Optical diagnosis in still images of colorectal polyps: comparison between expert endoscopists and PolyDeep, a Computer-Aided Diagnosis system.

Background: PolyDeep is a computer-aided detection and classification (CADe/x) system trained to detect and classify polyps. During colonoscopy, CADe/x systems help endoscopists to predict the histology of colonic lesions. Objective: To compare the diagnostic performance of PolyDeep and expert endoscopists for the optical diagnosis of colorectal polyps on still images. Methods: PolyDeep Image Classification (PIC) is an in vitro diagnostic test study. The PIC database contains NBI images of 491 colorectal polyps with histological diagnosis. We evaluated the diagnostic performance of PolyDeep and four expert endoscopists for neoplasia (adenoma, sessile serrated lesion, traditional serrated adenoma) and adenoma characterization and compared them with the McNemar test. Receiver operating characteristic curves were constructed to assess the overall discriminatory ability, comparing the area under the curve of endoscopists and PolyDeep with the chi- square homogeneity areas test. Results: The diagnostic performance of the endoscopists and PolyDeep in the characterization of neoplasia is similar in terms of sensitivity (PolyDeep: 89.05%; E1: 91.23%, p=0.5; E2: 96.11%, p<0.001; E3: 86.65%, p=0.3; E4: 91.26% p=0.3) and specificity (PolyDeep: 35.53%; E1: 33.80%, p=0.8; E2: 34.72%, p=1; E3: 39.24%, p=0.8; E4: 46.84%, p=0.2). The overall discriminative ability also showed no statistically significant differences (PolyDeep: 0.623; E1: 0.625, p=0.8; E2: 0.654, p=0.2; E3: 0.629, p=0.9; E4: 0.690, p=0.09). In the optical diagnosis of adenomatous polyps, we found that PolyDeep had a significantly higher sensitivity and a significantly lower specificity. The overall discriminative ability of adenomatous lesions by expert endoscopists is significantly higher than PolyDeep (PolyDeep: 0.582; E1: 0.685, p < 0.001; E2: 0.677, p < 0.0001; E3: 0.658, p < 0.01; E4: 0.694, p < 0.0001). Conclusion: PolyDeep and endoscopists have similar diagnostic performance in the optical diagnosis of neoplastic lesions. However, endoscopists have a better global discriminatory ability than PolyDeep in the optical diagnosis of adenomatous polyps.

PanDrugs2: prioritizing cancer therapies using integrated individual multi-omics data.

Genomics studies routinely confront researchers with long lists of tumor alterations detected in patients. Such lists are difficult to interpret since only a minority of the alterations are relevant biomarkers for diagnosis and for designing therapeutic strategies. PanDrugs is a methodology that facilitates the interpretation of tumor molecular alterations and guides the selection of personalized treatments. To do so, PanDrugs scores gene actionability and drug feasibility to provide a prioritized evidence-based list of drugs. Here, we introduce PanDrugs2, a major upgrade of PanDrugs that, in addition to somatic variant analysis, supports a new integrated multi-omics analysis which simultaneously combines somatic and germline variants, copy number variation and gene expression data. Moreover, PanDrugs2 now considers cancer genetic dependencies to extend tumor vulnerabilities providing therapeutic options for untargetable genes. Importantly, a novel intuitive report to support clinical decision-making is generated. PanDrugs database has been updated, integrating 23 primary sources that support >74K drug-gene associations obtained from 4642 genes and 14 659 unique compounds. The database has also been reimplemented to allow semi-automatic updates to facilitate maintenance and release of future versions. PanDrugs2 does not require login and is freely available at https://www.pandrugs.org/.

Negative Samples for Improving Object Detection-A Case Study in AI-Assisted Colonoscopy for Polyp Detection.

