PURPOSE: In recent years, computer-aided diagnosis (CAD) using deep learning methods for medical images has been studied. Although studies have been conducted to classify ultrasound images of tumors of the liver into fou...PURPOSE: In recent years, computer-aided diagnosis (CAD) using deep learning methods for medical images has been studied. Although studies have been conducted to classify ultrasound images of tumors of the liver into four categories (liver cysts (Cyst), liver hemangiomas (Hemangioma), hepatocellular carcinoma (HCC), and metastatic liver cancer (Meta)), no studies with additional information for deep learning have been reported. Therefore, we attempted to improve the classification accuracy of ultrasound images of hepatic tumors by adding hepatitis virus infection information to deep learning. METHODS: Four combinations of hepatitis virus infection information were assigned to each image, plus or minus HBs antigen and plus or minus HCV antibody, and the classification accuracy was compared before and after the information was input and weighted to fully connected layers. RESULTS: With the addition of hepatitis virus infection information, accuracy changed from 0.574 to 0.643. The F1-Score for Cyst, Hemangioma, HCC, and Meta changed from 0.87 to 0.88, 0.55 to 0.57, 0.46 to 0.59, and 0.54 to 0.62, respectively, remaining the same for Hemangioma but increasing for the rest. CONCLUSION: Learning hepatitis virus infection information showed the highest increase in the F1-Score for HCC, resulting in improved classification accuracy of ultrasound images of hepatic tumors.
PURPOSE: To explore the value of ultrasound in efficacy assessment and prediction of preoperative targeted treatment for gastrointestinal stromal tumor (GIST), using pathological assessment as a reference. METHODS: A tot...PURPOSE: To explore the value of ultrasound in efficacy assessment and prediction of preoperative targeted treatment for gastrointestinal stromal tumor (GIST), using pathological assessment as a reference. METHODS: A total of 35 GIST patients with preoperative targeted therapy were included in this retrospective study. The efficacy was evaluated using both ultrasound and pathology. Spearman correlation analysis and Kappa test were used to analyze the correlation and consistency between the evaluation results of ultrasound and pathology. Univariate analysis was used to obtain relevant predictive indicators of treatment response, which were then included in ordered logistic regression analysis to screen for independent predictive factors. RESULTS: In the 35 patients who underwent targeted therapy, the results of pathological assessment suggested complete response in one patient, high response in 11 patients, partial response in 15 patients, and no response in eight patients; the results of ultrasound assessment were complete response in zero patients, partial response in 20 patients, stable disease in nine patients, and progressive disease in six patients. Preoperative ultrasound evaluation of targeted therapy for GIST was moderately consistent and highly correlated with the results of postoperative pathological evaluation. Short-to-length diameter (S/L) ratio and tumor shape were independent predictors of treatment response. CONCLUSION: Ultrasound is potentially beneficial for evaluating and predicting the response to treatment of GIST.
PURPOSE: Reports on the usefulness of abdominal aortic aneurysm (AAA) screening during transthoracic echocardiography (TTE) in Japan are limited. This study aimed to describe the prevalence of AAA among patients who unde...PURPOSE: Reports on the usefulness of abdominal aortic aneurysm (AAA) screening during transthoracic echocardiography (TTE) in Japan are limited. This study aimed to describe the prevalence of AAA among patients who underwent routine screening during TTE, as well as the long-term clinical outcomes of patients in whom AAA was detected. METHODS: We screened 46,353 consecutive patients who underwent TTE for suspected cardiac disease at our institution. Among these, a total of 1133 patients were identified as having AAA, defined as an abdominal aorta diameter of 30 mm or greater. After excluding patients with prior aortic surgery, including endovascular repair (n = 104), those with known AAA (n = 569), and those with known aortic dissection (n = 25), the study population consisted of 435 patients, all diagnosed with AAA for the first time. RESULTS: The overall prevalence of AAA among patients undergoing TTE was 0.94%. The mean age was 76.8 years, and the study population was predominantly males (81.6%). The prevalence of AAA in patients under 60 years of age was low: 0.24% for men and 0.076% for women. The left atrial volume index was 43.8 ± 23.1 ml/m, the left ventricular mass was 164.9 ± 52.0 g, and the diameter of the sinus of Valsalva was 32.6 ± 4.4 mm, all of which were numerically higher than the normal values observed in a healthy Japanese population. During the median follow-up period of 2.0 years, 43 surgical or endovascular repairs of AAA, six aorta-related deaths, and 90 all-cause deaths occurred. The cumulative incidence of surgical or endovascular repair of AAA was 5.3% at 1 year, 11.5% at 3 years, and 18.1% at 5 years. The cumulative incidence of aorta-related death was modest: 0.3% at 1 year, 0.8% at 3 years, and 1.6% at 5 years. CONCLUSION: The prevalence of newly diagnosed AAA among patients who underwent routine screening during TTE for suspected cardiac disease was 0.94% in the Japanese population, with the majority being 60 years or older. Approximately 10% of patients diagnosed with AAA underwent surgical or endovascular repair during follow-up, suggesting that this approach may be effective in preventing deaths caused by AAA.
