Quality indicators for colonoscopy in Egypt: A prospective multicenter study.

BACKGROUND AND STUDY AIMS: Despite its wide availability, we do not have sufficient data aboutthe quality of colonoscopy in Egypt. In this study, we proposed 13 indicators to assess the quality of colonoscopy procedures in the included study centers aiming to attain a representative image of the quality of CS in Egypt. PATIENTS AND METHODS: A multicenter prospective study was conducted between July and December 2020, which included all patients who underwent colonoscopy in the participating centers. The following were the proposed quality indicators: indications for colonoscopy, preprocedure clinical assessment, obtaining written informed consent, adequate colon preparation, sedation, cecal intubation rate (CIR), withdrawal time, adenoma detection rate (ADR), complication rate, photographic documentation, automated sterilization, regular infection control check, and well-equipped postprocedure recovery room. RESULT: A total of 1,006 colonoscopy procedures were performed during the study duration in the included centers. Our analysis showed the following four indicators that were fulfilled in all centers: appropriate indications for colonoscopy, preprocedure assessment, written informed consent, and automated sterilization. However, photographic documentation and postprocedure follow-up room were fulfilled only in 57 %. Furthermore, 71 % of the centers performed regular infection control checks. Adequate colon preparation was achieved in 61 % of the procedures, 81 % of the procedures were performed under sedation, 95.4 % CIR, 11-min mean withdrawal time, 15 % ADR, and 0.1 % overall complication rate. Statistically significant factors affecting CIR were age > 40 years, high-definition endoscope, previous colon intervention, and rectal bleeding, whereas those affecting ADR were age > 40 years, the use of image enhancement, previous colon intervention, rectal bleeding, the use of water pump, and a withdrawal time of > 9 min. CONCLUSION: Our study revealed the bright aspects of colonoscopy practice in Egypt, including high CIRs and low complication rates; conversely, ADR, bowel cleansing quality, and infection control measures should be improved.

Compression Helps Deep Learning in Image Classification.

The impact of JPEG compression on deep learning (DL) in image classification is revisited. Given an underlying deep neural network (DNN) pre-trained with pristine ImageNet images, it is demonstrated that, if, for any original image, one can select, among its many JPEG compressed versions including its original version, a suitable version as an input to the underlying DNN, then the classification accuracy of the underlying DNN can be improved significantly while the size in bits of the selected input is, on average, reduced dramatically in comparison with the original image. This is in contrast to the conventional understanding that JPEG compression generally degrades the classification accuracy of DL. Specifically, for each original image, consider its 10 JPEG compressed versions with their quality factor (QF) values from {100,90,80,70,60,50,40,30,20,10}. Under the assumption that the ground truth label of the original image is known at the time of selecting an input, but unknown to the underlying DNN, we present a selector called Highest Rank Selector (HRS). It is shown that HRS is optimal in the sense of achieving the highest Top k accuracy on any set of images for any k among all possible selectors. When the underlying DNN is Inception V3 or ResNet-50 V2, HRS improves, on average, the Top 1 classification accuracy and Top 5 classification accuracy on the whole ImageNet validation dataset by 5.6% and 1.9%, respectively, while reducing the input size in bits dramatically-the compression ratio (CR) between the size of the original images and the size of the selected input images by HRS is 8 for the whole ImageNet validation dataset. When the ground truth label of the original image is unknown at the time of selection, we further propose a new convolutional neural network (CNN) topology which is based on the underlying DNN and takes the original image and its 10 JPEG compressed versions as 11 parallel inputs. It is demonstrated that the proposed new CNN topology, even when partially trained, can consistently improve the Top 1 accuracy of Inception V3 and ResNet-50 V2 by approximately 0.4% and the Top 5 accuracy of Inception V3 and ResNet-50 V2 by 0.32% and 0.2%, respectively. Other selectors without the knowledge of the ground truth label of the original image are also presented. They maintain the Top 1 accuracy, the Top 5 accuracy, or the Top 1 and Top 5 accuracy of the underlying DNN, while achieving CRs of 8.8, 3.3, and 3.1, respectively.