Pattern Of Vessels Research Articles

Treatment of congenital atypical haemangiosarcoma in a foal

SummaryHaemangiosarcoma is a rare vascular tumour in horses, usually originating from blood vessel endothelial cells. We present the case of an 8‐day‐old foal, referred for an atypical large subcutaneous mass on the left side since birth. Ultrasonographically, it showed multiple cavities with hypoechoic content, marked vascularisation and fluid movement between cavities. As the nature of the mass suggested that surgery could result in profuse bleeding, we decided to perform an initial arteriography to identify the pattern and calibre of the main vessels and embolisation of this vascular supply, which allowed surgical removal with less bleeding than expected. This approach, with pre‐surgical transarterial embolisation of the tumour, is not commonly used in equine surgery. Histology established a diagnosis of cutaneous haemangiosarcoma. During 1‐year post‐surgery, clinical and ultrasound examinations were carried out without any signs of recurrence or metastasis. One year later, the foal was euthanised due to a limb fracture. No macroscopic signs of metastasis were observed at necropsy. Histology showed no signs of recurrence. Cutaneous haemangiosarcomas, though rare, should be included in the differential of masses and growths with compatible ultrasound or cytological findings. Transcatheter arterial embolisation of highly vascularised neoplasms can reduce bleeding and facilitate subsequent surgical resection.

Tristar Vessels: A Newly Described Dermoscopic Vessel Pattern of Miescher’s Nevus

Purpose: Although it is very common in people over 30 years old, little is known about the validity of dermoscopic criteria to differentiate Miescher’s nevus (MN) from other papulonodular lesions located on the head and neck. The aim of this study is to evaluate the dermoscopic findings in MN on the head and neck in patients over 40 years by using dermoscopy.
 Methods: In this descriptive cross-sectional study 170 MN were evaluated by using polarized light dermoscopy. frequencies of dermoscopic findings in MN were determined using Statistical Package for Social Sciences for Windows 15.0.
 Results: The most frequently detected dermoscopic pattern in MN was globular pattern (64.5%), less often homogeneous (32.4%) or cobblestone pattern (2.9%). Globules were observed in 75.3% of MN and dots were seen in 12.4%. They frequently had skin-colored (87.1%) or light-brown (49.4%) homogeneous structureless areas. Elongated comma vessels (47.1%) were the most common vascular findings. Although comma vessels (33.5%) and linear vessels (4.7%) were also observed, 11.2% of MN presented “tristar vessels” (a newly described vascular pattern) that showed regular ‘tristar like ramifications’ in the distal part of the vessels.
 Conclusions: Firstly identified “tristar vessel pattern” is a dermoscopic description of MN that can be a useful clue to differential diagnosis.

Assessment of vascular patterns during the treatment of psoriatic patients using narrow-band ultraviolet B phototherapy by the dermoscope.

Phototherapy is a traditional treatment for psoriasis and patients using it for a long time may be exposed to cumulative toxicity, so dermatologists need continuously diagnostic tools that help in monitoring the disease progression. To detect dermoscopic changes with the improvement of skin in patients with chronic plaque psoriasis on narrow-band ultraviolet B phototherapy and evaluate the role of dermoscopy in monitoring the patients. Narrowband ultraviolet B phototherapy was prescribed to thirty (30) patients with chronic plaque psoriasis for three months according to their disease condition. Psoriasis area and severity index (PASI score) were calculated, and dermoscopic evaluation was done at the first visit (W0), after 6 weeks, and after 12 weeks of beginning the phototherapy. According to PASI score calculations, a significant correlation was found between changes in the vessel patterns and the improvement that occurred during the treatment sessions in psoriatic lesions, whereas the patients with globular blood vessels were significantly associated with weak clinical results. Dermoscopy is a rapid, simple tool to predict the response of psoriatic patients to phototherapy using vascular pattern assessment.