J Med Ultrason (2001)
· 2025 Apr · PMID 40088406
·
Full text
PURPOSE: This study aims to assess the effectiveness of Superb Microvascular Imaging (SMI) in evaluating intraplaque neovascularization (IPN) in carotid plaques and its association with ischemic stroke in elderly hyperte...PURPOSE: This study aims to assess the effectiveness of Superb Microvascular Imaging (SMI) in evaluating intraplaque neovascularization (IPN) in carotid plaques and its association with ischemic stroke in elderly hypertensive patients, and to develop and validate a prediction model for ischemic stroke based on SMI characteristics. METHODS: This retrospective study included 314 elderly hypertensive patients with carotid plaques, divided into a training cohort (235 cases) and a validation cohort (79 cases). Patients were categorized into stroke and non-stroke groups. SMI characteristics of carotid plaques and baseline variables were analyzed using univariate logistic regression and Least Absolute Shrinkage and Selection Operator (LASSO) regression to develop a multivariate logistic regression model. The model was then validated. RESULTS: In the training cohort, 79 patients (33.6%) experienced ischemic stroke. Significant predictors included BMI, hypertension grade, IPN grade, and stenosis percentage. These factors were incorporated into a logistic regression model, which was validated with an area under the curve (AUC) of 0.79, 69.6% accuracy, 60.8% sensitivity, and 85.7% specificity. CONCLUSION: BMI, hypertension grade, IPN grade, and carotid plaque stenosis are associated with ischemic stroke in elderly hypertensive patients. The developed logistic regression model based on these indicators can improve the prediction of ischemic stroke in this population.
J Med Ultrason (2001)
· 2025 Apr · PMID 40029506
·
Full text
PURPOSE: Tunneled central venous catheters (CVC) are essential medical devices for pediatric patients facing extended treatment periods. This study aimed to demonstrate the usefulness of ultrasound in evaluating complica...PURPOSE: Tunneled central venous catheters (CVC) are essential medical devices for pediatric patients facing extended treatment periods. This study aimed to demonstrate the usefulness of ultrasound in evaluating complications in subcutaneous tissue associated with unplanned extraction of tunneled CVC. METHODS: Twenty-five patients who underwent ultrasound examination for suspected complications in the subcutaneous tissue associated with tunneled areas from CVC were included. The following patient characteristics and imaging findings were evaluated: infection in subcutaneous tissue, high echogenicity and hypoechoic effusion around the catheter within the subcutaneous tissue, and hyperechoic foci around the catheter. Patients with CVC were classified into two groups: those with and those without unplanned extraction of tunneled CVC. Fisher's exact test was used to compare the two groups. RESULTS: Nine patients had unplanned extraction of tunneled CVC. A significant difference was found in infection at tunneled areas (presence/absence in patients with vs. those without unplanned extraction = 7/2 vs. 2/14, P = 0.002), as well as in hypoechoic effusion around the catheter within the subcutaneous tissues (presence/absence in patients with vs. those without unplanned extraction = 9/0 vs. 3/13, P < 0.001). However, no significant differences were found in the presence or absence of high echogenicity (presence/absence in patients with vs. those without unplanned extraction = 7/2 vs. 6/10, P = 0.097) or hyperechoic foci around the catheter (presence/absence in patients with vs. those without unplanned extraction = 3/6 vs. 1/15, P = 0.116). CONCLUSION: The ultrasound findings were useful for determining the necessity of tunneled CVC extraction. These results will be helpful for improving management of pediatric patients with CVC.
