Problems in the reproducibility of classification of small lung adenocarcinoma: an international interobserver study

Reproducibility of Assessment of Lepidic (Noninvasive) Patterns in Lung Adenocarcinoma With Cytokeratin Immunostain Compared With Hematoxylin and Eosin and the Proposed New International Association for the Study of Lung Cancer (IASLC) Algorithm

Introduction

Lepidic growth is considered noninvasive in lung nonmucinous adenocarcinoma, whereas other patterns are invasive. Considerable interobserver variability in assessing "invasion" has been reported. We assessed the utility of cytokeratin 7 (CK7) stain and recently proposed International Association for the Study of Lung Cancer criteria to improve assessment of noninvasion in lung adenocarcinoma.

Methods

Four pathologists (two staff, two trainees) assessed 158 hematoxylin and eosin (HE)- and CK7-stained slides of 108 pT1N0-2 nonmucinous lung adenocarcinoma cases. Scoring took place in four rounds. First, sections were independently scored for percentage of noninvasive or probable noninvasive and invasive or probable invasive patterns. Second, after a consensus scoring algorithm for CK7 was formulated, the slides were rescored. Subsequent third-round scoring was conducted only on HE slides using the 2023 International Association for the Study of Lung Cancer proposed criteria, and fourth-round scoring on both HE and CK7 slides simultaneously. Intraclass correlation coefficient (ICC) was calculated for each round. Recurrence-free survival was assessed using Cox proportional hazards regression methods.

Results

In the first two rounds, interobserver concordance was consistently higher with CK7 (ICC range = 0.44-0.6) than HE (range = 0.24-0.49) scores. The IASLC proposed algorithm improved ICC of HE scores to 0.60 (95% confidence interval: 0.52-0.67), and round 4 HE and CK7 combined improved ICC to 0.75 (95% confidence interval: 0.70-0.80). Continuous measures of averaged noninvasive and probable noninvasive scores on HE were associated with improved recurrence-free survival (hazard ratio: 0.83-0.86).

Conclusions

CK7 staining consistently increased interobserver concordance in assessment of invasive versus noninvasive patterns than HE. Combining CK7 with the 2023 IASLC criteria for morphologic features of invasion may further improve the interobservers' concordance for the recognition of lepidic growth in nonmucinous lung adenocarcinoma.

Invasion and Grading of Pulmonary Non-Mucinous Adenocarcinoma

Lung adenocarcinoma staging and grading were recently updated to reflect the link between histologic growth patterns and outcomes. The lepidic growth pattern is regarded as "in-situ," whereas all other patterns are regarded as invasive, though with stratification. Solid, micropapillary, and complex glandular patterns are associated with worse prognosis than papillary and acinar patterns. These recent changes have improved prognostic stratification. However, multiple pitfalls exist in measuring invasive size and in classifying lung adenocarcinoma growth patterns. Awareness of these limitations and recommended practices will help the pathology community achieve consistent prognostic performance and potentially contribute to improved patient management.

Clinical Significance of the Proposed Pathologic Criteria for Invasion by the International Association for the Study of Lung Cancer in Resected Nonmucinous Lung Adenocarcinoma

INTRODUCTION

Accurate diagnostic criteria for tumor invasion are essential for precise pathologic tumor (pT) staging. Recently, the International Association for the Study of Lung Cancer (IASLC) Pathology Committee suggested a new set of criteria for assessing tumor invasion, but the clinical usefulness of the proposed criteria has not been evaluated.

METHODS

The study included 1295 patients with resected part-solid lung adenocarcinoma from January 2017 to December 2019 at the Samsung Medical Center, Seoul, Korea. The revised pT stage was determined by the extent of the newly measured invasive component using the IASLC criteria. The primary outcome was to compare the performance of the revised pT stage with the original pT stage in predicting recurrence-free survival and proof of invasion status (i.e., recurrence or lymph node metastasis). The secondary outcome was the correlation with radiologic surrogates of tumor invasiveness (consolidation-to-tumor ratio and maximum standardized uptake value) and pathologic risk factors.

