17 February 2021 in Neuroradiology
21 September 2021 in Journal of Medical Internet Research
Background: Recently, the analysis of endolymphatic hydropses (EHs) via inner ear magnetic resonance imaging (MRI) for patients with Ménière disease has been attempted in various studies. In addition, artificial intelligence has rapidly been incorporated into the medical field. In our previous studies, an automated algorithm for EH analysis was developed by using a convolutional neural network. However, several limitations existed, and further studies were conducted to compensate for these limitations. Objective: The aim of this study is to develop a fully automated analytic system for measuring EH ratios that enhances EH analysis accuracy and clinical usability when studying Ménière disease via MRI. Methods: We proposed the 3into3Inception and 3intoUNet networks. Their network architectures were based on those of the Inception-v3 and U-Net networks, respectively. The developed networks were trained for inner ear segmentation by using the magnetic resonance images of 124 people and were embedded in a new, automated EH analysis system—inner-ear hydrops estimation via artificial intelligence (INHEARIT)-version 2 (INHEARIT-v2). After fivefold cross-validation, an additional test was performed by using 60 new, unseen magnetic resonance images to evaluate the performance of our system. The INHEARIT-v2 system has a new function that automatically selects representative images from a full MRI stack. Results: The average segmentation performance of the fivefold cross-validation was measured via the intersection of union method, resulting in performance values of 0.743 (SD 0.030) for the 3into3Inception network and 0.811 (SD 0.032) for the 3intoUNet network. The representative magnetic resonance slices (ie, from a data set of unseen magnetic resonance images) that were automatically selected by the INHEARIT-v2 system only differed from a maximum of 2 expert-selected slices. After comparing the ratios calculated by experienced physicians and those calculated by the INHEARIT-v2 system, we found that the average intraclass correlation coefficient for all cases was 0.941; the average intraclass correlation coefficient of the vestibules was 0.968, and that of the cochleae was 0.914. The time required for the fully automated system to accurately analyze EH ratios based on a patient's MRI stack was approximately 3.5 seconds. Conclusions: In this study, a fully automated full-stack magnetic resonance analysis system for measuring EH ratios was developed (named INHEARIT-v2), and the results showed that there was a high correlation between the expert-calculated EH ratio values and those calculated by the INHEARIT-v2 system. The system is an upgraded version of the INHEARIT system; it has higher segmentation performance and automatically selects representative images from an MRI stack. The new model can help clinicians by providing objective analysis results and reducing the workload for interpreting magnetic resonance images.
1 January 2023 in Korean Journal of Radiology
Jeong HS, et al. Korean J Radiol. 2023 Aug;24:e48. https://doi.org/10.3348/kjr.2022.0850
8 September 2020 in Journal of Neuro-Oncology
25 January 2018 in American Journal of Neuroradiology
BACKGROUND AND PURPOSE: Various tumors of the sinonasal tract can exhibit high signal intensity on T1WI. The purpose of this study was to determine the value of a septate pattern on precontrast T1WI for diagnosing sinonasal melanoma. MATERIALS AND METHODS: Retrospectively, 3 observers independently reviewed MR images of 31 histologically proved sinonasal melanomas with special attention to the presence or absence of a septate pattern on precontrast T1WI, defined as alternating hyperintense and hypointense striations on precontrast T1WI. For comparison, we evaluated the prevalence of a septate pattern on precontrast T1WI in 106 nonmelanomatous sinonasal malignant tumors with 16 different histologic types. We also tried to identify the histopathologic features responsible for the septate pattern on precontrast T1WI. RESULTS: Twenty-seven (87.1%) of 31 sinonasal melanomas showed hyperintense foci on T1WI, among which a septate pattern on precontrast T1WI was seen in 23 (74.2%), while 22 (20.8%) of 106 nonmelanomatous malignant tumors demonstrated hyperintense foci on T1WI, among which only 3 (2.8%) showed a septate pattern on precontrast T1WI. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of a septate pattern on precontrast T1WI for the diagnosis of sinonasal melanoma were 74%, 97%, 88%, 93%, and 92%, respectively. Although limited due to the retrospective nature, 4 of 23 histologically reviewed sinonasal melanomas revealed an uneven distribution of melanin with alternating melanin and fibrous bands within the tumors. CONCLUSIONS: A septate pattern on precontrast T1WI might be an adjunctive imaging finding for the diagnosis of sinonasal melanoma. This might be attributed histologically to an uneven distribution of melanin and hemorrhage within the tumors.
15 March 2021 in Journal of Pathology and Translational Medicine
Salivary gland tumors are histologically diverse, and each entity has distinctive histopathological and molecular features. We report two cases of salivary gland tumors with unique histological and molecular findings, which have not been documented previously. The tumors were located in the base of the tongue in both patients. Most tumor cells were arranged in cords and nests, giving a trabecularlike appearance. Focally, glandular structures with intraluminal mucin and perivascular pseudorosette-like configurations were identified. Tumor cells had eosinophilic to clear cytoplasm, and showed mild nuclear atypia. They were positive for pancytokeratin and negative for S-100, p63, c-KIT, androgen receptor, and neuroendocrine markers. Multiple foci of capsular or lymphovascular invasion were identified, but the Ki-67 labeling index was low (< 5%). Fluorescence in situ hybridization revealed concurrent alterations of MAML2 and EWSR1 gene. Further investigations with a larger number of cases with similar histological and molecular features will accurately classify this tumor.