Real-Time Evaluation of Helicobacter pylori Infection by Convolution Neural Network During White-Light Endoscopy: A Prospective, Multicenter Study (With Video).

INTRODUCTION: Convolutional neural network during endoscopy may facilitate evaluation of Helicobacter pylori infection without obtaining gastric biopsies. The aim of the study was to evaluate the diagnosis accuracy of a computer-aided decision support system for H. pylori infection (CADSS-HP) based on convolutional neural network under white-light endoscopy. METHODS: Archived video recordings of upper endoscopy with white-light examinations performed at Sir Run Run Shaw Hospital (January 2019-September 2020) were used to develop CADSS-HP. Patients receiving endoscopy were prospectively enrolled (August 2021-August 2022) from 3 centers to calculate the diagnostic property. Accuracy of CADSS-HP for H. pylori infection was also compared with endoscopic impression, urea breath test (URT), and histopathology. H. pylori infection was defined by positive test on histopathology and/or URT. RESULTS: Video recordings of 599 patients who received endoscopy were used to develop CADSS-HP. Subsequently, 456 patients participated in the prospective evaluation including 189 (41.4%) with H. pylori infection. With a threshold of 0.5, CADSS-HP achieved an area under the curve of 0.95 (95% confidence interval [CI], 0.93-0.97) with sensitivity and specificity of 91.5% (95% CI 86.4%-94.9%) and 88.8% (95% CI 84.2%-92.2%), respectively. CADSS-HP demonstrated higher sensitivity (91.5% vs 78.3%; mean difference = 13.2%, 95% CI 5.7%-20.7%) and accuracy (89.9% vs 83.8%, mean difference = 6.1%, 95% CI 1.6%-10.7%) compared with endoscopic diagnosis by endoscopists. Sensitivity of CADSS-HP in diagnosing H. pylori was comparable with URT (91.5% vs 95.2%; mean difference = 3.7%, 95% CI -1.8% to 9.4%), better than histopathology (91.5% vs 82.0%; mean difference = 9.5%, 95% CI 2.3%-16.8%). DISCUSSION: CADSS-HP achieved high sensitivity in the diagnosis of H. pylori infection in the real-time test, outperforming endoscopic diagnosis by endoscopists and comparable with URT. Clinicaltrials.gov ; ChiCTR2000030724.

Neoadjuvant therapy with anlotinib in a locally advanced and pulmonary metastasis PTC patient harboring TERT promoter and BRAFV600E mutations: a case report.

A 71-year-old woman with recurrent papillary thyroid carcinoma (PTC) was referred to our hospital. A computed tomography scan revealed extensive recurrence in the neck, invading sternocleidomastoid muscle, internal jugular vein, sternal end of the clavicle, strap muscle and skin; and lateral compartment and subclavian lymph nodes were also involved. Multiple pulmonary micrometastases also noticed. The tumor was considered unresectable; however, the patient was unwilling to accept highly invasive surgery. Therefore, we initiated neoadjuvant therapy with anlotinib, 12mg p.o. daily with a 2-week on/1-week off regimen. The tumor shrunk to resectable state after 4 cycles of treatment, and after 3 weeks of withdrawal, successful surgical resection without gross tumor residual was performed. Pathology confirmed as classic PTC harboring coexistent TERT promoter and BRAFV600E mutations by NGS. After anlotinib therapy, apoptosis induction was observed, and proliferation increased, which was due to three weeks of anlotinib withdraw. Structual recurrence was recorded at 6 months after operation due to no further treatment was taken. Our finding suggests that anlotinib could represent as a good treatment option for patients with locally advanced (with or without distant metastasis) PTC; Anlotinib treatment resulted in sufficient reduction of the tumor mass to enable total thyroidectomy and radioactive iodine treatment, providing long-term control of the disease.

Neoadjuvant therapy with anlotinib in a locally advanced and pulmonary metastasis PTC patient harboring TERT promoter and BRAFV600E mutations: a case report

SUMMARY A 71-year-old woman with recurrent papillary thyroid carcinoma (PTC) was referred to our hospital. A computed tomography scan revealed extensive recurrence in the neck, invading sternocleidomastoid muscle, internal jugular vein, sternal end of the clavicle, strap muscle and skin; and lateral compartment and subclavian lymph nodes were also involved. Multiple pulmonary micrometastases also noticed. The tumor was considered unresectable; however, the patient was unwilling to accept highly invasive surgery. Therefore, we initiated neoadjuvant therapy with anlotinib, 12mg p.o. daily with a 2-week on/1-week off regimen. The tumor shrunk to resectable state after 4 cycles of treatment, and after 3 weeks of withdrawal, successful surgical resection without gross tumor residual was performed. Pathology confirmed as classic PTC harboring coexistent TERT promoter and BRAFV600E mutations by NGS. After anlotinib therapy, apoptosis induction was observed, and proliferation increased, which was due to three weeks of anlotinib withdraw. Structual recurrence was recorded at 6 months after operation due to no further treatment was taken. Our finding suggests that anlotinib could represent as a good treatment option for patients with locally advanced (with or without distant metastasis) PTC; Anlotinib treatment resulted in sufficient reduction of the tumor mass to enable total thyroidectomy and radioactive iodine treatment, providing long-term control of the disease.

