Identification of cecum time-location in a colonoscopy video by deep learning analysis of colonoscope movement

Density clustering-based automatic anatomical section recognition in colonoscopy video using deep learning

Recognizing anatomical sections during colonoscopy is crucial for diagnosing colonic diseases and generating accurate reports. While recent studies have endeavored to identify anatomical regions of the colon using deep learning, the deformable anatomical characteristics of the colon pose challenges for establishing a reliable localization system. This study presents a system utilizing 100 colonoscopy videos, combining density clustering and deep learning. Cascaded CNN models are employed to estimate the appendix orifice (AO), flexures, and "outside of the body," sequentially. Subsequently, DBSCAN algorithm is applied to identify anatomical sections. Clustering-based analysis integrates clinical knowledge and context based on the anatomical section within the model. We address challenges posed by colonoscopy images through non-informative removal preprocessing. The image data is labeled by clinicians, and the system deduces section correspondence stochastically. The model categorizes the colon into three sections: right (cecum and ascending colon), middle (transverse colon), and left (descending colon, sigmoid colon, rectum). We estimated the appearance time of anatomical boundaries with an average error of 6.31 s for AO, 9.79 s for HF, 27.69 s for SF, and 3.26 s for outside of the body. The proposed method can facilitate future advancements towards AI-based automatic reporting, offering time-saving efficacy and standardization.

Public Imaging Datasets of Gastrointestinal Endoscopy for Artificial Intelligence: a Review

With the advances in endoscopic technologies and artificial intelligence, a large number of endoscopic imaging datasets have been made public to researchers around the world. This study aims to review and introduce these datasets. An extensive literature search was conducted to identify appropriate datasets in PubMed, and other targeted searches were conducted in GitHub, Kaggle, and Simula to identify datasets directly. We provided a brief introduction to each dataset and evaluated the characteristics of the datasets included. Moreover, two national datasets in progress were discussed. A total of 40 datasets of endoscopic images were included, of which 34 were accessible for use. Basic and detailed information on each dataset was reported. Of all the datasets, 16 focus on polyps, and 6 focus on small bowel lesions. Most datasets (n = 16) were constructed by colonoscopy only, followed by normal gastrointestinal endoscopy and capsule endoscopy (n = 9). This review may facilitate the usage of public dataset resources in endoscopic research.

Development and validation of a deep learning-based algorithm for colonoscopy quality assessment

BACKGROUND

Quality indicators should be assessed and monitored to improve colonoscopy quality in clinical practice. Endoscopists must enter relevant information in the endoscopy reporting system to facilitate data collection, which may be inaccurate. The current study aimed to develop a full deep learning-based algorithm to identify and analyze intra-procedural colonoscopy quality indicators based on endoscopy images obtained during the procedure.

METHODS

A deep learning system for classifying colonoscopy images for quality assurance purposes was developed and its performance was assessed with an independent dataset. The system was utilized to analyze captured images and results were compared with those of real-world reports.

RESULTS

In total, 10,417 images from the hospital endoscopy database and 3157 from Hyper-Kvasir open dataset were utilized to develop the quality assurance algorithm. The overall accuracy of the algorithm was 96.72% and that of the independent test dataset was 94.71%. Moreover, 761 real-world reports and colonoscopy images were analyzed. The accuracy of electronic reports about cecal intubation rate was 99.34% and that of the algorithm was 98.95%. The agreement rate for the assessment of polypectomy rates using the electronic reports and the algorithm was 0.87 (95% confidence interval 0.83-0.90). A good correlation was found between the withdrawal time calculated using the algorithm and that entered by the physician (correlation coefficient r = 0.959, p < 0.0001).

CONCLUSION

We proposed a novel deep learning-based algorithm that used colonoscopy images for quality assurance purposes. This model can be used to automatically assess intra-procedural colonoscopy quality indicators in clinical practice.

Deep learning model for classifying endometrial lesions

BACKGROUND

Hysteroscopy is a commonly used technique for diagnosing endometrial lesions. It is essential to develop an objective model to aid clinicians in lesion diagnosis, as each type of lesion has a distinct treatment, and judgments of hysteroscopists are relatively subjective. This study constructs a convolutional neural network model that can automatically classify endometrial lesions using hysteroscopic images as input.

METHODS

All histopathologically confirmed endometrial lesion images were obtained from the Shengjing Hospital of China Medical University, including endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyps, and submucous myomas. The study included 1851 images from 454 patients. After the images were preprocessed (histogram equalization, addition of noise, rotations, and flips), a training set of 6478 images was input into a tuned VGGNet-16 model; 250 images were used as the test set to evaluate the model's performance. Thereafter, we compared the model's results with the diagnosis of gynecologists.

RESULTS

The overall accuracy of the VGGNet-16 model in classifying endometrial lesions is 80.8%. Its sensitivity to endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyp, and submucous myoma is 84.0%, 68.0%, 78.0%, 94.0%, and 80.0%, respectively; for these diagnoses, the model's specificity is 92.5%, 95.5%, 96.5%, 95.0%, and 96.5%, respectively. When classifying lesions as benign or as premalignant/malignant, the VGGNet-16 model's accuracy, sensitivity, and specificity are 90.8%, 83.0%, and 96.0%, respectively. The diagnostic performance of the VGGNet-16 model is slightly better than that of the three gynecologists in both classification tasks. With the aid of the model, the overall accuracy of the diagnosis of endometrial lesions by gynecologists can be improved.

CONCLUSIONS

The VGGNet-16 model performs well in classifying endometrial lesions from hysteroscopic images and can provide objective diagnostic evidence for hysteroscopists.