RESULTS

The re-evaluation resulted in a 22% downstaging and 2.5% upstaging of pT, which improved the correlation with radiologic (consolidation-to-tumor ratio and maximum standardized uptake value) and pathologic risk factors. The revised pT staging allowed for more accurate discrimination of recurrence-free survival than the original pT staging (c-index = 0.794 versus 0.717). Moreover, the revised pT staging significantly improved the prediction of recurrence or lymph node metastasis (area under the curve = 0.818 versus 0.741, p < 0.001).

CONCLUSIONS

To our knowledge, this is the first study evaluating the clinical significance of the IASLC-proposed criteria for invasion. The proposed IASLC criteria offered better alignment with clinicopathologic risk factors and improved prognostication. Further studies are warranted to assess the impact of the IASLC criteria on treatment decisions and patient outcomes.

Endobronchial spread of adenocarcinoma is a distinct pattern of invasion and associated with inferior clinical outcomes in lung adenocarcinoma

AIM

The spread of lung adenocarcinoma cells into the bronchi and bronchioles is not well documented. We termed this histological finding "endobronchial spreading of adenocarcinoma" (EBSA) and investigated its prevalence and clinical significance.

METHODS AND RESULTS

We reviewed 320 resected specimens from patients diagnosed with invasive adenocarcinoma, and EBSA was observed in 144 patients (45%). EBSA was significantly associated with advanced pathological stage, higher histological grade, larger tumour invasion, lymphovascular infiltration, and spread through air spaces. Patients with EBSA had significantly shorter relapse-free survival (RFS) and cancer-specific survival (CSS) in univariate analysis (P < 0.001). In a subgroup analysis of patient with small-sized (invasion size ≤30 mm) adenocarcinoma in the localized stage, EBSA was an independent inferior prognostic indicator in multivariate analysis. In a subgroup analysis of patients with small-sized Grade 1 nonmucinous adenocarcinoma (n = 61), EBSA was observed in 11 patients, and the presence of EBSA was associated with significantly shorter RFS and CSS (P = 0.026 and P = 0.001, respectively).

CONCLUSION

Our results demonstrated that EBSA is a significant risk factor for disease recurrence and cancer-related deaths. EBSA can be regarded as a distinctive pattern of invasion and its recognition can be beneficial in the diagnosis of lung adenocarcinoma.

Updates on lung adenocarcinoma: invasive size, grading and STAS

Advancements in the classification of lung adenocarcinoma have resulted in significant changes in pathological reporting. The eighth edition of the tumour-node-metastasis (TNM) staging guidelines calls for the use of invasive size in staging in place of total tumour size. This shift improves prognostic stratification and requires a more nuanced approach to tumour measurements in challenging situations. Similarly, the adoption of new grading criteria based on the predominant and highest-grade pattern proposed by the International Association for the Study of Lung Cancer (IASLC) shows improved prognostication, and therefore clinical utility, relative to previous grading systems. Spread through airspaces (STAS) is a form of tumour invasion involving tumour cells spreading through the airspaces, which has been highly researched in recent years. This review discusses updates in pathological T staging, adenocarcinoma grading and STAS and illustrates the utility and limitations of current concepts in lung adenocarcinoma.

Standardized Classification of Lung Adenocarcinoma Subtypes and Improvement of Grading Assessment Through Deep Learning

The histopathologic distinction of lung adenocarcinoma (LADC) subtypes is subject to high interobserver variability, which can compromise the optimal assessment of patient prognosis. Therefore, this study developed convolutional neural networks capable of distinguishing LADC subtypes and predicting disease-specific survival, according to the recently established LADC tumor grades. Consensus LADC histopathologic images were obtained from 17 expert pulmonary pathologists and one pathologist in training. Two deep learning models (AI-1 and AI-2) were trained to predict eight different LADC classes. Furthermore, the trained models were tested on an independent cohort of 133 patients. The models achieved high precision, recall, and F1 scores exceeding 0.90 for most of the LADC classes. Clear stratification of the three LADC grades was reached in predicting the disease-specific survival by the two models, with both Kaplan-Meier curves showing significance (P = 0.0017 and 0.0003). Moreover, both trained models showed high stability in the segmentation of each pair of predicted grades with low variation in the hazard ratio across 200 bootstrapped samples. These findings indicate that the trained convolutional neural networks improve the diagnostic accuracy of the pathologist and refine LADC grade assessment. Thus, the trained models are promising tools that may assist in the routine evaluation of LADC subtypes and grades in clinical practice.

