Breast Tumor Classification using Short-ResNet with Pixel-based Tumor Probability Map in Ultrasound Images.

Breast cancer is the most common form of cancer and is still the second leading cause of death for women in the world. Early detection and treatment of breast cancer can reduce mortality rates. Breast ultrasound is always used to detect and diagnose breast cancer. The accurate breast segmentation and diagnosis as benign or malignant is still a challenging task in the ultrasound image. In this paper, we proposed a classification model as short-ResNet with DC-UNet to solve the segmentation and diagnosis challenge to find the tumor and classify benign or malignant with breast ultrasonic images. The proposed model has a dice coefficient of 83% for segmentation and achieves an accuracy of 90% for classification with breast tumors. In the experiment, we have compared with segmentation task and classification result in different datasets to prove that the proposed model is more general and demonstrates better results. The deep learning model using short-ResNet to classify tumor whether benign or malignant, that combine DC-UNet of segmentation task to assist in improving the classification results.

First-Pass Arrival Interval of Ultrasound Contrast Medium in the Hepatic Artery and Portal Vein as a Marker for Assessment of Liver Transplant Recipients.

BACKGROUND: This study measures the first-pass arrival times in the hepatic artery and portal vein of the transplanted liver using contrast-enhanced ultrasound (CEUS) and assess its correlation with graft performance in the early posttransplant period. METHODS: This study evaluated 35 liver transplant recipients who underwent CEUS examination within 1 month of transplant surgery. CEUS under contrast-specific harmonic imaging mode were recorded for 60 seconds immediately after intravenous administration of microbubble ultrasound contrast medium (Sonazoid, GE Healthcare, Oslo, Norway). The recorded video clips were reviewed by 2 readers to determine the first-pass arrival times in the hepatic artery and portal vein, and the difference between the 2 was defined as the arterial-portal arrival interval (APAI). Laboratory data on the same date of CEUS examination were collected as indicators to correlate with APAI. RESULTS: The intra- and inter-rater reliability for APAI measurement were excellent, with intraclass correlation coefficients > .95. The mean APAI was 4.5 ± 1.8 seconds (range, 2.0-10.5 seconds). The APAI was positively correlated with the serum total bilirubin level (r = 0.357, P = .035) and negatively correlated with the platelet count (r = -0.354, P = .037). At the 5 second cutoff point, a total serum bilirubin of >8 mg/dL was reported in 5 of 11 patients (45.4%) with APAI of >5 seconds and in only 3 of 24 patients (12.5%) with APAI of <5 seconds (P < .05). CONCLUSIONS: The APAI is a quantitative marker that links the hemodynamics and the clinical status of the liver graft.

Radiofrequency Ablation of Benign Thyroid Nodules: Recommendations from the Asian Conference on Tumor Ablation Task Force - Secondary Publication.

Radiofrequency ablation (RFA) is a thermal ablation technique widely used for the management of benign thyroid nodules. To date, five academic societies in various countries have reported clinical practice guidelines, opinion statements, or recommendations regarding the use of thyroid RFA. However, despite some similarities, there are also differences among the guidelines, and a consensus is required regarding safe and effective treatment in Asian countries. Therefore, a task force was organized by the guideline committee of the Asian Conference on Tumor Ablation with the goal of devising recommendations for the clinical use of thyroid RFA. The recommendations in this article are based on a comprehensive analysis of the current literature and the consensus opinion of the task force members.

Consensus of Minimally Invasive and Multidisciplinary Comprehensive Treatment for Hepatocellular Carcinoma - 2020 Guangzhou Recommendations.

