vision Transformer (vViT), in the task of predicting isocitrate dehydrogenase (IDH) status among adult patients with diffuse glioma. MATERIALS AND METHODS: vViT was designed to predict IDH status using patient characteristics (sex and age), radiomic features, and contrast-enhanced T1-weighted images (CE-T1WI). Radiomic features were extracted from each enhancing tumor (ET), necrotic tumor core (NCR), and peritumoral edematous/infiltrated tissue (ED). CE-T1WI were split into four images and input to vViT. In the training, internal test, and external test, 271 patients with 1070 images (535 IDH wildtype, 535 IDH mutant), 35 patients with 194 images (97 IDH wildtype, 97 IDH mutant), and 291 patients with 872 images (436 IDH wildtype, 436 IDH mutant) were analyzed, respectively. Metrics including accuracy and AUC-ROC were calculated for the internal and external test datasets. Permutation importance analysis combined with the Mann-Whitney U test was performed to compare inputs. RESULTS: For the internal test dataset, vViT correctly predicted IDH status for all patients. For the external test dataset, an accuracy of 0.935 (95% confidence interval; 0.913-0.945) and AUC-ROC of 0.887 (0.798-0.956) were obtained. For both internal and external test datasets, CE-T1WI ET radiomic features and patient characteristics had higher importance than other inputs (p < 0.05). CONCLUSIONS: The vViT has the potential to be a competent model in predicting IDH status among adult patients with diffuse glioma. Our results indicate that age, sex, and CE-T1WI ET radiomic features have key information in estimating IDH status.

Isolated tuberculous liver abscess invading the abdominal wall: report of a case.

Isolated tuberculous liver parenchymal and subcapsular abscesses are unusual,^but an abdominal wall abscess secondary to a tubercular liver abscess is extremely rare. To our knowledge, there is only one reported case of an abdominal wall abscess occurring secondary to a subcapsular liver abscess. We report the first documented case of direct invasion of the abdominal wall from an isolated tuberculous liver parenchymal abscess, diagnosed by imaging, surgical, and pathological findings. Although ultrasonography and computed tomography showed nonspecific hypoechoic and hypodense findings with peripheral contrast enhancement, T2-weighted magnetic resonance imaging (MRI) revealed a heterogeneous mass with characteristic hypointensity, suggesting the presence of free radicals produced by macrophages during active phagocytosis in tuberculosis. Although our case is extremely unusual, when hypointensity on T2-weighted MRI is seen, the possibility of tuberculosis should be considered and the results of polymerase chain reaction, culture, and histopathological diagnosis must be taken into account to avoid needless invasive surgery.

Data management solution for large-volume computed tomography in an existing picture archiving and communication system (PACS).

Multidetector row computed tomography (MDCT) creates massive amounts of data, which can overload a picture archiving and communication system (PACS). To solve this problem, we designed a new data storage and image interpretation system in an existing PACS. Two MDCT image datasets, a thick- and a thin-section dataset, and a single-detector CT thick-section dataset were reconstructed. The thin-section dataset was archived in existing PACS disk space reserved for temporary storage, and the system overwrote the source data to preserve available disk space. The thick-section datasets were archived permanently. Multiplanar reformation (MPR) images were reconstructed from the stored thin-section datasets on the PACS workstation. In regular interpretations by eight radiologists during the same week, the volume of images and the times taken for interpretation of thick-section images with (246 CT examinations) or without (170 CT examinations) thin-section images were recorded, and the diagnostic usefulness of the thin-section images was evaluated. Thin-section datasets and MPR images were used in 79% and 18% of cases, respectively. The radiologists' assessments of this system were useful, though the volume of images and times taken to archive, retrieve, and interpret thick-section images together with thin-section images were significantly greater than the times taken without thin-section images. The limitations were compensated for by the usefulness of thin-section images. This data storage and image interpretation system improves the storage and availability of the thin-section datasets of MDCT and can prevent overloading problems in an existing PACS for the moment.

A computer-assisted system for diagnostic workstations: automated bone labeling for CT images.

Although accurate information on thoracolumbar bone structure is essential when computed tomography (CT) images are examined, there is no automated method of labeling all the vertebrae and ribs on a CT scan. We are developing a computer-aided diagnosis system that labels ribs and thoracolumbar vertebrae automatically and have evaluated its accuracy. A candidate bone was extracted from the CT image volume data by pixel thresholding and connectivity analysis. All non-bony anatomical structures were removed using a linear discriminate of distribution of CT values and anatomical characteristics. The vertebrae were separated from the ribs on the basis of their distances from the centers of the vertebral bodies. Finally, the thoracic cage and lumbar vertebrae were extracted, and each vertebra was labeled with its own anatomical number by histogram analysis along the craniocaudal midline. The ribs were labeled in a similar manner, based on location data. Twenty-three cases were used for accuracy comparison between our method and the radiologist's. The automated labeling of the thoracolumbar vertebrae was concordant with the judgments of the radiologist in all cases, and all but the first and second ribs were labeled correctly. These two ribs were frequently misidentified, presumably because of pericostal anatomical clutter or high densities of contrast material in the injected veins. We are confident that this system can contribute usefully as part of a picture archiving and communication system workstation, though further technical improvement is required for identification of the upper ribs.