Deep learning object-detection models are being successfully applied to develop computer-aided diagnosis systems for aiding polyp detection during colonoscopies. Here, we evidence the need to include negative samples for both (i) reducing false positives during the polyp-finding phase, by including images with artifacts that may confuse the detection models (e.g., medical instruments, water jets, feces, blood, excessive proximity of the camera to the colon wall, blurred images, etc.) that are usually not included in model development datasets, and (ii) correctly estimating a more realistic performance of the models. By retraining our previously developed YOLOv3-based detection model with a dataset that includes 15% of additional not-polyp images with a variety of artifacts, we were able to generally improve its F1 performance in our internal test datasets (from an average F1 of 0.869 to 0.893), which now include such type of images, as well as in four public datasets that include not-polyp images (from an average F1 of 0.695 to 0.722).

Performance of Convolutional Neural Networks for Polyp Localization on Public Colonoscopy Image Datasets.

Colorectal cancer is one of the most frequent malignancies. Colonoscopy is the de facto standard for precancerous lesion detection in the colon, i.e., polyps, during screening studies or after facultative recommendation. In recent years, artificial intelligence, and especially deep learning techniques such as convolutional neural networks, have been applied to polyp detection and localization in order to develop real-time CADe systems. However, the performance of machine learning models is very sensitive to changes in the nature of the testing instances, especially when trying to reproduce results for totally different datasets to those used for model development, i.e., inter-dataset testing. Here, we report the results of testing of our previously published polyp detection model using ten public colonoscopy image datasets and analyze them in the context of the results of other 20 state-of-the-art publications using the same datasets. The F1-score of our recently published model was 0.88 when evaluated on a private test partition, i.e., intra-dataset testing, but it decayed, on average, by 13.65% when tested on ten public datasets. In the published research, the average intra-dataset F1-score is 0.91, and we observed that it also decays in the inter-dataset setting to an average F1-score of 0.83.

Compi: a framework for portable and reproducible pipelines.

Compi is an application framework to develop end-user, pipeline-based applications with a primary emphasis on: (i) user interface generation, by automatically generating a command-line interface based on the pipeline specific parameter definitions; (ii) application packaging, with compi-dk, which is a version-control-friendly tool to package the pipeline application and its dependencies into a Docker image; and (iii) application distribution provided through a public repository of Compi pipelines, named Compi Hub, which allows users to discover, browse and reuse them easily. By addressing these three aspects, Compi goes beyond traditional workflow engines, having been specially designed for researchers who want to take advantage of common workflow engine features (such as automatic job scheduling or logging, among others) while keeping the simplicity and readability of shell scripts without the need to learn a new programming language. Here we discuss the design of various pipelines developed with Compi to describe its main functionalities, as well as to highlight the similarities and differences with similar tools that are available. An open-source distribution under the Apache 2.0 License is available from GitHub (available at https://github.com/sing-group/compi). Documentation and installers are available from https://www.sing-group.org/compi. A specific repository for Compi pipelines is available from Compi Hub (available at https://www.sing-group.org/compihub.

Metatax: Metataxonomics with a Compi-Based Pipeline for Precision Medicine.

The human body immune system, metabolism and homeostasis are affected by microbes. Dysbiosis occurs when the homeostatic equilibrium is disrupted due to an alteration in the normal microbiota of the intestine. Dysbiosis can cause cancer, and also affect a patient's ability to respond to treatment. Metataxonomics seeks to identify the bacteria present in a biological sample, based on the sequencing of the 16S rRNA genetic marker. Precision medicine attempts to find relationships between the microbiota and the risk of acquiring cancer, and design new therapies targeting bacteria. Flexible and portable bioinformatic pipelines are necessary to be able to bring metataxonomics to the clinical field, which allow groups of biological samples to be classified according to their diversity in the microbiota. With this aim we implemented Metatax, a new pipeline to analyze biological samples based on 16S rRNA gene sequencing. The results obtained with our pipeline should complement those obtained by sequencing a patient's DNA and RNA, in addition to clinical data, to improve knowledge of the possible reasons for a disease or a worse response to treatment.