Comparing spatial patterns of marine vessels between vessel-tracking data and satellite imagery

Monitoring marine use is essential to effective management but is extremely challenging, particularly where capacity and resources are limited. To overcome these limitations, satellite imagery has emerged as a promising tool for monitoring marine vessel activities that are difficult to observe through publicly available vessel-tracking data. However, the broader use of satellite imagery is hindered by the lack of a clear understanding of where and when it would bring novel information to existing vessel-tracking data. Here, we outline an analytical framework to (1) automatically detect marine vessels in optical satellite imagery using deep learning and (2) statistically contrast geospatial distributions of vessels with the vessel-tracking data. As a proof of concept, we applied our framework to the coastal regions of Peru, where vessels without the Automatic Information System (AIS) are prevalent. Quantifying differences in spatial information between disparate datasets—satellite imagery and vessel-tracking data—offers insight into the biases of each dataset and the potential for additional knowledge through data integration. Our study lays the foundation for understanding how satellite imagery can complement existing vessel-tracking data to improve marine oversight and due diligence.

Associations of carotid artery flow parameters with MRI markers of cerebral small vessel disease and patterns of brain atrophy

ObjectivesA growing body of evidence links age related brain pathologies to systemic vascular processes. We aimed to study the prevalence and interrelations between magnetic resonance imaging (MRI) markers of cerebral small vessel disease and patterns of brain atrophy, and their association to carotid duplex ultrasound flow parameters. Materials and methodsWe investigated a population based randomised cohort of older adults (n=391) aged 70-87, part of the Swedish Good Aging in Skåne Study. Peak systolic and end diastolic velocities of the carotid arteries were measured by ultrasound, and resistivity- and pulsatility indexes were calculated. Subjects with increased peak systolic velocity indicating carotid stenosis were excluded from analysis. Nine MRI findings were rated by visual scales: white matter changes, pontine white matter changes, microbleeds, lacunar infarctions, medial temporal lobe atrophy, global cortical atrophy, parietal atrophy, precuneus atrophy and central atrophy. ResultsMRI pathologies were found in 80% of subjects. Mean end diastolic velocity in common carotid arteries was inversely associated with white matter hyperintensities (OR=0.92; p=0.004), parietal lobe atrophy (OR=0.94; p=0.039), global cortical atrophy (OR=0.90; p=0.013), precuneus atrophy (OR=0.94; p=0.022), “number of CSV pathologies” (β=-0.07; p<0.001) and “MRI-burden score” (β=-0.11; p<0.001), after adjustment for age and sex. The latter three were also associated with pulsatility and resistivity indexes. ConclusionsLow carotid end diastolic velocity, as well as increased carotid resistivity and pulsatility, were associated with signs of cerebral small vessel disease and patterns of brain atrophy, indicating a vascular component in the process of brain aging.

Highly accurate blood vessel segmentation using texture‐based modified K‐means clustering with deep learning model

SummaryThis paper suggests a blood vessel segmentation using the Texture‐Based Modified K‐means Clustering (TBMKC) technique to lessen the detrimental effects of light lesions. In the suggested method, the K value is chosen automatically by maximizing the local pixel data of the input image. Utilizing the Gabor Filter and Scale‐Invariant Feature Transform (SIFT), respectively, texture and statistical characteristics are used to extract the local information. The number of pixels present in each class is used to alter the cluster centroid using Particle Swarm Optimization (PSO) methods. Local adaptive thresholding is then used to separate the blood vessel pattern. The proposed method is invariant to scales and rotations due to SIFT features. The thresholding output is given to the modified DCNN (Deep Convolutional Neural Network). Finally, the performance of the (MDCNN+ TBMKC+ PSO) scheme is computed over other extant schemes. The outcomes of the adopted scheme is determined and tested using the retinal image from DRIVE, STARE, HRF, and CHASE_DBI databases. The accuracy of the proposed method is 13.41%, 7.22%, 9.56%, 6.24%, 2.35%, 14.54%, 13.23%, 3.71%, 10.82%, 8.28%, 7.98%, and 54.01% better than the existing method like M‐GAN, MCET‐HHO, CNN, DBN, SVM, RNN, NN, MDCNN+PSO, MDCNN+GA, MCNN+FF, MDCNN+ABC, and MDCNN+LA.

