Endoscopic Ultrasound Imaging Research Articles

Enhanced endoscopic ultrasound imaging for pancreatic lesions: The road to artificial intelligence.

Early detection of pancreatic cancer has long eluded clinicians because of its insidious nature and onset. Often metastatic or locally invasive when symptomatic, most patients are deemed inoperable. In those who are symptomatic, multi-modal imaging modalities evaluate and confirm pancreatic ductal adenocarcinoma. In asymptomatic patients, detected pancreatic lesions can be either solid or cystic. The clinical implications of identifying small asymptomatic solid pancreatic lesions (SPLs) of < 2 cm are tantamount to a better outcome. The accurate detection of SPLs undoubtedly promotes higher life expectancy when resected early, driving the development of existing imaging tools while promoting more comprehensive screening programs. An imaging tool that has matured in its reiterations and received many image-enhancing adjuncts is endoscopic ultrasound (EUS). It carries significant importance when risk stratifying cystic lesions and has substantial diagnostic value when combined with fine needle aspiration/biopsy (FNA/FNB). Adjuncts to EUS imaging include contrast-enhanced harmonic EUS and EUS-elastography, both having improved the specificity of FNA and FNB. This review intends to compile all existing enhancement modalities and explore ongoing research around the most promising of all adjuncts in the field of EUS imaging, artificial intelligence.

The expanding role of endoscopic ultrasound elastography.

Endoscopic ultrasound (EUS) is an invaluable tool for assessing various GI diseases. However, using just the conventional B-mode EUS imaging may not be sufficient to accurately delineate the lesion's character. Using the principle of stress-induced tissue strain, EUS elastography (EUS-E) can help in the real-time sonographic assessment of the level of tissue stiffness or hardness of any organ of interest during a routine EUS procedure. Thus, EUS-E can better characterize the lesion's nature and highlight the more suspicious areas within an individual lesion. The most commonly studied lesions with EUS-E are the pancreatic lesions, namely, chronic pancreatitis, pancreatic cancer, and lymph nodes. However, EUS-E is gradually expanding its use for lesion characterization of the liver, bile duct, adrenals, gastrointestinal tract, and even therapy response. Moreover, the use of EUS-E along with other image enhancement techniques such as harmonic EUS and contrast-enhanced EUS can improve the accuracy of the diagnosis. However, several technical aspects need to be standardized before EUS-E can be truly used as a tool for "virtual biopsy". This review focuses on the various technical aspects of the use of EUS-E, it is established and expanding indications and an extensive outline of the various studies on EUS-E. We also discuss the current pitfalls and future trends in EUS-E.

New Screening System Using Forward-Viewing Radial Endoscopic Ultrasound and Magnetic Resonance Imaging for High-Risk Individuals With Familial History of Pancreatic Cancer.

Background and AimsAttention is increasingly being paid to family history of pancreatic cancer (PC) as a risk factor for developing PC. It is mandatory to develop a screening system for early detection of PC; however, the relationship between a family history of PC and the incidence of pancreatic abnormalities, such as pancreatic cyst and chronic pancreatitis (CP), in the Japanese population remains unknown.Patients and MethodsIndividuals with a family history of PC were prospectively enrolled in a screening program using forward-viewing radial endoscopic ultrasound (FR-EUS) and magnetic resonance imaging (MRI) with magnetic resonance cholangiopancreatography (MRCP) as the diagnostic modalities.ResultsIn total, forty-three individuals in 37 families were enrolled (mean age, 54 years). All individuals underwent FR-EUS and MRI with no complications. FR-EUS revealed resectable PC (n = 1, 2.3%), pancreatic cysts (n = 24, 55.8%), intraductal papillary mucinous neoplasm (IPMN; n = 13, 30.2%), and early CP-like appearance (n = 15, 34.9%). The detection rate of early CP-like appearance was significantly higher by EUS than by MRI. Pancreatic cysts and IPMN detected by FR-EUS were significantly correlated to age (≥60 years) and less correlated to men (hazard ratio [HR] 22.4; 95% confidence interval [CI], 2.10–236.0; p < 0.01 and HR 0.092; 95% CI, 0.01–0.83; p = 0.033, respectively). Early CP-like appearance detected by FR-EUS was significantly correlated with men and smoking (HR 5.0; 95% CI, 1.3–19.3; p = 0.02 and HR 4.02; 95% CI, 0.991–16.3; p = 0.05, respectively).ConclusionA screening system using FR-EUS and MRI/MRCP for individuals with a family history of PC was useful for identifying curable PC and pancreatic abnormalities. The incidence of pancreatic cysts, such as IPMN and early CP-like appearance, was also high in the Japanese cohort.

