Applications of artificial intelligence in interventional oncology: An up-to-date review of the literature.

Interventional oncology provides image-guided therapies, including transarterial tumor embolization and percutaneous tumor ablation, for malignant tumors in a minimally invasive manner. As in other medical fields, the application of artificial intelligence (AI) in interventional oncology has garnered significant attention. This narrative review describes the current state of AI applications in interventional oncology based on recent literature. A literature search revealed a rapid increase in the number of studies relevant to this topic recently. Investigators have attempted to use AI for various tasks, including automatic segmentation of organs, tumors, and treatment areas; treatment simulation; improvement of intraprocedural image quality; prediction of treatment outcomes; and detection of post-treatment recurrence. Among these, the AI-based prediction of treatment outcomes has been the most studied. Various deep and conventional machine learning algorithms have been proposed for these tasks. Radiomics has often been incorporated into prediction and detection models. Current literature suggests that AI is potentially useful in various aspects of interventional oncology, from treatment planning to post-treatment follow-up. However, most AI-based methods discussed in this review are still at the research stage, and few have been implemented in clinical practice. To achieve widespread adoption of AI technologies in interventional oncology procedures, further research on their reliability and clinical utility is necessary. Nevertheless, considering the rapid research progress in this field, various AI technologies will be integrated into interventional oncology practices in the near future.

Generative AI and large language models in nuclear medicine: current status and future prospects.

This review explores the potential applications of Large Language Models (LLMs) in nuclear medicine, especially nuclear medicine examinations such as PET and SPECT, reviewing recent advancements in both fields. Despite the rapid adoption of LLMs in various medical specialties, their integration into nuclear medicine has not yet been sufficiently explored. We first discuss the latest developments in nuclear medicine, including new radiopharmaceuticals, imaging techniques, and clinical applications. We then analyze how LLMs are being utilized in radiology, particularly in report generation, image interpretation, and medical education. We highlight the potential of LLMs to enhance nuclear medicine practices, such as improving report structuring, assisting in diagnosis, and facilitating research. However, challenges remain, including the need for improved reliability, explainability, and bias reduction in LLMs. The review also addresses the ethical considerations and potential limitations of AI in healthcare. In conclusion, LLMs have significant potential to transform existing frameworks in nuclear medicine, making it a critical area for future research and development.

Correlation of Endolysmphatic Duct Signal Intensity With Clinical Features in Otological Diseases.

OBJECTIVE: Bilateral high signal intensity (SI) in the endolymphatic duct (ED) on magnetic resonance imaging (MRI) has been reported as a common characteristic in ears with large vestibular aqueduct syndrome (LVAS). However, the significance of bilateral high SI in the ED remains unknown. The present study aimed to compare the correlation between SI in the ED and the clinical manifestations in various otological disorders and consider the significance of the MRI findings. STUDY DESIGN: Retrospective study. SETTING: University hospital. PATIENTS: The study included 2,450 ears from 1,225 patients with various otological disorders. INTERVENTION: All ears underwent 3T enhanced MRI and were evaluated for the degree of endolymphatic hydrops (EH) and the SI ratios (SIRs; i.e., the calculation between SIs in the ED and those in the cerebellum). MAIN OUTCOME MEASURE: The imaging findings were compared with their clinical symptoms. RESULTS: Ears with bilateral high SIRs in the ED tended to have considerably less occurrence of EH in both the cochlea and vestibule than those with bilateral low SIRs. Ears with SIR ≥8 showed significantly elevated hearing thresholds at lower frequencies on pure-tone audiometry, although they exhibited a markedly lower incidence of cochlear EH than those with SIR <8. Moreover, ears with vertigo exhibited notably higher SIRs than those without vertigo. CONCLUSION: Bilateral high SI in the ED on MRI may reflect pathophysiology underlying sensorineural hearing loss and vestibular symptoms, which are not associated with EH formation.

Comparing Lesion Conspicuity and ADC Reliability in High-resolution Diffusion-weighted Imaging of the Breast.