In China, the majority of patients with hepatocellular carcinoma (HCC) result from long-term infection of hepatitis B. Pathologically, HCC is characterized by rich blood supply, multicentric origins, early vascular invasion and intrahepatic metastasis. Therefore, HCC is not a local disease but a systemic disease at the beginning of its occurrence. For this reason, a comprehensive treatment strategy should be adopted in the management of HCC, including local treatments (such as surgical resection, radiofrequency ablation, microwave ablation, chemical ablation and cryoablation, etc.), organ-level treatments [such as transcatheter arterial infusion of chemotherapy and transcatheter arterial chemoembolization (TACE)], and systemic treatments (such as immunotherapy, antiviral therapy and molecular targeted therapy, etc.). This consensus sets forth the minimally-invasive and multidisciplinary comprehensive guideline of HCC, focusing on the following eight aspects (1) using hepaticarteriography, CT hepatic arteriography (CTHA), CT arterial portography (CTAP), lipiodol CT (Lp-CT), TACE-CT to find the intrahepatic lesion and make precise staging (2) TACE combined with ablation or ablation as the first choice of treatment for early stage or small HCC, while other therapies are considered only when ablation is not applicable (3) infiltrating HCC should be regarded as an independent subtype of HCC (4) minimally-invasive comprehensive treatment could be adopted in treating metastatic lymph nodes (5) multi-level subdivision of M-staging should be used for individualized treatment and predicting prognosis (6) HCC with severe hepatic decompensation is the only candidate criterion for liver transplantation (7) bio-immunotherapy, traditional Chinese medicine therapy, antiviral therapy, and psychosocial and psychopharmacological interventions should be advocated through the whole course of HCC treatment (8) implementation of multicenter randomized controlled trials of minimally-invasive therapy versus surgery for early and intermediate stage HCC is recommended.

Prospective assessment of diagnostic efficacy and safety of SonazoidTM and SonoVue® ultrasound contrast agents in patients with focal liver lesions.

OBJECTIVES: To assess the respective diagnostic value of Sonazoid™ and SonoVue® for characterizing FLLs as benign or malignant and the corresponding safety. METHODS: This prospective Phase 3 study was conducted at 17 centres in China and Korea (May 2014 to April 2015); 424 patients (20 to 80 years) with at least 1 untreated focal liver lesion (FLL) (< 10 cm in diameter) underwent a contrast-enhanced ultrasound (CEUS) examination (218 received Sonazoid of 0.12 µL microbubbles/kg; 206 received SonoVue of 2.4 mL). Three independent blinded readers evaluated pre- and post-contrast images characterising the FLLs as benign or malignant. RESULTS: Sonazoid-enhanced and SonoVue-enhanced ultrasound provided a statistically significant improvement in specificity for all 3 readers comparing to unenhanced ultrasound (for Sonazoid: p = 0.0093, < 0.0001, 0.0011; for SonoVue: p = 0.002, 0.03, 0.12, respectively). Difference in accuracy improvement between the 2 groups was within the pre-specified non-inferiority margin of 20% for all 3 readers (6.1%, 95% CI: - 5.0 to 17.2; - 7.5%, 95% CI: - 18.4 to 3.5; - 0.3%, 95% CI: - 11.3 to 10.7). The diagnostic confidence level for all 3 readers increased with post-contrast images relative to pre-contrast images. Both contrast agents were well tolerated. CONCLUSION: Results showed a similar efficacy for Sonazoid™ and SonoVue® in diagnosing FLLs as benign or malignant, and underlined the benefit of CEUS imaging over unenhanced ultrasound imaging in reaching a confident diagnosis without having to refer patients for additional imaging exams.

The status of radiation protection in medicine in the Asia-Pacific region.

More than half of the world's population live in Asia-Pacific. This region is culturally diverse, with significant disparities in terms of socio-economic status, provision of health care and access to advanced technology. The medical use of ionising radiation is increasing worldwide and similarly within the Asia-Pacific region. In this paper, we highlight the current status in usage of ionising radiation in medicine in the region, and review the legal framework, implementation and activities in radiation protection. Asia-Pacific countries are active in strengthening radiation protection by promoting education and training. Various projects and activities initiated by international organisations such as the IAEA, WHO and ICRP have provided stimulation in the region, but more work is needed to continue to improve protection practices.

Radiofrequency ablation of benign thyroid nodules: recommendations from the Asian Conference on Tumor Ablation Task Force.

Radiofrequency ablation (RFA) is a thermal ablation technique widely used for the management of benign thyroid nodules. To date, five academic societies in various countries have reported clinical practice guidelines, opinion statements, or recommendations regarding the use of thyroid RFA. However, despite some similarities, there are also differences among the guidelines, and a consensus is required regarding safe and effective treatment in Asian countries. Therefore, a task force was organized by the guideline committee of the Asian Conference on Tumor Ablation with the goal of devising recommendations for the clinical use of thyroid RFA. The recommendations in this article are based on a comprehensive analysis of the current literature and the consensus opinion of the task force members.

