The Effect of Vitamin D3 and Valproic Acid on the Maturation of Human-Induced Pluripotent Stem Cell-Derived Enterocyte-Like Cells.

Cytochrome P450 3A4 (CYP3A4) is involved in first-pass metabolism in the small intestine and is heavily implicated in oral drug bioavailability and pharmacokinetics. We previously reported that vitamin D3 (VD3), a known CYP enzyme inducer, induces functional maturation of iPSC-derived enterocyte-like cells (iPSC-ent). Here, we identified a Notch activator and CYP modulator valproic acid (VPA), as a promotor for the maturation of iPSC-ent. We performed bulk RNA sequencing to investigate the changes in gene expression during the differentiation and maturation periods of these cells. VPA potentiated gene expression of key enterocyte markers ALPI, FABP2, and transporters such as SULT1B1. RNA-sequencing analysis further elucidated several function-related pathways involved in fatty acid metabolism, significantly upregulated by VPA when combined with VD3. Particularly, VPA treatment in tandem with VD3 significantly upregulated key regulators of enterohepatic circulation, such as FGF19, apical bile acid transporter SLCO1A2 and basolateral bile acid transporters SLC51A and SLC51B. To sum up, we could ascertain the genetic profile of our iPSC-ent cells to be specialized toward fatty acid absorption and metabolism instead of transporting other nutrients, such as amino acids, with the addition of VD3 and VPA in tandem. Together, these results suggest the possible application of VPA-treated iPSC-ent for modelling enterohepatic circulation.

Understanding Flexdispersion: Structure-Function Relationship Studies of Organic Amphiphilic Ligands.

Since inorganic nanoparticles have unique properties that differ from those of bulk materials, their material applications have attracted attention in various fields. In order to utilize inorganic nanoparticles for functional materials, they must be dispersed without agglomeration. Therefore, the surfaces of inorganic nanoparticles are typically modified with organic ligands to improve their dispersibility. Nevertheless, the relationship between the tail group structure in organic ligands and the dispersibility of inorganic nanoparticles in organic solvents remains poorly understood. We previously developed amphiphilic ligands that consist of ethylene glycol chains and alkyl chains to disperse inorganic nanoparticles in a variety of organic solvents. However, the structural requirements for amphiphilic ligands to "flexibly" disperse nanoparticles in less polar to polar solvents are still unclear. Here, we designed and synthesized several phosphonic acid ligands for structure-function relationship studies of flexdispersion. Dynamic light scattering analysis and visible light transmittance measurements revealed that the ratio of alkyl/ethylene glycol chains in organic ligands alone does not determine the dispersibility of the nanoparticles in organic solvents, but the arrangement of the individual chains also has an effect. From a practical application standpoint, it is preferable to design ligands with ethylene glycol chains on the outside relative to the particle surface.

AAA+ Ring and linker swing mechanism in the dynein motor.

Dynein ATPases power diverse microtubule-based motilities. Each dynein motor domain comprises a ring-like head containing six AAA+ modules and N- and C-terminal regions, together with a stalk that binds microtubules. How these subdomains are arranged and generate force remains poorly understood. Here, using electron microscopy and image processing of tagged and truncated Dictyostelium cytoplasmic dynein constructs, we show that the heart of the motor is a hexameric ring of AAA+ modules, with the stalk emerging opposite the primary ATPase site (AAA1). The C-terminal region is not an integral part of the ring but spans between AAA6 and near the stalk base. The N-terminal region includes a lever-like linker whose N terminus swings by approximately 17 nm during the ATPase cycle between AAA2 and the stalk base. Together with evidence of stalk tilting, which may communicate changes in microtubule binding affinity, these findings suggest a model for dynein's structure and mechanism.

Comparison of clinical utility of deep learning-based systems for small-bowel capsule endoscopy reading.

