Deep learning-based vessel automatic recognition for laparoscopic right hemicolectomy.

BACKGROUND: In laparoscopic right hemicolectomy (RHC) for right-sided colon cancer, accurate recognition of the vascular anatomy is required for appropriate lymph node harvesting and safe operative procedures. We aimed to develop a deep learning model that enables the automatic recognition and visualization of major blood vessels in laparoscopic RHC. MATERIALS AND METHODS: This was a single-institution retrospective feasibility study. Semantic segmentation of three vessel areas, including the superior mesenteric vein (SMV), ileocolic artery (ICA), and ileocolic vein (ICV), was performed using the developed deep learning model. The Dice coefficient, recall, and precision were utilized as evaluation metrics to quantify the model performance after fivefold cross-validation. The model was further qualitatively appraised by 13 surgeons, based on a grading rubric to assess its potential for clinical application. RESULTS: In total, 2624 images were extracted from 104 laparoscopic colectomy for right-sided colon cancer videos, and the pixels corresponding to the SMV, ICA, and ICV were manually annotated and utilized as training data. SMV recognition was the most accurate, with all three evaluation metrics having values above 0.75, whereas the recognition accuracy of ICA and ICV ranged from 0.53 to 0.57 for the three evaluation metrics. Additionally, all 13 surgeons gave acceptable ratings for the possibility of clinical application in rubric-based quantitative evaluations. CONCLUSION: We developed a DL-based vessel segmentation model capable of achieving feasible identification and visualization of major blood vessels in association with RHC. This model may be used by surgeons to accomplish reliable navigation of vessel visualization.

Deep-learning-based semantic segmentation of autonomic nerves from laparoscopic images of colorectal surgery: an experimental pilot study.

BACKGROUND: The preservation of autonomic nerves is the most important factor in maintaining genitourinary function in colorectal surgery; however, these nerves are not clearly recognisable, and their identification is strongly affected by the surgical ability. Therefore, this study aimed to develop a deep learning model for the semantic segmentation of autonomic nerves during laparoscopic colorectal surgery and to experimentally verify the model through intraoperative use and pathological examination. MATERIALS AND METHODS: The annotation data set comprised videos of laparoscopic colorectal surgery. The images of the hypogastric nerve (HGN) and superior hypogastric plexus (SHP) were manually annotated under a surgeon's supervision. The Dice coefficient was used to quantify the model performance after five-fold cross-validation. The model was used in actual surgeries to compare the recognition timing of the model with that of surgeons, and pathological examination was performed to confirm whether the samples labelled by the model from the colorectal branches of the HGN and SHP were nerves. RESULTS: The data set comprised 12 978 video frames of the HGN from 245 videos and 5198 frames of the SHP from 44 videos. The mean (±SD) Dice coefficients of the HGN and SHP were 0.56 (±0.03) and 0.49 (±0.07), respectively. The proposed model was used in 12 surgeries, and it recognised the right HGN earlier than the surgeons did in 50.0% of the cases, the left HGN earlier in 41.7% of the cases and the SHP earlier in 50.0% of the cases. Pathological examination confirmed that all 11 samples were nerve tissue. CONCLUSION: An approach for the deep-learning-based semantic segmentation of autonomic nerves was developed and experimentally validated. This model may facilitate intraoperative recognition during laparoscopic colorectal surgery.

Development and Validation of a Model for Laparoscopic Colorectal Surgical Instrument Recognition Using Convolutional Neural Network-Based Instance Segmentation and Videos of Laparoscopic Procedures.

Importance: Deep learning-based automatic surgical instrument recognition is an indispensable technology for surgical research and development. However, pixel-level recognition with high accuracy is required to make it suitable for surgical automation. Objective: To develop a deep learning model that can simultaneously recognize 8 types of surgical instruments frequently used in laparoscopic colorectal operations and evaluate its recognition performance. Design, Setting, and Participants: This quality improvement study was conducted at a single institution with a multi-institutional data set. Laparoscopic colorectal surgical videos recorded between April 1, 2009, and December 31, 2021, were included in the video data set. Deep learning-based instance segmentation, an image recognition approach that recognizes each object individually and pixel by pixel instead of roughly enclosing with a bounding box, was performed for 8 types of surgical instruments. Main Outcomes and Measures: Average precision, calculated from the area under the precision-recall curve, was used as an evaluation metric. The average precision represents the number of instances of true-positive, false-positive, and false-negative results, and the mean average precision value for 8 types of surgical instruments was calculated. Five-fold cross-validation was used as the validation method. The annotation data set was split into 5 segments, of which 4 were used for training and the remainder for validation. The data set was split at the per-case level instead of the per-frame level; thus, the images extracted from an intraoperative video in the training set never appeared in the validation set. Validation was performed for all 5 validation sets, and the average mean average precision was calculated. Results: In total, 337 laparoscopic colorectal surgical videos were used. Pixel-by-pixel annotation was manually performed for 81 760 labels on 38 628 static images, constituting the annotation data set. The mean average precisions of the instance segmentation for surgical instruments were 90.9% for 3 instruments, 90.3% for 4 instruments, 91.6% for 6 instruments, and 91.8% for 8 instruments. Conclusions and Relevance: A deep learning-based instance segmentation model that simultaneously recognizes 8 types of surgical instruments with high accuracy was successfully developed. The accuracy was maintained even when the number of types of surgical instruments increased. This model can be applied to surgical innovations, such as intraoperative navigation and surgical automation.