Overcoming the Interobserver Variability in Lung Adenocarcinoma Subtyping: A Clustering Approach to Establish a Ground Truth for Downstream Applications

CONTEXT.—

The accurate identification of different lung adenocarcinoma histologic subtypes is important for determining prognosis but can be challenging because of overlaps in the diagnostic features, leading to considerable interobserver variability.

OBJECTIVE.—

To provide an overview of the diagnostic agreement for lung adenocarcinoma subtypes among pathologists and to create a ground truth using the clustering approach for downstream computational applications.

DESIGN.—

Three sets of lung adenocarcinoma histologic images with different evaluation levels (small patches, areas with relatively uniform histology, and whole slide images) were reviewed by 17 international expert lung pathologists and 1 pathologist in training. Each image was classified into one or several lung adenocarcinoma subtypes.

RESULTS.—

Among the 4702 patches of the first set, 1742 (37%) had an overall consensus among all pathologists. The overall Fleiss κ score for the agreement of all subtypes was 0.58. Using cluster analysis, pathologists were hierarchically grouped into 2 clusters, with κ scores of 0.588 and 0.563 in clusters 1 and 2, respectively. Similar results were obtained for the second and third sets, with fair-to-moderate agreements. Patches from the first 2 sets that obtained the consensus of the 18 pathologists were retrieved to form consensus patches and were regarded as the ground truth of lung adenocarcinoma subtypes.

CONCLUSIONS.—

Our observations highlight discrepancies among experts when assessing lung adenocarcinoma subtypes. However, a subsequent number of consensus patches could be retrieved from each cluster, which can be used as ground truth for the downstream computational pathology applications, with minimal influence from interobserver variability.

Systematic assessment of prognostic molecular features across cancers

Precision oncology promises accurate prediction of disease trajectories by utilizing molecular features of tumors. We present a systematic analysis of the prognostic potential of diverse molecular features across large cancer cohorts. We find that the mRNA expression of biologically coherent sets of genes (modules) is substantially more predictive of patient survival than single-locus genomic and transcriptomic aberrations. Extending our analysis beyond existing curated gene modules, we find a large novel class of highly prognostic DNA/RNA cis-regulatory modules associated with dynamic gene expression within cancers. Remarkably, in more than 82% of cancers, modules substantially improve survival stratification compared with conventional clinical factors and prominent genomic aberrations. The prognostic potential of cancer modules generalizes to external cohorts better than conventionally used single-gene features. Finally, a machine-learning framework demonstrates the combined predictive power of multiple modules, yielding prognostic models that perform substantially better than existing histopathological and clinical factors in common use.

Defining Morphologic Features of Invasion in Pulmonary Nonmucinous Adenocarcinoma With Lepidic Growth: A Proposal by the International Association for the Study of Lung Cancer Pathology Committee

INTRODUCTION

Since the eight edition of the Union for International Cancer Control and American Joint Committee on Cancer TNM classification system, the primary tumor pT stage is determined on the basis of presence and size of the invasive components. The aim of this study was to identify histologic features in tumors with lepidic growth pattern which may be used to establish criteria for distinguishing invasive from noninvasive areas.

METHODS

A Delphi approach was used with two rounds of blinded anonymized analysis of resected nonmucinous lung adenocarcinoma cases with presumed invasive and noninvasive components, followed by one round of reviewer de-anonymized and unblinded review of cases with known outcomes. A digital pathology platform was used for measuring total tumor size and invasive tumor size.

RESULTS

The mean coefficient of variation for measuring total tumor size and tumor invasive size was 6.9% (range: 1.7%-22.3%) and 54% (range: 14.7%-155%), respectively, with substantial variations in interpretation of the size and location of invasion among pathologists. Following the presentation of the results and further discussion among members at large of the International Association for the Study of Lung Cancer Pathology Committee, extensive epithelial proliferation (EEP) in areas of collapsed lepidic growth pattern is recognized as a feature likely to be associated with invasive growth. The EEP is characterized by multilayered luminal epithelial cell growth, usually with high-grade cytologic features in several alveolar spaces.