BACKGROUND AND AIM: Convolutional neural network (CNN) systems that automatically detect abnormalities from small-bowel capsule endoscopy (SBCE) images are still experimental, and no studies have directly compared the clinical usefulness of different systems. We compared endoscopist readings using an existing and a novel CNN system in a real-world SBCE setting. METHODS: Thirty-six complete SBCE videos, including 43 abnormal lesions (18 mucosal breaks, 8 angioectasia, and 17 protruding lesions), were retrospectively prepared. Three reading processes were compared: (A) endoscopist readings without CNN screening, (B) endoscopist readings after an existing CNN screening, and (C) endoscopist readings after a novel CNN screening. RESULTS: The mean number of small-bowel images was 14 747 per patient. Among these images, existing and novel CNN systems automatically captured 24.3% and 9.4% of the images, respectively. In this process, both systems extracted all 43 abnormal lesions. Next, we focused on the clinical usefulness. The detection rates of abnormalities by trainee endoscopists were not significantly different across the three processes: A, 77%; B, 67%; and C, 79%. The mean reading time of the trainees was the shortest during process C (10.1 min per patient), followed by processes B (23.1 min per patient) and A (33.6 min per patient). The mean psychological stress score while reading videos (scale, 1-5) was the lowest in process C (1.8) but was not significantly different between processes B (2.8) and A (3.2). CONCLUSIONS: Our novel CNN system significantly reduced endoscopist reading time and psychological stress while maintaining the detectability of abnormalities. CNN performance directly affects clinical utility and should be carefully assessed.

Role of a novel ER-resident glycoprotein Mtc6/Ehg2 in high-pressure growth: Stability of tryptophan permease Tat2 in Saccharomyces cerevisiae.

Deep-sea organisms are subjected to extreme conditions; therefore, understanding their adaptive strategies is crucial. We utilize Saccharomyces cerevisiae as a model to investigate pressure-dependent protein regulation and piezo-adaptation. Using yeast deletion library analysis, we identified six poorly characterized genes that are crucial for high-pressure growth, forming novel functional modules associated with cell growth. In this study, we aimed to unravel the molecular mechanisms of high-pressure adaptation in S. cerevisiae, focusing on the role of MTC6. MTC6, the gene encoding the novel glycoprotein Mtc6/Ehg2, was found to stabilize tryptophan permease Tat2, ensuring efficient tryptophan uptake and growth under high pressure at 25 MPa. The loss of MTC6 led to promoted vacuolar degradation of Tat2, depending on the Rsp5-Bul1 ubiquitin ligase complex. These findings enhance our understanding of deep-sea adaptations and stress biology, with broad implications for biotechnology, environmental microbiology, and evolutionary insights across species.

A specific plasma amino acid profile in the Insulin2Q104del Kuma mice at the diabetic state and reversal from hyperglycemia.

The metabolites in the plasma serve as potential biomarkers of disease. We previously established an early-onset diabetes mouse model, Ins2+/Q104del Kuma mice, under a severe immune-deficient (Rag-2/Jak3 double-deficient in BALB/c) background. Here, we revealed the differences in plasma amino acid profiles between Kuma and the wild-type mice. We observed an early reduction in glucogenic and ketogenic amino acids, a late increase in branched-chain amino acids (BCAAs) and succinyl CoA-related amino acids, and a trend of increasing ketogenic amino acids in Kuma mice than in the wild-type mice. Kuma mice exhibited hyperglucagonemia at high blood glucose, leading to perturbations in plasma amino acid profiles. The reversal of blood glucose by islet transplantation normalized the increases of the BCAAs and several aspects of the altered metabolic profiles in Kuma mice. Our results indicate that the Kuma mice are a unique animal model to study the link between plasma amino acid profile and the progression of diabetes for monitoring the therapeutic effects.

Disease surveillance evaluation of primary small-bowel follicular lymphoma using capsule endoscopy images based on a deep convolutional neural network (with video).