Self-co-attention neural network for anatomy segmentation in whole breast ultrasound.

The automated whole breast ultrasound (AWBUS) is a new breast imaging technique that can depict the whole breast anatomy. To facilitate the reading of AWBUS images and support the breast density estimation, an automatic breast anatomy segmentation method for AWBUS images is proposed in this study. The problem at hand is quite challenging as it needs to address issues of low image quality, ill-defined boundary, large anatomical variation, etc. To address these issues, a new deep learning encoder-decoder segmentation method based on a self-co-attention mechanism is developed. The self-attention mechanism is comprised of spatial and channel attention module (SC) and embedded in the ResNeXt (i.e., Res-SC) block in the encoder path. A non-local context block (NCB) is further incorporated to augment the learning of high-level contextual cues. The decoder path of the proposed method is equipped with the weighted up-sampling block (WUB) to attain class-specific better up-sampling effect. Meanwhile, the co-attention mechanism is also developed to improve the segmentation coherence among two consecutive slices. Extensive experiments are conducted with comparison to several the state-of-the-art deep learning segmentation methods. The experimental results corroborate the effectiveness of the proposed method on the difficult breast anatomy segmentation problem on AWBUS images.

Fully automated lesion segmentation and visualization in automated whole breast ultrasound (ABUS) images.

BACKGROUND: The number of breast cancer patients has increased each year, and the demand for breast cancer detection has become quite large. There are many common breast cancer diagnostic tools. The latest automated whole breast ultrasound (ABUS) technology can obtain a complete breast tissue structure, which improves breast cancer detection technology. However, due to the large amount of ABUS image data, manual interpretation is time-consuming and labor-intensive. If there are lesions in multiple images, there may be some omissions. In addition, if further volume information or the three-dimensional shape of the lesion is needed for therapy, it is necessary to manually segment each lesion, which is inefficient for diagnosis. Therefore, automatic lesion segmentation for ABUS is an important issue for guiding therapy. METHODS: Due to the amount of speckle noise in an ultrasonic image and the low contrast of the lesion boundary, it is quite difficult to automatically segment the lesion. To address the above challenges, this study proposes an automated lesion segmentation algorithm. The architecture of the proposed algorithm can be divided into four parts: (I) volume of interest selection, (II) preprocessing, (III) segmentation, and (IV) visualization. A volume of interest (VOI) is automatically selected first via a three-dimensional level-set, and then the method uses anisotropic diffusion to address the speckled noise and intensity inhomogeneity correction to eliminate shadowing artifacts before the adaptive distance regularization level set method (DRLSE) conducts segmentation. Finally, the two-dimensional segmented images are reconstructed for visualization in the three-dimensional space. RESULTS: The ground truth is delineated by two radiologists with more than 10 years of experience in breast sonography. In this study, three performance assessments are carried out to evaluate the effectiveness of the proposed algorithm. The first assessment is the similarity measurement. The second assessment is the comparison of the results of the proposed algorithm and the Chan-Vese level set method. The third assessment is the volume estimation of phantom cases. In this study, in the 2D validation of the first assessment, the area Dice similarity coefficients of the real cases named cases A, real cases B and phantoms are 0.84±0.02, 0.86±0.03 and 0.92±0.02, respectively. The overlap fraction (OF) and overlap value (OV) of the real cases A are 0.84±0.06 and 0.78±0.04, real case B are 0.91±0.04 and 0.82±0.05, respectively. The overlap fraction (OF) and overlap value (OV) of the phantoms are 0.95±0.02 and 0.92±0.03, respectively. In the 3D validation, the volume Dice similarity coefficients of the real cases A, real cases B and phantoms are 0.85±0.02, 0.89±0.04 and 0.94±0.02, respectively. The overlap fraction (OF) and overlap value (OV) of the real cases A are 0.82±0.06 and 0.79±0.04, real cases B are 0.92±0.04 and 0.85±0.07, respectively. The overlap fraction (OF) and overlap value (OV) of the phantoms are 0.95±0.01 and 0.93±0.04, respectively. Therefore, the proposed algorithm is highly reliable in most cases. In the second assessment, compared with Chan-Vese level set method, the Dice of the proposed algorithm in real cases A, real cases B and phantoms are 0.84±0.02, 0.86±0.03 and 0.92±0.02, respectively. The Dice of Chan-Vese level set in real cases A, real cases B and phantoms are 0.65±0.23, 0.69±0.14 and 0.76±0.14, respectively. The Dice performance of different methods on segmentation shows a highly significant impact (P<0.01). The results show that the proposed algorithm is more accurate than Chan-Vese level set method. In the third assessment, the Spearman's correlation coefficient between the segmented volumes and the corresponding ground truth volumes is ρ=0.929 (P=0.01). CONCLUSIONS: In summary, the proposed method can batch process ABUS images, segment lesions, calculate their volumes and visualize lesions to facilitate observation by radiologists and physicians.

