A low-cost fiber-optic instrument to colorimetrically detect patients with Barrett's esophagus for early detection of esophageal adenocarcinoma

Attention Layer-Based Multidimensional Feature Extraction for Diagnosis of Lung Cancer

At present, early lung cancer screening is mainly based on radiologists' experience in diagnosing benign and malignant pulmonary nodules by lung CT images. On the other hand, intraoperative rapid freezing pathology needs to analyse the invasive adenocarcinoma nodules with the worst recovery in adenocarcinoma. Moreover, rapid freezing pathology has a low diagnostic accuracy for small-diameter nodules. Because of the above problems, an algorithm for diagnosing invasive adenocarcinoma nodules in ground-glass pulmonary nodules is based on CT images. According to the nodule space information and plane features, sample data of different dimensions are designed, namely, 3D space and 2D plane feature samples. The network structure is designed based on the attention mechanism and residual learning unit; 2D and 3D neural networks are along built. By fusing the feature vectors extracted from networks of different dimensions, the diagnosis results of invasive adenocarcinoma nodules are finally obtained. The algorithm was studied on 1760 ground-glass nodules with 5-20 mm diameter collected from a city chest hospital with surgical and pathological results. There were 340 nodules with invasive adenocarcinoma and 340 with noninvasive adenocarcinoma. A total of 1420 invasive nodule samples were cross-validated on this example dataset. The classification accuracy of the algorithm was 82.7%, the sensitivity was 82.9%, and the specificity was 82.6%.

Proposing Novel Data Analytics Method for Anatomical Landmark Identification from Endoscopic Video Frames

Background

The anatomical landmarks contain the characteristics that are used to guide the gastroenterologists during the endoscopy. The expert can also ensure the completion of examination with the help of the anatomical landmarks. Automatic detection of anatomical landmarks in endoscopic video frames can be helpful for guiding the physicians during screening the gastrointestinal tract (GI).

Method

This study presents an automatic novel method for anatomical landmark detection of GI tract from endoscopic video frames based on semisupervised deep convolutional neural network (CNN) and compares the results with supervised CNN model. We consider the anatomical landmarks from Kvasir dataset that includes 500 images for each class of Z-line, pylorus, and cecum. The resolution of these images varies from 750 × 576 up to 1920 × 1072 pixels.

Result

Experimental results show that the supervised CNN has highly desirable performance with accuracy of 100%. Also, our proposed semisupervised CNN can compete with a slight difference similar to the CNN model. Our proposed semisupervised model trained using 1, 5, 10, and 20 percent of training data records as labeled training dataset has the average accuracy of 83%, 98%, 99%, and 99%, respectively.

Conclusion

The main advantage of our proposed method is achieving the high accuracy with small amount of labeled data without spending time for labeling more data. The strength of our proposed method saves the required labor, cost, and time for data labeling.

Barrett's Esophagus: Emerging Knowledge and Management Strategies

The incidence of esophageal adenocarcinoma (EAC) has increased exponentially in the last 3 decades. Barrett's esophagus (BE) is the only known precursor of EAC. Patients with BE have a greater than 40 folds higher risk of EAC compared with the general population. Recent years have witnessed a revolution in the clinical and molecular research related to BE. However, several aspects of this condition remain controversial. Data regarding the true prevalence of BE have varied widely. Recent studies have suggested a lower incidence of EAC in nondysplastic BE (NDBE) than previously reported. There is paucity of prospective data showing a survival benefit of screening or surveillance for BE. Furthermore, the ever-increasing emphasis on healthcare cost containment has called for reexamination of the screening and surveillance strategies for BE. There is a need for identification of reliable clinical predictors or molecular biomarkers to risk-stratify patients who might benefit the most from screening or surveillance for BE. Finally, new therapies have emerged for the management of dysplastic BE. In this paper, we highlight the key areas of controversy and uncertainty surrounding BE. The paper discusses, in detail, the current literature about the molecular pathogenesis, biomarkers, histopathological diagnosis, and management strategies for BE.

Tethered capsule endoscopy, a low-cost and high-performance alternative technology for the screening of esophageal cancer and Barrett's esophagus

Esophageal cancer is currently the fastest growing cancer in the United States. To help combat the recent rise in morbidity, our laboratory has developed a low-cost tethered capsule endoscope system (TCE) aimed at improving early detection of esophageal cancer. The TCE contains a resonant fiberoptic laser scanner (1.6 mm O.D.) which fits into 6.4-mm easy-to-swallow capsule at the distal tip. The tethered portion contains a single mode optical fiber multiplexed to three laser diodes at the proximal end. This design offers two main advantages over current endoscope technology. First, because of its small size, the TCE can be swallowed with minimal patient discomfort, thereby obviating sedation. Second, by imaging via directed laser light, the TCE is strategically positioned to employ several burgeoning laser-based diagnostic technologies, such as narrow-band, hyperspectral, and fluorescence imaging. It is believed that the combination of such imaging techniques with novel biomarkers of dysplasia will greatly assist in identifying precancerous conditions such as Barrett's esophagus (BE). As the probe is swallowed, the fiber scanner captures high resolution, wide-field color images of the gastroesophageal junction (500 lines at 0.05-mm resolution) currently at 15-Hz frame rate. Video images are recorded as the capsule is slowly retracted by its tether. Accompanying software generates panoramic images from the video output by mosaicing individual frames to aid in pattern recognition. This initial report describes the rationale for the unique TCE system design, results from preliminary testing in vitro and in vivo, and discussion on the merits of this new platform technology as a basis for developing a low-cost screening program for esophageal cancer.