CONCLUSIONS

Collapsed alveoli and transition zones with EEP were identified by the Delphi process as morphologic features that were a source of interobserver variability. Definition criteria for collapse and EEP are proposed to improve reproducibility of invasion measurement.

Use of Computed Tomography-Guided Percutaneous Biopsy of Invasive Non-Mucinous Lung Adenocarcinoma to Predict the Degree of Histological Differentiation

Background

The International Association for the Study of Lung Cancer (IASLC) published a grading system for invasive pulmonary adenocarcinoma that is closely associated with prognosis. This study aimed to investigate the accuracy of computed tomography (CT)-guided biopsy specimen grading and surgery-guided grading systems for detecting invasive non-mucinous lung adenocarcinoma and to determine whether CT-guided biopsy can predict the degree of histological differentiation.

Methods

In total, 130 patients with invasive non-mucinous lung adenocarcinoma who underwent CT-guided biopsy before surgical excision were retrospectively studied. Biopsy and surgical specimen pathologies were compared. Grading was performed according to different subtypes proposed by the International Association for the Study of Lung Cancer. Sensitivity, specificity, positive and negative predictive values (PPV/NPV), and accuracy were calculated for each subtype and grade.

Results

The concordance rates of biopsy and surgical pathology subtypes and grades were 73.1% and 72.3%, respectively. Sensitivity, specificity, PPV, NPV, and accuracy of grade 3 were 54.8%, 100%, 100%, 87.6%, and 89.2%, respectively. Pathology grades were primarily discrepant with respect to two aspects of biopsy and surgical samples in the same patient. First, the biopsy and surgical specimen pathology findings indicated lepidic and acinar subtypes as the main subtypes in the same patient, respectively. Second, biopsy specimen histology did not find solid types; however, >20% of solid subtypes were identified in surgical pathology samples in the same patient.

Conclusions

The preoperative CT-guided biopsy specimen grading system showed relatively high accuracy and could predict the prognosis of invasive non-mucinous lung adenocarcinoma.

Preference of grade and lymphovascular invasion over invasive size measurement in stage I lung adenocarcinoma

AIMS

Although it is necessary to measure the invasive size of lung adenocarcinoma with a lepidic component, it is not uncommon to have trouble in measuring the invasive size of lung adenocarcinoma. This study examined whether there were other stronger prognostic factors than invasive size.

METHODS

We characterised the clinicopathological features associated with recurrence-free survival (RFS) of 686 patients with the pathological stage (p-Stage) I lung adenocarcinoma. Moreover, we compared the area under the curve (AUC) values for recurrence between various combinations of pathological-baseline (age & sex & p-Stage based on invasive size) (B(i)) and several prognostic factors, and various combinations of p-baseline based on total tumour size (B(t)) and several prognostic factors.

RESULTS

AUC showed no significant differences between B(i) & new International Association for the Study of Lung Cancer grade (G) or vascular invasion (V), and B(t) & G or V. AUC was the highest in B & G & lymphatic invasion (L) & V. RFS was significantly shorter in patients with G3 OR L(+) OR V(+) than in those with G≤2 AND L(-) AND V(-) in each p-Stage based on invasive size (p-Stage(i)) and p-Stage based on total tumour size (p-Stage(t)) (p<0.05), and there were no significant differences in RFS between each p-Stage(i) and p-Stage(t).

CONCLUSIONS

In any invasive size or total tumour size of p-Stage I lung adenocarcinoma, G, L and V are more powerful prognostic factors than the size criteria of p-Stage. Therefore, pathologists should focus on these pathological findings.

