Search

* Context.-Machine learning applications in the pathology clinical domain are emerging rapidly. As decision support systems continue to mature, laboratories will increasingly need guidance to evaluate their performance in clinical practice. Currently there are no formal guidelines to assist pathology laboratories in verification and/or validation of such systems. These recommendations are being proposed for the evaluation of machine learning systems in the clinical practice of pathology. Objective.-To propose recommendations for performance evaluation of in vitro diagnostic tests on patient samples that incorporate machine learning as part of the pre-analytical, analytical, or post-analytical phases of the laboratory workflow. Topics described include considerations for machine learning model evaluation including risk assessment, predeployment requirements, data sourcing and curation, verification and validation, change control management, human-computer interaction, practitioner training, and competency evaluation. Data Sources.-An expert panel performed a review of the literature, Clinical and Laboratory Standards Institute guidance, and laboratory and government regulatory frameworks. Conclusions.-Review of the literature and existing documents enabled the development of proposed recommendations. This white paper pertains to performance evaluation of machine learning systems intended to be implemented for clinical patient testing. Further studies with real-world clinical data are encouraged to support these proposed recommendations. Performance evaluation of machine learning models is critical to verification and/or validation of in vitro diagnostic tests using machine learning intended for clinical practice. (Arch Pathol Lab Med. 2024;148:e335-e361; doi: 10.5858/arpa.2023-0042-CP), Institution of machine learning (ML) in the pathology clinical domain has gained momentum and is rapidly advancing. As ML-based clinical decision support (CDS) systems continue to mature, laboratories will increasingly [...]

Context.--Myriad forces are changing teaching and learning strategies throughout all stages and types of pathology education. Pathology educators and learners face the challenge of adapting to and adopting new methods and tools. The digital pathology transformation and the associated educational ecosystem are major factors in this setting of change. Objective.--To identify and collect resources, tools, and examples of educational innovations involving digital pathology that are valuable to pathology learners and teachers at each phase of professional development. Data Sources.--Sources were a literature review and the personal experience of authors and educators. Conclusions.--High-quality digital pathology tools and resources have permeated all the major niches within anatomic pathology and are increasingly well applied to clinical pathology for learners at all levels. Coupled with other virtual tools, the training landscape in pathology is highly enriched and much more accessible than in the past. Digital pathology is well suited to the demands of peer-to-peer education, such as in the introduction of new testing, grading, or other standardized practices. We found that digital pathology was well adapted to apply our current understanding of optimal teaching strategies and was effective at the undergraduate, graduate, postgraduate, and peer-to-peer levels. We curated and tabulated many existing resources within some segments of pathology. We identified several best practices for each training or educational stage based on current materials and proposed high-priority areas for potential future development. doi: 10.5858/arpa.2021-0473-RA, We could just as well be writing this paper with a manually powered typewriter, or with ink drawn from a well by a quill pen, had not a series of [...]

Dedifferentiated carcinoma of the female genital tract is a relatively recently recognized aggressive tumor affecting predominantly perimenopausal and postmenopausal women. In addition to having an undifferentiated component, dedifferentiated carcinoma includes a juxtaposed endometrioid adenocarcinoma, FIGO grade 1 or 2. Molecular characterization of these tumors has been a subject of discussion in multiple recent articles. We present a case of dedifferentiated carcinoma of the ovary in a 70-year-old female demonstrating concurrent inactivation of ARID1A and ARID1B. To the best of our knowledge, this is the second clinical report demonstrating dedifferentiated carcinoma of the ovary with concurrent inactivation of ARID1A and ARID1B. ARID1A and ARID1B inactivation seems to represent an alternate mechanism of switch/sucrose nonfermentable complex inactivation in the development of dedifferentiated carcinoma. Additional studies are warranted to precisely understand the molecular mechanism of cellular dedifferentiation in the dedifferentiated endometrial/ovarian carcinomas, thus guiding the development of targeted therapy. [ABSTRACT FROM AUTHOR]

Background: Papillary thyroid carcinoma (PTC) is more frequently reported in patients with Hashimoto's thyroiditis (HT), which may be associated with the presence of solid cell nests (SCNs) and focal PTC-like nuclear alterations in the thyroid gland. The point of this consideration was to assess the morphological and immunohistochemical features of SCNs and follicular epithelial changes in Vietnamese patients with HT. Materials and Methods: Hematoxylin–eosin and immunohistochemistry were performed on 20 samples of HT patients who underwent thyroidectomy and were diagnosed with Hashimoto's thyroiditis at Military Medical Hospital 103 from 6/2018 to 6/2019. The expression of five markers (P63, Calcitonin, TTF1, CK19 and HBME-1) in SCNs and follicular epithelial changes were evaluated. Results: Ninety per cent of samples had SCNs with an average of 10 SCNs per section. Only type 1 and type 4 SCNs were presented (85% and 55%, respectively) and all SCNs were composed of main cells (p63-positive). Fifteen of the 18 cases having SCNs possessed nuclear features of PTC. C-cell hyperplasia was found in one case with 20 clusters. All SCNs showed strong staining with CK19 and weak staining with HBME-1. Follicular epithelial changes were Hürthle cell metaplasia, PTC-like nuclear alterations, atypical solid nodules, papillary and glomerular-like forms (40%, 100%, 25% and 50%, respectively). Follicular cells of glomerular-like forms (new alteration) especially were positive with CK19 (2+ ~ 3+), HBME-1 (1+) and TTF1, while the components in these follicles were negative with CK19, HBME-1 and TTF1. Among PTC-like nuclear alterations, all the atypical solid nodules related to HT showed markers related to PTC and without SCNs. Conclusions: Increasing the number of SCNs, as well as PTC-like nuclear alterations of main cells in SCNs and follicular epithelial changes were co-expressed CK19 and HBME-1. Therefore, the need for HT management should be considered. [ABSTRACT FROM AUTHOR]