The insufficiency of CT examination in early detection of central lung squamous cell carcinoma and squamous epithelial precancerous lesions.

BACKGROUND: CT examination for lung cancer has been carried out for more than 20 years and great achievements have been made in the early detection of lung cancer. However, in the clinical work, a large number of advanced central lung squamous cell carcinoma are still detected through bronchoscopy. Meanwhile, a part of CT-occult central lung squamous cell carcinoma and squamous epithelial precancerous lesions are also accidentally detected through bronchoscopy. METHODS: This study retrospectively collects the medical records of patients in the bronchoscopy room of the Endoscopy Department of Zhejiang Cancer Hospital from January 2014 to December 2018. The inclusion criteria for patients includes: 1.Patient medical records completed, 2.Without history of lung cancer before the diagnosis and first pathological diagnosis of primary lung cancer, 3.Have the lung CT data of the same period, 4.Have the bronchoscopy records and related pathological diagnosis, 5.The patients undergoing radical surgical treatment must have a complete postoperative pathological diagnosis. Finally, a total of 10,851 patients with primary lung cancer are included in the study, including 7175 males and 3676 females, aged 22-98 years. Firstly, 130 patients with CT-occult lesions are extracted and their clinical features are analyzed. Then, 604 cases of single central squamous cell carcinoma and 3569 cases of peripheral adenocarcinoma are extracted and compares in postoperative tumor diameter and lymph node metastasis. RESULTS: 115 cases of CT-occult central lung squamous cell carcinoma and 15 cases of squamous epithelial precancerous lesions are found. In the total lung cancer, the proportion of CT-occult lesions is 130/10,851 (1.20%). Meanwhile, all these patients are middle-aged and elderly men with a history of heavy smoking. There are statistically significant differences in postoperative median tumor diameter (3.65 cm vs.1.70 cm, P < 0.0001) and lymph node metastasis rate (50.99% vs.13.06%, P < 0.0001) between 604 patients with operable single central lung squamous cell carcinoma and 3569 patients with operable peripheral lung adenocarcinoma. Of the 604 patients with squamous cell carcinoma, 96.52% (583/604) are male with a history of heavy smoking and aged 40-82 years with a median age of 64 years. CONCLUSIONS: This study indicates that the current lung CT examination of lung cancer is indeed insufficiency for the early diagnosis of central squamous cell carcinoma and squamous epithelial precancerous lesions. Further bronchoscopy in middle-aged and elderly men with a history of heavy smoking can make up for the lack of routine lung CT examination.

Deep Learning in High-Resolution Anoscopy: Assessing the Impact of Staining and Therapeutic Manipulation on Automated Detection of Anal Cancer Precursors.

INTRODUCTION: High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell carcinoma (ASCC) precursors. Preliminary studies on the application of artificial intelligence (AI) models to this modality have revealed promising results. However, the impact of staining techniques and anal manipulation on the effectiveness of these algorithms has not been evaluated. We aimed to develop a deep learning system for automatic differentiation of high-grade squamous intraepithelial lesion vs low-grade squamous intraepithelial lesion in HRA images in different subsets of patients (nonstained, acetic acid, lugol, and after manipulation). METHODS: A convolutional neural network was developed to detect and differentiate high-grade and low-grade anal squamous intraepithelial lesions based on 27,770 images from 103 HRA examinations performed in 88 patients. Subanalyses were performed to evaluate the algorithm's performance in subsets of images without staining, acetic acid, lugol, and after manipulation of the anal canal. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve were calculated. RESULTS: The convolutional neural network achieved an overall accuracy of 98.3%. The algorithm had a sensitivity and specificity of 97.4% and 99.2%, respectively. The accuracy of the algorithm for differentiating high-grade squamous intraepithelial lesion vs low-grade squamous intraepithelial lesion varied between 91.5% (postmanipulation) and 100% (lugol) for the categories at subanalysis. The area under the curve ranged between 0.95 and 1.00. DISCUSSION: The introduction of AI to HRA may provide an accurate detection and differentiation of ASCC precursors. Our algorithm showed excellent performance at different staining settings. This is extremely important because real-time AI models during HRA examinations can help guide local treatment or detect relapsing disease.

CrossU-Net: Dual-modality cross-attention U-Net for segmentation of precancerous lesions in gastric cancer.

