CONTEXT-GUIDED FUTURE LIVER REMNANT VOLUME ESTIMATION USING ARTIFICIAL INTELLIGENCE MODELS

Artificial intelligence and, particularly, machine learning, have shown significant impact in diverse fields. Among the wide diversity of fields with impact from AI, medicine stands as one in which there is tremendous potential along with equally critical challenges. This can be observed by the increasing number of publications in this field. For instance, we have seen many publications on image-based diagnosis using AI. This covers areas like radiographs, histology, and optic fundi, among others.

Radiology is the field of medicine in which there are the greatest number of clinical solutions that use AI. These solutions focus on problems of detecting findings, classifying lesions, organ or lesion segmentation, image processing, among others. Segmentation problems are very common in medical imaging, with hepatic segmentation being one of the most explored due to its applications in volumetry. Liver segmentation for volumetry is indicated in patients undergoing major liver surgery, defined as the resection of four or more liver segments. Most hepatectomies are performed in patients with liver neoplasms, such as hepatocarcinoma, cholangiocarcinoma and liver metastases. The objective of the liver volumetry is to estimate the total liver volume and the future liver remnant, the amount of liver parenchyma that would be left post-resection. Future liver remnant volume is directly correlated with post-hepatectomy liver function, and its precise measurement is crucial to prevent patients from developing post-hepatectomy liver failure[1-2].

Current models are focused on liver and tumor segmentation that is an important task but not enough for surgical planning. An automatic liver and tumor segmentation method can greatly relieve physicians of the heavy workload of examining CT images [21]. However, for surgery, a more challenging task is required. Indeed, for surgery planning is critical to accurately estimate the remnant liver volume after resection; for instance in patients with liver metastases.

Estimating the future liver remnant is a challenging task because the type of surgery to be performed depends on each patient's clinical setting, the center's experience, number and location of liver lesions, among others. This means that future liver remnant segmentation depends on the patient's clinical context.

Therefore, the goal of this project is to design, implement and evaluate fine-grained liver segmentation guided by context that allows us to precisely estimate remnant liver volume. Our project is guided by the following specific objectives:

1. Evaluate SOTA liver segmentation models.
2. Design and evaluate models for fine-grained liver segmentation models.
3. Estimate remnant liver volume using the fine-grained liver segmentation model.
4. Integrate contextual information by prompts for liver segmentation.
5. Evaluation and adjusting the proposed models.