Automated gall bladder cancer detection using artificial gorilla troops optimizer with transfer learning on ultrasound images.

The gallbladder (GB) is a small pouch and a deep tissue placed under the liver. GB Cancer (GBC) is a deadly illness that is complex to discover in an initial phase. Initial diagnosis can significantly enhance the existence rate. Non-ionizing energy, low cost, and convenience make the US a general non-invasive analytical modality for patients with GB diseases. Automatic recognition of GBC from US imagery is a significant issue that has gained much attention from researchers. Recently, machine learning (ML) techniques dependent on convolutional neural network (CNN) architectures have prepared transformational growth in radiology and medical analysis for illnesses like lung, pancreatic, breast, and melanoma. Deep learning (DL) is a region of artificial intelligence (AI), a functional medical tomography model that can help in the initial analysis of GBC. This manuscript presents an Automated Gall Bladder Cancer Detection using an Artificial Gorilla Troops Optimizer with Transfer Learning (GBCD-AGTOTL) technique on Ultrasound Images. The GBCD-AGTOTL technique examines the US images for the presence of gall bladder cancer using the DL model. In the initial stage, the GBCD-AGTOTL technique preprocesses the US images using a median filtering (MF) approach. The GBCD-AGTOTL technique applies the Inception module for feature extraction, which learns the complex and intrinsic patterns in the pre-processed image. Besides, the AGTO algorithm-based hyperparameter tuning procedure takes place, which optimally picks the hyperparameter values of the Inception technique. Lastly, the bidirectional gated recurrent unit (BiGRU) model helps classify gall bladder cancer. A series of simulation analyses were performed to ensure the performance of the GBCD-AGTOTL technique on the GBC dataset. The experimental outcomes inferred the enhanced abilities of the GBCD-AGTOTL in detecting gall bladder cancer.

Comparison of the Size Measurement of Gallbladder Polyps by Three Different Radiologists in Abdominal Ultrasonography.

BACKGROUND: There is little information regarding the size measurement differences in gallbladder (GB) polyps performed by different radiologists on abdominal ultrasonography (US). AIM: To reveal the differences in GB polyp size measurements performed by different radiologists on abdominal US. METHODS: From June to September 2022, the maximum diameter of 228 GB polyps was measured twice on abdominal US by one of three radiologists (a third-year radiology resident [reader A], a radiologist with 7 years of experience in abdominal US [reader B], and an abdominal radiologist with 8 years of experience in abdominal US [reader C]). Intra-reader agreements for polyp size measurements were assessed by intraclass correlation coefficient (ICC). A Bland-Altman plot was used to visualize the differences between the first and second size measurements in each reader. RESULTS: Reader A, reader B, and reader C evaluated 65, 77, and 86 polyps, respectively. The mean size of measured 228 GB polyps was 5.0 ± 1.9 mm. Except for the case where reader A showed moderate intra-reader agreement (0.726) for polyps with size ≤ 5 mm, all readers showed an overall high intra-reader reliability (reader A, ICC = 0.859; reader B, ICC = 0.947, reader C, ICC = 0.948), indicative of good and excellent intra-reader agreements. The 95% limit of agreement of reader A, B, and C was 1.9 mm of the mean in all three readers. CONCLUSIONS: GB polyp size measurement on abdominal US showed good or excellent intra-reader agreements. However, size changes of approximately less than 1.9 mm should be interpreted carefully because these may be within the measurement error.

Transabdominal ultrasound evaluation of vascularity of gallbladder lesions: particularly those with wall thickening.

Gallbladder wall thickening is relatively common in clinical settings, and for appropriate diagnosis, the size, shape, internal structure, surface contour, and vascularity of the gallbladder wall must be evaluated. Morphological evaluation is the most important; however, some gallbladder lesions resemble gallbladder cancer in imaging studies, making differential diagnosis challenging. Vascular evaluation is indispensable for a precise diagnosis in these cases. In this review, we present the current status of vascular evaluation using US and diagnosis using vascular imaging for gallbladder lesions, including those presenting with wall thickening. To date, several ultrasound imaging techniques have been developed to assess vascularity, including Doppler imaging with high sensitivity, use of contrast agents, and microvascular imaging using a novel filter for Doppler imaging. Although conventional color Doppler imaging is rarely used for the diagnosis of gallbladder lesions, the efficacy of contrast-enhanced ultrasound in assessing the vascularity, enhancement pattern, or timing of enhancement/washout has been reported. Presence of multiple irregular microvessels has been speculated to indicate malignancy. However, few reports on microvessels have been published, and further studies are required for the precise diagnosis of gallbladder lesions with microvascular evaluation.