Specific liver volume parameters in cirrhotic patients with peribiliary cysts.

BACKGROUND: The presence of peribiliary cysts and morphological changes in the volumes of lobes in the livers of patients with cirrhosis are both related to the alteration of portal flow. Our study explored the relationship between these two features in patients with cirrhosis. METHODS: We retrospectively selected 150 computed tomography (CT) images of cirrhotic livers and 105 CT images of healthy livers. The cirrhotic livers were further classified according to the presence of peribiliary cysts (peribiliary cysts group) or the absence of peribiliary cysts (control cirrhotic group). The characteristic features of liver cirrhosis, including modified caudate-right lobe ratio (mCR ratio), splenomegaly, ascites, and collateral shunts, were reviewed. Liver volume calculations included the sum of the left hepatic volume (LHV) and right hepatic volume (RHV; LHV + RHV) and the ratio of LHV to RHV (LHV/RHV). RESULTS: The two groups did not differ in the presence of splenomegaly, ascites, or collateral shunts. The control cirrhotic group exhibited a significantly higher mCR ratio and LHV/RHV ratio than the peribiliary cysts group did (p < 0.001). The healthy liver group exhibited a significantly higher LHV + RHV value than either the peribiliary cysts group or the control cirrhotic group did (p < 0.001). The peribiliary cysts group and the control cirrhotic group did not differ significantly for LHV + RHV (p > 0.05). CONCLUSION: The control cirrhotic group exhibited a significantly higher mCR ratio and LHV/RHV ratio than the peribiliary cysts group did, but the two groups were similar for most measurements. Peribiliary cysts might result in reduction of portal flow, causing cirrhotic liver with peribiliary cysts with left-sided dominance not to demonstrate the typical morphological appearance of the common cirrhotic liver.

Percutaneous ethanol ablation of intrahepatic arterial pseudoaneurysm: A case report.

Hepatic arterial pseudoaneurysm is a rare but potentially fatal condition that requires prompt management. We report a case of hepatic arterial pseudoaneurysm developed after radiofrequency ablation of a hepatocellular carcinoma. The patient was successfully treated with percutaneous absolute ethanol injection under ultrasound guidance. Follow-up studies with ultrasound and computed tomography for 2 years after treatment revealed no evidence of local recurrence of hepatocellular carcinoma and of the pseudoaneurysm.

Characterization and management of various renal cystic lesions by sonographic features.

Renal cysts are common incidental findings in clinical practice. Most renal cysts detected in medical imaging are benign simple cysts. However, some are complicated by hemorrhage or infection or are associated with calcification. In these instances, difficulties can be encountered distinguishing the complicated cysts from cystic renal tumors such as cystic renal cell carcinoma, multilocular cystic nephroma, and mixed epithelial and stromal tumors. The Bosniak classification is widely used to categorize cystic renal lesions but is used to classify those discovered via computed tomography. Ultrasonography (US) and color Doppler US are the most frequently used imaging techniques for abdominal surveys and long-term follow-up because of their noninvasiveness, relatively low cost, wide availability, and frequently, lack of contrast medium. Herein, we review the features of various cystic lesions of the kidney that can be found using US, discuss differential diagnoses using US, and propose a feature-oriented algorithmic approach to classifying renal cystic lesions using US.