Current Landscape of Non-Small Cell Lung Cancer: Epidemiology, Histological Classification, Targeted Therapies, and Immunotherapy

Non-small cell lung cancer (NSCLC) is a subtype of the most frequently diagnosed cancer in the world. Its epidemiology depends not only on tobacco exposition but also air quality. While the global trends in NSCLC incidence have started to decline, we can observe region-dependent differences related to the education and the economic level of the patients. Due to an increasing understanding of NSCLC biology, new diagnostic and therapeutic strategies have been developed, such as the reorganization of histopathological classification or tumor genotyping. Precision medicine is focused on the recognition of a genetic mutation in lung cancer cells called "driver mutation" to provide a variety of specific inhibitors of improperly functioning proteins. A rapidly growing group of approved drugs for targeted therapy in NSCLC currently allows the following mutated proteins to be treated: EGFR family (ERBB-1, ERBB-2), ALK, ROS1, MET, RET, NTRK, and RAF. Nevertheless, one of the most frequent NSCLC molecular sub-types remains without successful treatment: the K-Ras protein. In this review, we discuss the current NSCLC landscape treatment focusing on targeted therapy and immunotherapy, including first- and second-line monotherapies, immune checkpoint inhibitors with chemotherapy treatment, and approved predictive biomarkers.

Verification of the eighth edition of the UICC-TNM classification on surgically resected lung adenocarcinoma: Comparison with previous classification in a local center

BACKGROUND

The UICC 8th TNM classification of lung cancer has been changed dramatically, especially in measuring methods of T-desriptors. Different from squamous- or small-cell carcinomas, in which the solid- and the invasive-diameter mostly agree with each other, the diameter of the radiological solid part and that of pathological invasive part in adenocarcinomas often does not match.

AIM

We aimed to determine radiological and pathological tumor diameters of pulmonary adenocarcinomas with clinicopathological factors and evaluate the validity of the 8th edition in comparison with the 7th edition.

METHODS AND RESULTS

We retrospectively analyzed clinicopathological factors of 429 patients with surgically resected pulmonary adenocarcinomas. The maximum tumor and their solid-part diameters were measured using thin-sectioned computed tomography and compared with pathological tumor and invasive diameters. Overall survival (OS) rate was determined using the Kaplan-Meier method for different subgroups of clinicopathological factors. Akaike's information criteria (AIC) was used as a discriminative measure for the univariate Cox model for the 7th and 8th editions. Multivariate Cox regression analysis was performed to explore independent prognostic factors. Correlation coefficients between radiological and pathological diameters in the 7th and 8th editions were 0.911 and 0.888, respectively, without a significant difference. The major reasons for the difference in the 8th edition were the presence of intratumoral fibrosis and papillary growth pattern. The weighted kappa coefficients in the 8th edition were superior those in the 7th edition for both the T and Stage classifications. In the univariate Cox model, AIC levels were the lowest in the 8th edition. Multivariate analysis revealed that age, lymphovascular invasion, pT(8th), and stage were the most important determinants for OS.

CONCLUSION

The UICC 8th edition is a more discriminative classification than the 7th edition. For subsolid nodules, continuous efforts are necessary to increase the universality of the measurement of solid and invasive diameters.

Pulmonary Adenocarcinomas of Low Malignant Potential: Proposed Criteria to Expand the Spectrum Beyond Adenocarcinoma In Situ and Minimally Invasive Adenocarcinoma

Lung cancer screening has improved mortality among high-risk smokers but has coincidentally detected a fraction of nonprogressive adenocarcinoma historically classified as bronchoalveolar carcinoma (BAC). In the National Lung Screening Trial (NLST) the majority of BAC-comprising 29% of computed tomography-detected stage I lung adenocarcinoma-were considered overdiagnosis after extended follow-up comparison with the control arm. In the current classification, adenocarcinoma in situ and minimally invasive adenocarcinoma have replaced BAC but together comprise only ∼5% of stage I lung adenocarcinoma. Lepidic and subsets of papillary and acinar adenocarcinoma also infrequently recur. We, therefore, propose criteria for low malignant potential (LMP) adenocarcinoma among nonmucinous adenocarcinoma measuring ≤3 cm in total, exhibiting ≥15% lepidic growth, and lacking nonpredominant high-grade patterns (≥10% cribriform, ≥5% micropapillary, ≥5% solid), >1 mitosis per 2 mm2, angiolymphatic or visceral pleural invasion, spread through air spaces or necrosis. We tested these criteria in a multi-institutional cohort of 328 invasive stage I (eighth edition) and in situ adenocarcinomas and observed 16% LMP and 7% adenocarcinoma in situ/minimally invasive adenocarcinoma which together (23%) approximated the frequency of overdiagnosed stage I BAC in the NLST. The LMP group had 100% disease-specific survival. The proposed LMP criteria, incorporating multiple histologic parameters, may be a clinically useful "low-grade" prognostic group. Validation of these criteria in additional retrospective cohorts and prospective screen-detected cohorts should be considered.