[Gallbladder carcinosarcoma associated with pancreaticobiliary maljunction with biliary dilation:a case report].

A 68-year-old female patient was referred to our hospital with acute cholangitis. Computed tomography revealed common bile duct dilatation, gallbladder fundal tumor, and gallbladder wall thickening attached to the tumor. Cholangiography revealed pancreaticobiliary maljunction with biliary dilation. The patient was diagnosed with pancreaticobiliary maljunction with biliary dilation and gallbladder cancer and underwent liver S4b+5 and bile duct resection and reconstruction. Pathological results revealed that the gallbladder fundal tumor included sarcoma, and the gallbladder wall thickening had adenocarcinoma;thus, the patient was diagnosed with gallbladder carcinosarcoma.

Laparoscopic Indocyanine Green-Guided Sentinel Lymph Node Biopsy for Gallbladder Neoplasms.

BACKGROUND: Surgical resection, the only potentially curative treatment for gallbladder cancer (GBC), entails an extended cholecystectomy with portal lymphadenectomy. Lymph node dissection is a key staging procedure, but its therapeutic value is unclear. Additionally, it is technically challenging and potentially harmful. Methods for better assessment of lymph node status are needed. This report presents a case of indocyanine green (ICG)-guided sentinel lymph node biopsy (SNLB) for a patient with a gallbladder mass suspicious for GBC. METHODS: An 81-year-old woman consulted for abdominal discomfort. Abdominal ultrasound showed an intraluminal gallbladder mass suspicious for GBC. Staging imaging did not show liver invasion, lymphadenopathy, or distant metastasis. Given the woman's advanced age and limited extent of disease, a laparoscopic extended cholecystectomy with an ICG-guided SLNB was performed. Injection of 1 ml of ICG (0.125 mg/mL) into the gallbladder bed was performed using a 22-gauge needle, avoiding direct injection into the gallbladder wall. RESULTS: A near-infrared camera was used to visualize real-time ICG flow through the lymphatic vessels of the gallbladder toward the cystic node. Then, a sentinel lymph node posterolateral to the bile duct (station 12b) was identified. The node was resected and sent for permanent section. The procedure continued with an extended cholecystectomy. Pathology showed an intracholecystic papillary neoplasm with high-grade dysplasia. Cystic and sentinel lymph nodes were negative for malignancy. CONCLUSION: For patients with gallbladder neoplasms, ICG-guided SLNB is a feasible technique that could allow for treatment de-escalation. Further evaluation in clinical trials is needed.

Primary pure squamous cell carcinoma of the gallbladder.

SummarySquamous cell carcinoma (SCC) is an uncommon and frequently aggressive subtype of gallbladder cancer known for its poor outcomes compared with other gallbladder tumours. Gallbladder SCC typically presents as higher grade and more advanced than adenocarcinoma, resulting in lower estimated survival. Early recognition of these tumours is ideal, but infrequently achieved. Herein is a case of a male patient in his 80s with new onset abdominal pain who was initially diagnosed with cholecystitis, but diagnostic imaging revealed a gallbladder mass. Surgical resection and pathology revealed pure SCC of the gallbladder without local organ invasion or metastatic disease. Pure SCC histology of the gallbladder is rare, with limited studies on clinical presentation, natural history, and optimal treatment.

Contributions of endoscopic ultrasonography-guided tissue acquisition (EUS-TA) to the diagnostics of biliary stricture and gallbladder lesions.