Gastric precancerous lesions (GPL) significantly elevate the risk of gastric cancer, and precise diagnosis and timely intervention are critical for patient survival. Due to the elusive pathological features of precancerous lesions, the early detection rate is less than 10%, which hinders lesion localization and diagnosis. In this paper, we provide a GPL pathological dataset and propose a novel method for improving the segmentation accuracy on a limited-scale dataset, namely RGB and Hyperspectral dual-modal pathological image Cross-attention U-Net (CrossU-Net). Specifically, we present a self-supervised pre-training model for hyperspectral images to serve downstream segmentation tasks. Secondly, we design a dual-stream U-Net-based network to extract features from different modal images. To promote information exchange between spatial information in RGB images and spectral information in hyperspectral images, we customize the cross-attention mechanism between the two networks. Furthermore, we use an intermediate agent in this mechanism to improve computational efficiency. Finally, we add a distillation loss to align predicted results for both branches, improving network generalization. Experimental results show that our CrossU-Net achieves accuracy and Dice of 96.53% and 91.62%, respectively, for GPL lesion segmentation, providing a promising spectral research approach for the localization and subsequent quantitative analysis of pathological features in early diagnosis.

Artificial intelligence-aided diagnostic imaging: A state-of-the-art technique in precancerous screening.

BACKGROUND AND AIM: Chromoendoscopy with the use of indigo carmine (IC) dye is a crucial endoscopic technique to identify gastrointestinal neoplasms. However, its performance is limited by the endoscopist's skill, and no standards are available for lesion identification. Thus, we developed an artificial intelligence (AI) model to replace chromoendoscopy. METHODS: This pilot study assessed the feasibility of our novel AI model in the conversion of white-light images (WLI) into virtual IC-dyed images based on a generative adversarial network. The predictions of our AI model were evaluated against the assessments of five endoscopic experts who were blinded to the purpose of this study with a staining quality rating from 1 (unacceptable) to 4 (excellent). RESULTS: The AI model successfully transformed the WLI of polyps with different morphologies and different types of lesions in the gastrointestinal tract into virtual IC-dyed images. The quality ratings of the real IC-dyed and AI images did not significantly differ concerning surface structure (AI vs IC: 3.08 vs 3.00), lesion border (3.04 vs 2.98), and overall contrast (3.14 vs 3.02) from 10 sets of images (10 AI images and 10 real IC-dyed images). Although the score depended significantly on the evaluator, the staining methods (AI or real IC) and evaluators had no significant interaction (P > 0.05) with each other. CONCLUSION: Our results demonstrated the feasibility of employing AI model's virtual IC staining, increasing the possibility of being employed in daily practice. This novel technology may facilitate gastrointestinal lesion identification in the future.

Effect of an artificial intelligence-assisted system on endoscopic diagnosis of superficial oesophageal squamous cell carcinoma and precancerous lesions: a multicentre, tandem, double-blind, randomised controlled trial.

BACKGROUND: Despite the usefulness of white light endoscopy (WLE) and non-magnified narrow-band imaging (NBI) for screening for superficial oesophageal squamous cell carcinoma and precancerous lesions, these lesions might be missed due to their subtle features and interpretation variations among endoscopists. Our team has developed an artificial intelligence (AI) system to detect superficial oesophageal squamous cell carcinoma and precancerous lesions using WLE and non-magnified NBI. We aimed to evaluate the auxiliary diagnostic performance of the AI system in a real clinical setting. METHODS: We did a multicentre, tandem, double-blind, randomised controlled trial at 12 hospitals in China. Eligible patients were aged 18 years or older and underwent sedated upper gastrointestinal endoscopy for screening, investigation of gastrointestinal symptoms, or surveillance. Patients were randomly assigned (1:1) to either the AI-first group or the routine-first group using a computerised random number generator. Patients, pathologists, and statistical analysts were masked to group assignment, whereas endoscopists and research assistants were not. The same endoscopist at each centre did tandem upper gastrointestinal endoscopy for each eligible patient on the same day. In the AI-first group, the endoscopist did the first examination with the assistance of the AI system and the second examination without it. In the routine-first group, the order of examinations was reversed. The primary outcome was the miss rate of superficial oesophageal squamous cell carcinoma and precancerous lesions, calculated on a per-lesion and per-patient basis. All analyses were done on a per-protocol basis. This trial is registered with the Chinese Clinical Trial Registry (ChiCTR2100052116) and is completed. FINDINGS: Between Oct 19, 2021, and June 8, 2022, 5934 patients were randomly assigned to the AI-first group and 5912 to the routine-first group, of whom 5865 and 5850 were eligible for analysis. Per-lesion miss rates were 1·7% (2/118; 95% CI 0·0-4·0) in the AI-first group versus 6·7% (6/90; 1·5-11·8) in the routine-first group (risk ratio 0·25, 95% CI 0·06-1·08; p=0·079). Per-patient miss rates were 1·9% (2/106; 0·0-4·5) in AI-first group versus 5·1% (4/79; 0·2-9·9) in the routine-first group (0·37, 0·08-1·71; p=0·40). Bleeding after biopsy of oesophageal lesions was observed in 13 (0·2%) patients in the AI-first group and 11 (0·2%) patients in the routine-first group. No serious adverse events were reported by patients in either group. INTERPRETATION: The observed effect of AI-assisted endoscopy on the per-lesion and per-patient miss rates of superficial oesophageal squamous cell carcinoma and precancerous lesions under WLE and non-magnified NBI was consistent with substantial benefit through to a neutral or small negative effect. The effectiveness and cost-benefit of this AI system in real-world clinical settings remain to be further assessed. FUNDING: National Natural Science Foundation of China, 1·3·5 project for disciplines of excellence, West China Hospital, Sichuan University, and Chengdu Science and Technology Project. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