A narrative review on characterization of acute respiratory distress syndrome in COVID-19-infected lungs using artificial intelligence

COVID-19 has infected 77.4 million people worldwide and has caused 1.7 million fatalities as of December 21, 2020. The primary cause of death due to COVID-19 is Acute Respiratory Distress Syndrome (ARDS). According to the World Health Organization (WHO), people who are at least 60 years old or have comorbidities that have primarily been targeted are at the highest risk from SARS-CoV-2. Medical imaging provides a non-invasive, touch-free, and relatively safer alternative tool for diagnosis during the current ongoing pandemic. Artificial intelligence (AI) scientists are developing several intelligent computer-aided diagnosis (CAD) tools in multiple imaging modalities, i.e., lung computed tomography (CT), chest X-rays, and lung ultrasounds. These AI tools assist the pulmonary and critical care clinicians through (a) faster detection of the presence of a virus, (b) classifying pneumonia types, and (c) measuring the severity of viral damage in COVID-19-infected patients. Thus, it is of the utmost importance to fully understand the requirements of for a fast and successful, and timely lung scans analysis. This narrative review first presents the pathological layout of the lungs in the COVID-19 scenario, followed by understanding and then explains the comorbid statistical distributions in the ARDS framework. The novelty of this review is the approach to classifying the AI models as per the by school of thought (SoTs), exhibiting based on segregation of techniques and their characteristics. The study also discusses the identification of AI models and its extension from non-ARDS lungs (pre-COVID-19) to ARDS lungs (post-COVID-19). Furthermore, it also presents AI workflow considerations of for medical imaging modalities in the COVID-19 framework. Finally, clinical AI design considerations will be discussed. We conclude that the design of the current existing AI models can be improved by considering comorbidity as an independent factor. Furthermore, ARDS post-processing clinical systems must involve include (i) the clinical validation and verification of AI-models, (ii) reliability and stability criteria, and (iii) easily adaptable, and (iv) generalization assessments of AI systems for their use in pulmonary, critical care, and radiological settings.

Mucinous Cell Clusters in Infantile Congenital Pulmonary Airway Malformations Mimic Adult Mucinous Adenocarcinoma But Are Not Associated With Poor Outcomes When Appropriately Resected

Congenital pulmonary airway malformations (CPAMs) are abnormalities of the lung arising during development. At our institution the majority of type I infantile CPAMs contain mucinous cell clusters (MCCs). The overlapping histology of MCCs and adult in situ mucinous adenocarcinomas, as well as reports of metastatic mucinous adenocarcinoma arising in CPAMs resected later in childhood raise concerns about the malignant potential of these cells. However, after adequate surgical resection, malignant recurrence has not been reported in infants with CPAMs. Despite benign behavior, MCCs often have histologic features that, in an adult, would be consistent with a diagnosis of adenocarcinoma. Therefore, to assess the spectrum of features that may be seen in these presumed precursor lesions, we characterized the histology of 671 MCCs spread across 44 infantile CPAMs and compared them to 10 adult mucinous adenocarcinomas. MCCs in CPAMS were often numerous, widespread, and located outside of the large cysts. Mucinous and nonmucinous epithelium within CPAMs showed complex architecture, making application of adult adenocarcinoma architectural patterns difficult. The MCCs within CPAMs displayed nuclear features similar to adult mucinous adenocarcinomas. The proliferative index in infantile MCCs was higher than in adult mucinous adenocarcinomas but was also higher in uninvolved infantile lung tissue. This work illustrates that histologic features typically associated with adenocarcinoma frequently occur within CPAMs; however, this does not alter their benign behavior. Therefore, extreme caution should be used if adult lung cancer terminology is applied to avoid significant potential psychological and physical harms associated with the label of adenocarcinoma.

