Search

High-resolution whole slide image scans of histopathology slides have been widely used in recent years for prediction in cancer. However, in some cases, clinical informatics practitioners may only have access to low-resolution snapshots of histopathology slides, not high-resolution scans. We evaluated strategies for training neural network prognostic models in non-small cell lung cancer (NSCLC) based on low-resolution snapshots, using data from the Veterans Affairs Precision Oncology Data Repository. We compared strategies without transfer learning, with transfer learning from general domain images, and with transfer learning from publicly available high-resolution histopathology scans. We found transfer learning from high-resolution scans achieved significantly better performance than other strategies. Our contribution provides a foundation for future development of prognostic models in NSCLC that incorporate data from low-resolution pathology slide snapshots alongside known clinical predictors. [ABSTRACT FROM AUTHOR]

The categorization of intraductal proliferative lesions of the breast based on routine light microscopic examination of histopathologic sections is in many cases challenging, even for experienced pathologists. The development of computational tools to aid pathologists in the characterization of these lesions would have great diagnostic and clinical value. As a first step to address this issue, we evaluated the ability of computational image analysis to accurately classify DCIS and UDH and to stratify nuclear grade within DCIS. Using 116 breast biopsies diagnosed as DCIS or UDH from the Massachusetts General Hospital (MGH), we developed a computational method to extract 392 features corresponding to the mean and standard deviation in nuclear size and shape, intensity, and texture across 8 color channels. We used L1-regularized logistic regression to build classification models to discriminate DCIS from UDH. The top-performing model contained 22 active features and achieved an AUC of 0.95 in cross-validation on the MGH data-set. We applied this model to an external validation set of 51 breast biopsies diagnosed as DCIS or UDH from the Beth Israel Deaconess Medical Center, and the model achieved an AUC of 0.86. The top-performing model contained active features from all color-spaces and from the three classes of features (morphology, intensity, and texture), suggesting the value of each for prediction. We built models to stratify grade within DCIS and obtained strong performance for stratifying low nuclear grade vs. high nuclear grade DCIS (AUC = 0.98 in cross-validation) with only moderate performance for discriminating low nuclear grade vs. intermediate nuclear grade and intermediate nuclear grade vs. high nuclear grade DCIS (AUC = 0.83 and 0.69, respectively). These data show that computational pathology models can robustly discriminate benign from malignant intraductal proliferative lesions of the breast and may aid pathologists in the diagnosis and classification of these lesions. [ABSTRACT FROM AUTHOR]

Objectives: The intersecting of pathology training and practice and the utilization of information technology has become an increasingly common occurrence, and the most effective means of teaching residents informatics during these invaluable years has yet to be firmly established. Methods: In offering the idea of longitudinal engagement that stresses early and extended trainee involvement, we attempt to provide a different manner of helping address some of the leading time-limited issues surrounding education in informatics. Results: The proposed model is intended to allow building off a base of fundamentals reached through introductory didactics, exposure to and active participation in departmental and hospital-wide administrative bodies, refining of initial skills gained through frequent mentoring and coaching, and combining these cumulative knowledge and experiential underpinnings with graduated responsibility in a particular area of expertise. Conclusions: In transforming the ways in which pathology residencies teach their trainees informatics, the prospects of realizing its potential utility are heightened. [ABSTRACT FROM AUTHOR]

The Partners HealthCare system's Clinical Fellowship in Pathology Informatics (Boston, MA, USA) faces ongoing challenges to the delivery of its core curriculum in the forms of: (1) New classes of fellows annually with new and varying educational needs and increasingly fractured, enterprise-wide commitments; (2) taxing electronic health record (EHR) and laboratory information system (LIS) implementations; and (3) increasing interest in the subspecialty at the academic medical centers (AMCs) in what is a large health care network. In response to these challenges, the fellowship has modified its existing didactic sessions and piloted both a network-wide pathology informatics lecture series and regular "learning laboratories". Didactic sessions, which had previously included more formal discussions of the four divisions of the core curriculum: Information fundamentals, information systems, workflow and process, and governance and management, now focus on group discussions concerning the fellows' ongoing projects, updates on the enterprise-wide EHR and LIS implementations, and directed questions about weekly readings. Lectures are given by the informatics faculty, guest informatics faculty, current and former fellows, and information systems members in the network, and are open to all professional members of the pathology departments at the AMCs. Learning laboratories consist of small-group exercises geared toward a variety of learning styles, and are driven by both the fellows and a member of the informatics faculty. The learning laboratories have created a forum for discussing real-time and real-world pathology informatics matters, and for incorporating awareness of and timely discussions about the latest pathology informatics literature. These changes have diversified the delivery of the fellowship's core curriculum, increased exposure of faculty, fellows and trainees to one another, and more equitably distributed teaching responsibilities among the entirety of the pathology informatics asset in the network. Though the above approach has been in place less than a year, we are presenting it now as a technical note to allow for further discussion of evolving educational opportunities in pathology informatics and clinical informatics in general, and to highlight the importance of having a flexible fellowship with active participation from its fellows. [ABSTRACT FROM AUTHOR]

Background: Pathology informatics is both emerging as a distinct subspecialty and simultaneously becoming deeply integrated within the breadth of pathology practice. As specialists, pathology informaticians need a broad skill set, including aptitude with information fundamentals, information systems, workflow and process, and governance and management. Currently, many of those seeking training in pathology informatics additionally choose training in a second subspecialty. Combining pathology informatics training with molecular pathology is a natural extension, as molecular pathology is a subspecialty with high potential for application of modern biomedical informatics techniques. Methods and Results: Pathology informatics and molecular pathology fellows and faculty evaluated the current fellowship program's core curriculum topics and subtopics for relevance to molecular pathology. By focusing on the overlap between the two disciplines, a structured curriculum consisting of didactics, operational rotations, and research projects was developed for those fellows interested in both pathology informatics and molecular pathology. Conclusions: The scope of molecular diagnostics is expanding dramatically as technology advances and our understanding of disease extends to the genetic level. Here, we highlight many of the informatics challenges facing molecular pathology today, and outline specific informatics principles necessary for the training of future molecular pathologists. [ABSTRACT FROM AUTHOR]

Background: Pathologists and informaticians are becoming increasingly interested in electronic clinical decision support for pathology, laboratory medicine and clinical diagnosis. Improved decision support may optimize laboratory test selection, improve test result interpretation and permit the extraction of enhanced diagnostic information from existing laboratory data. Nonetheless, the field of pathology decision support is still developing. To facilitate the exchange of ideas and preliminary studies, we convened a symposium entitled: Pathology data integration and clinical decision support. Methods: The symposium was held at the Massachusetts General Hospital, on May 10, 2013. Participants were selected to represent diverse backgrounds and interests and were from nine different institutions in eight different states. Results: The day included 16 plenary talks and three panel discussions, together covering four broad areas. Summaries of each presentation are included in this manuscript. Conclusions: A number of recurrent themes emerged from the symposium. Among the most pervasive was the dichotomy between diagnostic data and diagnostic information, including the opportunities that laboratories may have to use electronic systems and algorithms to convert the data they generate into more useful information. Differences between human talents and computer abilities were described; well-designed symbioses between humans and computers may ultimately optimize diagnosis. Another key theme related to the unique needs and challenges in providing decision support for genomics and other emerging diagnostic modalities. Finally, many talks relayed how the barriers to bringing decision support toward reality are primarily personnel, political, infrastructural and administrative challenges rather than technological limitations. [ABSTRACT FROM AUTHOR]