A self-supervised classification model for endometrial diseases.

PURPOSE: Ultrasound imaging is the preferred method for the early diagnosis of endometrial diseases because of its non-invasive nature, low cost, and real-time imaging features. However, the accurate evaluation of ultrasound images relies heavily on the experience of radiologist. Therefore, a stable and objective computer-aided diagnostic model is crucial to assist radiologists in diagnosing endometrial lesions. METHODS: Transvaginal ultrasound images were collected from multiple hospitals in Quzhou city, Zhejiang province. The dataset comprised 1875 images from 734 patients, including cases of endometrial polyps, hyperplasia, and cancer. Here, we proposed a based self-supervised endometrial disease classification model (BSEM) that learns a joint unified task (raw and self-supervised tasks) and applies self-distillation techniques and ensemble strategies to aid doctors in diagnosing endometrial diseases. RESULTS: The performance of BSEM was evaluated using fivefold cross-validation. The experimental results indicated that the BSEM model achieved satisfactory performance across indicators, with scores of 75.1%, 87.3%, 76.5%, 73.4%, and 74.1% for accuracy, area under the curve, precision, recall, and F1 score, respectively. Furthermore, compared to the baseline models ResNet, DenseNet, VGGNet, ConvNeXt, VIT, and CMT, the BSEM model enhanced accuracy, area under the curve, precision, recall, and F1 score in 3.3-7.9%, 3.2-7.3%, 3.9-8.5%, 3.1-8.5%, and 3.3-9.0%, respectively. CONCLUSION: The BSEM model is an auxiliary diagnostic tool for the early detection of endometrial diseases revealed by ultrasound and helps radiologists to be accurate and efficient while screening for precancerous endometrial lesions.

The predictive value of the change of the number of pixels under different CT value intervals in the CT-occult central lung squamous cell carcinoma and squamous epithelial precancerous lesions.

BACKGROUND: Due to the fact that the CT-occult central lung squamous cell carcinoma and squamous epithelial precancerous lesions. (CT-occult CLSCC and SEPL) cannot be detected by lung CT screening, early and timely diagnosis of central lung cancer becomes very difficult, which directly affects the prognosis of patients. METHODS: We retrospectively review medical records of patients at the Zhejiang Cancer Hospital and enrolled 41 patients with the CT-occult CLSCC and SEPL and 48 patients without the CT-occult CLSCC and SEPL. We compare the clinical characteristics, imaging features and Changes in the number of pixels under different CT value intervals of patients with and without the CT-occult CLSCC and SEPL and we perform univariate and multivariate logistic regression analysis to explore independent factors for the CT-occult CLSCC and SEPL in the patients. RESULTS: We demonstrate that pack-years ≥ 20 (OR: 3.848, 95% CI: 1.086 ~ 13.633), the number of pixels change of CT value in interval [-850 ~ -750HU] (OR: 5.302, 95% CI: 1.122 ~ 25.057) and in interval [-900 ~ -850HU] (OR: 3.478, 95% CI: 1.167 ~ 10.365) are independently associated with the CT-occult CLSCC and SEPL in the patients. Ultimately, the logistic model obtained is statistically significant (p < 0.05) and an area under the ROC curve is 0.776 (95% CI: 0.682-0.870). The sensitivity of this model is 90.2% and the specificity is 52.1%. CONCLUSION: The results of this study indicate that in the CT value range [-950 ~ -750HU], when the total number of lung pixels tend to increase towards the region with high CT value, the probability of the occurrence of CT-occult CLSCC and SEPL lesions also increases. Meanwhile, these results have guiding significance for the further study of radiomic.