A narrative review of digital pathology and artificial intelligence: focusing on lung cancer

The emergence of whole slide imaging technology allows for pathology diagnosis on a computer screen. The applications of digital pathology are expanding, from supporting remote institutes suffering from a shortage of pathologists to routine use in daily diagnosis including that of lung cancer. Through practice and research large archival databases of digital pathology images have been developed that will facilitate the development of artificial intelligence (AI) methods for image analysis. Currently, several AI applications have been reported in the field of lung cancer; these include the segmentation of carcinoma foci, detection of lymph node metastasis, counting of tumor cells, and prediction of gene mutations. Although the integration of AI algorithms into clinical practice remains a significant challenge, we have implemented tumor cell count for genetic analysis, a helpful application for routine use. Our experience suggests that pathologists often overestimate the contents of tumor cells, and the use of AI-based analysis increases the accuracy and makes the tasks less tedious. However, there are several difficulties encountered in the practical use of AI in clinical diagnosis. These include the lack of sufficient annotated data for the development and validation of AI systems, the explainability of black box AI models, such as those based on deep learning that offer the most promising performance, and the difficulty in defining the ground truth data for training and validation owing to inherent ambiguity in most applications. All of these together present significant challenges in the development and clinical translation of AI methods in the practice of pathology. Additional research on these problems will help in resolving the barriers to the clinical use of AI. Helping pathologists in developing knowledge of the working and limitations of AI will benefit the use of AI in both diagnostics and research.

Radiological-pathological correlation of subsolid pulmonary nodules: A single centre retrospective evaluation of the 2011 IASLC adenocarcinoma classification system

INTRODUCTION

The 2011 IASLC classification system proposes guidelines for radiologists and pathologists to classify adenocarcinomas spectrum lesions as preinvasive, minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IA). IA portends the worst clinical prognosis, and the imaging distinction between MIA and IA is controversial.

MATERIALS AND METHODS

Subsolid pulmonary nodules resected by microcoil localization over a three-year period were retrospectively reviewed by three chest radiologists and a pulmonary pathologist. Nodules were classified radiologically based on preoperative computed tomography (CT), with the solid nodule component measured on mediastinal windows applied to high-frequency lung kernel reconstructions, and pathologically according to 2011 IASLC criteria. Radiology interobserver and radiological-pathological variability of nodule classification, and potential reasons for nodule classification discordance were assessed.

RESULTS

Seventy-one subsolid nodules in 67 patients were included. The average size of invasive disease focus at histopathology was 5 mm (standard deviation 5 mm). Radiology interobserver agreement of nodule classification was good (Cohen's Kappa = 0.604, 95 % CI: 0.447 to 0.761). Agreement between consensus radiological interpretation and pathological category was fair (Cohen's Kappa = 0.236, 95 % CI: 0.054-0.421). Radiological and pathological nodule classification were concordant in 52 % (37 of 71) of nodules. The IASLC proposed CT solid component cut-off of 5 mm to distinguish MIA and IA yielded a sensitivity of 59 % and specificity of 80 %. Common reasons for nodule classification discordance included multiple solid components within a nodule on CT, scar and stromal collapse at pathology, and measurement variability.

CONCLUSION

Solid component(s) within persistent part-solid pulmonary nodules raise suspicion for invasive adenocarcinoma. Preoperative imaging classification is frequently discordant from final pathology, reflecting interpretive and technical challenges in radiological and pathological analysis.