Application of endoscopic ultrasonography for detecting esophageal lesions based on convolutional neural network.

BACKGROUNDA convolutional neural network (CNN) is a deep learning algorithm based on the principle of human brain visual cortex processing and image recognition.AIMTo automatically identify the invasion depth and origin of esophageal lesions based on a CNN.METHODSA total of 1670 white-light images were used to train and validate the CNN system. The method proposed in this paper included the following two parts: (1) Location module, an object detection network, locating the classified main image feature regions of the image for subsequent classification tasks; and (2) Classification module, a traditional classification CNN, classifying the images cut out by the object detection network.RESULTSThe CNN system proposed in this study achieved an overall accuracy of 82.49%, sensitivity of 80.23%, and specificity of 90.56%. In this study, after follow-up pathology, 726 patients were compared for endoscopic pathology. The misdiagnosis rate of endoscopic diagnosis in the lesion invasion range was approximately 9.5%; 41 patients showed no lesion invasion to the muscularis propria, but 36 of them pathologically showed invasion to the superficial muscularis propria. The patients with invasion of the tunica adventitia were all treated by surgery with an accuracy rate of 100%. For the examination of submucosal lesions, the accuracy of endoscopic ultrasonography (EUS) was approximately 99.3%. Results of this study showed that EUS had a high accuracy rate for the origin of submucosal lesions, whereas the misdiagnosis rate was slightly high in the evaluation of the invasion scope of lesions. Misdiagnosis could be due to different operating and diagnostic levels of endoscopists, unclear ultrasound probes, and unclear lesions.CONCLUSIONThis study is the first to recognize esophageal EUS images through deep learning, which can automatically identify the invasion depth and lesion origin of submucosal tumors and classify such tumors, thereby achieving good accuracy. In future studies, this method can provide guidance and help to clinical endoscopists.

Morphological and functional recovery following acute and acute recurrent pancreatitis in children: A prospective sequential 2-point evaluation

BackgroundThe functional and morphological recovery following an episode of acute pancreatitis (AP) in children still remains ill understood as research exploring this is limited. We aimed to characterize the morphological and functional changes in pancreas following AP and ARP (acute recurrent pancreatitis) in children. MethodsChildren with AP were followed prospectively and assessed at two time points at least 3 months apart, with the first assessment at least 3 months after the AP episode. Exocrine and endocrine functions were measured using fecal elastase and fasting blood sugar/HbA1c levels respectively. Morphological assessment was done using endoscopic ultrasound (EUS) and magnetic resonance imaging and cholangiopancreatography (MRI/MRCP). ResultsSeventy-three children (boys:59%; mean age:8.4 ± 3.2years) were studied and 21 of them (29%) progressed to ARP. Altered glucose homeostasis was seen in 19 (26%) at first and 16 (22%) at second assessment and it was significantly more in ARP group than the AP group at first (42.8%vs19.2%; p = 0.03) as well as second assessment (38.1%vs15.3%; p = 0.03). Twenty-one children (28.7%) at first and 24 (32.8%) at second assessment developed biochemical exocrine pancreatic insufficiency. EUS detected indeterminate and suggestive changes of chronic pancreatitis in 21% at first (n = 38) and 27.6% at second assessment (n = 58). On MRCP, main pancreatic duct and side branch dilatation were seen in 15 (20.5%) and 2 (2.7%) children respectively. ConclusionsMore than one-quarter of children have evidence of altered glucose homeostasis and biochemical exocrine pancreatic insufficiency following an episode of AP. Similarly, morphological features of chronicity seen in some of the children suggest that a fraction of subjects may develop chronic pancreatitis on longer follow-up.

High-Frequency Endoscopic Ultrasound Imaging With Phase-Corrected-and-Sum and Coherence Factor Weighting.