Endoscopic ultrasonography (EUS) provides high spatial resolution and more detailed images than other diagnostic modalities. Furthermore, EUS-guided tissue acquisition (EUS-TA), such as EUS-guided fine needle aspiration or biopsy (EUS-FNA/FNB), is an indispensable tool in pancreaticobiliary disease diagnostics, supporting a conclusive pathological diagnosis. In this review, we evaluate the current status and the usefulness of EUS-TA for the diagnostics of the following biliary tract diseases: (A) biliary stricture diagnostics, (B) biliary tract cancer (BTC) itself, and (C) staging of advanced BTC. Previous reports have shown that EUS-FNA for biliary lesions is a safe procedure that is useful in differentiating biliary cancer from benign lesions and in the staging of BTC. On the other hand, the diagnostic performance of EUS-TA for bile duct lesions is reported to be similar to that of transpapillary biopsy. Overall, EUS-TA for biliary lesions may be a safe and effective method, but it should be performed with an understanding of the risk of serious adverse events such as bile leakage and peritoneal dissemination of cancer. It is recommended for distal biliary stricture lesions for which endoscopic retrograde cholangiopancreatography cannot confirm the diagnosis or gallbladder lesions if they do not require the needle to pass through the biliary lumen.

Should we suspect gallbladder cancer if which CT finding is observed in patients with localized gallbladder wall thickening?

PURPOSE: To identify high-risk computed tomography (CT) features for predicting gallbladder (GB) cancer in patients presenting with localized GB wall thickening. METHODS: This retrospective analysis included 120 patients (mean age: 63.9 ± 10.0 years; 51 men) exhibiting localized GB wall thickening on CT scans obtained between January 2008 and May 2017. Two radiologists independently evaluated CT imaging features for predicting GB cancer. The diagnostic performance of significant imaging features and their combinations was evaluated. High-risk CT features ranked by accuracy were delineated for predicting GB cancer. RESULTS: This study included 55 patients with GB cancer and 65 with benign GB conditions. The top-four most accurate CT imaging features for predicting GB cancer were identified: heterogeneously enhancing single layer or strongly enhancing thick inner layer; GB wall thickness > 6.5 mm; hyperenhancement on arterial phase; and absence of intramural small cystic lesions (accuracies of 90.0 %, 88.3 %, 85.0 %, and 85.0 %, respectively). The combination of any three high-risk features exhibited the highest accuracy (94.2 %). The presence of any high-risk feature yielded a sensitivity of 100 %, whereas that of all high-risk features indicated a specificity of 100 %. CONCLUSION: CT imaging features, whether alone or in combination, could effectively and accurately predict GB cancer among patients with localized GB wall thickening. This finding holds significance in guiding decisions regarding further diagnostic tests and treatment planning.

Discrimination between benign and malignant gallbladder lesions on enhanced CT imaging using radiomics.

BACKGROUND: Gallbladder cancer is a rare but aggressive malignancy that is often diagnosed at an advanced stage and is associated with poor outcomes. PURPOSE: To develop a radiomics model to discriminate between benign and malignant gallbladder lesions using enhanced computed tomography (CT) imaging. MATERIAL AND METHODS: All patients had a preoperative contrast-enhanced CT scan, which was independently analyzed by two radiologists. Regions of interest were manually delineated on portal venous phase images, and radiomics features were extracted. Feature selection was performed using mRMR and LASSO methods. The patients were randomly divided into training and test groups at a ratio of 7:3. Clinical and radiomics parameters were identified in the training group, three models were constructed, and the models' prediction accuracy and ability were evaluated using AUC and calibration curves. RESULTS: In the training group, the AUCs of the clinical model and radiomics model were 0.914 and 0.968, and that of the nomogram model was 0.980, respectively. There were statistically significant differences in diagnostic accuracy between nomograms and radiomics features (P <0.05). There was no significant difference in diagnostic accuracy between the nomograms and clinical features (P >0.05) or between the clinical features and radiomics features (P >0.05). In the testing group, the AUC of the clinical model and radiomics model were 0.904 and 0.941, and that of the nomogram model was 0.948, respectively. There was no significant difference in diagnostic accuracy between the three groups (P >0.05). CONCLUSION: It was suggested that radiomics analysis using enhanced CT imaging can effectively discriminate between benign and malignant gallbladder lesions.

SMARCA4-Deficient Poorly Differentiated Adenocarcinoma of the Gallbladder.

