Interobserver variation in the classification of tumor deposits in rectal cancer—is the use of histopathological characteristics the way to go?

The focus on lymph node metastases (LNM) as the most important prognostic marker in colorectal cancer (CRC) has been challenged by the finding that other types of locoregional spread, including tumor deposits (TDs), extramural venous invasion (EMVI), and perineural invasion (PNI), also have significant impact. However, there are concerns about interobserver variation when differentiating between these features. Therefore, this study analyzed interobserver agreement between pathologists when assessing routine tumor nodules based on TNM 8. Electronic slides of 50 tumor nodules that were not treated with neoadjuvant therapy were reviewed by 8 gastrointestinal pathologists. They were asked to classify each nodule as TD, LNM, EMVI, or PNI, and to list which histological discriminatory features were present. There was overall agreement of 73.5% (κ 0.38, 95%-CI 0.33–0.43) if a nodal versus non-nodal classification was used, and 52.2% (κ 0.27, 95%-CI 0.23–0.31) if EMVI and PNI were classified separately. The interobserver agreement varied significantly between discriminatory features from κ 0.64 (95%-CI 0.58–0.70) for roundness to κ 0.26 (95%-CI 0.12–0.41) for a lone arteriole sign, and the presence of discriminatory features did not always correlate with the final classification. Since extranodal pathways of spread are prognostically relevant, classification of tumor nodules is important. There is currently no evidence for the prognostic relevance of the origin of TD, and although some histopathological characteristics showed good interobserver agreement, these are often non-specific. To optimize interobserver agreement, we recommend a binary classification of nodal versus extranodal tumor nodules which is based on prognostic evidence and yields good overall agreement.

Automating Periodontal bone loss measurement via dental landmark localisation

Purpose Periodontitis is the sixth most prevalent disease worldwide and periodontal bone loss (PBL) detection is crucial for its early recognition and establishment of the correct diagnosis and prognosis. Current radiographic assessment by clinicians exhibits substantial interobserver variation. Computer-assisted radiographic assessment can calculate bone loss objectively and aid in early bone loss detection. Understanding the rate of disease progression can guide the choice of treatment and lead to early initiation of periodontal therapy. Methodology We propose an end-to-end system that includes a deep neural network with hourglass architecture to predict dental landmarks in single, double and triple rooted teeth using periapical radiographs. We then estimate the PBL and disease severity stage using the predicted landmarks. We also introduce a novel adaptation of MixUp data augmentation that improves the landmark localisation. Results We evaluate the proposed system using cross-validation on 340 radiographs from 63 patient cases containing 463, 115 and 56 single, double and triple rooted teeth. The landmark localisation achieved Percentage Correct Keypoints (PCK) of 88.9%, 73.9% and 74.4%, respectively, and a combined PCK of 83.3% across all root morphologies, outperforming the next best architecture by 1.7%. When compared to clinicians’ visual evaluations of full radiographs, the average PBL error was 10.69%, with a severity stage accuracy of 58%. This simulates current interobserver variation, implying that diverse data could improve accuracy. Conclusions The system showed a promising capability to localise landmarks and estimate periodontal bone loss on periapical radiographs. An agreement was found with other literature that non-CEJ (Cemento-Enamel Junction) landmarks are the hardest to localise. Honing the system’s clinical pipeline will allow for its use in intervention applications.

Reliability of histopathologic diagnosis of fibrotic interstitial lung disease: an international collaborative standardization project

Background Current interstitial lung disease (ILD) diagnostic guidelines assess criteria across clinical, radiologic and pathologic domains. Significant interobserver variation in histopathologic evaluation has previously been shown but the specific source of these discrepancies is poorly documented. We sought to document specific areas of difficulty and develop improved criteria that would reduce overall interobserver variation. Methods Using an internet-based approach, we reviewed selected images of specific diagnostic features of ILD histopathology and whole slide images of fibrotic ILD. After an initial round of review, we confirmed the presence of interobserver variation among our group. We then developed refined criteria and reviewed a second set of cases. Results The initial round reproduced the existing literature on interobserver variation in diagnosis of ILD. Cases which were pre-selected as inconsistent with usual interstitial pneumonia/idiopathic pulmonary fibrosis (UIP/IPF) were confirmed as such by multi-observer review. Cases which were thought to be in the spectrum of chronic fibrotic ILD for which UIP/IPF were in the differential showed marked variation in nearly all aspects of ILD evaluation including extent of inflammation and extent and pattern of fibrosis. A proposed set of more explicit criteria had only modest effects on this outcome. While we were only modestly successful in reducing interobserver variation, we did identify specific reasons that current histopathologic criteria of fibrotic ILD are not well defined in practice. Conclusions Any additional classification scheme must address interobserver variation in histopathologic diagnosis of fibrotic ILD order to remain clinically relevant. Improvements to tissue-based diagnostics may require substantial resources such as larger datasets or novel technologies to improve reproducibility. Benchmarks should be established for expected outcomes among clinically defined subgroups as a quality metric.