PURPOSE: This study investigated the breast lesion conspicuity and apparent diffusion coefficient (ADC) reliability for three different diffusion-weighted imaging (DWI) protocols: spatiotemporal encoding (SPEN), single-shot echo-planar imaging (SS-EPI), and readout segmentation of long variable echo-trains (RESOLVE). METHODS: Sixty-five women suspected of having breast tumors were included in this study, with 44 lesions (36 malignant, 8 benign) analyzed further. Breast MRI was performed on a 3 Tesla (3T) system (MAGNETOM Prisma, Siemens) equipped with a dedicated 18-channel breast array coil for a phantom and patients. Three DWI protocols-SPEN, SS-EPI, and RESOLVE-were used. SS-EPI was acquired with an in-plane resolution of 2 × 2 mm2, a slice thickness of 3 mm, and b-values of 0 and 1000 s/mm2. SPEN had a higher in-plane resolution of 1 × 1 mm2, a slice thickness of 1.5 mm, and b-values of 0, 850, and 1500 s/mm2. RESOLVE was acquired with an in-plane resolution of 1 × 1 mm2, a slice thickness of 1.5 mm, and b-values of 0 and 850 s/mm2. Lesion conspicuity and ADC values were evaluated. RESULTS: The average lesion conspicuity scores were significantly higher for RESOLVE (3.54 ± 0.65) than for SPEN (3.07 ± 0.91) or SS-EPI (2.48 ± 0.78) (P < 0.01). The SPEN score was significantly higher than the SS-EPI score (P < 0.01). Phantom measurements indicated marginally lower ADC values for SPEN compared to SS-EPI and RESOLVE across all concentrations. The results revealed that SPEN (b = 0, 850, 1500 sec/mm2) yielded significantly lower ADC values compared to SPEN (b = 0, 850 sec/mm2) in malignant lesions (P < 0.01), with no significant difference observed between SPEN (b = 0, 850 sec/mm2), SS-EPI, and RESOLVE. For benign lesions, no significant difference in ADC values was found between SPEN (b = 0, 850 sec/mm2), SPEN (b = 0, 850, 1500 sec/mm2), SS-EPI, and RESOLVE. CONCLUSION: RESOLVE provided the highest lesion conspicuity, and ADC values in breast lesions were not significantly different among sequences ranging b values 850-1000 sec/mm2. SPEN with higher b-values (0, 850, 1500 vs. 0, 850 sec/mm2) yielded significantly lower ADC values in malignant lesions, highlighting the importance of b-value selection in ADC quantification.

Recent trends in AI applications for pelvic MRI: a comprehensive review.

Magnetic resonance imaging (MRI) is an essential tool for evaluating pelvic disorders affecting the prostate, bladder, uterus, ovaries, and/or rectum. Since the diagnostic pathway of pelvic MRI can involve various complex procedures depending on the affected organ, the Reporting and Data System (RADS) is used to standardize image acquisition and interpretation. Artificial intelligence (AI), which encompasses machine learning and deep learning algorithms, has been integrated into both pelvic MRI and the RADS, particularly for prostate MRI. This review outlines recent developments in the use of AI in various stages of the pelvic MRI diagnostic pathway, including image acquisition, image reconstruction, organ and lesion segmentation, lesion detection and classification, and risk stratification, with special emphasis on recent trends in multi-center studies, which can help to improve the generalizability of AI.

Visualization of distribution in the vitreous cavity via eye drops using ultra-heavily T2-weighted sequences in MRI: a preliminary study with enucleated pig eyes.