Clinical and ultrasonographic features of male breast tumors: A retrospective analysis.

OBJECTIVE: The purpose of this study was to determine clinical and ultrasonographic characteristics of male breast tumors. METHODS: The medical records of male patients with breast lesions were retrieved from an electronic medical record database and a pathology database and retrospectively reviewed. A total of 112 men (125 breast masses) with preoperative breast ultrasonography (US) were included (median age, 59.50 years; age range, 15-96 years). Data extracted included patient age, if the lesions were bilateral, palpable, and tender, and the presence of nipple discharge. Breast lesion features on static US images were reviewed by three experienced radiologists without knowledge of physical examination or pathology results, original breast US image interpretations, or surgical outcomes. The US features were documented according to the BI-RADS (Breast Imaging-Reporting and Data System) US lexicons. A forth radiologist compiled the data for analysis. RESULTS: Of the 125 breast masses, palpable tender lumps and bilateral synchronous masses were more likely to be benign than malignant (both, 100% vs 0%, P < 0.05). Advanced age and bloody discharge from nipples were common in malignant lesions (P <0.05). A mass eccentric to a nipple, irregular shape, the presence of an echogenic halo, predominantly internal vascularity, and rich color flow signal on color Doppler ultrasound were significantly related to malignancy (all, P < 0.05). An echogenic halo and the presence of rich color flow signal were independent predictors of malignancy. CONCLUSION: Specific clinical and US characteristics of male breast tumors may help guide treatment, and determine if surgery or conservative treatment is preferable.

Algorithmic approaches to the diagnosis of gallbladder intraluminal lesions on ultrasonography.

Ultrasound is a frequently used diagnostic tool for gallbladder diseases. Polypoid lesions are commonly depicted at routine abdominal ultrasonography (US). The characteristics of these lesions vary. Since most early malignant tumors in the gallbladder are asymptomatic, differentiation between malignancy and benignity is crucial. Knowledge of gallbladder polypoid lesions is important so that they can be appropriately included in the differential diagnosis in patients presenting with intra-gallbladder nodules on US. This article summarizes the algorithmic approach to the diagnosis of these lesions and our recent experience with contrast-enhanced US. The clinical and imaging features of gallbladder polypoid lesions are reviewed.

A Case of Tubular Adenoma of Gallbladder Diagnosed Using Contrast-Enhanced Ultrasonography.

Contrast-enhanced ultrasound (CEUS) has been used to diagnose gallbladder (GB) diseases for recent years because it is sensitive to visualize vascularity. Herein, we report a case who had a 1.7 cm × 1.2 cm polypoid lesion located in the gallbladder fundus with a feeding artery located in the stalk. On CEUS, the lesion showed early arterial phase enhancement (time to peak enhancement 18 s), persisting throughout the venous and delay phases. This enhancing pattern suggested that the lesion was a GB adenoma rather than a GB carcinoma. Cholecystectomy was performed, and pathology of the tissue revealed tubular adenoma of the GB.

Is Intensity Inhomogeneity Correction Useful for Classification of Breast Cancer in Sonograms Using Deep Neural Network?

The sonogram is currently an effective cancer screening and diagnosis way due to the convenience and harmlessness in humans. Traditionally, lesion boundary segmentation is first adopted and then classification is conducted, to reach the judgment of benign or malignant tumor. In addition, sonograms often contain much speckle noise and intensity inhomogeneity. This study proposes a novel benign or malignant tumor classification system, which comprises intensity inhomogeneity correction and stacked denoising autoencoder (SDAE), and it is suitable for small-size dataset. A classifier is established by extracting features in the multilayer training of SDAE; automatic analysis of imaging features by the deep learning algorithm is applied on image classification, thus allowing the system to have high efficiency and robust distinguishing. In this study, two kinds of dataset (private data and public data) are used for deep learning models training. For each dataset, two groups of test images are compared: the original images and the images after intensity inhomogeneity correction, respectively. The results show that when deep learning algorithm is applied on the sonograms after intensity inhomogeneity correction, there is a significant increase of the tumor distinguishing accuracy. This study demonstrated that it is important to use preprocessing to highlight the image features and further give these features for deep learning models. In this way, the classification accuracy will be better to just use the original images for deep learning.