Novel complex class 1 integron bearing an ISCR1 element in an Escherichia coli isolate carrying the blaCTX-M-14 gene.

This work identifies an ISCR1-related bla(CTX-M-14) gene, which has never been reported before, from a clinical isolate of Escherichia coli. The bla(CTX-M-14) gene was preceded by an ISCR1 element that was followed by a class 1 integron containing three different insert gene cassettes, i.e., dfrA12, orfF, and aadA2.

Genetic and biochemical characterization of GES-5, an extended-spectrum class A beta-lactamase from Klebsiella pneumoniae.

The present study was conducted to characterize a new class 1 integron containing the blaGES-5 gene cassette in Klebsiella pneumoniae clinical isolate CHAK36 and measure the kinetic parameters of GES-5 beta-lactamase. Long-range polymerase chain reactions (PCRs) and sequence analysis were performed to identify and analyze the blaGES-5 gene cassette-containing integrons. Kinetic parameters were determined from purified GES-5. Sequencing of the 6190-bp PCR amplicon from K. pneumoniae CHAK36 isolate revealed the new structure of class 1 integron. The integron has 3 unique gene cassettes (blaGES-5-aac(6')-IIa-blaOXA-17/orf4), but the 59-base element of the blaOXA-17 gene cassette was interrupted by a putative transposase gene, orf4. The kinetic parameters of GES-5 showed its broad-spectrum activity against most beta-lactams, including benzylpenicillin, cefaloridine, cefotaxime, and imipenem. This work shows that the blaGES-5 gene was located on a new class 1 integron as a gene cassette. Our kinetic characterizations show that GES-5 was more active against impenem than GES-2 and GES-4.

Detection of extended-spectrum beta-lactamases by using boronic acid as an AmpC beta-lactamase inhibitor in clinical isolates of Klebsiella spp. and Escherichia coli.

We evaluated highly sensitive methods using boronic acid (BA) to detect extended-spectrum beta-lactamase (ESBL) production. A total of 182 clinical isolates of Klebsiella spp. (n = 118) and Escherichia coli (n = 64) were analyzed: 62 harbored only ESBLs, 80 harbored both ESBLs and plasmid-mediated AmpC beta-lactamases (pAmpCs), and 40 harbored only pAmpCs. The CLSI confirmatory test detected all isolates that produce only ESBLs but detected 85% of isolates that produce both enzymes. When a >/=5-mm increase in the zone diameter of either the cefotaxime (CTX) or the ceftazidime (CAZ) disk in the presence of both clavulanic acid (CA) and BA was considered to be a positive result, the test detected all isolates that harbor ESBLs (+/- pAmpCs) but showed frequent false-positive results (50%) for isolates that produce only pAmpCs. Meanwhile, when a >/=3-mm increase in the zone diameter of either the CTX/BA or the CAZ/BA disk in the presence of CA was considered to be a positive result, the test also detected all isolates that harbor ESBLs (+/- pAmpCs) and showed less frequent false-positive results (5%) in isolates that produce only pAmpCs. The latter new interpretive guideline has enhanced detection of ESBLs in clinical isolates of Klebsiella spp. and Escherichia coli and allowed detection of an ESBL even when potentially masked by a pAmpC.

Emergence of CTX-M-12 extended-spectrum beta-lactamase-producing Escherichia coli in Korea.

OBJECTIVES: To characterize CTX-M-12 extended-spectrum beta-lactamase (ESBL) produced by clinical Escherichia coli isolates and to investigate its genetic environment. METHODS: Antimicrobial susceptibilities were determined by disc diffusion and agar dilution methods, and the double-disc synergy test was carried out. Detection of genes encoding class A beta-lactamases was performed by PCR amplification, and the genetic environments of the bla(CTX-M-12) genes were investigated by PCR and sequencing of the regions surrounding the genes. Kinetic parameters were determined from purified CTX-M-12. RESULTS: Sequence data for the CTX-M-1 cluster from three clinical E. coli isolates indicated the presence of CTX-M-12. An ISEcp1 insertion sequence was located 49 bp upstream of bla(CTX-M-12) in all three E. coli isolates. CTX-M-12 had a more potent hydrolytic activity against cefotaxime than against ceftazidime and was encoded on a self-transferable approximately 18 kbp plasmid. CONCLUSIONS: This work shows that CTX-M-12, which confers high-level resistance to cefotaxime but not to ceftazidime, has emerged in Korea. The bla(CTX-M-12) gene was associated with an upstream ISEcp1 insertion sequence.