NORMAL PERIPHERAL CHOROIDAL THICKNESS MEASURED BY WIDEFIELD OPTICAL COHERENCE TOMOGRAPHY.

Choroidal stasis plays an important role in the pathogenesis of many conditions and leads to choroidal thickening. However, the normal peripheral choroidal thickness (PCT) pattern remains unknown. This study investigated PCT and associated factors using ultrawidefield optical coherence tomography in healthy eyes. This cross-sectional study included 120 healthy eyes (57 males; age, 52.0 ± 20.5 years). We used choroidal thickness maps created by ultrawidefield optical coherence tomography (viewing angle, 200°) with real-shape correction. The peripheral area was defined from 60° to 100° and further separated vertically and horizontally. The PCT and the correlations between PCT and subjects' characteristics were examined. The PCT were 227.1 ± 57.0 µ m, 199.6 ± 53.9 µ m, 196.6 ± 57.1 µ m, and 148.0 ± 38.2 µ m in supratemporal, infratemporal, supranasal, and infranasal areas, respectively. The thickest peripheral sector was most frequently observed in supratemporal (69.2%). The PCT negatively correlated with age in all regions ( P -values < 0.001) and axial length in supratemporal, supranasal, and infranasal areas ( P -values ≤ 0.003). The temporal PCT was thicker on the side contiguous with the posterior pole Haller's vessels ( P -values ≤ 0.020). The PCT is associated with age, axial length, and the running pattern of Haller's vessels.

A numbers game: analyzing pottery usage patterns of 4th millennium BCE sites in the southern Levant

Excavations of 4th millennium BCE sites conducted in the past two decades have provided a significant amount of quantitative data regarding the use of pottery. This accumulated data provides an opportunity to engage in a comparative analysis between sites of different regions in the southern Levant, as well as of the different periods comprising the 4th millennium, including the Late Chalcolithic, Early Bronze Age IA, Early Bronze Age IB and Early Bronze Age II. The aim of the current study is to utilize quantitative data to detect general trends in the usage patterns of pottery vessels. The study was based on a division into three general categories: serving, cooking and storage vessels. The results show that each period had its own specific usage pattern or patterns, and that during the Late Chalcolithic and the late EBA IB these patterns were similar throughout the southern Levant. The results of this study are also used to explore some of the associated socio-political implications.

Real-World Experience of AI-Assisted Endocytoscopy Using EndoBRAIN—An Observational Study from a Tertiary Care Center

Abstract Background and Aims Precise optical diagnosis of colorectal polyps could improve the cost-effectiveness of colonoscopy and reduce polypectomy-related complications. We conducted this study to estimate the diagnostic performance of visual inspection alone (WLI + NBI) and of EndoBRAIN (endocytoscopy-computer-aided diagnosis [EC-CAD]) in identifying a lesion as neoplastic or nonneoplastic using EC in real-world scenario. Methods In this observational, prospective, pilot study, a total of 55 polyps were studied in the patients aged more than or equal to 18 years. EndoBRAIN is an artificial intelligence (AI)-based system that analyzes cell nuclei, crypt structure, and vessel pattern in differentiating neoplastic and nonneoplastic lesion in real-time. Endoscopist assessed polyps using white light imaging (WLI), narrow band imaging (NBI) initially followed by assessment using EC with NBI and EC with methylene blue staining. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of endoscopist and EndoBRAIN in identifying the neoplastic from nonneoplastic polyp was compared using histopathology as gold-standard. Results A total of 55 polyps were studied, in which most of them were diminutive (36/55) and located in rectum (21/55). The image acquisition rate was 78% (43/55) and histopathology of the majority was identified to be hyperplastic (20/43) and low-grade adenoma (16/43). EndoBRAIN identified colonic polyps with 100% sensitivity, 81.82% specificity (95% confidence interval [CI], 59.7–94.8%), 90.7% accuracy (95% CI, 77.86–97.41%), 84% positive predictive value (95% CI, 68.4–92.72%), and 100% negative predictive value. The sensitivity and negative predictive value were significantly greater than visual inspection of endoscopist. The diagnostic accuracy seems to be superior; however, it did not reach statistical significance. Specificity and positive predictive value were similar in both groups. Conclusion Optical diagnosis using EC and EC-CAD has a potential role in predicting the histopathological diagnosis. The diagnostic performance of CAD seems to be better than endoscopist using EC for predicting neoplastic lesions.