ABSTRACT: A 64-year-old woman presented with chest pain while eating and was referred to our hospital. Physical examination revealed abdominal distension, tenderness, and lower-extremity edema. Imaging revealed a large gallbladder tumor infiltrating the liver, with ascites and pleural effusion. A biopsy confirmed a poorly differentiated adenocarcinoma with SMARCA4 deficiency (cT3N2M1, cStage IV). Chemotherapy was ineffective and led to tumor progression. The patient died 9 months later. Recently, attention has been paid to SMARCA4 deficiency, which is a genetic mutation found in tumors. Here, we report on poorly differentiated adenocarcinomas of the gallbladder based on imaging findings, including FDG PET.

The value of CT radiomics combined with deep transfer learning in predicting the nature of gallbladder polypoid lesions.

BACKGROUND: Computed tomography (CT) radiomics combined with deep transfer learning was used to identify cholesterol and adenomatous gallbladder polyps that have not been well evaluated before surgery. PURPOSE: To investigate the potential of various machine learning models, incorporating radiomics and deep transfer learning, in predicting the nature of cholesterol and adenomatous gallbladder polyps. MATERIAL AND METHODS: A retrospective analysis was conducted on clinical and imaging data from 100 patients with cholesterol or adenomatous polyps confirmed by surgery and pathology at our hospital between September 2015 and February 2023. Preoperative contrast-enhanced CT radiomics combined with deep learning features were utilized, and t-tests and least absolute shrinkage and selection operator (LASSO) cross-validation were employed for feature selection. Subsequently, 11 machine learning algorithms were utilized to construct prediction models, and the area under the ROC curve (AUC), accuracy, and F1 measure were used to assess model performance, which was validated in a validation group. RESULTS: The Logistic algorithm demonstrated the most effective prediction in identifying polyp properties based on 10 radiomics combined with deep learning features, achieving the highest AUC (0.85 in the validation group, 95% confidence interval = 0.68-1.0). In addition, the accuracy (0.83 in the validation group) and F1 measure (0.76 in the validation group) also indicated strong performance. CONCLUSION: The machine learning radiomics combined with deep learning model based on enhanced CT proves valuable in predicting the characteristics of cholesterol and adenomatous gallbladder polyps. This approach provides a more reliable basis for preoperative diagnosis and treatment of these conditions.

Prediction of neoplastic gallbladder polyps in patients with different age level based on preoperative ultrasound: a multi-center retrospective real-world study.

BACKGROUND: The prevalence of neoplastic polyps in gallbladder polyps (GPs) increases sharply with age and is associated with gallbladder carcinoma (GBC). This study aims to predict neoplastic polyps and provide appropriate treatment strategies based on preoperative ultrasound features in patients with different age level. METHODS: According to the age classification of WHO, 1523 patients with GPs who underwent cholecystectomy from January 2015 to December 2019 at 11 tertiary hospitals in China were divided into young adults group (n=622), middle-aged group (n=665) and elderly group (n=236). Linear scoring models were established based on independent risk variables screened by the Logistic regression model in different age groups. The area under ROC (AUC) to evaluate the predictive ability of linear scoring models, long- and short- diameter of GPs. RESULTS: Independent risk factors for neoplastic polyps included the number of polyps, polyp size (long diameter), and fundus in the young adults and elderly groups, while the number of polyps, polyp size (long diameter), and polyp size (short diameter) in the middle-aged groups. In different age groups, the AUCs of its linear scoring model were higher than the AUCs of the long- and short- diameter of GPs for differentiating neoplastic and non-neoplastic polyps (all P<0.05), and Hosmer-Lemeshow goodness of fit test showed that the prediction accuracy of the linear scoring models was higher than the long- and short- diameter of GPs (all P>0.05). CONCLUSION: The linear scoring models of the young adults, middle-aged and elderly groups can effectively distinguish neoplastic polyps from non-neoplastic polyps based on preoperative ultrasound features.

Nonocclusive mesenteric ischemia (NOMI) on Roux limb after biliary reconstruction successfully treated by interventional radiology (IVR).

