Explore the vast range of titles available.

Objective To quantify the accuracy and reproducibility of pathologists’ diagnoses of melanocytic skin lesions.Design Observer accuracy and reproducibility study.Setting 10 US states.Participants Skin biopsy cases (n=240), grouped into sets of 36 or 48. Pathologists from 10 US states were randomized to independently interpret the same set on two occasions (phases 1 and 2), at least eight months apart.Main outcome measures Pathologists’ interpretations were condensed into five classes: I (eg, nevus or mild atypia); II (eg, moderate atypia); III (eg, severe atypia or melanoma in situ); IV (eg, pathologic stage T1a (pT1a) early invasive melanoma); and V (eg, ≥pT1b invasive melanoma). Reproducibility was assessed by intraobserver and interobserver concordance rates, and accuracy by concordance with three reference diagnoses.Results In phase 1, 187 pathologists completed 8976 independent case interpretations resulting in an average of 10 (SD 4) different diagnostic terms applied to each case. Among pathologists interpreting the same cases in both phases, when pathologists diagnosed a case as class I or class V during phase 1, they gave the same diagnosis in phase 2 for the majority of cases (class I 76.7%; class V 82.6%). However, the intraobserver reproducibility was lower for cases interpreted as class II (35.2%), class III (59.5%), and class IV (63.2%). Average interobserver concordance rates were lower, but with similar trends. Accuracy using a consensus diagnosis of experienced pathologists as reference varied by class: I, 92% (95% confidence interval 90% to 94%); II, 25% (22% to 28%); III, 40% (37% to 44%); IV, 43% (39% to 46%); and V, 72% (69% to 75%). It is estimated that at a population level, 82.8% (81.0% to 84.5%) of melanocytic skin biopsy diagnoses would have their diagnosis verified if reviewed by a consensus reference panel of experienced pathologists, with 8.0% (6.2% to 9.9%) of cases overinterpreted by the initial pathologist and 9.2% (8.8% to 9.6%) underinterpreted.Conclusion Diagnoses spanning moderately dysplastic nevi to early stage invasive melanoma were neither reproducible nor accurate in this large study of pathologists in the USA. Efforts to improve clinical practice should include using a standardized classification system, acknowledging uncertainty in pathology reports, and developing tools such as molecular markers to support pathologists’ visual assessments.

Expert-level artificial intelligence (AI) algorithms for prostate biopsy grading have recently been developed. However, the potential impact of integrating such algorithms into pathologist workflows remains largely unexplored. To evaluate an expert-level AI-based assistive tool when used by pathologists for the grading of prostate biopsies. This diagnostic study used a fully crossed multiple-reader, multiple-case design to evaluate an AI-based assistive tool for prostate biopsy grading. Retrospective grading of prostate core needle biopsies from 2 independent medical laboratories in the US was performed between October 2019 and January 2020. A total of 20 general pathologists reviewed 240 prostate core needle biopsies from 240 patients. Each pathologist was randomized to 1 of 2 study cohorts. The 2 cohorts reviewed every case in the opposite modality (with AI assistance vs without AI assistance) to each other, with the modality switching after every 10 cases. After a minimum 4-week washout period for each batch, the pathologists reviewed the cases for a second time using the opposite modality. The pathologist-provided grade group for each biopsy was compared with the majority opinion of urologic pathology subspecialists. An AI-based assistive tool for Gleason grading of prostate biopsies. Agreement between pathologists and subspecialists with and without the use of an AI-based assistive tool for the grading of all prostate biopsies and Gleason grade group 1 biopsies. Biopsies from 240 patients (median age, 67 years; range, 39-91 years) with a median prostate-specific antigen level of 6.5 ng/mL (range, 0.6-97.0 ng/mL) were included in the analyses. Artificial intelligence-assisted review by pathologists was associated with a 5.6% increase (95% CI, 3.2%-7.9%; P < .001) in agreement with subspecialists (from 69.7% for unassisted reviews to 75.3% for assisted reviews) across all biopsies and a 6.2% increase (95% CI, 2.7%-9.8%; P = .001) in agreement with subspecialists (from 72.3% for unassisted reviews to 78.5% for assisted reviews) for grade group 1 biopsies. A secondary analysis indicated that AI assistance was also associated with improvements in tumor detection, mean review time, mean self-reported confidence, and interpathologist agreement. In this study, the use of an AI-based assistive tool for the review of prostate biopsies was associated with improvements in the quality, efficiency, and consistency of cancer detection and grading.

