A new endoscopic ultrasonography image processing method to evaluate the prognosis for pancreatic cancer treated with interstitial brachytherapy

Endoscopic innovations in diagnosis and management of pancreatic cancer: a narrative review and future directions

Pancreatic cancer serves as the third leading cause of cancer-associated morbidity and mortality in the United States, with a 5-year survival rate of only 12% with an expected increase in incidence and mortality in the coming years. Pancreatic ductal adenocarcinomas constitute most pancreatic malignancies. Certain genetic syndromes, including Lynch syndrome, hereditary breast and ovarian cancer syndrome, hereditary pancreatitis, familial adenomatous polyposis, Peutz-Jeghers syndrome, familial pancreatic cancer mutation, and ataxia telangiectasia, confer a significantly higher risk. Screening for pancreatic malignancies currently targets patients with germline mutations or those with significant family history. Screening the general population is not currently viable owing to overall low incidence and lack of specific tests. Endoscopic ultrasound (EUS) and its applied advances are increasingly being used for surveillance, diagnosis, and management of pancreatic malignancies and have now become an indispensable tool in their management. For patients with risk factors, EUS in combination with magnetic resonance imaging/magnetic resonance cholangiopancreatography is used for screening. The role of endoscopic modalities has been expanding with the increased utilization of endoscopic retrograde cholangiopancreatography, EUS-directed therapies include EUS-guided fine-needle aspiration and EUS-fine-needle biopsy (FNB). EUS combined with FNB has the highest specificity and sensitivity for detecting pancreatic cancer amongst available modalities. Studies also recognize that artificial intelligence assisted EUS in the early detection of pancreatic cancer. At the same time, surgical resection has been historically considered the only curative treatment for pancreatic cancer, over 80% of patients present with unresectable disease. We also discuss EUS-guided therapies of physicochemicals (radiofrequency ablation, brachytherapy, and intratumor chemotherapy), biological agents (gene therapies and oncolytic viruses), and immunotherapy. We aim to perform a detailed review of the current burden, risk factors, role of screening, diagnosis, and endoscopic advances in the treatment modalities available for pancreatic cancer.

Artificial intelligence in pancreatic cancer

Pancreatic cancer is the deadliest disease, with a five-year overall survival rate of just 11%. The pancreatic cancer patients diagnosed with early screening have a median overall survival of nearly ten years, compared with 1.5 years for those not diagnosed with early screening. Therefore, early diagnosis and early treatment of pancreatic cancer are particularly critical. However, as a rare disease, the general screening cost of pancreatic cancer is high, the accuracy of existing tumor markers is not enough, and the efficacy of treatment methods is not exact. In terms of early diagnosis, artificial intelligence technology can quickly locate high-risk groups through medical images, pathological examination, biomarkers, and other aspects, then screening pancreatic cancer lesions early. At the same time, the artificial intelligence algorithm can also be used to predict the survival time, recurrence risk, metastasis, and therapy response which could affect the prognosis. In addition, artificial intelligence is widely used in pancreatic cancer health records, estimating medical imaging parameters, developing computer-aided diagnosis systems, etc. Advances in AI applications for pancreatic cancer will require a concerted effort among clinicians, basic scientists, statisticians, and engineers. Although it has some limitations, it will play an essential role in overcoming pancreatic cancer in the foreseeable future due to its mighty computing power.

Update on quantitative radiomics of pancreatic tumors

Radiomics is a newer approach for analyzing radiological images obtained from conventional imaging modalities such as computed tomography, magnetic resonance imaging, endoscopic ultrasonography, and positron emission tomography. Radiomics involves extracting quantitative data from the images and assessing them to identify diagnostic or prognostic features such as tumor grade, resectability, tumor response to neoadjuvant therapy, and survival. The purpose of this review is to discuss the basic principles of radiomics and provide an overview of the current clinical applications of radiomics in the field of pancreatic tumors.

Application of artificial intelligence in diagnosis of pancreatic malignancies by endoscopic ultrasound: a systemic review

BACKGROUND

Pancreatic cancer (PC) is a highly fatal malignancy with a global overall 5-year survival of under 10%. Screening of PC is not recommended outside of clinical trials. Endoscopic ultrasonography (EUS) is a very sensitive test to identify PC but lacks specificity and is operator-dependent, especially in the presence of chronic pancreatitis (CP). Artificial Intelligence (AI) is a growing field with a wide range of applications to augment the currently available modalities. This study was undertaken to study the effectiveness of AI with EUS in the diagnosis of PC.