Management of screening-detected lobular neoplasia in the era of digital breast tomosynthesis: A preliminary study.

PURPOSE: The purpose of this study is to determine upgrade rates of lobular neoplasia detected by screening digital breast tomosynthesis (DBT) and to determine imaging and clinicopathological features that may influence risk of upgrade. METHODS: Medical records were reviewed of consecutive women who presented with screening DBT-detected atypical lobular hyperplasia (ALH) and/or lobular carcinoma in situ (LCIS) from January 1, 2013, to June 30, 2020. Included patients underwent needle biopsy and had surgery or at least two-year imaging follow-up. Imaging and clinicopathological features were compared between upgraded and nonupgraded cases of lobular neoplasia using the Pearson's chi-squared test and the Wilcoxon signed-rank test. RESULTS: During the study period, 107 women (mean age 55 years, range 40-88 years) with 110 cases of ALH and/or LCIS underwent surgery (80.9%, n = 89) or at least two-year imaging follow-up (19.1%, n = 21). The overall upgrade rate to cancer was 5.5% (6/110), and the upgrade rate to invasive cancer was 3.6% (4/110). The upgrade rate of ALH to cancer was 4.1% (3/74), whereas the upgrade rate of LCIS to cancer was 9.4% (3/32) (p = .28). The upgrade rate of cases presenting as calcifications was 4.2% (3/71), whereas the upgrade rates of cases presenting as noncalcified findings was 7.7% (3/39) (p = .44). CONCLUSIONS: The upgrade rate of screening DBT-detected lobular neoplasia is less than 6%. Surveillance rather than surgery can be considered for lobular neoplasia, particularly in patients with ALH and in those with screening-detected calcifications leading to the diagnosis.

Update on Lobular Neoplasia.

Lobular neoplasia (LN) is a histopathologic entity that encompasses both lobular carcinoma in situ (LCIS) and atypical lobular hyperplasia (ALH). Management of LN is known to be variable and institutionally dependent. The variability in approach after a diagnosis of LN at percutaneous breast biopsy derives in part from heterogeneity in the literature, resulting in a range of reported upgrade rates to malignancy after initial identification at percutaneous biopsy, and also from historical shifts in understanding of the natural history of LN. It has become increasingly recognized that not all LN is the same and that distinct variants of LN such as pleomorphic LCIS and florid LCIS have distinct natural histories and distinct likelihoods of upgrade to malignancy. In addition, it is also increasingly understood that appropriate management of LN relies on scrupulous radiologic-pathologic correlation. This review details the imaging features and histopathologic nature of ALH, classic-type LCIS, and the LCIS variants; addresses changes in the historical understanding of this entity contributing to confusion regarding its management; and discusses the importance of performing radiologic-pathologic correlation after percutaneous biopsy to help guide appropriate management steps when LN is encountered. In addition to the short-term implications of an LN diagnosis in terms of upgrade and surgical outcomes, the long-term implications of an LN diagnosis regarding risk of developing a later breast cancer are examined. ©RSNA, 2023 Quiz questions for this article are available through the Online Learning Center.

Magnifying image-enhanced endoscopy-only mode boosted early cancer diagnostic efficiency: a multicenter randomized controlled trial.

