Development of an artificial intelligence system for real-time intraoperative assessment of the Critical View of Safety in laparoscopic cholecystectomy.

BACKGROUND: The Critical View of Safety (CVS) was proposed in 1995 to prevent bile duct injury during laparoscopic cholecystectomy (LC). The achievement of CVS was evaluated subjectively. This study aimed to develop an artificial intelligence (AI) system to evaluate CVS scores in LC. MATERIALS AND METHODS: AI software was developed to evaluate the achievement of CVS using an algorithm for image classification based on a deep convolutional neural network. Short clips of hepatocystic triangle dissection were converted from 72 LC videos, and 23,793 images were labeled for training data. The learning models were examined using metrics commonly used in machine learning. RESULTS: The mean values of precision, recall, F-measure, specificity, and overall accuracy for all the criteria of the best model were 0.971, 0.737, 0.832, 0.966, and 0.834, respectively. It took approximately 6 fps to obtain scores for a single image. CONCLUSIONS: Using the AI system, we successfully evaluated the achievement of the CVS criteria using still images and videos of hepatocystic triangle dissection in LC. This encourages surgeons to be aware of CVS and is expected to improve surgical safety.

Development of a cross-artificial intelligence system for identifying intraoperative anatomical landmarks and surgical phases during laparoscopic cholecystectomy.

BACKGROUND: Attention to anatomical landmarks in the appropriate surgical phase is important to prevent bile duct injury (BDI) during laparoscopic cholecystectomy (LC). Therefore, we created a cross-AI system that works with two different AI algorithms simultaneously, landmark detection and phase recognition. We assessed whether landmark detection was activated in the appropriate phase by phase recognition during LC and the potential contribution of the cross-AI system in preventing BDI through a clinical feasibility study (J-SUMMIT-C-02). METHODS: A prototype was designed to display landmarks during the preparation phase and Calot's triangle dissection. A prospective clinical feasibility study using the cross-AI system was performed in 20 LC cases. The primary endpoint of this study was the appropriateness of the detection timing of landmarks, which was assessed by an external evaluation committee (EEC). The secondary endpoint was the correctness of landmark detection and the contribution of cross-AI in preventing BDI, which were assessed based on the annotation and 4-point rubric questionnaire. RESULTS: Cross-AI-detected landmarks in 92% of the phases where the EEC considered landmarks necessary. In the questionnaire, each landmark detected by AI had high accuracy, especially the landmarks of the common bile duct and cystic duct, which were assessed at 3.78 and 3.67, respectively. In addition, the contribution to preventing BDI was relatively high at 3.65. CONCLUSIONS: The cross-AI system provided landmark detection at appropriate situations. The surgeons who previewed the model suggested that the landmark information provided by the cross-AI system may be effective in preventing BDI. Therefore, it is suggested that our system could help prevent BDI in practice. Trial registration University Hospital Medical Information Network Research Center Clinical Trial Registration System (UMIN000045731).

An intraoperative artificial intelligence system identifying anatomical landmarks for laparoscopic cholecystectomy: a prospective clinical feasibility trial (J-SUMMIT-C-01).

BACKGROUND: We have implemented Smart Endoscopic Surgery (SES), a surgical system that uses artificial intelligence (AI) to detect the anatomical landmarks that expert surgeons base on to perform certain surgical maneuvers. No report has verified the use of AI-based support systems for surgery in clinical practice, and no evaluation method has been established. To evaluate the detection performance of SES, we have developed and established a new evaluation method by conducting a clinical feasibility trial. METHODS: A single-center prospective clinical feasibility trial was conducted on 10 cases of LC performed at Oita University hospital. Subsequently, an external evaluation committee (EEC) evaluated the AI detection accuracy for each landmark using five-grade rubric evaluation and DICE coefficient. We defined LM-CBD as the expert surgeon's "judge" of the cystic bile duct in endoscopic images. RESULTS: The average detection accuracy on the rubric by the EEC was 4.2 ± 0.8 for the LM-CBD. The DICE coefficient between the AI detection area of the LM-CBD and the EEC members' evaluation was similar to the mean value of the DICE coefficient between the EEC members. The DICE coefficient was high score for the case that was highly evaluated by the EEC on a five-grade scale. CONCLUSION: This is the first feasible clinical trial of an AI system designed for intraoperative use and to evaluate the AI system using an EEC. In the future, this concept of evaluation for the AI system would contribute to the development of new AI navigation systems for surgery.

Artificial intelligence software available for medical devices: surgical phase recognition in laparoscopic cholecystectomy.