BACKGROUND AND AIMS: Capsule endoscopy (CE) is useful in evaluating disease surveillance for primary small-bowel follicular lymphoma (FL), but some cases are difficult to evaluate objectively. This study evaluated the usefulness of a deep convolutional neural network (CNN) system using CE images for disease surveillance of primary small-bowel FL. METHODS: We enrolled 26 consecutive patients with primary small-bowel FL diagnosed between January 2011 and January 2021 who underwent CE before and after a watch-and-wait strategy or chemotherapy. Disease surveillance by the CNN system was evaluated by the percentage of FL-detected images among all CE images of the small-bowel mucosa. RESULTS: Eighteen cases (69%) were managed with a watch-and-wait approach, and 8 cases (31%) were treated with chemotherapy. Among the 18 cases managed with the watch-and-wait approach, the outcome of lesion evaluation by the CNN system was almost the same in 13 cases (72%), aggravation in 4 (22%), and improvement in 1 (6%). Among the 8 cases treated with chemotherapy, the outcome of lesion evaluation by the CNN system was improvement in 5 cases (63%), almost the same in 2 (25%), and aggravation in 1 (12%). The physician and CNN system reported similar results regarding disease surveillance evaluation in 23 of 26 cases (88%), whereas a discrepancy between the 2 was found in the remaining 3 cases (12%), attributed to poor small-bowel cleansing level. CONCLUSIONS: Disease surveillance evaluation of primary small-bowel FL using CE images by the developed CNN system was useful under the condition of excellent small-bowel cleansing level.

A single-center prospective study evaluating the usefulness of artificial intelligence for the diagnosis of esophageal squamous cell carcinoma in a real-time setting.

BACKGROUND: Several pre-clinical studies have reported the usefulness of artificial intelligence (AI) systems in the diagnosis of esophageal squamous cell carcinoma (ESCC). We conducted this study to evaluate the usefulness of an AI system for real-time diagnosis of ESCC in a clinical setting. METHODS: This study followed a single-center prospective single-arm non-inferiority design. Patients at high risk for ESCC were recruited and real-time diagnosis by the AI system was compared with that of endoscopists for lesions suspected to be ESCC. The primary outcomes were the diagnostic accuracy of the AI system and endoscopists. The secondary outcomes were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and adverse events. RESULTS: A total of 237 lesions were evaluated. The accuracy, sensitivity, and specificity of the AI system were 80.6%, 68.2%, and 83.4%, respectively. The accuracy, sensitivity, and specificity of endoscopists were 85.7%, 61.4%, and 91.2%, respectively. The difference between the accuracy of the AI system and that of the endoscopists was - 5.1%, and the lower limit of the 90% confidence interval was less than the non-inferiority margin. CONCLUSIONS: The non-inferiority of the AI system in comparison with endoscopists in the real-time diagnosis of ESCC in a clinical setting was not proven. TRIAL REGISTRATION: Japan Registry of Clinical Trials (jRCTs052200015, 18/05/2020).

Synchronization and stability analysis of an exponentially diverging solution in a mathematical model of asymmetrically interacting agents.

This study deals with an existing mathematical model of asymmetrically interacting agents. We analyze the following two previously unfocused features of the model: (i) synchronization of growth rates and (ii) initial value dependence of damped oscillation. By applying the techniques of variable transformation and timescale separation, we perform the stability analysis of a diverging solution. We find that (i) all growth rates synchronize to the same value that is as small as the smallest growth rate and (ii) oscillatory dynamics appear if the initial value of the slowest-growing agent is sufficiently small. Furthermore, our analytical method proposes a way to apply stability analysis to an exponentially diverging solution, which we believe is also a contribution of this study. Although the employed model is originally proposed as a model of infectious disease, we do not discuss its biological relevance but merely focus on the technical aspects.

Performance of an artificial intelligence-based diagnostic support tool for early gastric cancers: Retrospective study.