Granular cell tumor of the neurohypophysis with optic tract edema.

Granular cell tumor of the neurohypophysis is a rare disease entity. To our knowledge, this is the first report concerning a granular cell tumor of the neurohypophysis associated with optic tract edema. A 55-year-old man underwent brain magnetic resonance imaging (MRI) for a medical check-up, and a suprasellar tumor was detected. Brain computed tomography (CT) demonstrated a well delineated, homogenous, slightly hyperdense suprasellar tumor. MRI detected a lobular tumor that was isointense on T1-weighted images, hypointense on T2-weighted images, and showed homogeneous enhancement after administration of a gadopentetate dimeglumine. T2-weighted images and fluid-attenuated inversion recovery (FLAIR) images demonstrated a hyperintense region in the optic tract. Subtotal tumor resection was performed, and histological examination confirmed the diagnosis of granular cell tumor. Postoperative MRI showed that the tumor volume was reduced and optic tract edema diminished compared with the preoperative findings. We also review the literature focusing on radiographic findings, and compare the effectiveness of MRI and CT for diagnosing granular cell tumor of the neurohypophysis.

Efficacy of distortion correction on diffusion imaging: comparison of FSL eddy and eddy_correct using 30 and 60 directions diffusion encoding.

Diffusion imaging is a unique noninvasive tool to detect brain white matter trajectory and integrity in vivo. However, this technique suffers from spatial distortion and signal pileup or dropout originating from local susceptibility gradients and eddy currents. Although there are several methods to mitigate these problems, most techniques can be applicable either to susceptibility or eddy-current induced distortion alone with a few exceptions. The present study compared the correction efficiency of FSL tools, "eddy_correct" and the combination of "eddy" and "topup" in terms of diffusion-derived fractional anisotropy (FA). The brain diffusion images were acquired from 10 healthy subjects using 30 and 60 directions encoding schemes based on the electrostatic repulsive forces. For the 30 directions encoding, 2 sets of diffusion images were acquired with the same parameters, except for the phase-encode blips which had opposing polarities along the anteroposterior direction. For the 60 directions encoding, non-diffusion-weighted and diffusion-weighted images were obtained with forward phase-encoding blips and non-diffusion-weighted images with the same parameter, except for the phase-encode blips, which had opposing polarities. FA images without and with distortion correction were compared in a voxel-wise manner with tract-based spatial statistics. We showed that images corrected with eddy and topup possessed higher FA values than images uncorrected and corrected with eddy_correct with trilinear (FSL default setting) or spline interpolation in most white matter skeletons, using both encoding schemes. Furthermore, the 60 directions encoding scheme was superior as measured by increased FA values to the 30 directions encoding scheme, despite comparable acquisition time. This study supports the combination of eddy and topup as a superior correction tool in diffusion imaging rather than the eddy_correct tool, especially with trilinear interpolation, using 60 directions encoding scheme.

Diffusion tensor imaging analysis for psychiatric disorders.

The pathophysiology of psychiatric disorders is complex and cannot be easily assessed by laboratory studies. Diffusion tensor imaging (DTI) is a magnetic resonance imaging technique increasingly used for noninvasive and quantitative evaluation of abnormalities of the cerebral white matter because it provides exquisite details on tissue microstructures and also can perform sophisticated computer-based analyses. We review basic principles of DTI; methods of diffusion tensor analysis; recent DTI findings in major psychiatric diseases, such as schizophrenia, bipolar disorder, major depressive disorder, and anxiety disorder; and factors to keep in mind when interpreting the results of DTI analysis. We recommend the frequent use of DTI as a routine clinical protocol to assess white matter abnormalities in patients with psychiatric disorders.

Radiological assessment following thermoradiation therapy for primary pleural synovial sarcoma: case report.

Primary pleural synovial sarcoma is a rare disease with poor outcomes. Although hyperthermia therapy as part of a combined treatment regimen can offer improved local tumor control, only two reports of hyperthermia therapy for synovial sarcoma have appeared in the literature, and these sarcomas were not of pleuropulmonary origin. This report of an advanced inoperable primary pleural synovial sarcoma is the first to address the use of hyperthermia therapy in combination with chemoradiotherapy for this disease, together with radiological assessment following that therapy. Computed tomography performed after thermoradiation showed a decrease in tumor size and a characteristic unenhanced low-density area in the tumor suggesting that tumor necrosis resulted from the therapy. These image findings were helpful in assessing the tumor response to thermoradiation. We believe that hyperthermia therapy combined with chemoradiotherapy should be regarded as an option for advanced primary pleural synovial sarcoma. This would give computed tomography important role in evaluating this approach.