High-frequency endoscopic ultrasound (HFEUS) imaging is an important tool commonly used in clinical practice for imaging hollow organs. The virtual source synthetic aperture (VSSA) method is effective in improving the imaging quality of HFEUS. However, interference from the motor control unit severely affects the accuracy of the conventional delay and sum (DAS) method, thus compromising the effectiveness of VSSA. In this article, a new computational method based on phase correction was proposed to overcome these shortcomings, which is named phase-corrected-and-sum (PCAS). Meanwhile, the parameters of coherence factor weighting (CFW) can be obtained from the correlation coefficient of the superimposed signals to further increase the imaging quality. Three kinds of imaging experiments were designed to evaluate the proposed method. Compared with the conventional method, the results show that the PCAS-CFW method improves the lateral resolution by about 10% and the contrast-to-noise ratio (CNR) by about 44%. Therefore, this proposed method is capable of significantly improving HFEUS image quality, and this method can be easily integrated into current HFEUS imaging systems, showing great potential for clinical applications.

Gastric Adenocarcinoma of the Remnant Stomach Presenting With a Cystic Intra-abdominal Mass 11 Years After Roux-en-Y Gastric Bypass.

CASE REPORT Morbid obesity defined as a body mass index of ≥ 40 kg/m2 is associated with increased morbidity and all-cause mortality.1 Roux-en-Y gastric bypass (RYGB) is the desired surgical intervention because of its proven benefits.1,2 Morbid obesity is associated with increased risk of gastric cancer; however, the altered anatomy of the stomach after bypass is challenging for ongoing surveillance of the remnant stomach.2 To date, only 17 cases of gastric remnant malignancy after RYGB are reported.2 We present a rare case of gastric remnant adenocarcinoma 11 years after RYGB presenting with abdominal pain and weight loss due to a large intra-abdominal cystic mass abutting the gastric remnant. Abdominal computed tomography without contrast revealed a large cystic structure abutting the stomach and pancreas (Figure 1). An esophagogastroduodenoscopy was normal. An endoscopic ultrasound (EUS) revealed a single round anechoic lesion >100 mm in size in the peripancreatic and perigastric peritoneal space (Figure 2). Typical mucosal, submucosal, and muscular propria layers were noted within the wall of the cystic structure without communication to the excluded stomach (Figure 3). Fine-needle aspiration of fluid (Expect 19 Gauge Flex Needle [Boston Scientific, Marlborough, MA]) demonstrated 750 mL of brown fluid with unremarkable cytology and normal lipase and amylase levels. The carcinoembryonic antigen (CEA) level in the cystic fluid was markedly elevated at 2,358 ng/mL when compared with serum CEA of 76.6 ng/mL.Figure 1.: Axial images of the abdomen and pelvis show the cystic dilation.Figure 2.: The cystic structure seen before fine-needle aspiration (FNA) (thick arrow).Figure 3.: Endoscopic ultrasound (EUS) images revealing the wall layers of the cystic structure (thick arrow) is seen after cyst fluid fine-needle aspiration (FNA), which demonstrates that it is not a cyst but a gastrointestinal structure.A second EUS performed because of recurrent abdominal distension showed a persistent cystic structure. Injection of contrast within the cystic structure demonstrated communication between the cyst and the excluded stomach. Fine-needle biopsy (Acquire 25 Gauge Needle [Boston Scientific]) of an area of the thickened gastric wall demonstrated poorly differentiated adenocarcinoma (Figure 4).Figure 4.: The area of the excluded stomach (thick arrow) with abnormal thickening of the stomach wall was biopsied revealing adenocarcinoma.Diagnosis of gastric remnant malignancy is usually confirmed at a median of 9 years after RYGB (range is 1–22 years) with abdominal computed tomography scans.2 EUS and transgastric endoscopy may be considered as alternatives to double-balloon enteroscopy for tissue biopsy in the setting of technically difficult access of the gastric remnant.3,4 Prevention and surveillance methods including remnant gastrectomy proposed in regions with a high prevalence of gastric cancer remain controversial and not well established. More studies are needed to determine whether CEA can be considered for screening of the cancer in the excluded stomach in patients with a history of morbid obesity and RYGB.5 DISCLOSURES Author contributions: GW Khneizer and BL Bick conceived and drafted the work. N. Mahendraker designed and critically revised the work, and all authors gave final approval of the version to be published and agreed to be accountable for all aspects of the work. GW Khneizer is the article guarantor. Financial disclosure: None to report. Informed consent could not be obtained from the family of the deceased. All identifying information has been removed from this case report to protect patient privacy.

Voice-Assisted Image Labeling for Endoscopic Ultrasound Classification Using Neural Networks.