OBJECTIVES: Endoscopists' abilities to diagnose early gastric cancers (EGCs) vary, especially between specialists and nonspecialists. We developed an artificial intelligence (AI)-based diagnostic support tool "Tango" to differentiate EGCs and compared its performance with that of endoscopists. METHODS: The diagnostic performances of Tango and endoscopists (34 specialists, 42 nonspecialists) were compared using still images of 150 neoplastic and 165 non-neoplastic lesions. Neoplastic lesions included EGCs and adenomas. The primary outcome was to show the noninferiority of Tango (based on sensitivity) over specialists. The secondary outcomes were the noninferiority of Tango (based on accuracy) over specialists and the superiority of Tango (based on sensitivity and accuracy) over nonspecialists. The lower limit of the 95% confidence interval (CI) of the difference between Tango and the specialists for sensitivity was calculated, with >-10% defined as noninferiority and >0% defined as superiority in the primary outcome. The comparable differences between Tango and the endoscopists for each performance were calculated, with >10% defined as superiority and >0% defined as noninferiority in the secondary outcomes. RESULTS: Tango achieved superiority over the specialists based on sensitivity (84.7% vs. 65.8%, difference 18.9%, 95% CI 12.3-25.3%) and demonstrated noninferiority based on accuracy (70.8% vs. 67.4%). Tango achieved superiority over the nonspecialists based on sensitivity (84.7% vs. 51.0%) and accuracy (70.8% vs. 58.4%). CONCLUSIONS: The AI-based diagnostic support tool for EGCs demonstrated a robust performance and may be useful to reduce misdiagnosis.

Artificial intelligence versus expert endoscopists for diagnosis of gastric cancer in patients who have undergone upper gastrointestinal endoscopy.

AIMS: To compare endoscopy gastric cancer images diagnosis rate between artificial intelligence (AI) and expert endoscopists. PATIENTS AND METHODS: We used the retrospective data of 500 patients, including 100 with gastric cancer, matched 1:1 to diagnosis by AI or expert endoscopists. We retrospectively evaluated the noninferiority (prespecified margin 5 %) of the per-patient rate of gastric cancer diagnosis by AI and compared the per-image rate of gastric cancer diagnosis. RESULTS: Gastric cancer was diagnosed in 49 of 49 patients (100 %) in the AI group and 48 of 51 patients (94.12 %) in the expert endoscopist group (difference 5.88, 95 % confidence interval: -0.58 to 12.3). The per-image rate of gastric cancer diagnosis was higher in the AI group (99.87 %, 747 /748 images) than in the expert endoscopist group (88.17 %, 693 /786 images) (difference 11.7 %). CONCLUSIONS: Noninferiority of the rate of gastric cancer diagnosis by AI was demonstrated but superiority was not demonstrated.

Phos-tag-based approach to study protein phosphorylation in the thylakoid membrane.

Protein phosphorylation is a fundamental post-translational modification in all organisms. In photoautotrophic organisms, protein phosphorylation is essential for the fine-tuning of photosynthesis. The reversible phosphorylation of the photosystem II (PSII) core and the light-harvesting complex of PSII (LHCII) contribute to the regulation of photosynthetic activities. Besides the phosphorylation of these major proteins, recent phosphoproteomic analyses have revealed that several proteins are phosphorylated in the thylakoid membrane. In this study, we utilized the Phos-tag technology for a comprehensive assessment of protein phosphorylation in the thylakoid membrane of Arabidopsis. Phos-tag SDS-PAGE enables the mobility shift of phosphorylated proteins compared with their non-phosphorylated isoform, thus differentiating phosphorylated proteins from their non-phosphorylated isoforms. We extrapolated this technique to two-dimensional (2D) SDS-PAGE for detecting protein phosphorylation in the thylakoid membrane. Thylakoid proteins were separated in the first dimension by conventional SDS-PAGE and in the second dimension by Phos-tag SDS-PAGE. In addition to the isolation of major phosphorylated photosynthesis-related proteins, 2D Phos-tag SDS-PAGE enabled the detection of several minor phosphorylated proteins in the thylakoid membrane. The analysis of the thylakoid kinase mutants demonstrated that light-dependent protein phosphorylation was mainly restricted to the phosphorylation of the PSII core and LHCII proteins. Furthermore, we assessed the phosphorylation states of the structural domains of the thylakoid membrane, grana core, grana margin, and stroma lamella. Overall, these results demonstrated that Phos-tag SDS-PAGE is a useful biochemical tool for studying in vivo protein phosphorylation in the thylakoid membrane protein.

