Multi-Scale Attention Convolutional Network for Masson Stained Bile Duct Segmentation from Liver Pathology Images.

In clinical practice, the Ishak Score system would be adopted to perform the evaluation of the grading and staging of hepatitis according to whether portal areas have fibrous expansion, bridging with other portal areas, or bridging with central veins. Based on these staging criteria, it is necessary to identify portal areas and central veins when performing the Ishak Score staging. The bile ducts have variant types and are very difficult to be detected under a single magnification, hence pathologists must observe bile ducts at different magnifications to obtain sufficient information. This pathologic examinations in routine clinical practice, however, would result in the labor intensive and expensive examination process. Therefore, the automatic quantitative analysis for pathologic examinations has had an increased demand and attracted significant attention recently. A multi-scale inputs of attention convolutional network is proposed in this study to simulate pathologists' examination procedure for observing bile ducts under different magnifications in liver biopsy. The proposed multi-scale attention network integrates cell-level information and adjacent structural feature information for bile duct segmentation. In addition, the attention mechanism of proposed model enables the network to focus the segmentation task on the input of high magnification, reducing the influence from low magnification input, but still helps to provide wider field of surrounding information. In comparison with existing models, including FCN, U-Net, SegNet, DeepLabv3 and DeepLabv3-plus, the experimental results demonstrated that the proposed model improved the segmentation performance on Masson bile duct segmentation task with 72.5% IOU and 84.1% F1-score.

Pilot Report for Intracranial Hemorrhage Detection with Deep Learning Implanted Head Computed Tomography Images at Emergency Department.

Hemorrhagic stroke is a serious clinical condition that requires timely diagnosis. An artificial intelligence algorithm system called DeepCT can identify hemorrhagic lesions rapidly from non-contrast head computed tomography (NCCT) images and has received regulatory clearance. A non-controlled retrospective pilot clinical trial was conducted. Patients who received NCCT at the emergency department (ED) of Kaohsiung Veteran General Hospital were collected. From 2020 January-1st to April-30th, the physicians read NCCT images without DeepCT. From 2020May-1st to August-31st, the physicians were assisted by DeepCT. The length of ED stays (LOS) for the patients was collected. 2,999 patients were included (188 and 2811 with and without ICH). For patients with a final diagnosis of ICH, implementing DeepCT significantly shortened their LOS (560.67 ± 604.93 min with DeepCT vs. 780.83 ± 710.27 min without DeepCT; p = 0.0232). For patients with a non-ICH diagnosis, the LOS did not significantly differ (705.90 ± 760.86 min with DeepCT vs. 679.45 ± 681.97 min without DeepCT; p = 0.3362). For patients with ICH, those assisted with DeepCT had a significantly shorter LOS than those without DeepCT. For patients with a non-ICH diagnosis, implementing DeepCT did not affect the LOS, because emergency physicians need same efforts to identify the underlying problem(s) with or without DeepCT. In summary, implementing DeepCT system in the ED will save costs, decrease LOS, and accelerate patient flow; most importantly, it will improve the quality of care and increase the confidence and shorten the response time of the physicians and radiologists.

Realizing digital signatures for medical imaging and reporting in a PACS environment.

According to Taiwan's legislation pertaining to the protection of electronic data, the creators of electronic medical records (EMR) are solely responsible for the security of EMR. However, actual implementations that fulfill the security standards and requirements for electronic medical record systems are still lacking. Most EMR created from picture archive and communication system are not considered secure, as security protection mechanisms have not yet been granted legal status. This paper describes the details of establishing a digital signature system using Taiwan health professional cards. A digital signature system has been included to ensure quality assurance (QA) operations are controlled by technicians, and reporting capabilities have been provided for radiologist. Six imaging modalities and eight types of radiology reports have also been included in the system. Results indicate that the process of creating QA signatures does not have an adverse effect on the workflow of the facility, requiring less time for the signing and verification of radiology reports. This system has already been used routinely online in a real clinical setting for more than 2 years.

Custom-designed sensors embedded 3D-printed wearable device for improving the hemodialysis-related vascular dysfunction detection.