Ultrasound imaging is a commonly used technology for visualising patient anatomy in real-time during diagnostic and therapeutic procedures. High operator dependency and low reproducibility make ultrasound imaging and interpretation challenging with a steep learning curve. Automatic image classification using deep learning has the potential to overcome some of these challenges by supporting ultrasound training in novices, as well as aiding ultrasound image interpretation in patient with complex pathology for more experienced practitioners. However, the use of deep learning methods requires a large amount of data in order to provide accurate results. Labelling large ultrasound datasets is a challenging task because labels are retrospectively assigned to 2D images without the 3D spatial context available in vivo or that would be inferred while visually tracking structures between frames during the procedure. In this work, we propose a multi-modal convolutional neural network (CNN) architecture that labels endoscopic ultrasound (EUS) images from raw verbal comments provided by a clinician during the procedure. We use a CNN composed of two branches, one for voice data and another for image data, which are joined to predict image labels from the spoken names of anatomical landmarks. The network was trained using recorded verbal comments from expert operators. Our results show a prediction accuracy of 76% at image level on a dataset with 5 different labels. We conclude that the addition of spoken commentaries can increase the performance of ultrasound image classification, and eliminate the burden of manually labelling large EUS datasets necessary for deep learning applications.

Endoscopic ultrasound as a reliable tool for assessment of pancreatic adenocarcinoma treatment: Example of in situ gene therapy.

Background and study aims In pancreatic cancer, the antitumor effect can only be assessed by means of a computed tomography (CT) scan using RECIST (Response Evaluation Criteria in Solid Tumours) criteria. The aim of this study was to assess the intra-observer and interobserver agreement of endoscopic ultrasound (EUS) imaging in assessing tumor volume in primary pancreatic cancer. Patients and methods During a Phase 1 gene therapy trial, 21 patients had EUS before the first and second EUS-guided in situ gene therapy injections. All anonymized EUS files were then randomly distributed to three gastroenterologists/endosonographers and three radiologists (blind status). The largest tumor diameter was measured and the intraclass correlation coefficient (ICC) was determined. Results Intra-observer and interobserver agreements were good to excellent, regardless of operator experience (junior versus senior member of staff) (ICC: 0.65 to 0.84). A comparison of pretreatment and post-treatment measurements by the investigators highlighted a significant antitumor effect (–11 %; P = 0.0098), similar to that obtained during the generic protocol (–10 %; P = 0.0045). Conclusions Interobserver agreement regarding primary pancreatic adenocarcinoma measurements appears good to excellent, thus paving the way for the future inclusion of EUS assessments, particularly in trials assessing local therapies for pancreatic tumors.

Why is endosonography insufficient for residual diagnosis after neoadjuvant therapy for esophageal cancer? Solutions using muscle layer evaluation.

BACKGROUNDThe diagnosis of residual tumors using endoscopic ultrasound (EUS) after neoadjuvant therapy for esophageal cancer is considered challenging. However, the reasons for this difficulty are not well understood.AIMTo investigate the ultrasound imaging features of residual tumors and identify the limitations and potential of EUS.METHODSThis exploratory prospective observational study enrolled 23 esophageal squamous cell carcinoma patients receiving esophagectomy after neoadjuvant therapy [15 patients after neoadjuvant chemotherapy (NAC) and 8 patients after chemoradiotherapy (CRT)] at the Department of Surgery, Chiba University Hospital, between May 2020 and October 2021. We diagnosed the T stage for specimens using ultrasound just after surgery and compared ultrasound images with the cut surface of the fixed specimens of the same level of residual tumor. The ratio of esophageal muscle layer defect measured by ultrasound was compared with clinicopathological factors. Furthermore, the rate of reduction for the muscle layer defect was evaluated using EUS images obtained before and after neoadjuvant therapy.RESULTSThe accuracy of T stage rate was 61% (n = 14/23), which worsened after CRT (38%, n = 3/8) than after NAC (73%, n = 11/15) because of overstaging. Moreover, pT0 could not be diagnosed in all cases. The detection rate of residual tumor for specimens using ultrasound retrospectively was 75% (n = 15/20). There was no correlation between after-NAC (79%, n = 11/14) and after-CRT (67%, n = 4/6) detection rate. The detection of superficial and submucosal types was poor. The pathologic tumor size and pathological response were correlated. Tumor borders were irregular and echogenicity was mixed type after CRT. There was a correlation between the pT stage (pT0/1 vs pT2/3) and the length of muscle layer circumference (P = 0.025), the length of muscle layer defect (P < 0.001), and the ratio of muscle layer defect (P < 0.001). There was also a correlation between the pT stage and the rate of muscle layer defect reduction measured by EUS (P = 0.001).CONCLUSIONCompared to pathological images, some tumors are undetectable by ultrasound. Focusing on the esophageal muscle layer might help diagnose the depth of the residual tumor.