Automatic detection of various abnormalities in capsule endoscopy videos by a deep learning-based system: a multicenter study.

BACKGROUND AND AIMS: A deep convolutional neural network (CNN) system could be a high-level screening tool for capsule endoscopy (CE) reading but has not been established for targeting various abnormalities. We aimed to develop a CNN-based system and compare it with the existing QuickView mode in terms of their ability to detect various abnormalities. METHODS: We trained a CNN system using 66,028 CE images (44,684 images of abnormalities and 21,344 normal images). The detection rate of the CNN for various abnormalities was assessed per patient, using an independent test set of 379 consecutive small-bowel CE videos from 3 institutions. Mucosal breaks, angioectasia, protruding lesions, and blood content were present in 94, 29, 81, and 23 patients, respectively. The detection capability of the CNN was compared with that of QuickView mode. RESULTS: The CNN picked up 1,135,104 images (22.5%) from the 5,050,226 test images, and thus, the sampling rate of QuickView mode was set to 23% in this study. In total, the detection rate of the CNN for abnormalities per patient was significantly higher than that of QuickView mode (99% vs 89%, P < .001). The detection rates of the CNN for mucosal breaks, angioectasia, protruding lesions, and blood content were 100% (94 of 94), 97% (28 of 29), 99% (80 of 81), and 100% (23 of 23), respectively, and those of QuickView mode were 91%, 97%, 80%, and 96%, respectively. CONCLUSIONS: We developed and tested a CNN-based detection system for various abnormalities using multicenter CE videos. This system could serve as an alternative high-level screening tool to QuickView mode.

Application of artificial intelligence using a convolutional neural network for diagnosis of early gastric cancer based on magnifying endoscopy with narrow-band imaging.

BACKGROUND AND AIM: Magnifying endoscopy with narrow-band imaging (ME-NBI) has made a huge contribution to clinical practice. However, acquiring skill at ME-NBI diagnosis of early gastric cancer (EGC) requires considerable expertise and experience. Recently, artificial intelligence (AI), using deep learning and a convolutional neural network (CNN), has made remarkable progress in various medical fields. Here, we constructed an AI-assisted CNN computer-aided diagnosis (CAD) system, based on ME-NBI images, to diagnose EGC and evaluated the diagnostic accuracy of the AI-assisted CNN-CAD system. METHODS: The AI-assisted CNN-CAD system (ResNet50) was trained and validated on a dataset of 5574 ME-NBI images (3797 EGCs, 1777 non-cancerous mucosa and lesions). To evaluate the diagnostic accuracy, a separate test dataset of 2300 ME-NBI images (1430 EGCs, 870 non-cancerous mucosa and lesions) was assessed using the AI-assisted CNN-CAD system. RESULTS: The AI-assisted CNN-CAD system required 60 s to analyze 2300 test images. The overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the CNN were 98.7%, 98%, 100%, 100%, and 96.8%, respectively. All misdiagnosed images of EGCs were of low-quality or of superficially depressed and intestinal-type intramucosal cancers that were difficult to distinguish from gastritis, even by experienced endoscopists. CONCLUSIONS: The AI-assisted CNN-CAD system for ME-NBI diagnosis of EGC could process many stored ME-NBI images in a short period of time and had a high diagnostic ability. This system may have great potential for future application to real clinical settings, which could facilitate ME-NBI diagnosis of EGC in practice.

Diagnosis of pharyngeal cancer on endoscopic video images by Mask region-based convolutional neural network.

