Identifying key mechanisms leading to visual recognition errors for missed colorectal polyps using eye-tracking technology.

BACKGROUND AND AIM: Lack of visual recognition of colorectal polyps may lead to interval cancers. The mechanisms contributing to perceptual variation, particularly for subtle and advanced colorectal neoplasia, have scarcely been investigated. We aimed to evaluate visual recognition errors and provide novel mechanistic insights. METHODS: Eleven participants (seven trainees and four medical students) evaluated images from the UCL polyp perception dataset, containing 25 polyps, using eye-tracking equipment. Gaze errors were defined as those where the lesion was not observed according to eye-tracking technology. Cognitive errors occurred when lesions were observed but not recognized as polyps by participants. A video study was also performed including 39 subtle polyps, where polyp recognition performance was compared with a convolutional neural network. RESULTS: Cognitive errors occurred more frequently than gaze errors overall (65.6%), with a significantly higher proportion in trainees (P = 0.0264). In the video validation, the convolutional neural network detected significantly more polyps than trainees and medical students, with per-polyp sensitivities of 79.5%, 30.0%, and 15.4%, respectively. CONCLUSIONS: Cognitive errors were the most common reason for visual recognition errors. The impact of interventions such as artificial intelligence, particularly on different types of perceptual errors, needs further investigation including potential effects on learning curves. To facilitate future research, a publicly accessible visual perception colonoscopy polyp database was created.

Care at the first postnatal hour in two hospitals of the Adequate Birth Project: qualitative analysis of experiences in two stages of the Healthy Birth research.

BACKGROUND:  The Adequate Childbirth Project (PPA) is a quality improvement project that aims to enhance normal delivery and reduce cesarean sections with no clinical indication in the Brazilian supplementary health care system. This study aims to analyze the care model of the first postpartum hour in hospitals that participated in the PPA. METHODS: Qualitative analysis based on the narrative of 102 women attended at two hospitals participating in the evaluative "Healthy Birth" research that analyzed the degree of implementation and the effects of the PPA. We assessed three practices within the first hour after delivery: skin-to-skin contact, breastfeeding and appropriate clamping of the umbilical cord. Data was collected through semi-structured interviews by telephone and submitted to thematic content analysis. RESULTS: The categories that emerged from the analysis of the results were "Dimension of time and care expressed in the lived experience" and "Interferences in care in the first hour of life". In the first category, women reported that in the first hour after delivery the newborn was placed on the mother's chest, but the length of time of the newborn's stay in skin-to-skin contact was less than one hour. This experience, even in a shorter period of time, was said to be positive by the women interviewed. Two barriers were observed: interruption of skin-to-skin contact for neonatal care and the transfer to the recovery room, both separating baby from mother without observing the duration of the "golden hour". It was identified that a process of improvement of the quality of care for childbirth is underway, with a gradual incorporation of recommended practices for care in newborn's first hour of life. CONCLUSIONS: Women reported access to the three care practices at two hospitals participating in the PPA quality improvement project. All practices were valued by women as a positive experience and should be promoted. Information during antenatal care to increase women´s autonomy, review of hospital practices to reduce barriers, and support from health care providers during the first hour after birth are needed to improve the implementation of these practices and access to their health benefits.

This study aims to analyze the care model of the first postpartum hour offered by two hospitals participating in the Adequate Childbirth Project (PPA), a quality improvement project to enhance normal delivery and reduce unnecessary cesarean sections in Brazilian private hospital. It is a qualitative analysis, based on the narrative of 102 women attended at two hospitals participating in the PPA. Categories that emerged from the analysis: "First hour; dimension of time and care expressed in the lived experience" and "Interferences in care in the first hour of life". Most women expressed a chronological time of skin-to-skin contact far from the ideal recommended in the first postpartum hour; however, they valued the experience and its meaning. Two barriers were observed in this care process: the interruption of skin-to-skin contact for neonatal care and the transfer to the recovery room, without observing the duration of the "golden hour". We can conclude that women evaluated the service positively, with indications that point to the sustainability of the PPA. Information during antenatal care to increase women´s autonomy are needed to improve the implementation of these practices and access to their health benefits.

Polyp characterization using deep learning and a publicly accessible polyp video database.

