Artificial intelligence for advance requesting of immunohistochemistry in diagnostically uncertain prostate biopsies.

The use of immunohistochemistry in the reporting of prostate biopsies is an important adjunct when the diagnosis is not definite on haematoxylin and eosin (H&E) morphology alone. The process is however inherently inefficient with delays while waiting for pathologist review to make the request and duplicated effort reviewing a case more than once. In this study, we aimed to capture the workflow implications of immunohistochemistry requests and demonstrate a novel artificial intelligence tool to identify cases in which immunohistochemistry (IHC) is required and generate an automated request. We conducted audits of the workflow for prostate biopsies in order to understand the potential implications of automated immunohistochemistry requesting and collected prospective cases to train a deep neural network algorithm to detect tissue regions that presented ambiguous morphology on whole slide images. These ambiguous foci were selected on the basis of the pathologist requesting immunohistochemistry to aid diagnosis. A gradient boosted trees classifier was then used to make a slide-level prediction based on the outputs of the neural network prediction. The algorithm was trained on annotations of 219 immunohistochemistry-requested and 80 control images, and tested by threefold cross-validation. Validation was conducted on a separate validation dataset of 222 images. Non IHC-requested cases were diagnosed in 17.9 min on average, while IHC-requested cases took 33.4 min over multiple reporting sessions. We estimated 11 min could be saved on average per case by automated IHC requesting, by removing duplication of effort. The tool attained 99% accuracy and 0.99 Area Under the Curve (AUC) on the test data. In the validation, the average agreement with pathologists was 0.81, with a mean AUC of 0.80. We demonstrate the proof-of-principle that an AI tool making automated immunohistochemistry requests could create a significantly leaner workflow and result in pathologist time savings.

Real-Time Assessment of Mechanical Tissue Trauma in Surgery.

OBJECTIVE: This work presents a method to assess and prevent tissue trauma in real-time during surgery. BACKGROUND: Tissue trauma occurs routinely during laparoscopic surgery with potentially severe consequences. As such, it is crucial that a surgeon is able to regulate the pressure exerted by surgical instruments. We propose a novel method to assess the onset of tissue trauma by considering the mechanical response of tissue as it is loaded in real-time. METHODS: We conducted a parametric study using a lab-based grasping model and differing load conditions. Mechanical stress-time data were analyzed to characterize the tissue response to grasps. Qualitative and quantitative histological analyses were performed to inspect damage characteristics of the tissue under different load conditions. These were correlated against the mechanical measures to identify the nature of trauma onset with respect to our predictive metric. RESULTS: Results showed increasing tissue trauma with load and a strong correlation with the mechanical response of the tissue. Load rate and load history also showed a clear effect on tissue response. The proposed method for trauma assessment was effective in identifying damage. The metric can be normalized with respect to loading rate and history, making it feasible in the unconstrained environment of intraoperative surgery. SIGNIFICANCE: This work demonstrates that tissue trauma can be predicted using mechanical measures in real-time. Applying this technique to laparoscopic tools has the potential to reduce unnecessary tissue trauma and its associated complications by indicating through user feedback or actively regulating the mechanical impact of surgical instruments.