We investigated whether magnetic resonance imaging can visualize the distribution in the vitreous cavity via eye drops of ophthalmic solutions, gadolinium-based contrast agent, and 17O-water, and to clarify the usefulness of ultra-heavily T2-weighted sequences in the research of intraocular distribution. Five different solutions (V-ROHTO, TRAVATANZ, gadobutrol, H217O, and saline) were administered to excised pig eye specimens. The samples were scanned using T1 mapping, T2 mapping, 3D T2-weighted (echo times (TE): 500, 3200, and 4500 ms), a half-Fourier single-shot turbo-spin echo sequence (HASTE; TE: 440 and 3000 ms), and 3D-real inversion-recovery before eye drops administration. Subsequently, we used a plastic dropper to drop a 0.5 mL solution each, and images were obtained up to 26 h later. Temporal changes in the T1 and T2 values of the anterior chamber and vitreous cavity were compared. The other sequences were evaluated by determining temporal signal changes as signal intensity ratio (SIR) compared to "No drop." The T1 and T2 values of samples treated with gadobutrol and H217O decreased over time. The SIR of samples treated with gadobutrol and H217O showed remarkable changes in the 3D T2-weighted images, whereas no remarkable temporal changes were observed in the other solutions. Longer TEs resulted in remarkable changes. We demonstrated that visualization of distribution in the vitreous cavity via eye drops could be achieved with excised pig eyes using gadobutrol and H217O, but not with ophthalmic solutions. Ultra-heavily T2-weighted sequences may be promising for the early and highly sensitive visualization of the intraocular distribution of eye drops.

Efficacy of 100 hz sound stimulation on saccular dysfunction in meniere's disease.

BACKGROUND: Although various medical remedies have been attempted to alleviate the symptoms of Meniere's disease (MD), the risk-benefit ratios of these various treatments remain debatable. OBJECTIVE: We investigated the efficacy of sound stimulation of 100 Hz for treating vestibular dysfunction in patients with Meniere's disease (MD). MATERIALS AND METHODS: Patients with definitive MD with intractable vestibular symptoms and endolymphatic hydrops (EH) in the inner ear were evaluated. The experimental group received sound stimulation of 75 dB at a frequency of 100 Hz for 5 min, and the control group received sound stimulation of 75 dB at a frequency of 250 Hz for 5 min. Cervical vestibular-evoked myogenic potentials (cVEMPs) were measured before and after each sound stimulation, and the results of the clinical tests were compared between the two patient groups. RESULTS: Significant increases in cVEMP amplitudes were observed after sound stimulation of 100 Hz in ears with vestibular endolymphatic hydrops, although no such improvement was observed in the control group. CONCLUSION: Sound stimulation of 75 dB at a frequency of 100 Hz leads to improvement in cVEMP amplitude in patients with definitive MD. Adequate sound stimulation might be a new method for treating vestibular dysfunction associated with MD.

Climate change and artificial intelligence in healthcare: Review and recommendations towards a sustainable future.

The rapid advancement of artificial intelligence (AI) in healthcare has revolutionized the industry, offering significant improvements in diagnostic accuracy, efficiency, and patient outcomes. However, the increasing adoption of AI systems also raises concerns about their environmental impact, particularly in the context of climate change. This review explores the intersection of climate change and AI in healthcare, examining the challenges posed by the energy consumption and carbon footprint of AI systems, as well as the potential solutions to mitigate their environmental impact. The review highlights the energy-intensive nature of AI model training and deployment, the contribution of data centers to greenhouse gas emissions, and the generation of electronic waste. To address these challenges, the development of energy-efficient AI models, the adoption of green computing practices, and the integration of renewable energy sources are discussed as potential solutions. The review also emphasizes the role of AI in optimizing healthcare workflows, reducing resource waste, and facilitating sustainable practices such as telemedicine. Furthermore, the importance of policy and governance frameworks, global initiatives, and collaborative efforts in promoting sustainable AI practices in healthcare is explored. The review concludes by outlining best practices for sustainable AI deployment, including eco-design, lifecycle assessment, responsible data management, and continuous monitoring and improvement. As the healthcare industry continues to embrace AI technologies, prioritizing sustainability and environmental responsibility is crucial to ensure that the benefits of AI are realized while actively contributing to the preservation of our planet.

The current state and future perspectives of radiotherapy for cervical cancer.