Arterial circle of the brain in the common wildebeest (Connochaetes taurinus).

The main aim of this study was to analyze the arterial circle of the brain and rostral epidural rete mirabile in specimens of the common wildebeest (Connochaetes taurinus). The arterial circle of the brain is a circulatory anastomosis that supplies blood to particular lobes of the brain and surrounding structures. The study was conducted on male and female adults (n=12) by bilateral injection of an acetone solution of vinyl superchloride or latex LBS3060, which resulted in a cast of arteries of the head and encephalic base. We describe the exact structure of the arterial circle of the brain and rostral epidural rete mirabile. The shape of the arterial circle of the brain in the common wildebeest is heart-shaped, as in other Bovidae. It is formed by bilateral rostral cerebral arteries, caudal communicating arteries, and the basilar artery, with a general pattern of vessels forming and branching off from the arterial circle of the brain, as described in other ruminants. The rostral cerebral and caudal communicating arteries emerge from an intracranial segment of the internal carotid artery, which in turn arises from vessels of the rostral epidural rete mirabile. This structure, well developed in the examined individuals, has mechanisms underlying selective cooling of the brain, protecting animals from hyperthermia, and affecting body water balance.

Computational Model Exploring Characteristic Pattern Regulation in Periventricular Vessels.

The developing neocortical vasculature exhibits a distinctive pattern in each layer. In murine embryos, vessels in the cortical plate (CP) are vertically oriented, whereas those in the intermediate zone (IZ) and the subventricular zone (SVZ) form a honeycomb structure. The formation of tissue-specific vessels suggests that the behavior of endothelial cells is under a specific regulatory regime in each layer, although the mechanisms involved remain unknown. In the present study, we aimed to explore the conditions required to form these vessel patterns by conducting simulations using a computational model. We developed a novel model framework describing the collective migration of endothelial cells to represent the angiogenic process and performed a simulation using two-dimensional approximation. The attractive and repulsive guidance of tip cells was incorporated into the model based on the function and distribution of guidance molecules such as VEGF and Unc ligands. It is shown that an appropriate combination of guidance effects reproduces both the parallel straight pattern in the CP and meshwork patterns in the IZ/SVZ. Our model demonstrated how the guidance of the tip cell causes a variety of vessel patterns and predicted how tissue-specific vascular formation was regulated in the early development of neocortical vessels.

