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.

Impact of AI system on recognition for anatomical landmarks related to reducing bile duct injury during laparoscopic cholecystectomy.

BACKGROUND: According to the National Clinical Database of Japan, the incidence of bile duct injury (BDI) during laparoscopic cholecystectomy has hovered around 0.4% for the last 10 years and has not declined. On the other hand, it has been found that about 60% of BDI occurrences are due to misidentifying anatomical landmarks. However, the authors developed an artificial intelligence (AI) system that gave intraoperative data to recognize the extrahepatic bile duct (EHBD), cystic duct (CD), inferior border of liver S4 (S4), and Rouviere sulcus (RS). The purpose of this research was to evaluate how the AI system affects landmark identification. METHODS: We prepared a 20-s intraoperative video before the serosal incision of Calot's triangle dissection and created a short video with landmarks overwritten by AI. The landmarks were defined as landmark (LM)-EHBD, LM-CD, LM-RS, and LM-S4. Four beginners and four experts were recruited as subjects. After viewing a 20-s intraoperative video, subjects annotated the LM-EHBD and LM-CD. Then, a short video is shown with the AI overwriting landmark instructions; if there is a change in each perspective, the annotation is changed. The subjects answered a three-point scale questionnaire to clarify whether the AI teaching data advanced their confidence in verifying the LM-RS and LM-S4. Four external evaluation committee members investigated the clinical importance. RESULTS: In 43 of 160 (26.9%) images, the subjects transformed their annotations. Annotation changes were primarily observed in the gallbladder line of the LM-EHBD and LM-CD, and 70% of these shifts were considered safer changes. The AI-based teaching data encouraged both beginners and experts to affirm the LM-RS and LM-S4. CONCLUSION: The AI system provided significant awareness to beginners and experts and prompted them to identify anatomical landmarks linked to reducing BDI.

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).

Do Dolls Resemble Their Makers?

Many often say that people resemble their pets or that the faces of manga characters and Buddha statues resemble those of their artists. Previous studies demonstrated that participants could match dogs with their owners, suggesting that pets resemble their owners. Other studies also demonstrated that people can match personal belongings, including inanimate objects, to their owners. However, it is unknown whether people tend to make objects that resemble themselves. In this study, we examined whether people tend to make objects that resemble themselves with dolls made of cloth as stimuli. The results demonstrated that people tend to project themselves into dolls, even in the case of amateur college students. The mere exposure effect or the algorithm "self seeks like" may be at play in not only people's selection of pets but also their making of objects.

Effect of personality traits on matching dolls and their makers.

Studies have shown that possessions such as cars and dogs resemble their owners, and products such as dolls resemble their makers even when students make them. We conducted three experiments to examine which part of the dolls resembled their makers. The results demonstrated that people match dolls to their makers when their eye regions were masked (Experiment 1), and the matching is possible even with the back views of the dolls (Experiment 2). These results may indicate people match dolls to their makers based on resemblances other than faces. Experiment 3 demonstrated that no effect of resemblance in personality traits was observed when dolls' faces were visible. However, the resemblance of personality traits assumed by the dolls and their makers play an important role in the matching judgment when dolls' faces were invisible (because of back views).

An efficient method for high-fidelity messenger RNA amplification from a small amount of total RNA.

Comprehensive analyses of gene expression have been carried out by the development of microarrays and deep sequencers. However, it is difficult to obtain comprehensive information on gene expression from a small amount of ribonucleic acid (RNA). Therefore, we investigated the reproducibility and application of T7 RNA polymerase-mediated transcription, adaptor ligation and polymerase chain reaction (PCR) amplification, followed by T7 transcription (TALPAT), an efficient method for amplifying poly (A)-positive RNA, such as messenger RNA (mRNA). When amplified complementary RNA (cRNA) was electrophoresed, a large number of amplified cRNA was detected in the size of 0.2-0.5 kb. This indicates that the region up to 0.2-0.5 kb from the 3' end of the original mRNA was amplified by the TALPAT method. Seven housekeeping genes, glyceraldehyde-3-phosphate dehydrogenase (GAPDH), hydroxymethylbilane synthase (HMBS), hypoxanthine phosphoribosyltransferase (HPRT1), ribosomal protein L13a (RPL13A), succinate dehydrogenase complex (SDHA), TATA box-binding protein (TBP) and ubiquitin C (UBC), showed high reproducibility (square of the correlation coefficient, R2=0.9954), according to scatter plots of Ct values obtained in the real-time PCR analysis of amplified cRNA. In addition, relative expression ratios of amplified cRNA of the seven housekeeping genes were approximately equal to the ratio of the original RNA solution. Furthermore, cRNA was amplified from 20 pg total RNA. In the present study, we confirmed the characteristics of mRNA amplification using the TALPAT method. This method may be applicable to mRNA and poly (A)-positive non-coding RNA amplification, using a small amount of RNA from single, laser-captured and sorted cells, as well as exosomes from serum, urine and body fluids.

Exosomes secreted from human colorectal cancer cell lines contain mRNAs, microRNAs and natural antisense RNAs, that can transfer into the human hepatoma HepG2 and lung cancer A549 cell lines.

Exosomes are microvesicles that are released from various cells into the extracellular space. It has been reported that the components within exosomes vary according to the type of secreted cell. In the present study, we investigated the tetraspanin family proteins CD63, CD9 and CD81 as useful collection markers of exosomes derived from the three colorectal cancer (CRC) cell lines HCT-15, SW480 and WiDr. In addition, we aimed to detect the mRNAs, microRNAs and natural antisense RNAs within the exosomes secreted from the three CRC cell lines. Furthermore, we examined whether exosomes containing their RNAs were transferred into the hepatoma cell line HepG2 and lung cancer cell line A549. CD81 was detected in exosomes secreted from the three CRC cell lines. This result indicates that CD81 can be a collection marker of exosomes derived from the three CRC cell lines. When the RNA species within exosomes derived from the three CRC cell lines were examined, the mRNAs of housekeeping genes such as ACTB and GAPDH, the microRNAs such as miR-21, miR-192 and miR-221, and the natural antisense RNAs of LRRC24, MDM2 and CDKN1A genes, were detected. We discovered their natural antisense RNAs within exosomes for the first time in the present study. Furthermore, PKH67-labeled exosomes derived from the CRC cell lines were taken up into HepG2 and A549 cells. These findings indicate that the intracellular RNAs enclosed within exosomes are secreted to the outside, and exosomes derived from the CRC cell lines are transferred into HepG2 and A549 cells. In conclusion, we reveal that exosomes derived from the CRC cell lines contain mRNAs, microRNAs and natural antisense RNAs, and can be delivered into HepG2 and A549 cells. These findings indicate that exosomal RNAs can shuttle between cells, and may be involved in the regulation of gene expression in recipient cells.