BACKGROUND: The increasing prevalence of end-stage renal disease (ESRD) imposes a substantial economic burden on public health-care systems. Hemodialysis (HD) is a pivotal treatment modality for patients with ESRD. However, prolonged use of HD vessels may result in stenosis, thrombosis, and occlusion due to repeated daily punctures. Thus, early detection and prevention of the dysfunction of dialysis routes are crucial. OBJECTIVE: In this study, we designed a wearable device for the early and accurate detection of arteriovenous access (AVA) stenosis in HD patients. METHODS: A personalized three-dimensional (3D) printed wearable device was designed by combining the phonoangiography (PAG) and photoplethysmography (PPG) techniques. The capability of this device to monitor AVA dysfunction before and after percutaneous transluminal angioplasty (PTA) was evaluated. RESULTS: After PTA, the amplitudes of both PAG and PPG signals increased in patients with arteriovenous fistulas and those with arteriovenous grafts; this might be due to increased blood flow. CONCLUSION: Our designed multi-sensor wearable medical device using PAG, PPG, and 3D printing appears suitable for early and accurate detection of AVA stenosis in HD patients.

Effects of an Intranet-Based Call-for-Help System on Teamwork, Work Efficiency, Job Satisfaction, and Job Stress in Nurses.

OBJECTIVES: In the medical environment, teamwork among medical care personnel is closely related to patient safety and care quality. This research has developed an Intranet-based call-for-help system to establish an emergency support system. Few studies have explored the effects of the timely call-for-help system on teamwork. This study explored the effects of the timely call-for-help system intervention. METHODS: This study was designed by 2 groups of pretest and posttest. This research was conducted at a medical center in Taiwan. The subjects of the study were nurses in inpatient wards. The newly established call-for-help system was used in the 4 experimental wards, enabling nurses to immediately seek help from each other when faced with challenges and difficulties. This study was blind with the outcome evaluator and data analyst blinded to the group of participants. RESULTS: A total of 165 nurses were included in the study, 84 in the intervention group and 81 in the control group. After the intervention of the call-for-help system, the experimental group had significantly better teamwork, work efficiency, job satisfaction, and lower job stress than the control group ( P < 0.01). The generalized estimating equation showed that the progress scores of the experimental group on the 4 scales were significantly higher than those of the control group ( P < 0.01). CONCLUSIONS: The implementation of timely call-for-help system can enable nursing staff to get immediate support, strengthen teamwork, create a positive nursing practice environment, and improve patient safety and quality of care. These improvements in teamwork and support are very important and worthy of promotion.

Pathologic liver tumor detection using feature aligned multi-scale convolutional network.

The detection of the most common type of liver tumor, that is, hepatocellular carcinoma (HCC), is one essential step to liver pathology image analysis. In liver tissue, common cell change phenomena such as apoptosis, necrosis, and steatosis are similar in tumor and benign tissue. Hence, the detection of HCC may fail when the patches covered only limited tissue region without enough neighboring cell structure information. To address this problem, a Feature Aligned Multi-Scale Convolutional Network (FA-MSCN) architecture is proposed in this paper for automatic liver tumor detection based on whole slide images (WSI). The proposed network integrates the features obtained at different magnification levels to improve the detection performance by referencing more neighboring information. The FA-MSCN consists of two parallel convolutional networks in which one would extract high-resolution features and the other would extract low-resolution features by atrous convolution. The low-resolution features then go through central cropping, upsampling, and concatenation with high-resolution features for final classification. The experimental results demonstrated that Multi-Scale Convolutional Network (MSCN) improves the detection performance compared to Single-Scale Convolutional Network (SSCN), and that the FA-MSCN is superior to both SSCN and MSCN, demonstrating on HCC detection.

The Use of Customized Three-Dimensionally Printed Mandible Prostheses with a Pressure-Reducing Device: A Finite Element Analysis in Different Chewing Positions, Biomechanical Testing, and In Vivo Animal Study Using Lanyu Pigs.

Segmental bony defects of the mandible constitute a complete loss of the regional part of the mandible. Although several types of customized three-dimension-printed mandible prostheses (CMPs) have been developed, this technique has yet to be widely used. We used CMP with a pressure-reducing device (PRD) to investigate its clinical applicability. First, we used the finite element analysis (FEA). We designed four models of CMP (P1 to P4), and the result showed that CMP with posterior PRD deployment (P4 group) had the maximum total deformation in the protrusion and right excursion positions, and in clenching and left excursion positions, posterior screws had the minimum von Mises stress. Second, the P4 CMP-PRD was produced using LaserCUSING from titanium alloy (Ti-6Al-4V). The fracture test result revealed that the maximum static pressure that could be withstood was 189 N, and a fatigue test was conducted for 5,000,000 cycles. Third, animal study was conducted on five male 4-month-old Lanyu pigs. Four animals completed the experiment. Two animals had CMP exposure in the oral cavity, but there was no significant inflammation, and one animal had a rear wing fracture. According to a CT scan, the lingual cortex of the mandible crawled along the CMP surface, and a bony front-to-back connection was noted in one animal. A histological examination indicated that CMP was significantly less reactive than control materials (p = 0.0170). Adequate PRD deployment in CMP may solve a challenge associated with CMP, thus promoting its use in clinical practice.

