Japanese Journal of Radiology最新文献

Hereby inviting young rising stars in chest radiology in Japan for contributing what they are working currently, we would like to show the potentials and directions of the near future research trends in the research field. I will provide a reflection on my own research topics. At the end, we also would like to discuss on how to choose the themes and topics of research: What to do or not to do? We strongly believe it will stimulate and help investigators in the field.

Artificial intelligence (AI) has emerged as a transformative tool in breast cancer screening, with two distinct applications: computer-aided cancer detection (CAD) and risk prediction. While AI CAD systems are slowly finding its way into clinical practice to assist radiologists or make independent reads, this review focuses on AI risk models, which aim to predict a patient's likelihood of being diagnosed with breast cancer within a few years after negative screening. Unlike AI CAD systems, AI risk models are mainly explored in research settings without widespread clinical adoption. This review synthesizes advances in AI-driven risk prediction models, from traditional imaging biomarkers to cutting-edge deep learning methodologies and multimodal approaches. Contributions by leading researchers are explored with critical appraisal of their methods and findings. Ethical, practical, and clinical challenges in implementing AI models are also discussed, with an emphasis on real-world applications. This review concludes by proposing future directions to optimize the adoption of AI tools in breast cancer screening and improve equity and outcomes for diverse populations.

Purpose: Magnetization prepared rapid gradient echo (MPRAGE) is a useful three-dimensional (3D) T1-weighted sequence, but is not a priority in routine brain examinations. We hypothesized that converting 3D MRI localizer (AutoAlign Head) images to MPRAGE-like images with deep learning (DL) would be beneficial for diagnosing and researching dementia and neurodegenerative diseases. We aimed to establish and evaluate a DL-based model for generating MPRAGE-like images from MRI localizers.

Materials and methods: Brain MRI examinations including MPRAGE taken at a single institution for investigation of mild cognitive impairment, dementia and epilepsy between January 2020 and December 2022 were included retrospectively. Images taken in 2020 or 2021 were assigned to training and validation datasets, and images from 2022 were used for the test dataset. Using the training and validation set, we determined one model using visual evaluation by radiologists with reference to image quality metrics of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS). The test dataset was evaluated by visual assessment and quality metrics. Voxel-based morphometric analysis was also performed, and we evaluated Dice score and volume differences between generated and original images of major structures were calculated as absolute symmetrized percent change.

Results: Training, validation, and test datasets comprised 340 patients (mean age, 56.1 ± 24.4 years; 195 women), 36 patients (67.3 ± 18.3 years, 20 women), and 193 patients (59.5 ± 24.4 years; 111 women), respectively. The test dataset showed: PSNR, 35.4 ± 4.91; SSIM, 0.871 ± 0.058; and LPIPS 0.045 ± 0.017. No overfitting was observed. Dice scores for the segmentation of main structures ranged from 0.788 (left amygdala) to 0.926 (left ventricle). Quadratic weighted Cohen kappa values of visual score for medial temporal lobe between original and generated images were 0.80-0.88.

Conclusion: Images generated using our DL-based model can be used for post-processing and visual evaluation of medial temporal lobe atrophy.

Adrenal diseases pose significant diagnostic challenges due to the wide range of neoplastic and non-neoplastic pathologies. Radiologists have a crucial role in diagnosing and managing these conditions by, leveraging advanced imaging techniques. This review discusses the vital role of computed tomography (CT), magnetic resonance imaging (MRI), and nuclear medicine in adrenal imaging, and focuses on morphological and functional evaluations. First, the anatomy and physiology of the adrenal glands are described, followed by a discussion on ectopic adrenocortical adenomas and how they develop. The concepts and imaging findings of congenital diseases, such as congenital adrenal hyperplasia (CAH), adrenal rest tumors, and adrenocortical nodular disease, considering recent updates to the WHO Classification of Tumours (5th ed.) terminology are highlighted. The diagnostic value of dynamic contrast-enhanced CT and chemical-shift MRI for identifying adrenocortical adenomas are emphasized, alongside the use of adrenocortical scintigraphy such as ¹³¹I-adosterol scintigraphy for diagnosing Cushing's disease, Cushing's syndrome (CS), subclinical CS, and ectopic adrenocorticotropic hormone-producing tumors. Systemic complications associated with CS, and the diagnosis and treatment of pheochromocytomas, paragangliomas (PPGLs), and neuroblastomas, will also be discussed focusing on ¹²³I-metaiodobenzylguanidine (MIBG) imaging and ¹³¹I-MIBG therapy. Pitfalls in ¹²³I-MIBG imaging and the increasing importance of diagnosing hereditary PPGLs due to increased genetic testing are also be discussed. Additionally, the broad differential diagnosis for adrenal masses-including malignancies like adrenal carcinoma, metastases, and malignant lymphoma, as well as benign conditions like myelolipoma and ganglioneuroma, and complications, such as adrenal hemorrhage, infarction, and infections-will be outlined. The goal of this review was to provide an overview of adrenal diseases that includes the most recent information for radiologists to stay updated on the latest imaging techniques and advancements that can ensure accurate diagnosis and effective management.