OBJECTIVES: We aimed to develop an artificial intelligence (AI) system for the real-time diagnosis of pharyngeal cancers. METHODS: Endoscopic video images and still images of pharyngeal cancer treated in our facility were collected. A total of 4559 images of pathologically proven pharyngeal cancer (1243 using white light imaging and 3316 using narrow-band imaging/blue laser imaging) from 276 patients were used as a training dataset. The AI system used a convolutional neural network (CNN) model typical of the type used to analyze visual imagery. Supervised learning was used to train the CNN. The AI system was evaluated using an independent validation dataset of 25 video images of pharyngeal cancer and 36 video images of normal pharynx taken at our hospital. RESULTS: The AI system diagnosed 23/25 (92%) pharyngeal cancers as cancers and 17/36 (47%) non-cancers as non-cancers. The transaction speed of the AI system was 0.03 s per image, which meets the required speed for real-time diagnosis. The sensitivity, specificity, and accuracy for the detection of cancer were 92%, 47%, and 66% respectively. CONCLUSIONS: Our single-institution study showed that our AI system for diagnosing cancers of the pharyngeal region had promising performance with high sensitivity and acceptable specificity. Further training and improvement of the system are required with a larger dataset including multiple centers.

Usefulness of an artificial intelligence system for the detection of esophageal squamous cell carcinoma evaluated with videos simulating overlooking situation.

OBJECTIVES: Artificial intelligence (AI) systems have shown favorable performance in the detection of esophageal squamous cell carcinoma (ESCC). However, previous studies were limited by the quality of their validation methods. In this study, we evaluated the performance of an AI system with videos simulating situations in which ESCC has been overlooked. METHODS: We used 17,336 images from 1376 superficial ESCCs and 1461 images from 196 noncancerous and normal esophagi to construct the AI system. To record validation videos, the endoscope was passed through the esophagus at a constant speed without focusing on the lesion to simulate situations in which ESCC has been missed. Validation videos were evaluated by the AI system and 21 endoscopists. RESULTS: We prepared 100 video datasets, including 50 superficial ESCCs, 22 noncancerous lesions, and 28 normal esophagi. The AI system had sensitivity of 85.7% (54 of 63 ESCCs) and specificity of 40%. Initial evaluation by endoscopists conducted with plain video (without AI support) had average sensitivity of 75.0% (47.3 of 63 ESCC) and specificity of 91.4%. Subsequent evaluation by endoscopists was conducted with AI assistance, which improved their sensitivity to 77.7% (P = 0.00696) without changing their specificity (91.6%, P = 0.756). CONCLUSIONS: Our AI system had high sensitivity for the detection of ESCC. As a support tool, the system has the potential to enhance detection of ESCC without reducing specificity. (UMIN000039645).

Plasmid Curing and Exchange Using a Novel Counter-Selectable Marker Based on Unnatural Amino Acid Incorporation at a Sense Codon.

A protocol was designed for plasmid curing using a novel counter-selectable marker, named pylSZK-pylT, in Escherichia coli. The pylSZK-pylT marker consists of the archaeal pyrrolysyl-tRNA synthetase (PylRS) and its cognate tRNA (tRNApyl) with modification, and incorporates an unnatural amino acid (Uaa), Nε-benzyloxycarbonyl-l-lysine (ZK), at a sense codon in ribosomally synthesized proteins, resulting in bacterial growth inhibition or killing. Plasmid curing is performed by exerting toxicity on pylSZK-pylT located on the target plasmid, and selecting only proliferative bacteria. All tested bacteria obtained using this protocol had lost the target plasmid (64/64), suggesting that plasmid curing was successful. Next, we attempted to exchange plasmids with the identical replication origin and an antibiotic resistance gene without plasmid curing using a modified protocol, assuming substitution of plasmids complementing genomic essential genes. All randomly selected bacteria after screening had only the substitute plasmid and no target plasmid (25/25), suggesting that plasmid exchange was also accomplished. Counter-selectable markers based on PylRS-tRNApyl, such as pylSZK-pylT, may be scalable in application due to their independence from the host genotype, applicability to a wide range of species, and high tunability due to the freedom of choice of target codons and Uaa's to be incorporated.

Impaired PSII Proteostasis Promotes Retrograde Signaling via Salicylic Acid.