Abstract Aims Extraprostatic extension of prostate cancer in radical prostatectomy specimens significantly affects patient management. We evaluated the degree of interobserver variation between uropathologists at a tertiary referral teaching hospital in assessing the extraprostatic extension of prostate cancer in radical prostatectomy specimens. Methods Histopathological data from a consecutive series of 293 radical prostatectomy specimens (January 2007–December 2012) were reviewed. A subset of 50 consecutive radical prostatectomy cases originally staged as tumours confined to the prostate (pT2) or tumours extending into periprostatic tissue (pT3a) during this period were reviewed by four specialist uropathologists. Results Five consultant histopathologists reported these specimens with significant differences in the reported stage (p=0.0164) between pathologists. Double-blind review by 4 uropathologists of 50 consecutive radical prostatectomy cases showed a lack of consensus in 16/50 (32%) cases (κ score 0.58, moderate agreement). A consensus meeting was held, but consensus could still not be reached in 9/16 cases. Conclusions Our findings highlight variability in the reporting of pT stage in radical prostatectomy specimens even by specialist uropathologists. Assessment of extraprostatic extension has important implications for patient management and there is a need for more precise guidance.

Histopathology image evaluation is indispensable for cancer diagnoses and subtype classification. Standard artificial intelligence methods for histopathology image analyses have focused on optimizing specialized models for each diagnostic task 1 , 2 . Although such methods have achieved some success, they often have limited generalizability to images generated by different digitization protocols or samples collected from different populations 3 . Here, to address this challenge, we devised the Clinical Histopathology Imaging Evaluation Foundation (CHIEF) model, a general-purpose weakly supervised machine learning framework to extract pathology imaging features for systematic cancer evaluation. CHIEF leverages two complementary pretraining methods to extract diverse pathology representations: unsupervised pretraining for tile-level feature identification and weakly supervised pretraining for whole-slide pattern recognition. We developed CHIEF using 60,530 whole-slide images spanning 19 anatomical sites. Through pretraining on 44 terabytes of high-resolution pathology imaging datasets, CHIEF extracted microscopic representations useful for cancer cell detection, tumour origin identification, molecular profile characterization and prognostic prediction. We successfully validated CHIEF using 19,491 whole-slide images from 32 independent slide sets collected from 24 hospitals and cohorts internationally. Overall, CHIEF outperformed the state-of-the-art deep learning methods by up to 36.1%, showing its ability to address domain shifts observed in samples from diverse populations and processed by different slide preparation methods. CHIEF provides a generalizable foundation for efficient digital pathology evaluation for patients with cancer. A study describes the development of a generalizable foundation machine learning framework to extract pathology imaging features for cancer diagnosis and prognosis prediction.

The correct identification of HER2-positive cases is a key point to provide the most appropriate therapy to breast cancer (BC) patients. We aimed at investigating the reproducibility and accuracy of HER2 expression by immunohistochemistry (IHC) in a selected series of 35 invasive BC cases across the pathological anatomy laboratories in Tuscany, Italy. Unstained sections of each BC case were sent to 12 participating laboratories. Pathologists were required to score according to the Food and Drug Administration (FDA) four-tier scoring system (0, 1+, 2+, 3+). Sixteen and nineteen cases were HER2 non-amplified and amplified respectively on fluorescence in situ hybridization. Among 192 readings of the 16 HER2 non-amplified samples, 153 (79.7 %) were coded as 0 or 1+, 39 (20.3 %) were 2+, and none was 3+ (false positive rate 0 %). Among 228 readings of the 19 HER2 amplified samples, 56 (24.6 %) were scored 0 or 1+, 79 (34.6 %) were 2+, and 93 (40.8 %) were 3+. The average sensitivity was 75.4 %, ranging between 47 % and 100 %, and the overall false negative rate was 24.6 %. Participation of pathological anatomy laboratories performing HER2 testing by IHC in external quality assurance programs should be made mandatory, as the system is able to identify laboratories with suboptimal performance that may need technical advice. Updated 2013 ASCO/CAP recommendations should be adopted as the widening of IHC 2+ “equivocal” category would improve overall accuracy of HER2 testing, as more cases would be classified in this category and, consequently, tested with an in situ hybridisation method.

Tumor budding is a well-established independent prognostic factor in colorectal cancer but a standardized method for its assessment has been lacking. The primary aim of the International Tumor Budding Consensus Conference (ITBCC) was to reach agreement on an international, evidence-based standardized scoring system for tumor budding in colorectal cancer. The ITBCC included nine sessions with presentations, a pre-meeting survey and an e-book covering the key publications on tumor budding in colorectal cancer. The ‘Grading of Recommendation Assessment, Development and Evaluation’ method was used to determine the strength of recommendations and quality of evidence. The following 10 statements achieved consensus: tumor budding is defined as a single tumor cell or a cell cluster consisting of four tumor cells or less (22/22, 100%). Tumor budding is an independent predictor of lymph node metastases in pT1 colorectal cancer (23/23, 100%). Tumor budding is an independent predictor of survival in stage II colorectal cancer (23/23, 100%). Tumor budding should be taken into account along with other clinicopathological features in a multidisciplinary setting (23/23, 100%). Tumor budding is counted on H&E (19/22, 86%). Intratumoral budding exists in colorectal cancer and has been shown to be related to lymph node metastasis (22/22, 100%). Tumor budding is assessed in one hotspot (in a field measuring 0.785 mm 2 ) at the invasive front (22/22, 100%). A three-tier system should be used along with the budding count in order to facilitate risk stratification in colorectal cancer (23/23, 100%). Tumor budding and tumor grade are not the same (23/23, 100%). Tumor budding should be included in guidelines/protocols for colorectal cancer reporting (23/23, 100%). Members of the ITBCC were able to reach strong consensus on a single international, evidence-based method for tumor budding assessment and reporting. It is proposed that this method be incorporated into colorectal cancer guidelines/protocols and staging systems.