Radiotherapy is an effective treatment method for cervical cancer and is typically administered as external beam radiotherapy followed by intracavitary brachytherapy. In Japan, center shielding is used in external beam radiotherapy to shorten treatment time and reduce the doses delivered to the rectum or bladder. However, it has several challenges, such as uncertainties in calculating the cumulative dose. Recently, external beam radiotherapy has been increasingly performed with intensity-modulated radiotherapy, which reduces doses to the rectum or bladder without center shielding. In highly conformal radiotherapy, uncertainties in treatment delivery, such as inter-fractional anatomical structure movements, affect treatment outcomes; therefore, image-guided radiotherapy is essential for appropriate and safe performance. Regarding intracavitary brachytherapy, the use of magnetic resonance imaging-based image-guided adaptive brachytherapy is becoming increasingly widespread because it allows dose escalation to the tumor and accurately evaluates the dose delivered to the surrounding normal organs. According to current evidence, a minimal dose of D90% of the high-risk clinical target volume is significantly relevant to local control. Further improvements in target coverage have been achieved with combined interstitial and intracavity brachytherapy for massive tumors with extensive parametrical involvement. Introducing artificial intelligence will enable faster and more accurate generation of brachytherapy plans. Charged-particle therapies have biological and dosimetric advantages, and current evidence has proven their effectiveness and safety in cervical cancer treatment. Recently, radiotherapy-related technologies have advanced dramatically. This review provides an overview of technological innovations and future perspectives in radiotherapy for cervical cancer.

Correlation between the thyroid computed tomography value and thyroid function in hyperthyroidism: a retrospective study.

OBJECTIVE: Radioiodine (I-131) therapy for hyperthyroidism is a well-established and safe treatment option. This study aimed to investigate the relationship between the computed tomography (CT) value and the function and volume of the thyroid gland by identifying the factors that induce changes in the CT value of patients with hyperthyroidism. METHODS: This retrospective study evaluated 38 patients with Graves' disease and 10 patients with Plummer disease. To obtain the mean CT value and volume of the thyroid gland, the entire thyroid gland was set as the region of interest. A test dose of 3.7 MBq I-131 was administered before initiating I-131 therapy, and the radioiodine uptake (RIU) rate was assessed after 3, 24, 96, and 168 h. An approximate curve was plotted based on the RIU values obtained, and the effective half-life (EHL) was calculated. The correlation between the mean CT value and the volume of the thyroid gland, 24-h RIU, EHL, and the free triiodothyronine (FT3), free thyroxine (FT4), thyroid-stimulating hormone (TSH), and TSH receptor antibody (TRAb) levels was evaluated. RESULTS: The CT value exhibited a significant positive correlation with EHL in patients with Graves' disease (r = 0.62, p < 0.0001) as well as patients with Plummer disease (r = 0.74, p < 0.05). However, it did not display any correlation with the remaining parameters. CONCLUSION: The CT value is significantly correlated with EHL, suggesting that it reflects thyroid function and is mainly related to the factors associated with iodine discharge.

Predictive Performance of Radiomic Features Extracted from Breast MR Imaging in Postoperative Upgrading of Ductal Carcinoma in Situ to Invasive Carcinoma.