Shoulder joint synovial chondromatosis presenting as multiple axillary masses: A case report.

Synovial chondromatosis is a rare, benign, proliferative cartilaginous lesion arising from the synovial tissue, tenosynovium, or bursal lining. We describe the case of a patient who initially presented with multiple axillary masses. Breast ultrasound (US) was requested due to the concern of a breast tumor with axillary lymph node metastases. US study was helpful and provided adequate information to suggest the diagnosis.

The use of fine needle aspiration and trends in incidence of thyroid cancer in Taiwan.

BACKGROUND: Thyroid cancer is the most prevalent endocrine malignancy, and the incidence of thyroid cancer has increased worldwide. Fine needle aspiration (FNA) for cytology of thyroid tissue is used for differentiating thyroid cancers from benign thyroid nodules. Overuse of FNA may detect subclinical thyroid cancer and play a role in the increased incidence of thyroid cancer. The aim of this study was to evaluate trends in incidence of thyroid cancer and the use of palpation-guided FNA thyroid and ultrasound-guided FNA thyroid in Taiwan. METHODS: By retrospectively analyzing a cohort dataset of one million people randomly sample to represent as NHI beneficiaries of Taiwan National Health Insurance Research Database from 2004 to 2010, patients who received palpation-guided and ultrasound-guided thyroid FNA were identified. Individuals who were diagnosed as having thyroid cancer were determined. Age-standardized, yearly rates of palpation-guided thyroid FNA and ultrasound-guided FNA, and age-standardized, yearly incidence rates of thyroid cancer were calculated. RESULTS: In the study period, a total of 541 patients were newly diagnosed with thyroid cancer, 14,240 individuals received palpation-guided thyroid FNA, and 3823 individuals underwent ultrasound-guided thyroid FNA. There was a 94.8% increase in the age-standardized annual incidence rate of thyroid cancer. The age-standardized rates of palpation-guided thyroid FNA and ultrasound-guided thyroid FNA increased by 10.9% and 349.3%, respectively. CONCLUSION: FNA for cytology of thyroid tissue, especially ultrasound-guided FNA, was conducted by physicians more frequently in Taiwan. Increased use of FNA, especially ultrasound-guided FNA for cytology of thyroid tissue, may attribute to the increased incidence of thyroid cancer in Taiwan.

Unusual gastric tumors and tumor-like lesions: Radiological with pathological correlation and literature review.

Although gastric tumors have overlapping radiologic appearances, some unusual tumors may present specific imaging features. Using multidetector computed tomography (MDCT), with water as a negative oral contrast agent and intravenous contrast medium, can provide critical information for the diagnosis of gastric diseases. In addition, MDCT can evaluate the involvement of the gastric wall and extragastric extent of the disease, as compared with gastroenteroscopy and double-contrast upper gastrointestinal study. Regarding lesion location and size, enhancing and growth patterns, presence of calcification or fat, and involvement of the gastric wall and adjacent structures, CT may provide useful information. In this review article, we review the relevant literature and discuss the CT features and the histopathologic findings of different types of gastric lesions. The lesions are divided into benign (glomus tumors, schwannomas, leiomyomas, and lipomas), malignant (gastrointestinal stromal tumors, mucinous carcinomas, lymphomas, and carcinoid tumors), and tumor-like lesions (ectopic pancreas and bezoar). Familiarity with imaging appearances and pathologic findings can help physicians make an accurate diagnosis.

Solitary fibrous tumor of the breast: A case report and review of the literature.

Solitary fibrous tumor (SFT) is an uncommon neoplasm of mesenchymal origin, which can be benign or malignant. Most SFTs develop from the pleura, but they can also be found in other sites. There are only few reports of SFT occurring in the breast. We herein report such a rare case. Sonography demonstrated an ovoid lesion mimicking a fibroadenoma, whereas color Doppler imaging showed marked internal vascularity. A brief literature review on imaging features of SFTs is added. © 2016 Wiley Periodicals, Inc. J Clin Ultrasound 45:350-354, 2017.