OBJECTIVES: Convolutional neural networks (CNN) for computer-aided diagnosis of polyps are often trained using high-quality still images in a single chromoendoscopy imaging modality with sessile serrated lesions (SSLs) often excluded. This study developed a CNN from videos to classify polyps as adenomatous or nonadenomatous using standard narrow-band imaging (NBI) and NBI-near focus (NBI-NF) and created a publicly accessible polyp video database. METHODS: We trained a CNN with 16,832 high and moderate quality frames from 229 polyp videos (56 SSLs). It was evaluated with 222 polyp videos (36 SSLs) across two test-sets. Test-set I consists of 14,320 frames (157 polyps, 111 diminutive). Test-set II, which is publicly accessible, 3317 video frames (65 polyps, 41 diminutive), which was benchmarked with three expert and three nonexpert endoscopists. RESULTS: Sensitivity for adenoma characterization was 91.6% in test-set I and 89.7% in test-set II. Specificity was 91.9% and 88.5%. Sensitivity for diminutive polyps was 89.9% and 87.5%; specificity 90.5% and 88.2%. In NBI-NF, sensitivity was 89.4% and 89.5%, with a specificity of 94.7% and 83.3%. In NBI, sensitivity was 85.3% and 91.7%, with a specificity of 87.5% and 90.0%, respectively. The CNN achieved preservation and incorporation of valuable endoscopic innovations (PIVI)-1 and PIVI-2 thresholds for each test-set. In the benchmarking of test-set II, the CNN was significantly more accurate than nonexperts (13.8% difference [95% confidence interval 3.2-23.6], P = 0.01) with no significant difference with experts. CONCLUSIONS: A single CNN can differentiate adenomas from SSLs and hyperplastic polyps in both NBI and NBI-NF. A publicly accessible NBI polyp video database was created and benchmarked.

Performance of artificial intelligence for detection of subtle and advanced colorectal neoplasia.

OBJECTIVES: There is uncertainty regarding the efficacy of artificial intelligence (AI) software to detect advanced subtle neoplasia, particularly flat lesions and sessile serrated lesions (SSLs), due to low prevalence in testing datasets and prospective trials. This has been highlighted as a top research priority for the field. METHODS: An AI algorithm was evaluated on four video test datasets containing 173 polyps (35,114 polyp-positive frames and 634,988 polyp-negative frames) specifically enriched with flat lesions and SSLs, including a challenging dataset containing subtle advanced neoplasia. The challenging dataset was also evaluated by eight endoscopists (four independent, four trainees, according to the Joint Advisory Group on gastrointestinal endoscopy [JAG] standards in the UK). RESULTS: In the first two video datasets, the algorithm achieved per-polyp sensitivities of 100% and 98.9%. Per-frame sensitivities were 84.1% and 85.2%. In the subtle dataset, the algorithm detected a significantly higher number of polyps (P < 0.0001), compared to JAG-independent and trainee endoscopists, achieving per-polyp sensitivities of 79.5%, 37.2% and 11.5%, respectively. Furthermore, when considering subtle polyps detected by both the algorithm and at least one endoscopist, the AI detected polyps significantly faster on average. CONCLUSIONS: The AI based algorithm achieved high per-polyp sensitivities for advanced colorectal neoplasia, including flat lesions and SSLs, outperforming both JAG independent and trainees on a very challenging dataset containing subtle lesions that could have been overlooked easily and contribute to interval colorectal cancer. Further prospective trials should evaluate AI to detect subtle advanced neoplasia in higher risk populations for colorectal cancer.

Widening siamese architectures for stereo matching.

Computational stereo is one of the classical problems in computer vision. Numerous algorithms and solutions have been reported in recent years focusing on developing methods for computing similarity, aggregating it to obtain spatial support and finally optimizing an energy function to find the final disparity. In this paper, we focus on the feature extraction component of stereo matching architecture and we show standard CNNs operation can be used to improve the quality of the features used to find point correspondences. Furthermore, we use a simple space aggregation that hugely simplifies the correlation learning problem, allowing us to better evaluate the quality of the features extracted. Our results on benchmark data are compelling and show promising potential even without refining the solution.

Automated colonoscopy withdrawal phase duration estimation using cecum detection and surgical tasks classification.

Colorectal cancer is the third most common type of cancer with almost two million new cases worldwide. They develop from neoplastic polyps, most commonly adenomas, which can be removed during colonoscopy to prevent colorectal cancer from occurring. Unfortunately, up to a quarter of polyps are missed during colonoscopies. Studies have shown that polyp detection during a procedure correlates with the time spent searching for polyps, called the withdrawal time. The different phases of the procedure (cleaning, therapeutic, and exploration phases) make it difficult to precisely measure the withdrawal time, which should only include the exploration phase. Separating this from the other phases requires manual time measurement during the procedure which is rarely performed. In this study, we propose a method to automatically detect the cecum, which is the start of the withdrawal phase, and to classify the different phases of the colonoscopy, which allows precise estimation of the final withdrawal time. This is achieved using a Resnet for both detection and classification trained with two public datasets and a private dataset composed of 96 full procedures. Out of 19 testing procedures, 18 have their withdrawal time correctly estimated, with a mean error of 5.52 seconds per minute per procedure.