Objective: Calcific tendinopathy, predominantly affecting rotator cuff tendons, leads to significant pain and tendon degeneration. Although US-guided percutaneous irrigation (US-PICT) is an effective treatment for this condition, prediction of patient' s response and long-term outcomes remains a challenge. This study introduces a novel radiomics-based model to forecast patient outcomes, addressing a gap in the current predictive methodologies.

Materials and methods: The study involved 84 patients who underwent US-PICT, with data collected on clinical and demographic factors, alongside radiomic features extracted from ultrasound images. Key radiomic features predictive of the outcome were discerned through Least Absolute Shrinkage and Selection Operator (LASSO) method. Machine Learning models, including Random Forest, XGBoost, and Support Vector Machines, were employed to analyze the radiomics, the clinical and the combined dataset, focusing on calcium removal extent. An external testing was conducted using an independent cohort from a different institution to assess the model's generalizability. Metrics were calculated for the best-performing models, namely area under the curve (AUC) score, sensitivity, specificity, precision or positive predictive value, and negative predictive value.

Results: The selected features were merged with clinical data, notably the calcification's maximum diameter. This enriched dataset was fed into classification models. The superior model achieved an AUC of 0.88 (95% CI 0.73-0.99), with a positive predictive value of 0.92 and a sensitivity of 0.90. In external testing, the combined model achieved an AUC of 0.78. SHAP analysis was employed to highlight the impact of the selected features on the optimal model's effectiveness.

Conclusion: The developed radiomics model offers a promising tool for predicting outcomes of US-PICT, potentially guiding clinical decision-making.

Purpose: This study evaluates the impact of the 2021 revision of Japan's Ordinance on the Prevention of Ionizing Radiation Hazards on radiation protection practices, focusing on the deployment of radiation protection devices and the involvement of radiology technologists in Japanese hospitals.

Methods: A two-phase web-based questionnaire survey was conducted among hospitals registered as training facilities with the Japanese Radiological Society. The survey included 53 questions covering facility information, radiation worker management, training, and working environment.

Results: The use of lens-specific dosimeters significantly increased post-revision (p = 0.005). Protective eyewear availability showed minor improvements, particularly in angiographic rooms (p = 0.019). The involvement of radiology technologists remained high in angiographic rooms but showed no significant changes in endoscopy and fluoroscopy rooms. Larger hospitals exhibited better compliance with protective measures, though gaps in resource allocation persisted.

Conclusion: The ordinance revision led to significant improvements in dosimeter usage but only minor changes in protective eyewear deployment and technologist involvement.

Purpose: A large-scale language model is expected to have been trained with a large volume of data including cancer treatment protocols. The current study aimed to investigate the use of generative pretrained transformer 4 (GPT-4) for identifying the TNM classification of pancreatic cancers from existing radiology reports written in Japanese.

Materials and methods: We screened 100 consecutive radiology reports on computed tomography scan for pancreatic cancer from April 2020 to June 2022. GPT-4 was requested to classify the TNM from the radiology reports based on the General Rules for the Study of Pancreatic Cancer 7th Edition. The accuracy and kappa coefficient of the TNM classifications by GPT-4 was evaluated with the classifications by two experienced abdominal radiologists as gold standard.

Results: The accuracy values of the T, N, and M factors were 0.73, 0.91, and 0.93, respectively. The kappa coefficients were 0.45 for T, 0.79 for N, and 0.83 for M.

Conclusion: Although GPT is familiar with the TNM classification for pancreatic cancer, its performance in classifying actual cases in this experiment may not be adequate.