Feasibility of Breast MRI as the Primary Imaging Modality in a Large Asian Cohort.

Purpose Contrast-enhanced MRI has repeatedly demonstrated significantly enhanced sensitivity compared to mammography and ultrasound in breast cancer detection. The purpose of this study was to evaluate the feasibility and outcomes of using breast MRI as the initial imaging study for screening and diagnosis.  Materials and methods In this retrospective review of a cohort of 10,374 breast MRI scans in 7967 patients in Taitung County, Taiwan, a total of 5619 participants met inclusion criteria and were included in our analysis. We reviewed all biopsies that were performed subsequent to MRI studies in women (screening vs. diagnostic). The primary outcomes were false-positive (FP) biopsy rates and positive predictive value (PPV) of MRI - parameters that have historically been associated with performance that restricts more widespread use of MRI. False-positive rate based on benign biopsies (FPR-3) and the positive predictive value (PPV-3) were calculated. Results Without complementary imaging or follow-up to identify false negatives, the study of performance characteristics was limited to false positives and PPV. There were 351 benign biopsies generated by MRI out of the cohort of 5555 participants (5619 minus the malignant biopsies), generating a false-positive rate of 6.3%. Sixty-four patients out of 415 biopsies were malignant, generating a PPV-3 of 15.4%. Conclusion In this Asian cohort, utilizing breast MRI as the initial study for screening and/or diagnosis appears to be limited more by practical considerations such as cost and patient flow efficiency than by feasibility based on performance characteristics. With well-established superior sensitivity, coupled with improved interpretive skills and techniques that allow for low false-positive rates, MRI should be further studied for its role as the primary imaging modality in breast screening and diagnosis.

Kinetic patterns of benign and malignant breast lesions on contrast enhanced digital mammogram.

PURPOSE: To evaluate the kinetic patterns of benign and malignant breast lesions using contrast-enhanced digital mammogram (CEDM). METHODS: Women with suspicious breast lesions on mammography or ultrasound were enrolled. Single-view mediolateral oblique (MLO) CEDM of an affected breast was acquired at 2, 3, 4, 7, and 10 min after injection of contrast agent. Three readers visually and semi-quantitatively analyzed the enhancement of suspicious lesions. The kinetic pattern of each lesion was classified as persistent, plateau, or washout over two time intervals, 2-4 min and 2-10 min, by comparing the signal intensity at the first time interval with that at the second. RESULTS: There were 73 malignant and 75 benign lesions in 148 patients (mean age: 52 years). Benign and malignant breast lesions showed the highest signal intensity at 3 min and 2 min, respectively. Average areas under receiver operating characteristic (ROC) curve for diagnostic accuracy based on lesion enhancement at different time points were 0.73 at 2 min, 0.72 at 3 min, 0.69 at 4 min, 0.67 at 7 min, and 0.64 at 10 min. Diagnostic performance was significantly better at 2, 3, and 4 min than at 7 and 10 min (all p < 0.05). A washout kinetic pattern was significantly associated with malignant lesions at 2-4 min and 2-10 min frames according to two of the three readers' interpretations (all p ≤ 0.001). CONCLUSION: Applications of optimal time intervals and kinetic patterns show promise in differentiation of benign and malignant breast lesions on CEDM.

Hash Transformation and Machine Learning-Based Decision-Making Classifier Improved the Accuracy Rate of Automated Parkinson's Disease Screening.

Digitalized hand-drawn pattern is a noninvasive and reproducible assistive manner to obtain hand actions and motions for evaluating functional tremors and upper-limb movement disorders. In this study, spirals and straight lines in polar coordinates are used to extract polar expression features such as the key parameters deviation (cm) and accumulation angle (rad). These parameters are quantitative manner to scale the variations of functional tremors in normal control subjects and patients with Parkinson's disease (PD) and essential tremor (ET). However, difficulty arises in using nonlinear polar expression features in the two-dimensional feature space to separate normal control subjects from those with PD and ET. To solve the nonlinear separable classification problem, hash transformation is used to map polar expression features to a high-dimensional space using hash weighing function and modulo operation. Then, a machine learning method, such as the generalized regression neural network (GRNN), is implemented to train a decision-making classifier using the particle swarm optimization (PSO) algorithm for possible class assessment. With the enrolled data from 50 subjects, the fivefold cross validation, mean true positive, mean true negative, and mean hit rates of 98.93%, 98.96%, and 98.93%, respectively, are obtained to quantify the performance of the proposed decision-making classifier to identify normal controls and subjects with PD or ET. The experimental results indicate that the proposed screening model can improve the accuracy rate compared with the conventional machine learning classifier.