PURPOSE: To investigate the predictive performance of radiomic features extracted from breast MRI for upgrade of ductal carcinoma in situ (DCIS) to invasive carcinoma. METHODS: This retrospective study included 71 women with DCIS lesions diagnosed preoperatively by biopsy. All women underwent breast dynamic contrast-enhanced (DCE) MRI of the breast, which included pre-contrast and five post-contrast phases continuously with a time resolution of 60s. Lesion segmentation was performed manually, and 144 radiomic features of the lesions were extracted from T2-weighted images (T2WI), pre-contrast T1-weighted images (T1WI), and post-contrast 1st, 2nd, and 5th phase subtraction images on DCE-MRI. Qualitative features of mammography, ultrasound, and MRI were also assessed. Clinicopathological features were evaluated using medical records. The least absolute shrinkage and selection operator (LASSO) algorithm was applied for features selection and model building. The predictive performance of postoperative upgrade to invasive carcinoma was assessed using the area under the receiver operating characteristic curve. RESULTS: Surgical specimens revealed 13 lesions (18.3%) that were upgraded to invasive carcinoma. Among clinicopathological and qualitative features, age was the only significant predictive variable. No significant radiomic features were observed on T2WI and post-contrast 2nd phase subtraction images on DCE-MRI. The area under the curves (AUCs) of the LASSO radiomics model integrated with age were 0.915 for pre-contrast T1WI, 0.862 for post-contrast 1st phase subtraction images, and 0.833 for post-contrast 5th phase subtraction images. The AUCs of the 200-times bootstrap internal validations were 0.885, 0.832, and 0.775. CONCLUSION: A radiomics approach using breast MRI may be a promising method for predicting the postoperative upgrade of DCIS. The present study showed that the radiomic features extracted from pre-contrast T1WI and post-contrast subtraction images in the very early phase of DCE-MRI were more predictable.

Imaging evaluation and volumetric measurement of the space surrounding the diploic veins.

PURPOSE: The diploic veins have been suggested to be involved in the excretion of cerebrospinal fluid and intracranial waste products; however, to date, there have been no reports evaluating the space surrounding the diploic veins. Therefore, we aimed to visualize the distribution of gadolinium-based contrast agent (GBCA) in the space surrounding the diploic veins and to evaluate the spatial characteristics. MATERIALS AND METHODS: Ninety-eight participants (aged 14-84 years) were scanned 4 h after intravenous GBCA injection at Nagoya University Hospital between April 2021 and December 2022. The volume of the space surrounding the diploic veins where the GBCA was distributed was measured using contrast-enhanced T1-weighted images with the application of three-axis motion-sensitized driven equilibrium. The parasagittal dura (PSD) volume adjacent to the superior sagittal sinus was also measured using the same images. Both volumes were corrected for intracranial volume. The correlation between age and the corrected volume was examined using Spearman's rank correlation coefficient; the relationship between the corrected volume and sex was assessed using the Mann-Whitney U test. RESULTS: A significant weak negative correlation was observed between the volume of the space surrounding the diploic veins and age (r = -0.330, p < 0.001). Furthermore, there was a significant weak positive correlation between the PSD volume and age (r = 0.385, p < 0.001). Both volumes were significantly greater in men than in women. There was no correlation between the volume of the space surrounding the diploic veins and the volume of the PSD. CONCLUSION: The volume of the space surrounding the diploic veins was measurable and, in contrast to the volume of the PSD, was greater in younger participants. This space may be related to intracranial excretory mechanisms and immune responses during youth, requiring further research.

Diffusion Tensor Image Analysis ALong the Perivascular Space (DTI-ALPS): Revisiting the Meaning and Significance of the Method.

More than 5 years have passed since the Diffusion Tensor Image Analysis ALong the Perivascular Space (DTI-ALPS) method was proposed with the intention of evaluating the glymphatic system. This method is handy due to its noninvasiveness, provision of a simple index in a straightforward formula, and the possibility of retrospective analysis. Therefore, the ALPS method was adopted to evaluate the glymphatic system for many disorders in many studies. The purpose of this review is to look back and discuss the ALPS method at this moment.The ALPS-index was found to be an indicator of a number of conditions related to the glymphatic system. Thus, although this was expected in the original report, the results of the ALPS method are often interpreted as uniquely corresponding to the function of the glymphatic system. However, a number of subsequent studies have pointed out the problems on the data interpretation. As they rightly point out, a higher ALPS-index indicates predominant Brownian motion of water molecules in the radial direction at the lateral ventricular body level, no more and no less. Fortunately, the term "ALPS-index" has become common and is now known as a common term by many researchers. Therefore, the ALPS-index should simply be expressed as high or low, and whether it reflects a glymphatic system is better to be discussed carefully. In other words, when a decreased ALPS-index is observed, it should be expressed as "decreased ALPS-index" and not directly as "glymphatic dysfunction". Recently, various methods have been proposed to evaluate the glymphatic system. It has become clear that these methods also do not seem to reflect the entirety of the extremely complex glymphatic system. This means that it would be desirable to use various methods in combination to evaluate the glymphatic system in a comprehensive manner.