Spatio-temporal classification for polyp diagnosis.

Colonoscopy remains the gold standard investigation for colorectal cancer screening as it offers the opportunity to both detect and resect pre-cancerous polyps. Computer-aided polyp characterisation can determine which polyps need polypectomy and recent deep learning-based approaches have shown promising results as clinical decision support tools. Yet polyp appearance during a procedure can vary, making automatic predictions unstable. In this paper, we investigate the use of spatio-temporal information to improve the performance of lesions classification as adenoma or non-adenoma. Two methods are implemented showing an increase in performance and robustness during extensive experiments both on internal and openly available benchmark datasets.

Polyp detection on video colonoscopy using a hybrid 2D/3D CNN.

Colonoscopy is the gold standard for early diagnosis and pre-emptive treatment of colorectal cancer by detecting and removing colonic polyps. Deep learning approaches to polyp detection have shown potential for enhancing polyp detection rates. However, the majority of these systems are developed and evaluated on static images from colonoscopies, whilst in clinical practice the treatment is performed on a real-time video feed. Non-curated video data remains a challenge, as it contains low-quality frames when compared to still, selected images often obtained from diagnostic records. Nevertheless, it also embeds temporal information that can be exploited to increase predictions stability. A hybrid 2D/3D convolutional neural network architecture for polyp segmentation is presented in this paper. The network is used to improve polyp detection by encompassing spatial and temporal correlation of the predictions while preserving real-time detections. Extensive experiments show that the hybrid method outperforms a 2D baseline. The proposed architecture is validated on videos from 46 patients and on the publicly available SUN polyp database. A higher performance and increased generalisability indicate that real-world clinical implementations of automated polyp detection can benefit from the hybrid algorithm and the inclusion of temporal information.

Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions.

Computer-aided diagnosis offers a promising solution to reduce variation in colonoscopy performance. Pooled miss rates for polyps are as high as 22%, and associated interval colorectal cancers after colonoscopy are of concern. Optical biopsy, whereby in-vivo classification of polyps based on enhanced imaging replaces histopathology, has not been incorporated into routine practice because it is limited by interobserver variability and generally only meets accepted standards in expert settings. Real-time decision-support software has been developed to detect and characterise polyps, and also to offer feedback on the technical quality of inspection. Some of the current algorithms, particularly with recent advances in artificial intelligence techniques, match human expert performance for optical biopsy. In this Review, we summarise the evidence for clinical applications of computer-aided diagnosis and artificial intelligence in colonoscopy.

Towards computer-assisted TTTS: Laser ablation detection for workflow segmentation from fetoscopic video.

PURPOSE: Intrauterine foetal surgery is the treatment option for several congenital malformations. For twin-to-twin transfusion syndrome (TTTS), interventions involve the use of laser fibre to ablate vessels in a shared placenta. The procedure presents a number of challenges for the surgeon, and computer-assisted technologies can potentially be a significant support. Vision-based sensing is the primary source of information from the intrauterine environment, and hence, vision approaches present an appealing approach for extracting higher level information from the surgical site. METHODS: In this paper, we propose a framework to detect one of the key steps during TTTS interventions-ablation. We adopt a deep learning approach, specifically the ResNet101 architecture, for classification of different surgical actions performed during laser ablation therapy. RESULTS: We perform a two-fold cross-validation using almost 50 k frames from five different TTTS ablation procedures. Our results show that deep learning methods are a promising approach for ablation detection. CONCLUSION: To our knowledge, this is the first attempt at automating photocoagulation detection using video and our technique can be an important component of a larger assistive framework for enhanced foetal therapies. The current implementation does not include semantic segmentation or localisation of the ablation site, and this would be a natural extension in future work.

Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge.

Colonoscopy is the gold standard for colon cancer screening though some polyps are still missed, thus preventing early disease detection and treatment. Several computational systems have been proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack of publicly available annotated databases has made it difficult to compare methods and to assess if they achieve performance levels acceptable for clinical use. The Automatic Polyp Detection sub-challenge, conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org) at the international conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2015, was an effort to address this need. In this paper, we report the results of this comparative evaluation of polyp detection methods, as well as describe additional experiments to further explore differences between methods. We define performance metrics and provide evaluation databases that allow comparison of multiple methodologies. Results show that convolutional neural networks are the state of the art. Nevertheless, it is also demonstrated that combining different methodologies can lead to an improved overall performance.