BACKGROUND AND AIMS: Magnifying image-enhanced endoscopy (MIEE) is an advanced endoscopy with image enhancement and magnification used in preoperative examination. However, its impact on the detection rate is unknown. METHODS: We conducted an open-label, randomized, parallel (1:1:1), controlled trial in 6 hospitals in China. Patients were recruited between February 14, 2022 and July 30, 2022. Eligible patients were aged ≥18 years and undergoing gastroscopy in outpatient departments. Participants were randomly assigned to the MIEE-only mode (o-MIEE) group, white-light endoscopy-only mode (o-WLE) group, and MIEE when necessary mode (n-MIEE) group (initial WLE followed by switching to another endoscope with MIEE if necessary). Biopsy sampling of suspicious lesions of the lesser curvature of the gastric antrum was performed. Primary and secondary aims were to compare detection rates and positive predictive value (PPV) of early cancer and precancerous lesions in these 3 modes, respectively. RESULTS: A total of 5100 recruited patients were randomly assigned to the o-MIEE (n = 1700), o-WLE (n = 1700), and n-MIEE (n = 1700) groups. In the o-MIEE, o-WLE, and n-MIEE groups, 29 (1.51%; 95% confidence interval [CI], 1.05-2.16), 4 (.21%; 95% CI, .08-.54), and 8 (.43%; 95% CI, .22-.85) early cancers were found, respectively (P < .001). The PPV for early cancer was higher in the o-MIEE group compared with the o-WLE and n-MIEE groups (63.04%, 33.33%, and 38.1%, respectively; P = .062). The same trend was seen for precancerous lesions (36.67%, 10.00%, and 21.74%, respectively). CONCLUSIONS: The o-MIEE mode resulted in a significant improvement in diagnosing early upper GI cancer and precancerous lesions; thus, it could be used for opportunistic screening. (Clinical trial registration number: ChiCTR2200064174.).

Benefits of pancreatic parenchymal endoscopic ultrasonography in predicting microscopic precancerous lesions of pancreatic cancer.

Pancreatic cancer primarily arises from microscopic precancerous lesions, such as pancreatic intraepithelial neoplasia (PanIN) and acinar-to-ductal metaplasia (ADM). However, no established method exists for predicting pancreatic precancerous conditions. Endoscopic ultrasonography (EUS) can detect changes in pancreatic parenchymal histology, including fibrosis. This study aimed to elucidate the relationship between pancreatic parenchymal EUS findings and microscopic precancerous lesions. We retrospectively analyzed 114 patients with pancreatobiliary tumors resected between 2010 and 2020 and evaluated the association between pancreatic parenchymal EUS findings and the number of PanIN, ADM, and pancreatic duct gland (PDG). Of the 114 patients, 33 (29.0%), 55 (48.2%), and 26 (22.8%) had normal EUS findings, hyperechoic foci/stranding without lobularity, and hyperechoic foci/stranding with lobularity, respectively. Multivariate analyses revealed that abnormal EUS findings were significantly associated with the frequency of PanIN (hyperechoic foci/stranding without lobularity: OR [95% CI] = 2.7 [1.0-7.3], with lobularity: 6.5 [1.9-22.5], Ptrend = 0.01) and ADM (hyperechoic foci/stranding without lobularity: 3.1 [1.1-8.2], with lobularity: 9.7 [2.6-36.3], Ptrend = 0.003) but not with PDG (hyperechoic foci/stranding without lobularity: 2.2 [0.8-5.8], with lobularity: 3.2 [1.0-10.2], Ptrend = 0.12). We observed a trend toward a significantly higher number of precancerous lesions in the following order: normal findings, hyperechoic foci/stranding without lobularity, and hyperechoic foci/stranding with lobularity. Pancreatic parenchymal EUS findings were associated with the increased frequency of PanIN and ADM. Lobularity may help predict the increased number of precancerous lesions.

Investigation of artificial intelligence integrated fluorescence endoscopy image analysis with indocyanine green for interpretation of precancerous lesions in colon cancer.