Percutaneous retrieval of dislodged central venous port catheter: experience of 25 patients in a single institute.

BACKGROUND: For a dislodged port catheter, percutaneous retrieval by using a loop snare or a basket is the standard technique, with high success. However, once a loop snare fails, the likelihood of success with other tools is considered low. PURPOSE: To report our experience of percutaneous retrieval of dislodged port catheters and to emphasize the usefulness of grasping forceps. MATERIAL AND METHODS: During a 6-year period, a total of 25 dislodged port catheters were retrieved in our institute. The interval between port catheter implantation and dislodged catheter retrieval was 3-85 months (mean 23 months). The time of delayed retrieval ranged from 3 to 604 days (mean 58 days). A loop snare or grasping forceps were used via either the femoral or jugular route. RESULTS: The prevalence of port catheter dislodgement was 0.4% in our institute. All dislodged port catheters were successfully removed, including four patients with delayed retrieval of more than 90 days. A loop snare was used in 20 patients, with technical success in 18. Grasping forceps were used in seven patients, all with success (including the two patients who failed by initial use of a loop snare). No procedure-related complications were encountered, except transient arrhythmia in four patients requiring no medication. CONCLUSION: Although the prevalence of port catheter dislodgement is low, percutaneous attempts at retrieval should be performed in all patients, even in chronic settings. A loop snare is the instrument of choice for retrieval. Grasping forceps can be used as an auxiliary instrument, especially in patients where a loop snare fails.

Antegrade retrieval of ureteral stents through an 8-French percutaneous nephrostomy route.

OBJECTIVE: The purpose of this study was to describe the technique of antegrade retrieval of ureteral stents under fluoroscopic guidance through an 8-French nephrostomy. MATERIALS AND METHODS: During an 8-year period, we retrieved 26 ureteral stents from 24 patients who were not candidates for retrograde removal or had other conditions precluding use of a retrograde approach. A loop snare or grasping forceps was used to retrieve a ureteral stent in the renal pelvis or calyx or upper ureter through an 8-French vascular sheath with a safety wire in place. A snare catheter advanced into the bladder for retrieval of the bladder end was used in patients in whom retrieval with both a loop snare and a grasping forceps failed. RESULTS: All 26 ureteral stents were successfully retrieved by the antegrade approach. Ten stents were retrieved with a snare alone and nine with a forceps alone. Five stents were retrieved successfully with a forceps after initial failures with snare catheters. Two stents were retrieved with snare catheters advanced into the bladder. The major complication of nephrostomy wound infection occurred in a patient with a urinary tract infection who underwent a one-stage procedure. All minor complications, including pelvic perforation in one patient and blood clot in the renal pelvis in four patients, resolved spontaneously without adverse sequelae. CONCLUSION: Antegrade percutaneous retrieval of a ureteral stent through an 8-French nephrostomy is safe and effective and has a high degree of technical success. It can be used as a routine interventional practice in radiology.

Splenic inflammatory pseudotumor mimicking angiosarcoma.

Splenic tumors are rare. Differentiation of the tumors before operation is of great value regarding the outcome. A case of a 32-year-old man with a splenic inflammatory pseudotumor (IPT) mimicking splenic angiosarcoma is described. The tumor was highly suspected of being splenic angiosarcoma based on radiological findings preoperatively. However, after splenectomy, histopathological examinations revealed splenic IPT. Splenic IPT and angiosarcoma are rare and often pose diagnostic difficulties because the clinical and radiological findings are obscure. Due to large differences in prognosis, we briefly reviewed the clinical, radiological, and pathological features of both of the tumors.

CT images of a malignant-transformed ovarian mature cystic teratoma with rupture: a case report.

A malignant transformation or a tumor rupture is a rare complication of ovarian mature cystic teratoma (MCT). A tumor rupture in a malignant-transformed MCT has never been reported in the literature. We present the CT images of a 39-year-old woman showing a large, predominantly cystic mass in the lower abdomen, with fat-fluid-level ascites. A contrast-enhanced solid component, with regional discontinuity within the cystic lesion, is also demonstrated. The pathologic diagnosis of the ruptured MCT unveils the malignant transformation (squamous cell carcinoma) and mesenteric carcinomatosis.