НЕЙРОСЕТЕВАЯ МЕТОДИКА ИДЕНТИФИКАЦИИ ЛИЧНОСТИ ПО РИСУНКУ ВЕН ЛАДОНИ

The article describes the work on the creation of a neural network method for identifyinga person based on the mechanism of scanning and analyzing the pattern of palm veins as a biometricparameter. As part of the study, the prerequisites, goals and reasons for which the deve lopmentof a reliable biometric identification system is an important and relevant area of activityare described. A number of problems are formulated that are inherent in existing methods forsolving the problem: the graph method and the method based on calculating the distance expressedin various interval metrics. The description of the principles of their work is given.The tasks solved by personal identification systems are formulated: comparison of the subject ofidentification with its identifier, which uniquely identifies this subject in the information system.A mechanism for reading a pattern of veins from the palm of the hand, developed for analyzingan image obtained with a digital camera sensitive to infrared radiation, is described. When thepalm is in the frame, illuminated by the light of the near infrared range, the image obtainedfrom the camera becomes noticeable pattern of veins, vessels and capillaries that lie under theskin. Depending on the organization, the identification system may, based on the provided identifier,determine the appropriate access subject or verify that the same identifier belongs to theintended subject. Three methods for further analysis of biometric data and personal identificationare given: approaches based on categorical classification and binary classification, as wellas a combined approach, in which identification is first used by the first method, and then, bythe second, but already for a known access identifier defined on the first stage. The resultingarchitecture of the neural network for the categorical classification of the vein pattern is pr esented,a method for calculating the number of model parameters depending on the number ofregistered subjects is described. The main conclusions and experimental measurements of theaccuracy of the system when implementing various methods are presented, as well as diagrams ofchanges in the accuracy of models during training. The main advantages and disadvantages of theabove methods are revealed.

Crosstalk between Blood Vessels and Glia during the Central Nervous System Development.

The formation of proper blood vessel patterns in the central nervous system (CNS) is crucial to deliver oxygen and nutrient to neurons efficiently. At the same time, neurons must be isolated from the outer blood circulation by a specialized structure, the blood-brain barrier (BBB), to maintain the microenvironment of brain parenchyma for the survival of neurons and proper synaptic transmission. To develop this highly organized structure, glial cells, a major component of the brain, have been reported to play essential roles. In this review, the crosstalk between the macroglia, including astrocytes and oligodendrocytes, and endothelial cells during the development of CNS will be discussed. First, the known roles of astrocytes in neuro-vascular unit and its development, and then, the requirements of astrocytes for BBB development and maintenance are shown. Then, various genetic and cellular studies revealing the roles of astrocytes in the growth of blood vessels by providing a scaffold, including laminins and fibronectin, as well as by secreting trophic factors, including vascular endothelial growth factor (VEGF) and transforming growth factor-β (TGF-β) are introduced. Finally, the interactions between oligodendrocyte progenitors and blood vessels are overviewed. Although these studies revealed the necessity for proper communication between glia and endothelial cells for CNS development, our knowledge about the detailed cellular and molecular mechanisms for them is still limited. The questions to be clarified in the future are also discussed.

Clinical Case of Lymphomatoid Papulosis

Lymphomatoid papulosis is a rare skin disease. The incidence averages 1.5 cases per 1 million population. It is the most common in adults around the age of 40. It was previously considered as paraneoplastic dermatosis, but recent studies have confirmed that lymphomatoid papulosis is a primary CD30 + T-lymphoma of the skin. Despite the aggressive morphological features, it is benign. The disease is characterized by a tendency to spontaneous regression. Typically, skin lesions last 3-12 weeks, although in some severe cases they may last longer. Skin lesions may disappear or recur over decades. Patients require observation because a second lymphoproliferative disease develops in 10-40% of patients.&#x0D; A case of lymphomatoid papulosis in a patient with diffuse astrocytoma is presented. The patient was treated with systemic retinoids. The results of differential diagnosis and additional research methods, including dermoscopy, are given. Although the use of dermoscopy was not crucial, the results of the research showed microscopic visual differences between the elements of the rash, depending on the stage of the disease. The picture was mostly typical, however, spots formed by the areas of central erythema on the background of light brown areas, with a predominance of the reticular vessels pattern were also noted in addition to the rash elements on the hairy skull. Clarification of this feature requires further study.&#x0D; The purpose of our report is to draw the attention of dermatologists and family doctors to cases of rare dermatoses. The rareness of the disease, lack of knowledge on the clinical findings lead to diagnostic errors, “inadequate treatment”.