Indocyanine green (ICG) has been used in clinical practice for more than 40 years and its safety and preferential accumulation in tumors has been reported for various tumor types, including colon cancer. However, reports on clinical assessments of ICG-based molecular endoscopy imaging for precancerous lesions are scarce. We determined visualization ability of ICG fluorescence endoscopy in colitis-associated colon cancer using 30 lesions from an azoxymethane/dextran sulfate sodium (AOM/DSS) mouse model and 16 colon cancer patient tissue-samples. With a total of 60 images (optical, fluorescence) obtained during endoscopy observation of mouse colon cancer, we used deep learning network to predict four classes (Normal, Dysplasia, Adenoma, and Carcinoma) of colorectal cancer development. ICG could detect 100% of carcinoma, 90% of adenoma, and 57% of dysplasia, with little background signal at 30 min after injection via real-time fluorescence endoscopy. Correlation analysis with immunohistochemistry revealed a positive correlation of ICG with inducible nitric oxide synthase (iNOS; r > 0.5). Increased expression of iNOS resulted in increased levels of cellular nitric oxide in cancer cells compared to that in normal cells, which was related to the inhibition of drug efflux via the ABCB1 transporter down-regulation resulting in delayed retention of intracellular ICG. With artificial intelligence training, the accuracy of image classification into four classes using data sets, such as fluorescence, optical, and fluorescence/optical images was assessed. Fluorescence images obtained the highest accuracy (AUC of 0.8125) than optical and fluorescence/optical images (AUC of 0.75 and 0.6667, respectively). These findings highlight the clinical feasibility of ICG as a detector of precancerous lesions in real-time fluorescence endoscopy with artificial intelligence training and suggest that the mechanism of ICG retention in cancer cells is related to intracellular nitric oxide concentration.

Fluorescence colposcope with TMTP1-PEG4-ICG is comparable to the conventional colposcope in identifying cervical precancerous lesions: A randomized controlled trial.

OBJECTIVE: To compare the diagnostic efficiency of a fluorescence colposcope with TMTP1-PEG4-ICG dye versus a conventional colposcope with acetic acid and Lugol's iodine in identifying cervical precancerous lesions. METHODS: In all, 218 women with abnormal cervical cancer screening results including cytology and/or human papillomavirus (HPV) test were involved in the randomized controlled trial. Patients in the fluorescence colposcope group had TMTP1-PEG4-ICG dye applied to the cervix uteri before colposcopy. Patients in the conventional colposcope group were routinely administered acetic acid and Lugol's iodine to stain the cervix uteri. Two to four cervical sites per patient were taken out for biopsy. The diagnostic efficiency of fluorescence colposcopy and conventional colposcopy was calculated on a per-patient and per-site basis. χ2 test or Fisher exact test was used. RESULTS: A total of 194 patients and the corresponding 662 cervical sites were included in the final analysis. There was no statistically significant difference in the diagnostic efficiency between the two groups both on a per-patient and a per-site basis, including accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. CONCLUSIONS: The fluorescence colposcope with TMTP1-PEG4-ICG dye was comparable to the conventional colposcope in identifying cervical precancerous lesions.

Endoscopic resection of gastric low-grade dysplasia with high risk factors is associated with decreased advanced neoplasia: a single-center retrospective cohort study.

BACKGROUND: The natural course of gastric low-grade dysplasia (LGD) remains unclear, and there are inconsistent management recommendations among guidelines and consensus. OBJECTIVE: This study aimed to investigate the incidence of advanced neoplasia in patients with gastric LGD and identify the related risk factors. METHODS: Cases of biopsy demonstrated LGD (BD-LGD) at our center from 2010 to 2021 were reviewed retrospectively. Risk factors related to histological progression were identified, and outcomes of patients based on risk stratification were evaluated. RESULTS: Ninety-seven (23.0%) of 421 included BD-LGD lesions were diagnosed as advanced neoplasia. Among 409 superficial BD-LGD lesions, lesion in the upper third of the stomach, H. pylori infection, larger size, and narrow band imaging (NBI)-positive findings were independent risk factors of progression. NBI-positive lesions and NBI-negative lesions with or without other risk factors had 44.7%, 1.7%, and 0.0% risk of advanced neoplasia, respectively. Invisible lesions, visible lesions (VLs) without a clear margin, and VLs with a clear margin and size ≤ 10 mm, or > 10 mm had 4.8%, 7.9%, 16.7%, and 55.7% risk of advanced neoplasia, respectively. In addition, endoscopic resection decreased the risk of cancer (P < 0.001) and advanced neoplasia (P < 0.001) in patients with NBI-positive lesions, but not in NBI-negative patients. Similar results were found in patients with VLs with clear margin and size > 10 mm. Moreover, NBI-positive lesions had higher sensitivity and lower specificity for predicting advanced neoplasia than VLs with a clear margin and size > 10 mm determined by white-light endoscopy (97.6% vs. 62.7%, P < 0.001; and 63.0% vs. 85.6%, P < 0.001, respectively). CONCLUSION: Progression of superficial BD-LGD is associated with NBI-positive lesions, as well as with VLs with a clear margin (size > 10 mm) if NBI is unavailable, and selective resection of those lesions offers benefits for patients by decreasing the risk of advanced neoplasia.