Decreased diffusivity along the perivascular space and cerebral hemodynamic disturbance in adult moyamoya disease.

Moyamoya disease (MMD) causes cerebral arterial stenosis and hemodynamic disturbance, the latter of which may disrupt glymphatic system activity, the waste clearance system. We evaluated 46 adult patients with MMD and 33 age- and sex-matched controls using diffusivity along the perivascular space (ALPS) measured with diffusion tensor imaging (ALPS index), which may partly reflect glymphatic system activity, and multishell diffusion MRI to generate freewater maps. Twenty-three patients were also evaluated via 15O-gas positron emission tomography (PET), and all patients underwent cognitive tests. Compared to controls, patients (38.4 (13.2) years old, 35 females) had lower ALPS indices in the left and right hemispheres (1.94 (0.27) vs. 1.65 (0.25) and 1.94 (0.22) vs. 1.65 (0.19), P < 0.001). While the right ALPS index showed no correlation, the left ALPS index was correlated with parenchymal freewater (ρ = -0.47, P < 0.001); perfusion measured with PET (cerebral blood flow, ρ = 0.70, P < 0.001; mean transit time, ρ = -0.60, P = 0.003; and oxygen extraction fraction, ρ = -0.52, P = 0.003); and cognitive tests (trail making test part B for executive function; ρ = -0.37, P = 0.01). Adult patients with MMD may exhibit decreased glymphatic system activity, which is correlated with the degree of hemodynamic disturbance, increased interstitial freewater, and cognitive dysfunction, but further investigation is needed.

Direct Visualization of Tracer Permeation into the Endolymph in Human Patients Using MR Imaging.

PURPOSE: The endolymph of the inner ear, vital for balance and hearing, has long been considered impermeable to intravenously administered gadolinium-based contrast agents (GBCAs) due to the tight blood-endolymph barrier. However, anecdotal observations suggested potential GBCA entry in delayed heavily T2-weighted 3D-real inversion recovery (IR) MRI scans. This study systematically investigated GBCA distribution in the endolymph using this 3D-real IR sequence. METHODS: Forty-one patients suspected of endolymphatic hydrops (EHs) underwent pre-contrast, 4-h, and 24-h post-contrast 3D-real IR imaging. Signal intensity in cerebrospinal fluid (CSF), perilymph, and endolymph was measured and analyzed for temporal dynamics of GBCA uptake, correlations between compartments, and the influence of age and presence of EH. RESULTS: Endolymph showed a delayed peak GBCA uptake at 24h, contrasting with peaks in perilymph and CSF at 4h. Weak to moderate positive correlations between endolymph and CSF contrast effect were observed at both 4 (r = 0.483) and 24h (r = 0.585), suggesting possible inter-compartmental interactions. Neither the presence of EH nor age significantly influenced endolymph enhancement. However, both perilymph and CSF contrast effects significantly correlated with age at both time points. CONCLUSION: This study provides the first in vivo systematic confirmation of GBCA entering the endolymph following intravenous administration. Notably, endolymph uptake peaked at 24h, significantly later than perilymph and CSF. The lack of a link between endolymph contrast and both perilymph and age suggests distinct uptake mechanisms. These findings shed light on inner ear fluid dynamics and their potential implications in Ménière's disease and other inner ear disorders.

Assessing interstitial fluid dynamics in type 2 diabetes mellitus and prediabetes cases through diffusion tensor imaging analysis along the perivascular space.