Nonocclusive mesenteric ischemia (NOMI) is a life-threatening disorder. Early diagnosis is challenging because NOMI lacks specific symptoms. A 52-year-old man who received extended cholecystectomy with Roux-en-Y hepaticojejunostomy for gallbladder cancer (GBC) presented to our hospital with nausea and vomiting. Neither tender nor peritoneal irritation sign was present on abdominal examination. Blood test exhibited marked leukocytosis (WBC:19,800/mm3). A contrast-enhanced abdominal computed tomography (CT) scan revealed remarkable wall thickening and lower contrast enhancement effect localized to Roux limb. On hospital day 2, abdominal arterial angiography revealed angio-spasm at marginal artery and arterial recta between 2nd jejunal artery and 3rd jejunal artery, leading us to the diagnosis of NOMI. We then administered continuous catheter-directed infusion of papaverine hydrochloride until hospital day 7. Furthermore, the patient was anticoagulated with intravenous unfractionated heparin and antithrombin agents for increasing D-dimer level and decreasing antithrombin III level. On hospital day 8, diluted oral nutrition diet was initiated and gradually advanced as tolerated. On hospital day 21, the patient was confirmed of improved laboratory test data and discharged with eating a regular diet. We experienced a rare case of NOMI on Roux limb after 2 years of extended cholecystectomy with hepaticojejunostomy for GBC, promptly diagnosed and successfully treated by interventional radiology (IVR).

Diagnostic performance of EUS-guided elastography for differential diagnosis of gallbladder polyp.

BACKGROUND AND AIMS: It is difficult to differentiate between neoplastic and non-neoplastic gallbladder (GB) polyps before surgery. EUS-guided elastography (EUS-EG) is a noninvasive complementary diagnostic method. The utility of EUS-EG in the differential diagnosis of GB polyps has not been investigated. We investigated the diagnostic performance of EUS-EG for the differential diagnosis of GB polyps. METHODS: Patients with GB polyps were prospectively enrolled from June 2020 until November 2022. EUS-EG and semiquantitative evaluation of the strain ratio (SR) were performed for differential diagnosis of GB polyps. Fifty-three eligible patients were divided into 2 groups based on the final diagnosis after surgery. Patient demographics, EUS characteristics, and SR values were compared. A receiver-operating characteristic curve analysis was performed to determine the optimal cutoff SR value that discriminates between neoplastic and non-neoplastic GB polyps. RESULTS: The median SR value for neoplastic polyps (32.93 [interquartile range {IQR}, 22.37-69.02]) was significantly higher than for non-neoplastic polyps (5.40 [IQR, 2.36-14.44], P < .001). Significant differences were found in SR values between non-neoplastic, benign neoplastic (23.38 [IQR, 13.62-39.04]), and malignant polyps (49.25 [IQR, 27.90-82.00]). The optimal cutoff SR value to differentiate between neoplastic and non-neoplastic polyps was 18.4. In multivariable logistic regression, SR value >18.4 (odds ratio, 33.604; 95% confidence interval, 2.588-436.292) was an independent predictor of neoplastic polyps. CONCLUSIONS: EUS-EG and SR values can be used as a supplementary method for evaluating GB polyps. (Clinical trial registration number: NCT04416763.).

Applications of artificial intelligence in biliary tract cancers.

Biliary tract cancers are malignant neoplasms arising from bile duct epithelial cells. They include cholangiocarcinomas and gallbladder cancer. Gallbladder cancer has a marked geographical preference and is one of the most common cancers in women in northern India. Biliary tract cancers are usually diagnosed at an advanced, unresectable stage. Hence, the prognosis is extremely dismal. The five-year survival rate in advanced gallbladder cancer is < 5%. Hence, early detection and radical surgery are critical to improving biliary tract cancer prognoses. Radiological imaging plays an essential role in diagnosing and managing biliary tract cancers. However, the diagnosis is challenging because the biliary tract is affected by many diseases that may have radiological appearances similar to cancer. Artificial intelligence (AI) can improve radiologists' performance in various tasks. Deep learning (DL)-based approaches are increasingly incorporated into medical imaging to improve diagnostic performance. This paper reviews the AI-based strategies in biliary tract cancers to improve the diagnosis and prognosis.

Accuracy of preoperative T2 gallbladder tumor localization and the adequate surgical resection.