Is pulmonary fibrosis a precancerous disease?

Idiopathic pulmonary fibrosis (IPF) is the most common type of interstitial lung disease (ILD) characterized by a histopathological pattern of usual interstitial pneumonia with progressive fibrosis of the pulmonary epithelium. The incidence of IPF is increasing worldwide as the population ages and with that, there is a concomitant increase in the incidence of lung cancer in these patients who are living longer with the disease. The average length of time for lung cancer development following an IPF diagnosis is 3 years. Given the high prevalence of lung cancer among patients with pulmonary fibrosis, we wondered if pulmonary fibrosis could be classified as a precancerous disease. We provided support from the Pubmed published literature to investigate whether pulmonary fibrosis meets the five criteria of the National Cancer Institute's definition of premalignant conditions for classification as a precancerous disease. We found out pulmonary fibrosis meets the five criteria of the National Cancer Institute's definition of a premalignant condition and can be considered a precancerous disease. To identify early lung cancer in patients with pulmonary fibrosis, regular screening with HRCT and PET-CT scans is highly recommended for these patients.

Quantitative Evaluation of the Normal Cervix, Cervical Cancer, and Cervical Precancerous Changes Via Real-Time Shear Wave Elastography.

OBJECTIVES: The present study aims to evaluate the clinical application values of ultrasound real-time shear wave elastography (SWE) in the diagnosis and differential diagnosis of cervical cancer (CC). METHODS: A total of 285 married female patients were screened and divided into three groups according to the results of the pathological examination and the cervical ThinPrep cytologic test: 1) the CC group (n = 94); 2) the cervical intraepithelial neoplasia (CIN) group (n = 91); and 3) the normal control group (n = 100). The maximum Young's modulus (Emax), mean Young's modulus (Emean), minimum Young's modulus (Emin), and Young's modulus stability (Esd) in each group were measured and statistically analyzed. RESULTS: There were no statistically significant differences in Emax, Emean, Emin, and Esd values between the anterior and posterior cervical walls, premenopausal and postmenopausal women, and nonparturient and parturient women in the normal control group. The Emax, Emean, Emin, and Esd values in the CIN group showed no statistically significant differences in different periods when compared with the control group. The differences between the normal control group and the CC group were statistically significant; the CC group showed no statistically significant differences in Emax, Emean, Emin, and Esd values at different clinical stages and in different pathological types. The cutoff value of Emax for CC diagnosis, which was of the highest accuracy (89.7%), was 43.48 kpa. CONCLUSION: Ultrasound real-time SWE can be applied to CC diagnosis.

Image-enhanced endoscopy in the diagnosis of gastric premalignant conditions and gastric cancer. / Técnicas de imagen avanzada en la detección y caracterización de las lesiones precursoras del cáncer gástrico y del cáncer gástrico precoz.

Diagnosis of early gastric cancer and its precancerous lesions remains a challenge for great part of western endoscopists. Changes seen in the mucosal pattern are generally subtle and hence difficult to identify. In this article, we will review the usefulness of conventional and virtual chromoendoscopy and magnification endoscopy in the recognition and classification of these lesions.

Magnifying endoscopy with narrow-band imaging for diagnosis of subtype of gastric intestinal metaplasia.

BACKGROUND AND AIM: Patients with incomplete gastric intestinal metaplasia (GIM) have a higher risk of gastric cancer (GC) than those with complete GIM. We aimed to clarify whether micromucosal patterns of GIM in magnifying endoscopy with narrow-band imaging (M-NBI) were useful for diagnosis of incomplete GIM. METHODS: We enrolled patients with a history of endoscopic resection of GC or detailed inspection for suspicious or definite GC. The antrum greater curvature and corpus lesser curvature were regions of interest. Areas with endoscopic findings of light blue crest and/or white opaque substance (WOS) were defined as endoscopic GIM, and subsequent M-NBI was applied. Micromucosal patterns were classified into Foveola and Groove types, and targeted biopsies were performed on GIM with each pattern. GIM was classified into complete and incomplete types using mucin (MUC)2, MUC5AC, MUC6, and CD10 immunohistochemical staining. The primary endpoint was the association between micromucosal pattern and histological subtype. The secondary endpoint was endoscopic findings associated with incomplete GIM. RESULTS: We analyzed 98 patients with 156 GIMs. Univariate analysis (odds ratio [OR] 3.4, P = 0.004), but not multivariate analysis (OR 0.87, P = 0.822), demonstrated a significant association between micromucosal pattern and subtype. The antrum (OR 3.7, P = 0.006) and WOS (OR 43, P = 0.002) were independent predictors for incomplete GIM. The WOS had 69% sensitivity and 93% specificity. CONCLUSIONS: The M-NBI micromucosal pattern is not useful for diagnosis of GIM subtype. WOS is a promising endoscopic indicator for diagnosis of incomplete GIM. (UMIN-CTR000041119).