METHODS

Studies from MEDLINE and EMBASE databases reporting the AI performance applied to EUS imaging for recognizing PC. Data were analyzed using descriptive statistics. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was used to assess the quality of the included studies.

RESULTS

A total of 11 articles reported the role of EUS in the diagnosis of PC. The overall accuracy, sensitivity, and specificity of AI in recognizing PC were 80-97.5%, 83-100%, and 50-99%, respectively, with corresponding positive predictive value (PPV) and negative predictive value (NPV) of 75-99% and 57-100%, respectively. Types of AI studied were artificial neural networks (ANNs), convolutional neural networks (CNN), and support vector machine (SVM). Seven studies using other than basic ANN reported a sensitivity and specificity of 88-96% and 83-94% to differentiate PC from CP. Two studies using SVM reported a 94-96% sensitivity, 93%-99% specificity, and 94-98% accuracy to diagnose PC from CP. The reported sensitivity and specificity of detection of malignant from benign Intraductal Papillary Mucinous Neoplasms (IPMNs) was 96% and 92%, respectively.

CONCLUSION

AI reported a high sensitivity with high specificity and accuracy to diagnose PC, differentiate PC from CP, and differentiate benign from malignant IPMN when used with EUS.

Artificial intelligence in gastroenterology: A state-of-the-art review

The development of artificial intelligence (AI) has increased dramatically in the last 20 years, with clinical applications progressively being explored for most of the medical specialties. The field of gastroenterology and hepatology, substantially reliant on vast amounts of imaging studies, is not an exception. The clinical applications of AI systems in this field include the identification of premalignant or malignant lesions (e.g., identification of dysplasia or esophageal adenocarcinoma in Barrett’s esophagus, pancreatic malignancies), detection of lesions (e.g., polyp identification and classification, small-bowel bleeding lesion on capsule endoscopy, pancreatic cystic lesions), development of objective scoring systems for risk stratification, predicting disease prognosis or treatment response [e.g., determining survival in patients post-resection of hepatocellular carcinoma), determining which patients with inflammatory bowel disease (IBD) will benefit from biologic therapy], or evaluation of metrics such as bowel preparation score or quality of endoscopic examination. The objective of this comprehensive review is to analyze the available AI-related studies pertaining to the entirety of the gastrointestinal tract, including the upper, middle and lower tracts; IBD; the hepatobiliary system; and the pancreas, discussing the findings and clinical applications, as well as outlining the current limitations and future directions in this field.

Pancreas image mining: a systematic review of radiomics

OBJECTIVES

To systematically review published studies on the use of radiomics of the pancreas.

METHODS

The search was conducted in the MEDLINE database. Human studies that investigated the applications of radiomics in diseases of the pancreas were included. The radiomics quality score was calculated for each included study.

RESULTS

A total of 72 studies encompassing 8863 participants were included. Of them, 66 investigated focal pancreatic lesions (pancreatic cancer, precancerous lesions, or benign lesions); 4, pancreatitis; and 2, diabetes mellitus. The principal applications of radiomics were differential diagnosis between various types of focal pancreatic lesions (n = 19), classification of pancreatic diseases (n = 23), and prediction of prognosis or treatment response (n = 30). Second-order texture features were most useful for the purpose of differential diagnosis of diseases of the pancreas (with 100% of studies investigating them found a statistically significant feature), whereas filtered image features were most useful for the purpose of classification of diseases of the pancreas and prediction of diseases of the pancreas (with 100% of studies investigating them found a statistically significant feature). The median radiomics quality score of the included studies was 28%, with the interquartile range of 22% to 36%. The radiomics quality score was significantly correlated with the number of extracted radiomics features (r = 0.52, p < 0.001) and the study sample size (r = 0.34, p = 0.003).

CONCLUSIONS

Radiomics of the pancreas holds promise as a quantitative imaging biomarker of both focal pancreatic lesions and diffuse changes of the pancreas. The usefulness of radiomics features may vary depending on the purpose of their application. Standardisation of image acquisition protocols and image pre-processing is warranted prior to considering the use of radiomics of the pancreas in routine clinical practice.