Establishing a rabbit model of perianal fistulizing Crohn’s disease

BACKGROUNDCrohn's disease (CD) is a chronic nonspecific intestinal inflammatory disease. The aetiology and pathogenesis of CD are still unclear. Anal fistula is the main complication of CD and is a difficult problem to solve at present. The main limitation of developing new therapies is bound up with the short of preclinical security and effectiveness data. Therefore, an ideal animal model is needed to establish persistent anal fistula and an inflamed rectal mucosa.AIMTo improve the induction method of colitis and establish a reliable and reproducible perianal fistulizing Crohn’s disease animal model to evaluate new treatment strategies.METHODSTwenty male New Zealand rabbits underwent rectal enema with different doses of 2,4,6-trinitrobenzene sulfonic acid to induce proctitis. Group A was treated with an improved equal interval small dose increasing method. The dosage of group B was constant. Seven days later, the rabbits underwent surgical creation of a transsphincteric fistula. Then, three rabbits were randomly selected from each group every 7 d to remove the seton from the fistula. The rabbits were examined by endoscopy every 7 days, and biopsy forceps were used to obtain tissue samples from the obvious colon lesions for histological analysis. The disease activity index (DAI), colonoscopy and histological scores were recorded. Perianal endoscopic ultrasonography (EUS) was used to evaluate the healing of fistulas.RESULTSExcept for the DAI score, the colonoscopy and histological scores in group A were significantly higher than those in group B (P < 0.05). In the ideal model rabbit group, on the 7th day after the removal of the seton, all animals had persistent lumens on EUS imaging, showing continuous full-thickness high signals. Histological inspection of the fistula showed acute and chronic inflammation, fibrosis, epithelialization and peripheral proctitis of the adjoining rectum.CONCLUSIONThe improved method of CD colitis induction successfully established a rabbit perianal fistula CD preclinical model, which was confirmed by endoscopy and pathology.

Predicting Factors for Pancreatic Malignancy with Computed Tomography and Endoscopic Ultrasonography in Chronic Pancreatitis.

Diagnosing pancreatic malignancy is challenging, especially in patients with chronic pancreatitis (CP). Endoscopic ultrasonography (EUS) is a promising diagnostic procedure for discriminating between malignancy and CP. We aimed to investigate the predictive factors and reliability of computed tomography (CT) and EUS for differentiating pancreatic mass lesions and the diagnostic accuracy of EUS-FNA or FNB in patients with CP. Forty patients with CP, receiving CT and EUS-FNA or FNB for pancreatic mass lesion evaluation, were enrolled in the study. Patients’ data, CT and EUS characteristics, image-based diagnosis, cytopathology, and final diagnosis were recorded. EUS was superior to CT in terms of diagnostic accuracy (92.5% vs. 82.5%, p = 0.02). Both CT and EUS showed significant predictive factors (all p < 0.05) with the tumor image hypoattenuation pattern or vessel invasion on CT and pancreatic duct dilatation, or distal pancreatic atrophy on EUS. EUS imaging is a reliable modality for evaluating pancreatic lesions, even with a CP background. The EUS image has a higher diagnostic accuracy than CT. Predicting factors, including hypoechoic pattern, pancreatic duct dilatation, and distal pancreas atrophy, may help to differentiate benign or malignant in patients with CP.