S2272 Inlet Patch Polyp Mimicking Esophageal Cancer

Introduction: Heterotopic gastric mucosa (HGM) in the proximal esophagus also known as cervical inlet patch is a prevalent accidental finding during EGD. Case Description/Methods: 56 y.o. female with no prior PMH presented with a 4-year history of constipation, heartburn, epigastric pain, and weight loss. Symptoms were not controlled with the PPI trial. EGD showed 2 areas of gastric mucosa heterotopy in the duodenal bulb, sized up to 5 mm. In the cervical esophagus, an area of HGM sized 15x20 mm with protruding lesion Paris 0-Is sized 5x7mm was visualized. In the narrow-band imaging, the vessel pattern was irregular, with dilated interpupillary loops, and an irregular surface pattern. Malignancy was suspected with biopsies obtained. Pathology showed gastric-type epithelium with active inflammation, erosion, and hyperplastic polyp in HGM. On repeat EGD lesion was completely removed with hot snare polypectomy. Final pathology showed inflammatory (granulation) polyp without dysphasia or neoplastic process. The patient’s dyspeptic symptoms improved on follow-up with double dose PPI (Figure). Discussion: HGM is found in up to 10% of the general population. Some studies consider that HGM is a common benign finding which can be used as a surrogate marker for thorough esophagus examination. Other data suggest that inlet patches can be associated with reflux and dysphagia symptoms, dysplasia, and malignancy in rare cases. Quick insertion and withdrawal of the scope can lead to missed diagnoses of HGM and its complications. HGM detection rate can serve as an EGD quality indicator. Narrow band imaging can be used to improve the HGM detection rate. Various classifications of surface and vessel patterns are used to identify squamous cell malignancy in the upper esophagus, but they are inapplicable in HGM. Careful examination with histopathological examination of biopsies is recommended for mucosal abnormalities in HGM.Figure 1.: Narrow-band image of the HGM polyp.

A novel machine learning approach to analyzing geospatial vessel patterns using AIS data

ABSTRACT In the maritime environment, the Automatic Identification System (AIS) contains information related to vessel trajectories that can be used to detect unusual maritime occurrences and maritime traffic patterns. To detect such occurrences with supervised learning methods the AIS messages must be manually annotated, which can be a demanding process. Therefore, unsupervised methods are used to identify anomalous traffic patterns based on vessel trajectories. Typically, dense regions of maritime activity are studied to capture common traffic patterns which help identify trajectories that do not follow the norm. However, these approaches cannot detect anomalous behaviors along common pathways or incorporate time-related events into the analysis. Such challenges motivate the approach taken in this work by using auto-regressive techniques to model vessel trajectories and clustering analyses to explore behavior patterns of vessels. Results confirm that the Auto-regressive Integrated Moving Average (ARIMA) and Ornstein-Uhlenbeck (OU) processes are able to model the trajectories and can be used with density-based spatial clustering of applications with noise (DBSCAN), hierarchical clustering (HC), and spectral clustering (SC) to identify different behavioral patterns.

HT-Net: A Hybrid Transformer Network for Fundus Vessel Segmentation

Doctors usually diagnose a disease by evaluating the pattern of abnormal blood vessels in the fundus. At present, the segmentation of fundus blood vessels based on deep learning has achieved great success, but it still faces the problems of low accuracy and capillary rupture. A good vessel segmentation method can guide the early diagnosis of eye diseases, so we propose a novel hybrid Transformer network (HT-Net) for fundus imaging analysis. HT-Net can improve the vessel segmentation quality by capturing detailed local information and implementing long-range information interactions, and it mainly consists of the following blocks. The feature fusion block (FFB) is embedded in the shallow levels, and FFB enriches the feature space. In addition, the feature refinement block (FRB) is added to the shallow position of the network, which solves the problem of vessel scale change by fusing multi-scale feature information to improve the accuracy of segmentation. Finally, HT-Net’s bottom-level position can capture remote dependencies by combining the Transformer and CNN. We prove the performance of HT-Net on the DRIVE, CHASE_DB1, and STARE datasets. The experiment shows that FFB and FRB can effectively improve the quality of microvessel segmentation by extracting multi-scale information. Embedding efficient self-attention mechanisms in the network can effectively improve the vessel segmentation accuracy. The HT-Net exceeds most existing methods, indicating that it can perform the task of vessel segmentation competently.