KEY POINTS

• Methodologically sound studies on radiomics of the pancreas are characterised by a large sample size and a large number of extracted features. • Optimisation of the radiomics pipeline will increase the clinical utility of mineable pancreas imaging data. • Radiomics of the pancreas is a promising personalised medicine tool in diseases of the pancreas.

Radioactive 125I seed implantation for pancreatic cancer with unexpected liver metastasis: A preliminary experience with 26 patients

BACKGROUND

Preoperative diagnosis rate of pancreatic cancer has increased year by year. The prognosis of pancreatic cancer patients with unexpected liver metastasis found by intraoperative exploration is very poor, and there is no effective and unified treatment strategy.

AIM

To evaluate the therapeutic effect of radioactive ¹²⁵I seed implantation for pancreatic cancer patients with unexpected liver metastasis.

METHODS

The demographics and perioperative outcomes of patients who underwent ¹²⁵I seed implantation to treat pancreatic cancer with unexpected liver metastasis between January 1, 2017 and June 1, 2019 were retrospectively analyzed. During the operation, ¹²⁵I seeds were implanted into the pancreatic tumor under the guidance of intraoperative ultrasound, with a spacing of 1.5 cm and a row spacing of 1.5 cm. For patients with obstructive jaundice and digestive tract obstruction, choledochojejunostomy and gastroenterostomy were performed simultaneously. After operation, the patients were divided into a non-chemotherapy group and a chemotherapy group that received gemcitabine combined with albumin-bound paclitaxel treatment.

RESULTS

Preoperative imaging evaluation of all patients in this study showed that the tumor was resectable without liver metastasis. There were 26 patients in this study, including 18 males and 8 females, aged 60.5 ± 9.7 years. The most common tumor site was the pancreatic head (17, 65.4%), followed by the pancreatic neck and body (6, 23.2%) and pancreatic tail (3, 11.4%). Fourteen patients (53.8%) underwent palliative surgery and postoperative pain relief occurred in 22 patients (84.6%). The estimated blood loss in operation was 148.3 ± 282.1 mL and one patient received blood transfusion. The postoperative hospital stay was 7.6 ± 2.8 d. One patient had biliary fistula, one had pancreatic fistula, and all recovered after conservative treatment. After operation, 7 patients received chemotherapy and 19 did not. The 1-year survival rate was significantly higher in patients who received chemotherapy than in those who did not (68.6% vs 15.8%, P = 0.012). The mean overall survival of patients in the chemotherapy group and non-chemotherapy group was 16.3 mo and 10 mo, respectively (χ² = 7.083, P = 0.008).

CONCLUSION

Radioactive ¹²⁵I seed implantation combined with postoperative chemotherapy can prolong the survival time and relieve pain of pancreatic cancer patients with unexpected liver metastasis.

Artificial intelligence in pancreaticobiliary endoscopy

Artificial intelligence (AI) applications in health care have exponentially increased in recent years, and a few of these are related to pancreatobiliary disorders. AI-based methods were applied to extract information, in prognostication, to guide clinical treatment decisions and in pancreatobiliary endoscopy to characterize lesions. AI applications in endoscopy are expected to reduce inter-operator variability, improve the accuracy of diagnosis, and assist in therapeutic decision-making in real time. AI-based literature must however be interpreted with caution given the limited external validation. A multidisciplinary approach combining clinical and imaging or endoscopy data will better utilize AI-based technologies to further improve patient care.

Radioactive 125I seed implantation for locally advanced pancreatic cancer: A retrospective analysis of 50 cases

BACKGROUND

Pancreatic cancer is one of the common malignant tumors of the digestive system, and radical resection is the first choice of treatment for pancreatic cancer. If patients with locally advanced pancreatic cancer cannot be treated in time and effectively, their disease often develops rapidly and their survival period is very short.

AIM

To evaluate the therapeutic effect of ¹²⁵I seed implantation in patients with locally advanced pancreatic cancer.