Study protocol for a multi-institutional prospective surveillance study among kindreds with familial pancreatic cancer and individuals with hereditary pancreatic cancer syndrome: The Diamond Study

BackgroundFamily history of pancreatic cancer (PC) and some hereditary cancer syndromes are risk factors for PC. Previous studies suggest that conducting surveillance for kindreds at high risk for familial PC may be useful for diagnoses at the stage where resections can still be implemented; however, there is insufficient evidence linking surveillance and increased rates of resectable PC. MethodsWe launched a surveillance study for kindreds with familial PC and individuals with hereditary PC syndrome, titled the “Diamond Study,” in June 2020. This Japanese national multi-institutional prospective intervention study has been initiated to conduct evaluations within a prospective clinical trial format. ResultsThe primary endpoint is the fraction of patients with resectable PC among patients with PC found through surveillance interventions. Endoscopic ultrasound and magnetic resonance imaging combined with magnetic resonance cholangiopancreatography will be performed alternatively every 6 months for up to 15 years, with 400 as the predicted number of registered participants and a predicted registration period of 10 years. ConclusionWe intend to scientifically prove the usefulness of surveillance for kindreds with familial PC and individuals with hereditary PC syndrome to improve PC prognoses.

Factors associated with misdiagnosis of preoperative endoscopic ultrasound in patients with pancreatic cystic neoplasms undergoing surgical resection.

Pancreatic cystic lesions (PCLs) include various types of cysts. Accurate preoperative diagnosis is essential to avoid unnecessary surgery on benign cysts. In this study, we aimed to identify the factors associated with misdiagnosis in preoperative endoscopic ultrasound (EUS) imaging and clinicopathological findings for PCLs. This study included 302 surgically resected patients with PCLs who underwent preoperative EUS. The preoperative EUS findings were re-evaluated and compared with the pathological diagnosis. Additionally, the factors associated with misdiagnosis of PCLs were investigated by multivariate analysis. The preoperative diagnoses of PCLs were intraductal papillary mucinous neoplasm (IPMN) in 213 patients (70.5%), mucinous cystic neoplasm (MCN) in 33 patients (10.9%), serous neoplasm (SN) in 7 patients (2.3%), cystic degeneration cyst of solid tumor in 46 patients (15.2%), and pancreatic cancer with cystic degeneration in three patients (1.0%). A discrepancy between preoperative and postoperative diagnosis was found in 47 patients (15.6%). Based on the pathological diagnosis, the sensitivity of preoperative EUS imaging was IPMN 97.6% (206/211), MCN 90.0% (18/19), cystic degeneration 87.1% (27/31), and SN 15.4% (2/13). Multivariate analysis revealed that main pancreatic duct (MPD) communication (-) (odds ratio (OR), 4.54; 95% confidence interval (CI) 1.29-15.9), honeycomb-like structure ( +) (OR, 14.7; 95% CI 2.61-83.3), and MPD size≦2mm (OR, 16.3; 95% CI 3.93-67.6) were independently associated with misdiagnosis. For cases in which MCN and cystic degeneration of solid tumor are presumed based on preoperative EUS imaging and cases with PCLs with a honeycomb-like structure, diagnosis with multimodalities or fluid analysis with EUS-guided fine-needle aspiration should be considered.

A computed tomography—negative pancreatic lesion diagnosed by endoscopic ultrasound imaging enhancement (with video)

A 50-year-old woman was admitted for slightly elevated serum carbohydrate antigen 19-9 (39 U/mL) and negative findings from 2 rounds of computed tomography (CT) scanning at a 6-month interval (A). The patient underwent EUS examination. In the initial scanning, the pancreatic parenchyma was normal, without ductal dilatation. To avoid missing a potential isoechoic lesion, we next performed imaging enhancement by adjusting the acoustic parameters in the US (HI VISION Preirus, Hitachi, Tokyo, Japan).

A novel solution of deep learning for endoscopic ultrasound image segmentation: enhanced computer aided diagnosis of gastrointestinal stromal tumor

Gastrointestinal stromal tumor is one of the critical tumors that doctors do not suggest to get frequent endoscopy, so there is a need for a diagnosis system which can process ultrasound images and figure out the tumor. Many gastrointestinal tumor diagnosis methods were developed, but all of these methods used manual contour rather than automatic segmentation. The research adopts enhanced automatic segmentation to improve the diagnosis of the gastrointestinal stromal tumor with deep convolutional neural networks. This solution’s proposed system is an enhanced automated segmentation methodology using multi-scale Gaussian kernel fuzzy clustering and multi-scale vector field convolution, which segments the ultrasound image automatically into the region of interest (the infected area). Convolutional Neural Network with Class Activation Mapping is done to diagnose an image with the tumor for Four datasets, namely (USS1, SH Hospital, SNUH, BUSI). This proposed system helps to get a clearer tumor image, and the accuracy has increased from 84.275% to 88.4%, and the processing time has reduced from 28.525% to 24.575%. The proposed solution enhanced Automatic Segmentation helped to get clearer tumor image which resulted in increased accuracy and decreased performance time compared to the state-of-the-art. Automatic segmentation overcomes the dependency on the expert for drawing the Region of Interest (ROI).