Pathologists should probably forget about kappa. Percent agreement, diagnostic specificity and related metrics provide more clinically applicable measures of interobserver variability

Kappa statistics have been widely used in the pathology literature to compare interobserver diagnostic variability (IOV) among different pathologists but there has been limited discussion about the clinical significance of kappa scores. Five representative and recent pathology papers were queried using clinically relevant specific questions to learn how IOV was evaluated and how the clinical applicability of results was interpreted. The papers supported our anecdotal impression that pathologists usually assess IOV using Cohen's or Fleiss' kappa statistics and interpret the results using some variation of the scale proposed by Landis and Koch. The papers did not cite or propose specific guidelines to comment on the clinical applicability of results. The solutions proposed to decrease IOV included the development of better diagnostic criteria and additional educational efforts, but the possibility that the entities themselves represented a continuum of morphologic findings rather than distinct diagnostic categories was not considered in any of the studies. A dataset from a previous study of IOV reported by Thunnissen et al. was recalculated to estimate percent agreement among 19 international lung pathologists for the diagnosis of 74 challenging lung neuroendocrine neoplasms. Kappa scores and diagnostic sensitivity, specificity, positive and negative predictive values were calculated using the majority consensus diagnosis for each case as the gold reference diagnosis for that case. Diagnostic specificity estimates among multiple pathologists were > 90%, although kappa scores were considerably more variable. We explain why kappa scores are of limited clinical applicability in pathology and propose the use of positive and negative percent agreement and diagnostic specificity against a gold reference diagnosis to evaluate IOV among two and multiple raters, respectively.

A Grading System for Invasive Pulmonary Adenocarcinoma: A Proposal From the International Association for the Study of Lung Cancer Pathology Committee

INTRODUCTION

A grading system for pulmonary adenocarcinoma has not been established. The International Association for the Study of Lung Cancer pathology panel evaluated a set of histologic criteria associated with prognosis aimed at establishing a grading system for invasive pulmonary adenocarcinoma.

METHODS

A multi-institutional study involving multiple cohorts of invasive pulmonary adenocarcinomas was conducted. A cohort of 284 stage I pulmonary adenocarcinomas was used as a training set to identify histologic features associated with patient outcomes (recurrence-free survival [RFS] and overall survival [OS]). Receiver operating characteristic curve analysis was used to select the best model, which was validated (n = 212) and tested (n = 300, including stage I-III) in independent cohorts. Reproducibility of the model was assessed using kappa statistics.

RESULTS

The best model (area under the receiver operating characteristic curve [AUC] = 0.749 for RFS and 0.787 for OS) was composed of a combination of predominant plus high-grade histologic pattern with a cutoff of 20% for the latter. The model consists of the following: grade 1, lepidic predominant tumor; grade 2, acinar or papillary predominant tumor, both with no or less than 20% of high-grade patterns; and grade 3, any tumor with 20% or more of high-grade patterns (solid, micropapillary, or complex gland). Similar results were seen in the validation (AUC = 0.732 for RFS and 0.787 for OS) and test cohorts (AUC = 0.690 for RFS and 0.743 for OS), confirming the predictive value of the model. Interobserver reproducibility revealed good agreement (k = 0.617).

CONCLUSIONS

A grading system based on the predominant and high-grade patterns is practical and prognostic for invasive pulmonary adenocarcinoma.

8th Edition Tumor, Node, and Metastasis T-Stage Prognosis Discrepancies: Solid Component Diameter Predicts Prognosis Better than Invasive Component Diameter

The biggest change in the 8th edition of the tumor, lymph node, and metastasis (TNM) classification is the recommendation of the solid component diameter and invasive size for determining the clinical and pathological T-factor, respectively. Here, we validated new proposals for the Lung Cancer TNM classification’s revision and compared clinical and pathological T-stages. We retrospectively analyzed 177 cases of non-small cell lung cancers without lymph node metastasis, and involving complete resection, that occurred in our department between January 2017 and March 2019. We reviewed the overall tumor diameter, solid component diameter, and clinical T-factor on computed tomography (CT), and the pathological tumor diameter, pathological invasion diameter, pathological T-factor, and prognosis. The difference between the pathological invasive size and solid size on CT was within 5 mm in 99 cases (56%). At a two-year recurrence-free survival rate, the clinical T-stage demonstrated a better prognostic outcome than the pathological T-stage. Despite including the benign findings, the solid component diameter was better correlated with prognosis than the invasive size. Therefore, in cases of discrepancies of clinically and pathologically detected tumor size, the solid CT size should also be used for the pathological T classification.