The terminology and diagnostic criteria presently used by pathologists to report invasive placentation is inconsistent and does not reflect current knowledge of the pathogenesis of the disease or the needs of the clinical care team. A consensus panel was convened to recommend terminology and reporting elements unified across the spectrum of PAS specimens (i.e., delivered placenta, total or partial hysterectomy with or without extrauterine tissues, curetting for retained products of conception). The proposed nomenclature under the umbrella diagnosis of placenta accreta spectrum (PAS) replaces the traditional categorical terminology (placenta accreta, increta, percreta) with a descriptive grading system that parallels the guidelines endorsed by the International Federation of Gynaecology and Obstetrics (FIGO). In addition, the nomenclature for hysterectomy specimens is separated from that for delivered placentas. The goal for each element in the system of nomenclature was to provide diagnostic criteria and guidelines for expected use in clinical practice.

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. To propose recommendations for performance evaluation of in vitro diagnostic tests on patient samples that incorporate machine learning as part of the preanalytical, analytical, or postanalytical 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. An expert panel performed a review of the literature, Clinical and Laboratory Standards Institute guidance, and laboratory and government regulatory frameworks. 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.

Multiple independent studies have shown that tumor-infiltrating lymphocytes (TIL) are prognostic in breast cancer with potential relevance for response to immune-checkpoint inhibitor therapy. Although many groups are currently evaluating TIL, there is no standardized system for diagnostic applications. This study reports the results of two ring studies investigating TIL conducted by the International Working Group on Immuno-oncology Biomarkers. The study aim was to determine the intraclass correlation coefficient (ICC) for evaluation of TIL by different pathologists. A total of 120 slides were evaluated by a large group of pathologists with a web-based system in ring study 1 and a more advanced software-system in ring study 2 that included an integrated feedback with standardized reference images. The predefined aim for successful ring studies 1 and 2 was an ICC above 0.7 (lower limit of 95% confidence interval (CI)). In ring study 1 the prespecified endpoint was not reached (ICC: 0.70; 95% CI: 0.62–0.78). On the basis of an analysis of sources of variation, we developed a more advanced digital image evaluation system for ring study 2, which improved the ICC to 0.89 (95% CI: 0.85–0.92). The Fleiss' kappa value for <60 vs ≥60% TIL improved from 0.45 (ring study 1) to 0.63 in RS2 and the mean concordance improved from 88 to 92%. This large international standardization project shows that reproducible evaluation of TIL is feasible in breast cancer. This opens the way for standardized reporting of tumor immunological parameters in clinical studies and diagnostic practice. The software-guided image evaluation approach used in ring study 2 may be of value as a tool for evaluation of TIL in clinical trials and diagnostic practice. The experience gained from this approach might be applicable to the standardization of other diagnostic parameters in histopathology.

Neoadjuvant systemic therapy is being used increasingly in the treatment of early-stage breast cancer. Response, in the form of pathological complete response, is a validated and evaluable surrogate end point of survival after neoadjuvant therapy. Thus, pathological complete response has become a primary end point for clinical trials. However, there is a current lack of uniformity in the definition of pathological complete response. A review of standard operating procedures used by 28 major neoadjuvant breast cancer trials and/or 25 sites involved in such trials identified marked variability in specimen handling and histologic reporting. An international working group was convened to develop practical recommendations for the pathologic assessment of residual disease in neoadjuvant clinical trials of breast cancer and information expected from pathology reports. Systematic sampling of areas identified by informed mapping of the specimen and close correlation with radiological findings is preferable to overly exhaustive sampling, and permits taking tissue samples for translational research. Controversial areas are discussed, including measurement of lesion size, reporting of lymphovascular space invasion and the presence of isolated tumor cells in lymph nodes after neoadjuvant therapy, and retesting of markers after treatment. If there has been a pathological complete response, this must be clearly stated, and the presence/absence of residual ductal carcinoma in situ must be described. When there is residual invasive carcinoma, a comment must be made as to the presence/absence of chemotherapy effect in the breast and lymph nodes. The Residual Cancer Burden is the preferred method for quantifying residual disease in neoadjuvant clinical trials in breast cancer; other methods can be included per trial protocols and regional preference. Posttreatment tumor staging using the Tumor–Node–Metastasis system should be included. These recommendations for standardized pathological evaluation and reporting of neoadjuvant breast cancer specimens should improve prognostication for individual patients and allow comparison of treatment outcomes within and across clinical trials.