METHODS

The demographics and perioperative outcomes of a consecutive series of patients who underwent ¹²⁵I seed implantation to treat locally advanced pancreatic cancer between January 1, 2017 and June 30, 2019 were retrospectively analyzed. According to the results of preoperative computed tomography or magnetic resonance imaging, the treatment planning system was used to determine the area and number of ¹²⁵I seeds implanted. During the operation, ¹²⁵I seeds were implanted into the tumor under the guidance of intraoperative ultrasound, with a spacing of 1.5 cm and a row spacing of 1.5 cm. For patients with obstructive jaundice and digestive tract obstruction, choledochojejunostomy and gastroenterostomy were performed simultaneously. After operation, the patients were divided into a non-chemotherapy group and a chemotherapy group that received gemcitabine combined with albumin-bound paclitaxel treatment.

RESULTS

Among the 50 patients, there were 29 males and 21 females, with a mean age of 56.9 ± 9.8 years. The main reason for the failure of radical resection was superior mesenteric artery invasion (37, 74%), followed by superior mesenteric vein invasion (33, 66%). Twenty-one (62%) patients underwent palliative surgery and postoperative pain relief occurred in 40 (80%) patients. The estimated blood loss in operation was 107.4 ± 115.3 mL and none of the patient received blood transfusion. The postoperative hospital stay was 7.5 ± 4.2 d; one patient had biliary fistula and three had pancreatic fistula, all of whom recovered after conservative treatment. After operation, 26 patients received chemotherapy and 24 did not. The 1-year survival rate was significantly higher in patients who received chemotherapy than in those who did not (60.7% vs 35.9%, P = 0.034). The mean overall survival of patients of the chemotherapy group and non-chemotherapy group was 14 and 11 mo, respectively (χ² = 3.970, P = 0.046).

CONCLUSION

Radioactive ¹²⁵I seed implantation combined with postoperative chemotherapy can prolong the survival time, relieve pain, and improve the quality of life of patients with locally advanced pancreatic cancer.

A review on the efficacy and safety of iodine-125 seed implantation in unresectable pancreatic cancers

Background: Pancreatic cancers are the common digestive system tumors with poor prognosis and due to its late diagnosis, surgical resection does not remain a viable treatment option in about 80% of patients. Amongst different treatment options, radioactive 125I seed implantation therapy has also emerged as a good alternative in non-resectable pancreatic cancer patients.Purpose: The present review describes the efficacy and safety of iodine-125 seed implantation in unresectable pancreatic cancers in preclinical and clinical studies.Results: In this technique, small radioactive particles are implanted inside the tumor cells to produce the sustain effects. Due to the short radial distance of these radiations, there is a selective and efficient killing of cancer cells without any significant injury to the neighboring cells. Amongst the different methods for implanting 125I seeds in the pancreatic tissues, CT scan or ultrasound-guided percutaneous seed implantation is preferred as it offers shorter operative time, lesser bleeding, early recovery, lesser complications, and low medical costs. The clinical studies have shown that radioactive 125I seed implantation is a good option for the management of local tumor growth, pain palliation, and improvement in the life span of patients suffering from unresectable pancreatic cancer.Conclusion: It may be employed either alone or in combination with cryotherapy, existing chemotherapy, bypass surgery or radiations to achieve the optimal results in these patients. Nevertheless, there is a need to formulate a uniform dose and procedure to achieve homogeneity and develop references for clinical practices.

Permanent Iodine-125 Seed Implantation for the Treatment of Nonresectable Retroperitoneal Malignant Tumors

Purpose:

This study aimed to investigate the outcomes of permanent Iodine-125 (¹²⁵I) radiotherapy for patients with unresectable retroperitoneal malignant tumor.

Methods:

Twenty-six patients with retroperitoneal malignant tumors were implanted with ¹²⁵I seeds under ultrasound guidance from June 2012 to June 2015. The patients were then followed up for 3 to 36 months after the implantation. During the follow-up, pain relief, control of tumor growth, over survival rate, and complications were evaluated.

Results:

Most of the patients (90%, 24/26) suffered from mild to severe pain before ¹²⁵I seed treatment. After 1-month treatment, 16 patients had 100% pain relief, 4 patients had at least 50% pain relief, and 4 patients had no response, showing 83.3% of pain relief response. Results of computed tomography scan after 2-month ¹²⁵I treatment indicated that 3 patients had complete remission in the tumor size, 20 patients had partial remission in tumor size, 2 patients were stable, and 1 patient had progressive disease, accounting for 88.4% response in tumor size remission. The median survival of the 26 patients was 11 months. The 1-year and 2-year overall survival rates were 46% and 27%, respectively. The median survival of the 5 patients with pancreatic cancer was 9.4 months. None of the patients had any severe complications.