Inflammatory bowel disease (IBD) is an inflammatory disorder in which intestinal homeostasis is disrupted for some reason. Among them, ulcerative colitis (UC) and Crohn's disease (CD) are frequently referred to as IBD in...Inflammatory bowel disease (IBD) is an inflammatory disorder in which intestinal homeostasis is disrupted for some reason. Among them, ulcerative colitis (UC) and Crohn's disease (CD) are frequently referred to as IBD in the narrow sense, characterized by relapse episodes and remission periods. The differential diagnosis of IBD involves a broad spectrum of inflammatory or infectious diseases that mimic UC and/or CD, as well as others that may complicate existing IBD. Accordingly, these differential diseases and modifying factors should be considered in their pathological diagnosis, and a careful diagnosis should be made in close collaboration with clinicians. Here, we provide a pathological overview of UC, CD, and their differential diseases, as well as IBD-associated cancers, demonstrating their typical gross and histological features. Further, we introduce a pathological scoring system for biopsy specimens to diagnose IBD that may potentially be integrated into clinical practice.
Sugimoto M, Ishii Y, Nakashima Y
… +7 more, Kamei G, Nekomoto A, Hashizume T, Okinaka R, Matsumura K, Takahashi M, Adachi N
J Med Ultrason (2001)
· 2025 Apr · PMID 39987363
·
Full text
PURPOSE: The infrapatellar fat pad (IFP) absorbs mechanical stress in the knee joint owing to flexible morphological changes. The IFP is a key factor in knee osteoarthritis (OA); however, its dynamic feature during walki...PURPOSE: The infrapatellar fat pad (IFP) absorbs mechanical stress in the knee joint owing to flexible morphological changes. The IFP is a key factor in knee osteoarthritis (OA); however, its dynamic feature during walking remains unknown. This study aimed to investigate whether the morphological changes in the IFP during walking involve specific features for patients with knee OA. METHODS: Twelve patients with knee OA, 12 healthy young volunteers, and 12 healthy elderly volunteers were recruited. The IFP was evaluated using ultrasonography, and dynamics were recorded in video mode during walking. The IFP value was identified as the thickness between the patellar tendon and proximal tibial line. The morphological change in the IFP (ΔIFP) was shown as the difference in IFP value between maximum and at initial contact on the waveform. Kinematics and kinetics data were evaluated using a three-dimensional motion analysis system synchronized with ultrasonography, and the knee flexion angle and its moment in the stance phase were evaluated. RESULTS: In the patients with knee OA, the ΔIFP was lower than that in healthy volunteers, but there was no difference between control groups (knee OA: 1.4 ± 0.3 mm, elderly control: 1.8 ± 0.2 mm, young control: 2.1 ± 0.5 mm, p < 0.05). In all the groups, there was no significant correlation between the IFP values and kinetic parameters, including the range of knee flexion angles and gait speed. CONCLUSION: Insufficient morphological changes in the IFP during walking could be a feature of knee OA.
PURPOSE: The purpose of this study was to compare the value of contrast-enhanced ultrasound (CEUS) plus MicroFlow Imaging (CEUS-MFI), MicroFlow Imaging (MFI) alone, and color Doppler flow imaging (CDFI) in the differenti...PURPOSE: The purpose of this study was to compare the value of contrast-enhanced ultrasound (CEUS) plus MicroFlow Imaging (CEUS-MFI), MicroFlow Imaging (MFI) alone, and color Doppler flow imaging (CDFI) in the differential diagnosis of benign and malignant breast lesions. METHODS: A total of 116 patients with 116 breast lesions categorized as Breast Imaging Reporting and Data System (BI-RADS) category 4 were enrolled in this prospective study. CEUS-MFI, MFI, and CDFI were used to evaluate the microvascular morphology and distribution types of breast lesions. Pathological results were considered the gold standard. RESULTS: Compared with conventional CDFI and MFI, the CEUS-MFI technique can reveal microvasculature and distribution types at a higher resolution in breast masses. The sensitivity, specificity, and accuracy of CEUS-MFI were 96.3%, 80.6%, and 91.4%, respectively. The sensitivity, specificity, and accuracy of MFI were 87.5%, 75.0%, and 83.6%, respectively. The sensitivity, specificity, and accuracy of CDFI were 58.8%, 72.2%, and 62.9%, respectively. The accuracy was significantly different between CEUS-MFI and MFI (P = 0.024), and the accuracy was significantly different between CEUS-MFI and CDFI (P = 0.000). US BI-RADS 4A masses were downgraded based on CEUS-MFI features without any malignancy missed, with the biopsy rate decreasing from 100% (29/29) to 31.0% (9/29). CONCLUSION: CEUS-MFI provides improved diagnostic efficacy for breast lesions. The CEUS-MFI technique can be used as an effective supplement to conventional ultrasound in the diagnosis of breast tumors.