Prospective Study Assessing Impact of Ethylene Oxide Sterilization on Endoscopic Ultrasound Image Quality

Duodenoscope-associated transmission of infections has raised questions about efficacy of endoscope reprocessing using high-level disinfection (HLD). Although ethylene oxide (ETO) gas sterilization is effective in eradicating microbes, the impact of ETO on endoscopic ultrasound (EUS) imaging equipment remains unknown. In this study, we aimed to compare the changes in EUS image quality associated with HLD vs HLD followed by ETO sterilization. Four new EUS instruments were assigned to 2 groups: Group 1 (HLD) and Group 2 (HLD+ ETO). The echoendoscopes were assessed at baseline, monthly for 6 months, and once every 3 to 4 months thereafter, for a total of 12 time points. At each time point, review of EUS video and still image quality was performed by an expert panel of reviewers along with phantom-based objective testing. Linear mixed effects models were used to assess whether the modality of reprocessing impacted image and video quality. For clinical testing, mixed linear models showed minimal quantitative differences in linear analog score (P= .04; estimated change, 3.12; scale, 0-100) and overall image quality value (P= .007; estimated change,-0.12; scale, 1-5) favoring ETO but not for rank value (P= .06). On phantom testing, maximum depth of penetration was lower for ETO endoscopes (P < .001; change in depth, 0.49 cm). In this prospective study, expert review and phantom-based testing demonstrated minimal differences in image quality between echoendoscopes reprocessed using HLD vs ETO+ HLD over 2 years of clinical use. Further studies are warranted to assess the long-term clinical impact of these findings. In the interim, these results support use of ETO sterilization of EUS instruments if deemed clinically necessary.

Gastrointestinal: Endoscopic ultrasound of rectal subepithelial lesion mimicking gastrointestinal stromal tumor.

A 60-year-old man presented with anorexia, weight loss, and constipation for 3 months. On peri-rectal examination, a bulge was palpated in the rectum. He underwent colonoscopy, which showed large subepithelial lesion (SEL) starting from anorectal junction extending proximally till rectosigmoid junction obliterating the lumen without complete obstruction (Fig. 1a). Contrast-enhanced computed tomography of the pelvis showed a large lobulated heterogeneous enhancing soft tissue lesion within the rectum (Fig. 1b). Endoscopic ultrasound (EUS) was performed, which showed a large well defined lobulated hetero-echoic lesion (70 × 63 mm) with multiple cystic spaces in peri-rectal area (Fig. 1c). Possibility of rectal malignant gastrointestinal stromal tumor (GIST) was considered looking at CT and EUS image. To confirm our diagnosis, EUS-guided fine needle aspiration (FNA) was performed. During FNA, dark brownish fluid was aspirated (Fig. 2a). Possibility of bleed within tumor was considered because of dark brownish fluid aspiration; however, black pigments were noticed on slide preparation (Fig. 2b). Histopathological examination showed pleomorphic cells with abundant brownish pigment with multinucleation suggestive of malignant melanoma (Fig. 2c). Patient was advised for surgery and referred to the surgeons. Malignant melanoma is an extremely rare and aggressive tumor of the rectum. It accounts for 0.5–4% of all anorectal malignancies and < 1% of all melanomas. It is most common site of primary gastrointestinal melanoma followed by stomach, small intestine, and colon. Patients usually present in the fifth or sixth decade, and it is more common in female patients. Anorectal melanomas usually appear as ulcerated polypoidal lesions rather than SEL. EUS is an important diagnostic tool in diagnosis and differentiation of SEL. There is lack of characterization of anorectal melanoma on EUS because of rarity of tumor. Yonal et al. described the EUS morphological features of esophageal melanoma as iso to hypoechoic solid tumor mass with variable areas of internal hyper-echogenicity and anechoic cystic spaces, similar to the findings from our case. Morphological features of some SELs are confusing; therefore, EUS FNA plays an important role in differentiation of SELs. Therapy in anorectal melanomas is dictated by the local staging of disease and also the presence of lymph node and distant metastases. Multidisciplinary approach is required depending on the stage of tumor. Surgery has been the mainstay of treatment for anorectal melanoma. Although these tumors are usually radio-resistant and chemo-resistant, combination of chemotherapy and immunotherapy remains a therapeutic option for advanced metastatic disease. Overall, 5-year survival is only 3–22%, and survival in recurrent or metastatic disease is less than 10 months. Although a rare entity, anorectal melanoma can mimic GIST and may be a differential during the evaluation of rectal SEL. Early diagnosis of tumor is of paramount importance for favorable prognosis.

