The robotic-surgery propositional bank.

Robot-assisted minimally invasive surgery is the gold standard for the surgical treatment of many pathological conditions since it guarantees to the patient shorter hospital stay and quicker recovery. Several manuals and academic papers describe how to perform these interventions and thus contain important domain-specific knowledge. This information, if automatically extracted and processed, can be used to extract or summarize surgical practices or develop decision making systems that can help the surgeon or nurses to optimize the patient's management before, during, and after the surgery by providing theoretical-based suggestions. However, general English natural language understanding algorithms have lower efficacy and coverage issues when applied to domain others than those they are typically trained on, and a domain specific textual annotated corpus is missing. To overcome this problem, we annotated the first robotic-surgery procedural corpus, with PropBank-style semantic labels. Starting from the original PropBank framebank, we enriched it by adding new lemmas, frames and semantic arguments required to cover missing information in general English but needed in procedural surgical language, releasing the Robotic-Surgery Procedural Framebank (RSPF). We then collected from robotic-surgery textbooks as-is sentences for a total of 32,448 tokens, and we annotated them with RSPF labels. We so obtained and publicly released the first annotated corpus of the robotic-surgical domain that can be used to foster further research on language understanding and procedural entities and relations extraction from clinical and surgical scientific literature.

Machine understanding surgical actions from intervention procedure textbooks.

The automatic extraction of procedural surgical knowledge from surgery manuals, academic papers or other high-quality textual resources, is of the utmost importance to develop knowledge-based clinical decision support systems, to automatically execute some procedure's step or to summarize the procedural information, spread throughout the texts, in a structured form usable as a study resource by medical students. In this work, we propose a first benchmark on extracting detailed surgical actions from available intervention procedure textbooks and papers. We frame the problem as a Semantic Role Labeling task. Exploiting a manually annotated dataset, we apply different Transformer-based information extraction methods. Starting from RoBERTa and BioMedRoBERTa pre-trained language models, we first investigate a zero-shot scenario and compare the obtained results with a full fine-tuning setting. We then introduce a new ad-hoc surgical language model, named SurgicBERTa, pre-trained on a large collection of surgical materials, and we compare it with the previous ones. In the assessment, we explore different dataset splits (one in-domain and two out-of-domain) and we investigate also the effectiveness of the approach in a few-shot learning scenario. Performance is evaluated on three correlated sub-tasks: predicate disambiguation, semantic argument disambiguation and predicate-argument disambiguation. Results show that the fine-tuning of a pre-trained domain-specific language model achieves the highest performance on all splits and on all sub-tasks. All models are publicly released.

Automatic detection of procedural knowledge in robotic-assisted surgical texts.

PURPOSE: The automatic extraction of knowledge about intervention execution from surgical manuals would be of the utmost importance to develop expert surgical systems and assistants. In this work we assess the feasibility of automatically identifying the sentences of a surgical intervention text containing procedural information, a subtask of the broader goal of extracting intervention workflows from surgical manuals. METHODS: We frame the problem as a binary classification task. We first introduce a new public dataset of 1958 sentences from robotic surgery texts, manually annotated as procedural or non-procedural. We then apply different classification methods, from classical machine learning algorithms, to more recent neural-network approaches and classification methods exploiting transformers (e.g., BERT, ClinicalBERT). We also analyze the benefits of applying balancing techniques to the dataset. RESULTS: The architectures based on neural-networks fed with FastText's embeddings and the one based on ClinicalBERT outperform all the tested methods, empirically confirming the feasibility of the task. Adopting balancing techniques does not lead to substantial improvements in classification. CONCLUSION: This is the first work experimenting with machine / deep learning algorithms for automatically identifying procedural sentences in surgical texts. It also introduces the first public dataset that can be used for benchmarking different classification methods for the task.