Background and purpose: Glymphatic system in type 2 diabetes mellitus (T2DM) but not in the prodrome, prediabetes (Pre-DM) was investigated using diffusion tensor image analysis along the perivascular space (DTI-ALPS). Association between glymphatic system and insulin resistance of prominent characteristic in T2DM and Pre-DM between is yet elucidated. Therefore, this study delves into the interstitial fluid dynamics using the DTI-ALPS in both Pre-DM and T2DM and association with insulin resistance. Materials and methods: In our cross-sectional study, we assessed 70 elderly individuals from the Bunkyo Health Study, which included 22 with Pre-DM, 18 with T2DM, and 33 healthy controls with normal glucose metabolism (NGM). We utilized the general linear model (GLM) to evaluate the ALPS index based on DTI-ALPS across these groups, considering variables like sex, age, intracranial volume, years of education, anamnesis of hypertension and hyperlipidemia, and the total Fazekas scale. Furthermore, we have explored the relationship between the ALPS index and insulin resistance, as measured by the homeostasis model assessment of insulin resistance (HOMA-IR) using GLM and the same set of covariates. Results: In the T2DM group, the ALPS index demonstrated a reduction compared with the NGM group [family-wise error (FWE)-corrected p < 0.001; Cohen's d = -1.32]. Similarly, the Pre-DM group had a lower ALPS index than the NGM group (FWE-corrected p < 0.001; Cohen's d = -1.04). However, there was no significant disparity between the T2DM and Pre-DM groups (FWE-corrected p = 1.00; Cohen's d = -0.63). A negative correlation was observed between the ALPS index and HOMA-IR in the combined T2DM and Pre-DM groups (partial correlation coefficient r = -0.35, p < 0.005). Conclusion: The ALPS index significantly decreased in both the pre-DM and T2DM groups and showed a correlated with insulin resistance. This indicated that changes in interstitial fluid dynamics are associated with insulin resistance.

Development of automatic generation system for lung nodule finding descriptions.

Worldwide, lung cancer is the leading cause of cancer-related deaths. To manage lung nodules, radiologists observe computed tomography images, review various imaging findings, and record these in radiology reports. The report contents should be of high quality and uniform regardless of the radiologist. Here, we propose an artificial intelligence system that automatically generates descriptions related to lung nodules in computed tomography images. Our system consists of an image recognition method for extracting contents-namely, bronchopulmonary segments and nodule characteristics from images-and a natural language processing method to generate fluent descriptions. To verify our system's clinical usefulness, we conducted an experiment in which two radiologists created nodule descriptions of findings using our system. Through our system, the similarity of the described contents between the two radiologists (p = 0.001) and the comprehensiveness of the contents (p = 0.025) improved, while the accuracy did not significantly deteriorate (p = 0.484).

Clinical significance of posterior expansion of the utricular endolymphatic space.

BACKGROUND: Posterior expansion of the utricular endolymphatic space (ES) is a finding occasionally observed, and often occurs in bilateral ears. The clinical significance of posterior expansion of the utricular ES is not clear. OBJECTIVES: To investigate the clinical significance of posterior expansion of the utricular ES detected on magnetic resonance imaging (MRI). MATERIALS AND METHODS: Among 957 patients who underwent contrast-enhanced MRI to investigate the presence of endolymphatic hydrops (EH), clinical findings in cases with posterior expansion of the utricular ES were evaluated and the significance of their existence is considered. RESULTS: Posterior expansion of the utricular ES was detected in 30 ears from 20 cases (7 males, 13 females; mean age 48.7 years). The ears with posterior expansion had a significantly lower incidence of vestibular EH than those without, and this tendency was more prominent in cases in bilateral ears. Some cases with posterior expansion had vestibular symptoms and were diagnosed with Ménière's disease, although EH was not detected in their vestibules. CONCLUSION AND SIGNIFICANCE: Posterior expansion of the utricular ES was associated with Ménière's disease without vestibular EH. Posterior expansion of the utricular ES might not be associated with the formation of EH but may occur independently.