Background: Adoption of the Digital Imaging and Communications in Medicine (DICOM) standard for whole slide images (WSIs) has been slow, despite significant time and effort by standards curators. One reason for the lack of adoption is that there are few tools which exist that can meet the requirements of WSIs, given an evolving ecosystem of best practices for implementation. Eventually, vendors will conform to the specification to ensure enterprise interoperability, but what about archived slides? Millions of slides have been scanned in various proprietary formats, many with examples of rare histologies. Our hypothesis is that if users and developers had access to easy to use tools for migrating proprietary formats to the open DICOM standard, then more tools would be developed as DICOM first implementations. Methods: The technology we present here is dicom_wsi, a Python based toolkit for converting any slide capable of being read by the OpenSlide library into DICOM conformant and validated implementations. Moreover, additional postprocessing such as background removal, digital transformations (e.g., ink removal), and annotation storage are also described. dicom_wsi is a free and open source implementation that anyone can use or modify to meet their specific purposes. Results: We compare the output of dicom_wsi to two other existing implementations of WSI to DICOM converters and also validate the images using DICOM capable image viewers. Conclusion: dicom_wsi represents the first step in a long process of DICOM adoption for WSI. It is the first open source implementation released in the developer friendly Python programming language and can be freely downloaded at .

No abstract

Introduction: Intracerebral hemorrhage (ICH) is the second most common cause of stroke and remains the second leading cause of disability impacting underserved areas. Since 2015, there has been a paradigm shift in managing ischemic stroke through applying AI and ML. However, ICH patients lack such protocol. Objective: To create a rapid, cloud-based, and deployable ML method to detect ICH potentially across the Mayo Clinic enterprise then expand to involve underserved areas. Methods: We utilized RSNA dataset for ICH. We made four total iterations using Google Cloud Vertex AutoML. We trained an AutoML model with 2,000 images followed by 6,000 images from both ICH positive and negative classes. Pixel values were measured by the Hounsfield units presenting a width of 80 Hounsfield and a level of 40 Hounsfield as the bone window. This was followed by a more detailed image preprocessing approach by combining the pixel values from each of the brain, subdural, and soft tissue window-based grayscale images into R(red)G(green)B(blue)-channel images to boost the binary ICH classification performance. Four experiments with AutoML were applied to study the impacts of training sample size and image preprocessing on model performance. Results: Out of the four AutoML experiments, the best-performing model achieved a 95.8% average precision, 91.4% precision, and 91.4% recall. Based on this analysis, our binary ICH classifier HEADS UP is both accurate and performant. Conclusion: HEADS UP, is a rapid, cloud-based, deployable ML method to detect ICH. This tool can help expedite the care of patients with ICH in resource-limited hospitals.

Introduction: Aneurysmal subarachnoid hemorrhage (SAH) is a subtype of hemorrhagic stroke with thirty-day mortality as high as 40%. Given the expansion of Machine Learning (ML) and Artificial intelligence (AI) methods in health care, SAH patients desperately need an integrated AI system that detects, segments, and supports clinical decisions based on presentation and severity. Objectives: This review aims to synthesize the current state of the art of AI and ML tools for the management of SAH patients alongside providing an up-to-date account of future horizons in patient care. Methods: We performed a systematic review through various databases such as Cochrane Central Register of Controlled Trials, MEDLINE, Scopus, Cochrane Database of Systematic Reviews, and Embase. Results: A total of 507 articles were identified. Following extensive revision, only 21 articles were relevant. Two studies reported improved mortality prediction using Glasgow Coma Scale and biomarkers such as Neutrophil to Lymphocyte Ratio and glucose. One study reported that ffANN is equal to the SAHIT and VASOGRADE scores. One study reported that metabolic biomarkers Ornithine, Symmetric Dimethylarginine, and Dimethylguanidine Valeric acid were associated with poor outcomes. Nine studies reported improved prediction of complications and reduction in latency until intervention using clinical scores and imaging. Four studies reported accurate prediction of aneurysmal rupture based on size, shape, and CNN. One study reported AI-assisted Robotic Transcranial Doppler as a substitute for clinicians. Conclusion: AI/ML technologies possess tremendous potential in accelerating SAH systems-of-care. Keeping abreast of developments is vital in advancing timely interventions for critical diseases.

Colorectal cancer (CRC) is the 2nd most commonly diagnosed cancer in the United States. Genetic testing is critical in assisting in the early detection of CRC and selection of individualized treatment plans, which have shown to improve the survival rate of CRC patients. The tissue slides review (TSR), a tumor tissue macro-dissection procedure, is a required pre-analytical step to perform genetic testing. Due to the subjective nature of the process, major discrepancies in CRC diagnostics by pathologists are reported, and metrics for quality are often only qualitative. Progressive context encoder anomaly detection (P-CEAD) is an anomaly detection approach to detect tumor tissue from Whole Slide Images (WSIs), since tumor tissue is by its nature, an anomaly. P-CEAD-based CRC tumor segmentation achieves a 71% ± 26% sensitivity, 92% ± 7% specificity, and 63% ± 23% F1 score. The proposed approach provides an automated CRC tumor segmentation pipeline with a quantitatively reproducible quality compared with the conventional manual tumor segmentation procedure.