Enhancing surgeons' gaze strategies in endoscopic surgery during simulated surgical emergency situations thanks to computer vision.

Deficient visualization in minimally invasive surgery often causes misperceptions, which can lead to an increase of iatrogenic lesions and complications. This is especially critical for novice surgeons, who are prone to adopt inadequate switching gaze strategies, thereby increasing the chance of unforeseen complications. In this paper the use of an additional computer-aided vision system was tested for improvement of the reaction of the surgeons to unforeseen complications. Gaze patterns were analyzed using a gaze tracker, as well as other metrics such as task completion time or reaction time to sudden bleeding. While completion time did not show significant difference between tested modalities (p<0.1), the reaction time showed a downward trend as more auxiliary computer-aided vision systems were added (p<0.005). These results support the benefits of including additional vision systems for minimally invasive surgery processes.Clinical Relevance- This work assesses the advantages of including an additional computer vision system to prevent unforeseen complications during minimally invasive surgeries.

Automatic detection of surgical haemorrhage using computer vision.

BACKGROUND AND OBJECTIVES: On occasions, a surgical intervention can be associated with serious, potentially life-threatening complications. One of these complications is a haemorrhage during the operation, an unsolved issue that could delay the intervention or even cause the patient's death. On laparoscopic surgery this complication is even more dangerous, due to the limited vision and mobility imposed by the minimally invasive techniques. METHODS: In this paper it is described a computer vision algorithm designed to analyse the images captured by a laparoscopic camera, classifying the pixels of each frame in blood pixels and background pixels and finally detecting a massive haemorrhage. The pixel classification is carried out by comparing the parameter B/R and G/R of the RGB space colour of each pixel with a threshold obtained using the global average of the whole frame of these parameters. The detection of and starting haemorrhage is achieved by analysing the variation of the previous parameters and the amount of pixel blood classified. RESULTS: When classifying in vitro images, the proposed algorithm obtains accuracy over 96%, but during the analysis of an in vivo images obtained from real operations, the results worsen slightly due to poor illumination, visual interferences or sudden moves of the camera, obtaining accuracy over 88%. The detection of haemorrhages directly depends of the correct classification of blood pixels, so the analysis achieves an accuracy of 78%. CONCLUSIONS: The proposed algorithm turns out to be a good starting point for an automatic detection of blood and bleeding in the surgical environment which can be applied to enhance the surgeon vision, for example showing the last frame previous to a massive haemorrhage where the incision could be seen using augmented reality capabilities.