Jesper Molin

Implementation of large-scale routine diagnostics using whole slide imaging in Sweden: Digital pathology experiences 2006-2013.

Recent technological advances have improved the whole slide imaging (WSI) scanner quality and reduced the cost of storage, thereby enabling the deployment of digital pathology for routine diagnostics. In this paper we present the experiences from two Swedish sites having deployed routine large-scale WSI for primary review. At Kalmar County Hospital, the digitization process started in 2006 to reduce the time spent at the microscope in order to improve the ergonomics. Since 2008, more than 500,000 glass slides have been scanned in the routine operations of Kalmar and the neighboring Linköping University Hospital. All glass slides are digitally scanned yet they are also physically delivered to the consulting pathologist who can choose to review the slides on screen, in the microscope, or both. The digital operations include regular remote case reporting by a few hospital pathologists, as well as around 150 cases per week where primary review is outsourced to a private clinic. To investigate how the pathologists choose to use the digital slides, a web-based questionnaire was designed and sent out to the pathologists in Kalmar and Linköping. The responses showed that almost all pathologists think that ergonomics have improved and that image quality was sufficient for most histopathologic diagnostic work. 38 ± 28% of the cases were diagnosed digitally, but the survey also revealed that the pathologists commonly switch back and forth between digital and conventional microscopy within the same case. The fact that two full-scale digital systems have been implemented and that a large portion of the primary reporting is voluntarily performed digitally shows that large-scale digitization is possible today.

Feature-enhancing zoom to facilitate Ki-67 hot spot detection

Image processing algorithms in pathology commonly include automated decision points such as classifications. While this enables efficient automation, there is also a risk that errors are induced. A different paradigm is to use image processing for enhancements without introducing explicit classifications. Such enhancements can help pathologists to increase efficiency without sacrificing accuracy. In our work, this paradigm has been applied to Ki-67 hot spot detection. Ki-67 scoring is a routine analysis to quantify the proliferation rate of tumor cells. Cell counting in the hot spot, the region of highest concentration of positive tumor cells, is a method increasingly used in clinical routine. An obstacle for this method is that while hot spot selection is a task suitable for low magnification, high magnification is needed to discern positive nuclei, thus the pathologist must perform many zooming operations. We propose to address this issue by an image processing method that increases the visibility of the positive nuclei at low magnification levels. This tool displays the modified version at low magnification, while gradually blending into the original image at high magnification. The tool was evaluated in a feasibility study with four pathologists targeting routine clinical use. In a task to compare hot spot concentrations, the average accuracy was 75±4.1% using the tool and 69±4.6% without it (n=4). Feedback on the system, gathered from an observer study, indicate that the pathologists found the tool useful and fitting in their existing diagnostic process. The pathologists judged the tool to be feasible for implementation in clinical routine.

Towards grading gleason score using generically trained deep convolutional neural networks

We developed an automatic algorithm with the purpose to assist pathologists to report Gleason score on malignant prostatic adenocarcinoma specimen. In order to detect and classify the cancerous tissue, a deep convolutional neural network that had been pre-trained on a large set of photographic images was used. A specific aim was to support intuitive interaction with the result, to let pathologists adjust and correct the output. Therefore, we have designed an algorithm that makes a spatial classification of the whole slide into the same growth patterns as pathologists do. The 22-layer network was cut at an earlier layer and the output from that layer was used to train both a random forest classifier and a support vector machines classifier. At a specific layer a small patch of the image was used to calculate a feature vector and an image is represented by a number of those vectors. We have classified both the individual patches and the entire images. The classification results were compared for different scales of the images and feature vectors from two different layers from the network. Testing was made on a dataset consisting of 213 images, all containing a single class, benign tissue or Gleason score 35. Using 10-fold cross validation the accuracy per patch was 81 %. For whole images, the accuracy was increased to 89 %.

Understanding Design for Automated Image Analysis in Digital Pathology

Digital pathology is an emerging healthcare field taking advantage of technology that allows digitization of microscopy images. Such digitization enables the use of automated digital image analysis techniques, which could be beneficial for the diagnostic review and prognosis of a variety of conditions. As yet, human-computer interaction (HCI) issues in this field, which is mostly based on visual analysis, have not been systematically explored. Based on reflecting on the process of designing and deploying systems for digital pathology, we propose a new understanding to design automated tools for such environments. We used meeting minutes, design briefs, interviews, personal notes and other artifacts to conduct a thematic analysis. This enabled us to establish four design considerations for introducing digital image analysis to routine pathology that concern level of detail, verification, communication and transparency.

Slide navigation patterns among pathologists with long experience of digital review

In order to develop efficient digital pathology workstations, we studied the navigation patterns of pathologists diagnosing whole‐slide images. To gain a better understanding of these patterns, we built a conceptual model based on observations. We also determined whether or not new navigation patterns have emerged among pathologists with extensive digital experience.

Deep learning nuclei detection: A simple approach can deliver state-of-the-art results

BACKGROUND Deep convolutional neural networks have become a widespread tool for the detection of nuclei in histopathology images. Many implementations share a basic approach that includes generation of an intermediate map indicating the presence of a nucleus center, which we refer to as PMap. Nevertheless, these implementations often still differ in several parameters, resulting in different detection qualities. METHODS We identified several essential parameters and configured the basic PMap approach using combinations of them. We thoroughly evaluated and compared various configurations on multiple datasets with respect to detection quality, efficiency and training effort. RESULTS Post-processing of the PMap was found to have the largest impact on detection quality. Also, two different network architectures were identified that improve either detection quality or runtime performance. The best-performing configuration yields f1-measures of 0.816 on H&E stained images of colorectal adenocarcinomas and 0.819 on Ki-67 stained images of breast tumor tissue. On average, it was fully trained in less than 15,000 iterations and processed 4.15 megapixels per second at prediction time. CONCLUSIONS The basic PMap approach is greatly affected by certain parameters. Our evaluation provides guidance on their impact and best settings. When configured properly, this simple and efficient approach can yield equal detection quality as more complex and time-consuming state-of-the-art approaches.

Improving the creation and reporting of structured findings during digital pathology review.

Background: Today, pathology reporting consists of many separate tasks, carried out by multiple people. Common tasks include dictation during case review, transcription, verification of the transcription, report distribution, and report the key findings to follow-up registries. Introduction of digital workstations makes it possible to remove some of these tasks and simplify others. This study describes the work presented at the Nordic Symposium on Digital Pathology 2015, in Linköping, Sweden. Methods: We explored the possibility to have a digital tool that simplifies image review by assisting note-taking, and with minimal extra effort, populates a structured report. Thus, our prototype sees reporting as an activity interleaved with image review rather than a separate final step. We created an interface to collect, sort, and display findings for the most common reporting needs, such as tumor size, grading, and scoring. Results: The interface was designed to reduce the need to retain partial findings in the head or on paper, while at the same time be structured enough to support automatic extraction of key findings for follow-up registry reporting. The final prototype was evaluated with two pathologists, diagnosing complicated partial mastectomy cases. The pathologists experienced that the prototype aided them during the review and that it created a better overall workflow. Conclusions: These results show that it is feasible to simplify the reporting tasks in a way that is not distracting, while at the same time being able to automatically extract the key findings. This simplification is possible due to the realization that the structured format needed for automatic extraction of data can be used to offload the pathologists′ working memory during the diagnostic review.