Photodamage of the PSII reaction center (RC) is an inevitable process in an oxygen-rich environment. The damaged PSII RC proteins (Dam-PSII) undergo degradation via the thylakoid membrane-bound FtsH metalloprotease, followed by posttranslational assembly of PSII. While the effect of Dam-PSII on gene regulation is described for cyanobacteria, its role in land plants is largely unknown. In this study, we reveal an intriguing retrograde signaling pathway by using the Arabidopsis (Arabidopsis thaliana) yellow variegated2-9 mutant, which expresses a mutated FtsH2 (FtsH2G267D) metalloprotease, specifically impairing its substrate-unfolding activity. This lesion leads to the perturbation of PSII protein homeostasis (proteostasis) and the accumulation of Dam-PSII. Subsequently, this results in an up-regulation of salicylic acid (SA)-responsive genes, which is abrogated by inactivation of either an SA transporter in the chloroplast envelope membrane or extraplastidic SA signaling components as well as by removal of SA. These results suggest that the stress hormone SA, which is mainly synthesized via the chloroplast isochorismate pathway in response to the impaired PSII proteostasis, mediates the retrograde signaling. These findings reinforce the emerging view of chloroplast function toward plant stress responses and suggest SA as a potential plastid factor mediating retrograde signaling.

Comparison of performances of artificial intelligence versus expert endoscopists for real-time assisted diagnosis of esophageal squamous cell carcinoma (with video).

BACKGROUND AND AIMS: Narrow-band imaging (NBI) is currently regarded as the standard modality for diagnosing esophageal squamous cell carcinoma (SCC). We developed a computerized image-analysis system for diagnosing esophageal SCC by NBI and estimated its performance with video images. METHODS: Altogether, 23,746 images from 1544 pathologically proven superficial esophageal SCCs and 4587 images from 458 noncancerous and normal tissue were used to construct an artificial intelligence (AI) system. Five- to 9-second video clips from 144 patients captured by NBI or blue-light imaging were used as the validation dataset. These video images were diagnosed by the AI system and 13 board-certified specialists (experts). RESULTS: The diagnostic process was divided into 2 parts: detection (identify suspicious lesions) and characterization (differentiate cancer from noncancer). The sensitivities, specificities, and accuracies for the detection of SCC were, respectively, 91%, 51%, and 63% for the AI system and 79%, 72%, and 75% for the experts. The sensitivity of the AI system was significantly higher than that of the experts, but its specificity was significantly lower. Sensitivities, specificities, and accuracy for the characterization of SCC were, respectively, 86%, 89%, and 88% for the AI system and 74%, 76%, and 75% for the experts. The receiver operating characteristic curve showed that the AI system had significantly better diagnostic performance than the experts. CONCLUSIONS: Our AI system showed significantly higher sensitivity for detecting SCC and higher accuracy for characterizing SCC from noncancerous tissue than endoscopic experts.

Automatic detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network.

BACKGROUND AND AIMS: Protruding lesions of the small bowel vary in wireless capsule endoscopy (WCE) images, and their automatic detection may be difficult. We aimed to develop and test a deep learning-based system to automatically detect protruding lesions of various types in WCE images. METHODS: We trained a deep convolutional neural network (CNN), using 30,584 WCE images of protruding lesions from 292 patients. We evaluated CNN performance by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, using an independent set of 17,507 test images from 93 patients, including 7507 images of protruding lesions from 73 patients. RESULTS: The developed CNN analyzed 17,507 images in 530.462 seconds. The AUC for detection of protruding lesions was 0.911 (95% confidence interval [Cl], 0.9069-0.9155). The sensitivity and specificity of the CNN were 90.7% (95% CI, 90.0%-91.4%) and 79.8% (95% CI, 79.0%-80.6%), respectively, at the optimal cut-off value of 0.317 for probability score. In a subgroup analysis of the category of protruding lesions, the sensitivities were 86.5%, 92.0%, 95.8%, 77.0%, and 94.4% for the detection of polyps, nodules, epithelial tumors, submucosal tumors, and venous structures, respectively. In individual patient analyses (n = 73), the detection rate of protruding lesions was 98.6%. CONCLUSION: We developed and tested a new computer-aided system based on a CNN to automatically detect various protruding lesions in WCE images. Patient-level analyses with larger cohorts and efforts to achieve better diagnostic performance are necessary in further studies.