PURPOSE: Knee pain is a characteristic symptom of early-stage knee osteoarthritis. Recently, the association between knee symptoms and infrapatellar fat pad (IFP) degeneration has garnered attention. This study aimed to...PURPOSE: Knee pain is a characteristic symptom of early-stage knee osteoarthritis. Recently, the association between knee symptoms and infrapatellar fat pad (IFP) degeneration has garnered attention. This study aimed to clarify the association between ultrasound-derived size and echo intensity (EI) in the IFP and knee symptoms. METHODS: A total of 163 community-dwelling older individuals (women, n = 106; age, 75.1 ± 7.0 years) participated. An ultrasound imaging device was used to assess the area and EI of the superficial and deep parts of the central, medial, and lateral IFP and presence of medial meniscal extrusion (MME) and medial tibial osteophytes. Based on the 2011 version of the Knee Society Knee Scoring System (KSS) symptoms category, the participants were classified into a symptomatic (KSS symptom score < 23, n = 74) or asymptomatic (KSS symptom score ≧23, n = 89) group. Logistic regression analyses were performed with groups as dependent variables and EI and area of the IFP as independent variables. RESULTS: EI of the superficial part of the medial IFP was significantly associated with knee symptoms, adjusting for age, sex, body mass index, MME, and medial osteophytes (p < 0.05). MME was also significantly associated with knee symptoms (p < 0.05). EI of the other parts, area of any parts, and medial osteophytes were not associated with knee symptoms. CONCLUSION: These findings suggested the utility of evaluating EI on the superficial part of the medial IFP and MME as the articular structures associated with knee symptoms.
Fujimoto T, Hirokawa M, Suzuki A
… +6 more, Oshita M, Yamaoka H, Fujishima M, Onoda N, Miyauchi A, Akamizu T
J Med Ultrason (2001)
· 2025 Apr · PMID 39731664
·
Full text
PURPOSE: Parathyroid lipoadenomas are difficult to recognize preoperatively; hence, they may remain undetected. Difficulty in recognition is thought to be due to the adipocytes present in the tumor. This study aimed to c...PURPOSE: Parathyroid lipoadenomas are difficult to recognize preoperatively; hence, they may remain undetected. Difficulty in recognition is thought to be due to the adipocytes present in the tumor. This study aimed to clarify the impact of adipocytes as a component of parathyroid adenomas on ultrasound evaluation. METHODS: Eighteen parathyroid adenoma cases, in which the adipose tissue accounted for more than 10% of the tumors, were included in this study. Of these, five were consistent with lipoadenomas. Twenty-five consecutive patients with parathyroid adenoma without adipocytes were used as controls. RESULTS: Ultrasonography revealed a lipoadenoma detection rate of 20.0%. This increased to 80.0% at re-examinations performed after obtaining information from other imaging modalities. Compared with parathyroid adenoma cases with no adipocytes or few adipocytes, the frequencies of ill-defined margins, iso- and/or hyperechogenicity, heterogeneous consistency with a two-tone pattern, poor vascular flow, no polar artery, and no hyperechoic line were significantly higher in parathyroid lipoadenoma cases. The hyperechoic and isoechoic areas in tumors with a two-tone pattern correspond to adipocyte- and parathyroid cell-rich areas, respectively. The lipoadenoma tumor sizes measured using ultrasound tended to be smaller than the actual sizes. CONCLUSIONS: The characteristic ultrasound findings of lipoadenomas were clearly different from those of parathyroid adenomas with or without adipocytes. We believe that our findings may contribute to an increased detection rate of lipoadenomas and allow us to consider them in the differential diagnosis.