Breast cancer screening with digital breast tomosynthesis - 4 year experience and comparison with national data.

BACKGROUND: To determine if mammography combined with digital breast tomosynthesis (DBT), leads to superior performance in screening for breast cancer compared to digital mammography (DM) alone. METHODS: We retrospectively collected data from A) the results of population-based mammography-screening provided by the National Cancer Registry in Taiwan, and B) the results from all screening mammography performed with DBT from 2012 through 2015 at Kaohsiung Veterans General Hospital (VGHKS) since the institution of DBT at the end of 2011. This was compared data from 3 years with DM performed prior to DBT implementation. We calculated the results of medical audit of VGHKS and compared this with national data. Fisher's exact test is applied. RESULTS: VGHKS data demonstrated a higher cancer detection rate (CDR) and positive predictive value 1 (PPV 1) than the national average. Most prominently in the year 2014, our CDR was 120% better than that of the national average. CDR ranged from 6.3 to 8.1‰ prior to the introduction of DBT, and following DBT implementation this improved to 8.5-11.4‰, reflecting a mean increase of 32.2%. Early cancer detection was 50% higher and node negative rate was 25% higher than the national average of latest year. A 17.8% reduction in recall rate (RR) was achieved due to a decrease in unnecessary recall. CONCLUSION: There was a 32.2% increase in CDR and a 17.8% decrease in RR when DBT was used as an adjunct to DM, as compared to DM alone. CDRs were approximately twofold better than national average data. DBT was more effective at detecting cancer in ductal carcinoma in situ and stage 1.

Hepatic portal venous gas in ultrasonogram--benign or noxious.

The purpose of this study was to investigate and differentiate the characteristics of benign hepatic portal venous gas (HPVG) and noxious HPVG on sonographic images. This study included seven patients (age 65 to 89 y; mean 75 y) with sonograms and computed tomography (CT) images performed within 4-h interval. The sonographic findings of HPVG could be categorized into three patterns: (1) dot-like pattern in two patients; (2) streak-like pattern in three patients; and (3) fruit-pulp-like pattern in two. In the cases of dot-like pattern, it is of a benign transient situation; this phenomenon may be only demonstrated on sonograms but not necessarily on CT. The prognosis is more favorable and any subsequent CT may not be required. In the cases of streak-like or fruit-pulp-like patterns without localized liver lesions (e.g., abscess), it usually indicates a noxious scenario with worse clinical sequelae. We concluded that the identification of sonographic patterns of HPVG might be important to predict patient's outcome.

3D MRI for Quantitative Analysis of Quadrant Percent Breast Density: Correlation with Quadrant Location of Breast Cancer.

RATIONALE AND OBJECTIVES: Breast cancer occurs more frequently in the upper outer (UO) quadrant, but whether this higher cancer incidence is related to the greater amount of dense tissue is not known. Magnetic resonance imaging acquires three-dimensional volumetric images and is the most suitable among all breast imaging modalities for regional quantification of density. This study applied a magnetic resonance imaging-based method to measure quadrant percent density (QPD), and evaluated its association with the quadrant location of the developed breast cancer. MATERIALS AND METHODS: A total of 126 cases with pathologically confirmed breast cancer were reviewed. Only women who had unilateral breast cancer located in a clear quadrant were selected for analysis. A total of 84 women, including 47 Asian women and 37 western women, were included. An established computer-aided method was used to segment the diseased breast and the contralateral normal breast, and to separate the dense and fatty tissues. Then, a breast was further separated into four quadrants using the nipple and the centroid as anatomic landmarks. The tumor was segmented using a computer-aided method to determine its quadrant location. The distribution of cancer quadrant location, the quadrant with the highest QPD, and the proportion of cancers occurring in the highest QPD were analyzed. RESULTS: The highest incidence of cancer occurred in the UO quadrant (36 out of 84, 42.9%). The highest QPD was also noted most frequently in the UO quadrant (31 out of 84, 36.9%). When correlating the highest QPD with the quadrant location of breast cancer, only 17 women out of 84 (20.2%) had breast cancer occurring in the quadrant with the highest QPD. CONCLUSIONS: The results showed that the development of breast cancer in a specific quadrant could not be explained by the density in that quadrant, and further studies are needed to find the biological reasons accounting for the higher breast cancer incidence in the UO quadrant.