Columnar lined (Barrett's) esophagus: future perspectives

Columnar lined esophagus (CLE) or Barrett's esophagus is the precursor for esophageal adenocarcinoma. Future advances in understanding and management of this condition as well as improving the quality of care of CLE patients depends on answering essential questions. It is important to standardize the criteria for CLE definition. The rapid increase in incidence of CLE and adenocarcinoma raises serious concerns that the current management of gastroesophageal reflux disease (GERD) needs reassessment. The risk factors that determine who will and will not develop CLE are as yet undetermined. There is a need to develop a clinical risk stratification tool, which will help in determining who should be screened. The impact of elimination of GERD on the natural history of CLE is one important area for future research. The benefit of surveillance strategies remains unproven and the ideal endoscopic frequency, protocols and markers of cancer risk are unknown. Dysplasia may not provide the gold standard marker of cancer risk because of some inherited problems. A better technique than the current endoscopic pinch biopsy protocol is needed. To overcome the limitations of histological markers, many other markers of cancer risk needs to be developed and validated. The key question as to whether cancer risk is actually reduced by the new ablation modalities remains unanswered. The natural history of dysplasia and its management needs to be clarified. Although many questions have to be answered, it seems, however, that at least some answers exist, and these and proposals for answering some of these questions are underlined throughout this review.

Barrett's esophagus

Barrett's esophagus is an acquired condition resulting from severe esophageal mucosal injury. It still remains unclear why some patients with gastroesophageal reflux disease develop Barrett's esophagus whereas others do not. The diagnosis of Barrett's esophagus is established if the squamocolumnar junction is displaced proximal to the gastroesophageal junction and if intestinal metaplasia is detected by biopsy. Despite this seemingly simple definition, diagnostic inconsistencies remain a problem, especially in distinguishing short segment Barrett's esophagus from intestinal metaplasia of the gastric cardia. Barrett's esophagus would be of little importance were it not for its well-recognized association with adenocarcinoma of the esophagus. The incidence of esophageal adenocarcinoma continues to increase and the 5-year survival rate for this cancer remains dismal. However, cancer risk for a given patient with Barrett's esophagus is lower than previously estimated. Current strategies for improved survival in patients with esophageal adenocarcinoma focus on cancer detection at an early and potentially curable stage. This can be accomplished either by screening more patients for Barrett's esophagus or with endoscopic surveillance of patients with known Barrett's esophagus. Current screening and surveillance strategies are inherently expensive and inefficient. New techniques to improve the efficiency of cancer surveillance are evolving rapidly and hold the promise to change clinical practice in the future. Treatment options include aggressive acid suppression, antireflux surgery, chemoprevention, and ablation therapy, but there is still no clear consensus on the optimal treatment for these patients.

A low-cost fiber-optic instrument to colorimetrically detect patients with Barrett's esophagus for early detection of esophageal adenocarcinoma

In Barrett's esophagus, the precursor to esophageal adenocarcinoma, the squamocolumnar junction (SCJ) between the normal esophagus and the stomach like mucosa is proximally displaced. Currently it can be detected only by an expensive upper GI endoscopic procedure. We have developed a minimally invasive and easy to operate colorimetric instrument for the low-cost detection of Barrett's esophagus. The instrument is based on a flexible, narrow diameter, fiber-optic probe that performs a colorimetric scan of the esophageal lumen. The instrument was clinically evaluated in 50 subjects. The instrument could identify both symmetric and asymmetric SCJ's. The SCJ locations determined by the colorimetric instrument correlated strongly (R2 = 0.89) with those determined by endoscopy. The instrument identified the SCJ locations accurately (Mean of difference +/- SEM: 0.97 +/- 1.72 cm) and reproducibly (Mean of absolute difference +/- SEM: 1.33 +/- 1.40 cm). The instrument has a 90% sensitivity of identifying patients with Barrett's esophagus, based on the clinical algorithm that if the SCJ is located at a distance less than 37 cm from the teeth, then the subject has Barrett's esophagus, otherwise the subject does not have Barrett's esophagus. In conclusion, the colorimetric instrument has the potential of being a cost-effective way of determining patients likely to have Barrett's esophagus in the population.