Classification of precancerous lesions based on fusion of multiple hierarchical features.

PURPOSE: To investigate an identification method for precancerous gastric cancer based on the fusion of superficial features and deep features of gastroscopic images. The purpose of this study is to make most use of superficial features and deep features to provide clinicians with clinical decision support to assist the diagnosis of precancerous gastric diseases and reduce the workload of doctors. METHODS: According to the nature of gastroscopic images, 75-dimensional shallow features were manually designed, including histogram features, texture features and high-order features of the image; then, based on the constructed convolutional neural networks such as ResNet and GoogLeNet, before the output layer. A fully connected layer is added as the deep feature of the image. In order to ensure consistent feature weights, the number of neurons in the fully connected layer is designed to be 75 dimensions. Therefore, the superficial and deep features of the image are concatenated, and a machine learning classifier is used to identify gastric polyps, there are three types of gastric precancerous diseases such as gastric polyps, gastric ulcers and gastric erosions. RESULTS: A dataset with 420 images was collected for each disease, and divided into a training set and a test set with a ratio of 5:1, and then based on the dataset, three methods, such as traditional machine learning, deep learning, and feature fusion, were used respectively. For model training and testing of traditional machine learning and feature fusion, SVM, RF and BP neural network are used as the classification results of the classifier. For deep learning, the GoogLeNet, ResNet, and ResNeXt were implemented. The test results of the model on the test set show that the recognition accuracy of the proposed feature fusion method reaches (SVM: 85.18%; RF: 83.42%; BPNN: 85.18%), which is better than the traditional machine learning method (SVM: 80.17%; RF: 82.37%; BPNN: 84.12%) and the deep learning method (GoogLeNet: 82.54%; ResNet-18: 81.67%; ResNet-50: 81.67%; ResNeXt-50: 82.11%), which proves that this method has obvious advantages. CONCLUSION: This study provides a new strategy for the identification of precancerous gastric cancer, improving the efficiency and accuracy of precancerous gastric cancer identification, and hopes to provide substantial practical help for the identification of gastric precancerous diseases.

Artificial intelligence for detecting and delineating the extent of superficial esophageal squamous cell carcinoma and precancerous lesions under narrow-band imaging (with video).

BACKGROUND AND AIMS: Although narrow-band imaging (NBI) is a useful modality for detecting and delineating esophageal squamous cell carcinoma (ESCC), there is a risk of incorrectly determining the margins of some lesions even with NBI. This study aimed to develop an artificial intelligence (AI) system for detecting superficial ESCC and precancerous lesions and delineating the extent of lesions under NBI. METHODS: Nonmagnified NBI images from 4 hospitals were collected and annotated. Internal and external image test datasets were used to evaluate the detection and delineation performance of the system. The delineation performance of the system was compared with that of endoscopists. Furthermore, the system was directly integrated into the endoscopy equipment, and its real-time diagnostic capability was prospectively estimated. RESULTS: The system was trained and tested using 10,047 still images and 140 videos from 1112 patients and 1183 lesions. In the image testing, the accuracy of the system in detecting lesions in internal and external tests was 92.4% and 89.9%, respectively. The accuracy of the system in delineating extents in internal and external tests was 88.9% and 87.0%, respectively. The delineation performance of the system was superior to that of junior endoscopists and similar to that of senior endoscopists. In the prospective clinical evaluation, the system exhibited satisfactory performance, with an accuracy of 91.4% in detecting lesions and an accuracy of 85.9% in delineating extents. CONCLUSIONS: The proposed AI system could accurately detect superficial ESCC and precancerous lesions and delineate the extent of lesions under NBI.