Anatomical variations of the canine adrenal vessels.

The canine adrenal glands receive blood from the celiac artery, cranial mesenteric artery, caudal phrenic artery, cranial abdominal artery, phrenicoabdominal trunk, abdominal aorta, renal artery and lumbar artery. These are classified into three types: cranial, middle and caudal adrenal branches. It is also known that the adrenal vein flows into the phrenicoabdominal vein. However, individual differences in the branching pattern of adrenal vessels have not been systematically analysed. We evaluated adrenal vessels in dogs that underwent contrast-enhanced abdominal computed tomography (CT). There were 255 arteries travelling to the adrenal glands in 47 cases, with 1-6 arteries travelling per adrenal gland. The arteries included 67 caudal phrenic arteries, 62 aortic arteries, 60 cranial abdominal arteries, 39 renal arteries, 12 phrenicoabdominal trunks, 8 cranial mesenteric arteries, 6 celiac arteries and 1 lumbar artery. Most of the branches were from the aorta and caudal phrenic artery on the left side, and the cranial abdominal and caudal phrenic artery on the right side. A total of 110 adrenal veins were identified. Inflow into the phrenicoabdominal vein and into the right and left renal veins was observed, and we identified no inflow into other veins. This study demonstrated two points: laterality and individual differences in adrenal blood vessels. When evaluating adrenal blood vessels with abdominal contrast-enhanced CT, it is recommended to take images under general anaesthesia with breath-holding and observe them using multiplanar reconstruction.

Deep learning framework for biometric authentication using retinal images

ABSTRACT The inimitable blood vessel pattern of retina is a biometric feature used in person authentication. Rotation, translation and scaling of the retinal image affect the reliability and security of the biometric authentication system. Several feature extraction approaches have been proposed but to make authentication systems invariant to these variations is still challenging. This paper reports a robust retina identification system with the noble use of a convolution neural network (CNN) for automatic feature extraction. Colour image of retina is directly fed into the CNN model to extract features which are not only invariant in different geometric scales but also for illumination changes and pathological images. The network is trained using an optimisation algorithm and performed authentication using a softmax function in the final layer of the CNN model. Different CNN models are designed and tested using three groups of images consisting of coloured, grey and diseased retinal images obtained from different databases.

Early Rectal Cancer With Submucosal Infiltration: When to Avoid Cold Snare Polypectomy for

A 65-year-old man was referred to our hospital because of the presence of a rectal lesion. The patient had an 8-mm reddish sessile protruding lesion (Paris 0-Is) on the rectosigmoid with white light imaging (a). Cold snare polypectomy (CSP) is considered appropriate for adenomatous polyps measuring <10 mm. However, magnifying narrow-band imaging showed irregular vessel and surface patterns (Japan NBI Expert Team type 2B) (b). Magnifying chromoendoscopy with crystal violet staining revealed mild irregularity of the pits (Kudo type VI low grade) indicative of cancer (c). Pretreatment diagnosis indicated early rectal cancer, and the estimated depth of invasion was superficial submucosal invasion (Tis–T1a [SM1]). Therefore, endoscopic mucosal resection was performed instead of CSP. Histopathology revealed a well-differentiated tubular adenocarcinoma with an adenoma component and depth of pT1b (SM: 1,800 μm) (d). CSP was safe and effective against lesions measuring <10 mm, with the rate of en bloc resection reaching 100%. Nevertheless, a precise pretreatment diagnosis is required. After the detection of Japan NBI Expert Team type 2B, treating physicians should perform magnifying chromoendoscopy to evaluate the pit pattern. We report a rare case of a lesion measuring <10 mm in diameter with massive submucosal infiltration treated with endoscopic mucosal resection instead of CSP. (Informed consent was obtained from the patient to publish these images.)