Multi-label recognition of cancer-related lesions with clinical priors on white-light endoscopy.

Deep learning-based computer-aided diagnosis techniques have demonstrated encouraging performance in endoscopic lesion identification and detection, and have reduced the rate of missed and false detections of disease during endoscopy. However, the interpretability of the model-based results has not been adequately addressed by existing methods. This phenomenon is directly manifested by a significant bias in the representation of feature localization. Good recognition models experience severe feature localization errors, particularly for lesions with subtle morphological features, and such unsatisfactory performance hinders the clinical deployment of models. To effectively alleviate this problem, we proposed a solution to optimize the localization bias in feature representations of cancer-related recognition models that is difficult to accurately label and identify in clinical practice. Optimization was performed in the training phase of the model through the proposed data augmentation method and auxiliary loss function based on clinical priors. The data augmentation method, called partial jigsaw, can "break" the spatial structure of lesion-independent image blocks and enrich the data feature space to decouple the interference of background features on the space and focus on fine-grained lesion features. The annotation-based auxiliary loss function used class activation maps for sample distribution correction and led the model to present localization representation converging on the gold standard annotation of visualization maps. The results show that with the improvement of our method, the precision of model recognition reached an average of 92.79%, an F1-score of 92.61%, and accuracy of 95.56% based on a dataset constructed from 23 hospitals. In addition, we quantified the evaluation representation of visualization feature maps. The improved model yielded significant offset correction results for visualized feature maps compared with the baseline model. The average visualization-weighted positive coverage improved from 51.85% to 83.76%. The proposed approach did not change the deployment capability and inference speed of the original model and can be incorporated into any state-of-the-art neural network. It also shows the potential to provide more accurate localization inference results and assist in clinical examinations during endoscopies.

Simultaneous Recognition of Atrophic Gastritis and Intestinal Metaplasia on White Light Endoscopic Images Based on Convolutional Neural Networks: A Multicenter Study.

INTRODUCTION: Patients with atrophic gastritis (AG) or gastric intestinal metaplasia (GIM) have elevated risk of gastric adenocarcinoma. Endoscopic screening and surveillance have been implemented in high incidence countries. The study aimed to evaluate the accuracy of a deep convolutional neural network (CNN) for simultaneous recognition of AG and GIM. METHODS: Archived endoscopic white light images with corresponding gastric biopsies were collected from 14 hospitals located in different regions of China. Corresponding images by anatomic sites containing AG, GIM, and chronic non-AG were categorized using pathology reports. The participants were randomly assigned (8:1:1) to the training cohort for developing the CNN model (TResNet), the validation cohort for fine-tuning, and the test cohort for evaluating the diagnostic accuracy. The area under the curve (AUC), sensitivity, specificity, and accuracy with 95% confidence interval (CI) were calculated. RESULTS: A total of 7,037 endoscopic images from 2,741 participants were used to develop the CNN for recognition of AG and/or GIM. The AUC for recognizing AG was 0.98 (95% CI 0.97-0.99) with sensitivity, specificity, and accuracy of 96.2% (95% CI 94.2%-97.6%), 96.4% (95% CI 94.8%-97.9%), and 96.4% (95% CI 94.4%-97.8%), respectively. The AUC for recognizing GIM was 0.99 (95% CI 0.98-1.00) with sensitivity, specificity, and accuracy of 97.9% (95% CI 96.2%-98.9%), 97.5% (95% CI 95.8%-98.6%), and 97.6% (95% CI 95.8%-98.6%), respectively. DISCUSSION: CNN using endoscopic white light images achieved high diagnostic accuracy in recognizing AG and GIM.

Mesenchymal Stem Cells in Gastric Cancer: Vicious but Hopeful.

Tumor progression depends on the collaborative interactions between tumor cells and the surrounding stroma. First-line therapies direct against cancer cells may not reach a satisfactory outcome, such as gastric cancer (GC), with high risk of recurrence and metastasis. Therefore, novel treatments and drugs target the effects of stroma components are to be promising alternatives. Mesenchymal stem cells (MSC) represent the decisive components of tumor stroma that are found to strongly affect GC development and progression. MSC from bone marrow or adjacent normal tissues express homing profiles in timely response to GC-related inflammation signals and anchor into tumor bulks. Then the newly recruited "naïve" MSC would achieve phenotype and functional alternations and adopt the greater tumor-supporting potential under the reprogramming of GC cells. Conversely, both new-comers and tumor-resident MSC are able to modulate the tumor biology via aberrant activation of oncogenic signals, metabolic reprogramming and epithelial-to-mesenchymal transition. And they also engage in remodeling the stroma better suited for tumor progression through immunosuppression, pro-angiogenesis, as well as extracellular matrix reshaping. On the account of tumor tropism, MSC could be engineered to assist earlier diagnosis of GC and deliver tumor-killing agents precisely to the tumor microenvironment. Meanwhile, intercepting and abrogating vicious signals derived from MSC are of certain significance for the combat of GC. In this review, we mainly summarize current advances concerning the reciprocal metabolic interactions between MSC and GC and their underlying therapeutic implications in the future.