Conclusions:

¹²⁵I implantation could effectively relieve the pain in the patients with advanced primary or metastatic retroperitoneal malignant tumors and suppress local tumor progress.

EUS elastography (strain ratio) and fractal-based quantitative analysis for the diagnosis of solid pancreatic lesions

BACKGROUND AND AIMS

EUS elastography is useful in characterizing solid pancreatic lesions (SPLs), and fractal analysis-based technology has been used to evaluate geometric complexity in oncology. The aim of this study was to evaluate EUS elastography (strain ratio) and fractal analysis for the characterization of SPLs.

METHODS

Consecutive patients with SPLs were prospectively enrolled between December 2015 and February 2017. Elastographic evaluation included parenchymal strain ratio (pSR) and wall strain ratio (wSR) and was performed with a new compact US processor. Elastographic images were analyzed using a computer program to determine the 3-dimensional histogram fractal dimension. A composite cytology/histology/clinical reference standard was used to assess sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating curve.

RESULTS

Overall, 102 SPLs from 100 patients were studied. At final diagnosis, 69 (68%) were malignant and 33 benign. At elastography, both pSR and wSR appeared to be significantly higher in malignant as compared with benign SPLs (pSR, 24.5 vs 6.4 [P < .001]; wSR, 56.6 vs 15.3 [P < .001]). When the best cut-off levels of pSR and wSR at 9.10 and 16.2, respectively, were used, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating curve were 88.4%, 78.8%, 89.7%, 76.9%, and 86.7% and 91.3%, 69.7%, 86.5%, 80%, and 85.7%, respectively. Fractal analysis showed a significant statistical difference (P = .0087) between the mean surface fractal dimension of malignant lesions (D = 2.66 ± .01) versus neuroendocrine tumor (D = 2.73 ± .03) and a statistical difference for all 3 channels red, green, and blue (P < .0001).

CONCLUSIONS

EUS elastography with pSR and fractal-based analysis are useful in characterizing SPLs. (Clinical trial registration number: NCT02855151.).

Comparative study of intestinal tuberculosis and primary small intestinal lymphoma

AIM: To characterize the clinical, radiological, endoscopic and pathological features of intestinal tuberculosis (ITB) and primary small intestinal lymphoma (PSIL).

METHODS: This was a retrospective study from February 2005 to October 2012 of patients with a diagnosis of ITB (n = 41) or PSIL (n = 37). All patients with ITB or PSIL underwent computed tomography (CT) and pathological examination. Thirty-five patients with ITB and 32 patients with PSIL underwent endoscopy. These patients were followed for a further 18 mo to ascertain that the diagnosis had not changed. Clinical, endoscopic, CT and pathological features were compared between ITB and PSIL patients.

RESULTS: Night sweating, fever, pulmonary TB and ascites were discovered significantly more often in ITB than in PSIL patients (P < 0.05), however, abdominal mass, hematochezia and intestinal perforation were found significantly more frequently in PSIL than in ITB patients (P < 0.05). Ring-like and rodent-like ulcers occurred significantly more often in ITB than in PSIL patients (P < 0.05), however, enterorrhagia and raised lesions were significantly more frequent in PSIL than in ITB patients (P < 0.05). The rate of granuloma was significantly higher in ITB than in PSIL patients (87.8% vs 13.5%, χ² = 43.050, P < 0.05), and the incidence of confluent granulomas with caseous necrosis was significantly higher in ITB than in PSIL patients (47.2% vs 0.0%, χ² = 4.034, P < 0.05). Multi-segmental lesions, mural stratification, mural gas sign, and intestinal stricture were more frequent in ITB than in PSIL patients (P < 0.05), however, a single-layer thickening of bowel wall, single segmental lesions, and intussusception were more common in PSIL than in ITB patients (P < 0.05). Necrotic lymph nodes, comb sign and inflammatory mass were more frequent in ITB than in PSIL patients (P < 0.05). The bowel wall enhancement in ITB patients was greater than that in PSIL patients (P < 0.05), while the thickening and lymph node enlargement in PSIL patients were higher than those in ITB patients (P < 0.05).

CONCLUSION: Combined evaluation of clinical, radiological, endoscopic and pathological features is the key to differentiation between ITB and PSIL.