Staging of Biliary and Primary Liver Tumors

Deep Learning in Endoscopic Ultrasound: A Breakthrough in Detecting Distal Cholangiocarcinoma

INTRODUCTION

Cholangiocarcinoma (CCA) is a highly lethal malignancy originating in the bile ducts, often diagnosed late with poor prognosis. Differentiating benign from malignant biliary tumors remains challenging, necessitating advanced diagnostic techniques.

OBJECTIVE

This study aims to enhance the diagnostic accuracy of endoscopic ultrasound (EUS) for distal cholangiocarcinoma (dCCA) using advanced convolutional neural networks (CCNs) for the classification and segmentation of EUS images, specifically targeting dCCAs, the pancreas, and the bile duct.

MATERIALS AND METHODS

In this retrospective study, EUS images from patients diagnosed with dCCA via biopsy and an EUS-identified bile duct tumor were evaluated. A custom CNN was developed for classification, trained on 156 EUS images. To enhance the model's robustness, image augmentation techniques were applied, generating a total of 1248 images. For tumor and organ segmentation, the DeepLabv3+ network with ResNet50 architecture was utilized, employing Tversky loss to manage unbalanced classes. Performance evaluation included metrics such as accuracy, sensitivity, specificity, and Intersection over Union (IoU). These methods were implemented in collaboration with the ADAPTED Research Group at the Technical University of Cluj-Napoca.

RESULTS

The classification model achieved a high accuracy of 97.82%, with precision and specificity both at 100% and sensitivity at 94.44%. The segmentation models for the pancreas and bile duct demonstrated global accuracies of 84% and 90%, respectively, with robust IoU scores indicating good overlap between predicted and actual contours. The application performed better than the UNet model, particularly in generalization and boundary delineation.

CONCLUSIONS

This study demonstrates the significant potential of AI in EUS imaging for dCCA, presenting a robust tool that enhances diagnostic accuracy and efficiency. The developed MATLAB application serves as a valuable aid for medical professionals, facilitating informed decision-making and improving patient outcomes in the diagnosis of cholangiocarcinoma and related pathologies.

Recommendations on maximising the clinical value of tissue in the management of patients with intrahepatic cholangiocarcinoma

Background & Aims

Patients with intrahepatic cholangiocarcinoma can now be managed with targeted therapies directed against specific molecular alterations. Consequently, tissue samples submitted to the pathology department must produce molecular information in addition to a diagnosis or, for resection specimens, staging information. The pathologist's role when evaluating these specimens has therefore changed to accommodate such personalised approaches.

Methods

We developed recommendations and guidance for pathologists by conducting a systematic review of existing guidance to generate candidate statements followed by an international Delphi process. Fifty-nine pathologists from 28 countries in six continents rated statements mapped to all elements of the specimen pathway from receipt in the pathology department to authorisation of the final written report. A separate survey of 'end-users' of the report including surgeons, oncologists, and gastroenterologists was undertaken to evaluate what information should be included in the written report to enable appropriate patient management.

Results

Forty-eight statements reached consensus for inclusion in the guidance including 10 statements about the content of the written report that also reached consensus by end-user participants. A reporting proforma to allow easy inclusion of the recommended data points was developed.

Conclusions

These guiding principles and recommendations provide a framework to allow pathologists reporting on patients with intrahepatic cholangiocarcinoma to maximise the informational yield of specimens required for personalised patient management.

Impact and Implications

Biopsy or resection lesional tissue from intrahepatic cholangiocarcinoma must yield information about the molecular abnormalities within the tumour that define suitability for personalised therapies in addition to a diagnosis and staging information. Here, we have developed international consensus guidance for pathologists that report such cases using a Delphi process that sought the views of both pathologists and 'end-users of pathology reports. The guide highlights the need to report cases in a way that preserves tissue for molecular testing and emphasises that reporting requires interpretation of histological characteristics within the broader clinical and radiological context. The guide will allow pathologists to report cases of intrahepatic cholangiocarcinoma in a uniform manner that maximises the value of the tissue received to facilitate optimal multidisciplinary patient management.

Endoscopic Ultrasound in the Diagnosis of Extrahepatic Cholangiocarcinoma: What Do We Know in 2023?

Extrahepatic cholangiocarcinoma (CCA) is a rare and aggressive type of cancer, presenting as a mass or as a biliary stricture. This review summarizes the utility of endoscopic ultrasound (EUS) in the detection, staging, and determination of the differential diagnosis, especially when no cause of bile duct dilatation is revealed by cross-sectional imaging. The EUS detection rate for distal CCAs is higher than that for the proximal CCAs. The accuracy of T staging varies between 60 and 80%, and vascular involvement is correctly assessed by conventional EUS. EUS-tissue acquisition from the primary tumors is reserved for unresectable or metastatic CCA, especially in distal strictures or mass CCAs. For proximal lesions, EUS could be performed as an adjunctive to ERCP sampling when the latter is inconclusive. EUS is not appropriate for assessing the malignant features of lymph nodes in CCAs. Lymph node EUS-tissue acquisition should be performed only if it changes the surgical decision. Perhaps the development of EUS-fine needle biopsy and the detection of molecular genetic alteration will increase the diagnostic yield in CCAs.

Endoscopic Ultrasound for the Diagnosis and Staging of Biliary Malignancy

Cholangiocarcinoma (CCA) is the most common neoplasm of the biliary tract. The biological behavior and prognosis of CCA vary depending on the tumor's location in the biliary tree, dictating a different diagnostic, and treatment approach. Establishing a diagnosis of CCA remains a challenge and up to 20% of biliary strictures can yield indeterminate results, despite extensive evaluation. Endoscopic ultrasound (EUS) has become an effective diagnostic tool, as it provides high-quality images of the bile duct and allows for the sampling of strictures in the same plane of view. In this chapter, we explore the utility of EUS as a diagnostic and staging tool for biliary cancers.

Focused ultrasound tumour ablation in small animal oncology

The cancer incidence rates for humans and animals remain high, and efforts to improve cancer treatment are crucial. Cancer treatment for solid tumours includes both treatment of the primary tumour and of metastasis. Surgery is commonly employed to resect primary and metastatic tumours, but is invasive, and is not always the optimal treatment modality. Prevention and treatment of metastatic disease often utilizes a multimodal approach, but metastasis remains a major cause of death for both human and veterinary cancer patients. Focused ultrasound (FUS) tumour ablation techniques represent a novel non-invasive approach to treating cancer. FUS ablation is precise, thus sparing adjacent critical structures while ablating the tumour. FUS ablation can occur in a thermal or non-thermal fashion. Thermal FUS ablation, also known as high intensity focused ultrasound (HIFU) ablation, destroys tumour cells via heat, whereas non-thermal FUS, known as histotripsy, ablates tumour cells via mechanical disintegration of tissue. Not only can HIFU and histotripsy ablate tumours, they also demonstrate potential to upregulate the host immune system towards an anti-tumour response. The aim of this report is provide a description of HIFU and histotripsy tumour ablation, with a focus on the basic principles of their ablation mechanisms and their clinical applicability in the field of veterinary oncology.