INTRODUCTION: The agreement between the radiologic and histopathologic tumor locations in T2 gallbladder cancer is critical. There is no consensus regarding the extent of curative resection by tumor locations. METHODS: Between January 2010 and December 2019, a consecutive series of 118 patients with pathological T2 gallbladder cancer who underwent surgery were retrospectively analyzed in terms of the accordance between radiologic and histopathologic tumor locations, the extents of hepatic resection and the numbers of harvested lymph nodes. Radical resection was defined as liver resection with harvesting of at least four lymph nodes. RESULTS: The accuracy of preoperative tumor localization was only 68%. After radical resection, the 5-year overall survival (OS) was 59.4%; after nonradical resection, the figure was 46.1% (p = 0.092). In subanalyses, the 5-year OS was marginally better for patients who underwent liver resection or from whom at least four lymph nodes were harvested than those who did not undergo liver resection or from whom three or fewer lymph nodes were harvested (58.2% vs. 39.4%, p = 0.072; 59.9% vs. 50.0%, p = 0.072, respectively). In patients with peritoneal side tumor, the 5-year OSs of those who did and did not undergo liver resection were 67% and 41.2%, respectively (p = 0.028). In multivariate analysis, perineural invasion and radical resection were independently prognostic of OS. CONCLUSION: The accuracy of preoperative tumor localization was 68%. Hepatic resection, lymph node dissection harvesting of at least four lymph nodes are required for curative resection for gallbladder cancer, regardless of tumor location.

Risk prediction and analysis of gallbladder polyps with deep neural network.

The aim of this study is to analyze the risk factors associated with the development of adenomatous and malignant polyps in the gallbladder. Adenomatous polyps of the gallbladder are considered precancerous and have a high likelihood of progressing into malignancy. Preoperatively, distinguishing between benign gallbladder polyps, adenomatous polyps, and malignant polyps is challenging. Therefore, the objective is to develop a neural network model that utilizes these risk factors to accurately predict the nature of polyps. This predictive model can be employed to differentiate the nature of polyps before surgery, enhancing diagnostic accuracy. A retrospective study was done on patients who had cholecystectomy surgeries at the Department of Hepatobiliary Surgery of the Second People's Hospital of Shenzhen between January 2017 and December 2022. The patients' clinical characteristics, lab results, and ultrasonographic indices were examined. Using risk variables for the growth of adenomatous and malignant polyps in the gallbladder, a neural network model for predicting the kind of polyps will be created. A normalized confusion matrix, PR, and ROC curve were used to evaluate the performance of the model. In this comprehensive study, we meticulously analyzed a total of 287 cases of benign gallbladder polyps, 15 cases of adenomatous polyps, and 27 cases of malignant polyps. The data analysis revealed several significant findings. Specifically, hepatitis B core antibody (95% CI -0.237 to 0.061, p < 0.001), number of polyps (95% CI -0.214 to -0.052, p = 0.001), polyp size (95% CI 0.038 to 0.051, p < 0.001), wall thickness (95% CI 0.042 to 0.081, p < 0.001), and gallbladder size (95% CI 0.185 to 0.367, p < 0.001) emerged as independent predictors for gallbladder adenomatous polyps and malignant polyps. Based on these significant findings, we developed a predictive classification model for gallbladder polyps, represented as follows, Predictive classification model for GBPs = -0.149 * core antibody - 0.033 * number of polyps + 0.045 * polyp size + 0.061 * wall thickness + 0.276 * gallbladder size - 4.313. To assess the predictive efficiency of the model, we employed precision-recall (PR) and receiver operating characteristic (ROC) curves. The area under the curve (AUC) for the prediction model was 0.945 and 0.930, respectively, indicating excellent predictive capability. We determined that a polyp size of 10 mm served as the optimal cutoff value for diagnosing gallbladder adenoma, with a sensitivity of 81.5% and specificity of 60.0%. For the diagnosis of gallbladder cancer, the sensitivity and specificity were 81.5% and 92.5%, respectively. These findings highlight the potential of our predictive model and provide valuable insights into accurate diagnosis and risk assessment for gallbladder polyps. We identified several risk factors associated with the development of adenomatous and malignant polyps in the gallbladder, including hepatitis B core antibodies, polyp number, polyp size, wall thickness, and gallbladder size. To address the need for accurate prediction, we introduced a novel neural network learning algorithm. This algorithm utilizes the aforementioned risk factors to predict the nature of gallbladder polyps. By accurately identifying the nature of these polyps, our model can assist patients in making informed decisions regarding their treatment and management strategies. This innovative approach aims to improve patient outcomes and enhance the overall effectiveness of care.