Isolated IgG4-related cholecystitis with localized gallbladder wall thickening mimicking gallbladder cancer: a case report and literature review

BackgroundIgG4-related cholecystitis, which is a manifestation of IgG4-related disease in the gallbladder, is associated with autoimmune pancreatitis or IgG4-related sclerosing cholangitis in most cases; isolated gallbladder lesions without systemic manifestations are very rare. Gallbladder wall thickening is often diffuse, but sometimes localized, in which case, differentiation from gallbladder cancer becomes difficult. The characteristic features of IgG4-related cholecystitis on imaging that would enable differentiation from gallbladder cancer remain poorly described.Case presentationWe present a rare case of isolated IgG4-related cholecystitis with localized gallbladder wall thickening that was clinically difficult to distinguish from malignancy before resection. An 82-year-old man was referred to our hospital because of gallbladder wall thickening on abdominal ultrasonography without any symptoms. Dynamic computed tomography of the abdomen showed localized wall thickening from the body to the fundus of the gallbladder that was enhanced from an early stage with a prolonged contrast effect. There were no other findings, such as pancreatic enlargement and bile duct dilatation. Magnetic resonance cholangiopancreatography revealed neither dilatation nor stenosis of the bile duct and pancreatic duct. Endoscopic ultrasonography (EUS) showed a smooth layered thickening of the gallbladder wall with a maximum thickness of 6 mm and a well-preserved outermost hyperechoic layer in the same area. Laparoscopic cholecystectomy was performed because malignancy could not be completely ruled out. Pathological examination of a resected specimen revealed IgG4-positive plasma cell infiltration, fibrosis, and phlebitis. Although the serum IgG4 level measured after resection was normal, the condition was ultimately diagnosed as probable IgG4-related cholecystitis according to the 2020 revised comprehensive diagnostic criteria for IgG4-related disease. The EUS images reflected the pathological findings, in which lymphocytic infiltration was distributed in a laminar fashion in the gallbladder wall.ConclusionsAlthough rare, isolated IgG4-related cholecystitis with localized wall thickening mimicking gallbladder cancer remains a clinical problem. A smooth laminar thickening of the gallbladder wall on EUS imaging could be one of the most informative characteristics for differentiating IgG4-related cholecystitis from gallbladder cancer.

Sphincter of Oddi dysfunction.

Sphincter of Oddi dysfunction (SOD) is a benign non-tumoral disorder of the major papilla. It occurs mainly after cholecystectomy but can also occur before surgery. Biliary pain and biliary colic are the most frequent symptoms although recurrent pancreatic pain or pancreatitis can also be presenting symptoms. In about half of the cases, there is a fibrotic stricture of the sphincter of Oddi, probably secondary to the passage of biliary stones, while in the remaining half, the syndrome is due to ampullary motility disorders. The diagnosis of SOD first requires exclusion of choledocholithiasis or ampullary tumor, by means of ERCP, endoscopic ultrasound or magnetic resonance imaging. Findings on biliary manometry will establish the diagnosis, but this technique is performed less and less often because its high risk of inducing pancreatitis discourages its use as a diagnostic procedure. Biliary scintigraphy offers a risk-free alternative albeit with lower sensitivity. Medical treatment relies on the administration of trimebutine and nitroglycerine when pain occurs. Their efficacy is moderate. Sometimes patients are referred for endoscopic sphincterotomy. Endoscopic treatment should be performed only for patients with biliary pain associated with hepatic function disorders and/or bile duct dilatation. Practicians and patients should be aware that endoscopic sphincterotomy in this clinical setting is associated with a high risk of pancreatitis and its efficacy is limited in patients with pain but without laboratory anomalies or dilatation of the biliary duct (type III Milwaukee classification). Patients with Milwaukee classification type III disorders have mostly functional complaints or psychosocial disabilities and require only medical management.