BACKGROUND: Surgical process modeling automatically identifies surgical phases, and further improvement in recognition accuracy is expected with deep learning. Surgical tool or time series information has been used to improve the recognition accuracy of a model. However, it is difficult to collect this information continuously intraoperatively. The present study aimed to develop a deep convolution neural network (CNN) model that correctly identifies the surgical phase during laparoscopic cholecystectomy (LC). METHODS: We divided LC into six surgical phases (P1-P6) and one redundant phase (P0). We prepared 115 LC videos and converted them to image frames at 3 fps. Three experienced doctors labeled the surgical phases in all image frames. Our deep CNN model was trained with 106 of the 115 annotation datasets and was evaluated with the remaining datasets. By depending on both the prediction probability and frequency for a certain period, we aimed for highly accurate surgical phase recognition in the operation room. RESULTS: Nine full LC videos were converted into image frames and were fed to our deep CNN model. The average accuracy, precision, and recall were 0.970, 0.855, and 0.863, respectively. CONCLUSION: The deep learning CNN model in this study successfully identified both the six surgical phases and the redundant phase, P0, which may increase the versatility of the surgical process recognition model for clinical use. We believe that this model can be used in artificial intelligence for medical devices. The degree of recognition accuracy is expected to improve with developments in advanced deep learning algorithms.

Nutrients exported from upland stream water enlarge perennial biomass crops.

Rawanbuki, a variety of Japanese butterbur (Petasites japonicus subsp. giganteus), grow naturally along the Rawan River, Hokkaido, northern Japan. Most plants reach 2-3 m in height and 10 cm in diameter in 2 months and are much larger than those grown along other rivers. We examined the hypothesis that nutrients exported from upland streams enhance the growth of the Rawanbuki. Nutrient concentrations, including nitrogen, phosphorus, and base cations, in the Rawan River were much higher than those in rivers of adjacent watersheds. High nutrient concentrations and moisture contents were found in soil along the Rawan River and a significant relationship was found between physicochemical soil conditions and aboveground biomass of butterburs. This indicates that extremely large Rawanbuki plants could be caused by these high nutrient concentrations and moisture contents in the soils. A manipulation experiment showed that fertilization simulated the growth environment along the Rawan River and enhanced the stem height and stem diameter of butterburs. This study concluded that the extremely large butterburs are caused by a large amount of nutrients exported from upland areas. These results are the first demonstration of the role of stream water nutrients in enlarging agricultural crops.

Risk assessment of fluoride and arsenic in groundwater and a scenario analysis for reducing exposure in Inner Mongolia.

In contrast to Mongolia, family-owned land in Inner Mongolia is separated by fences, preventing the free movement of nomads and leading people to rely heavily on the same source of groundwater for their domestic water needs. Therefore, it is important to clarify groundwater quality and understand the associated human health concerns. To evaluate the risks of drinking groundwater to human health in Inner Mongolia, we examined groundwater quality by field surveys, a human health risk analysis, and a scenario analysis. During the summer of 2015 in Inner Mongolia, we measured the concentrations of major ions, metals, metalloids, and rare earth metals in groundwater samples (n = 32) and river water samples (n = 10), for which there were no known anthropogenic contamination sources. In addition, as part of a scenario analysis, samples of tap water (n = 1), snowmelt (n = 1), and bottled water (n = 1) were also evaluated. We used our analytical results to calculate hazard quotient (HQ) ratios by means of a probabilistic risk assessment method. The results indicated that residents who drank groundwater every day might have risk concerns for F- (mean ± standard deviation, 2.51 ± 1.80 mg L-1; range, 0.07-7.70 mg L-1) and As (6.49 ± 9.64 µg L-1; 0.31-47.0 µg L-1). We observed no relationships between well depth or any geophysical variation and groundwater quality. On the basis of the scenario analysis results, we concluded that using snow as a source of drinking water in winter could reduce health risks associated with using groundwater for this population in Inner Mongolia.

Nutrient deficiency promotes male-biased apparent sex ratios at the ramet level in the dioecious plant Myrica gale var. tomentosa in oligotrophic environments in bogs.

In populations of dioecious plants, the differences in the cost of reproduction between male and female plants can promote a male-biased sex ratio. In this study, we examine the macronutrient levels in tissues of the dioecious wetland shrub Myrica gale to identify the cost of reproduction for male and female plants and to examine the effect of nutrients on the apparent sex ratio at the ramet level. We examined plants across 12 populations of M. gale inhabiting bogs and fens in Japan. For each population, we used line transects to estimate the apparent sex ratio and measured the concentrations of nitrogen (N), phosphorus (P), and potassium (K) in the leaves sampled from male and female plants and in the fruits from female plants. For five of the populations, we calculated the flowering frequency, mortality, and the recruitment rate (as the rate of clonal propagation). We found that the proportion of females was positively affected, and the male bias of sex ratios reduced, by increases in P concentration in leaves sampled from female plants. Neither mortality nor recruitment was affected by sex or by the nutrient concentration (P, K). The flowering frequency was not affected by sex or by K concentration, but decreased with decreases in the P concentration measured in leaves. This study confirmed that reproduction in M. gale is P-limited. We found no distinct differences in the flowering frequency, mortality, or recruitment rate between the male and female plants.