Histological Subtype Classification Research Articles

P1.24-17 The Paradoxical Behavior of Kappa When Quantifying Agreement in Histological Subtype Classification among Thoracic Pathologists

P1.24-17 The Paradoxical Behavior of Kappa When Quantifying Agreement in Histological Subtype Classification among Thoracic Pathologists

The proteomic landscape of soft tissue sarcomas

Soft tissue sarcomas (STS) are rare and diverse mesenchymal cancers with limited treatment options. Here we undertake comprehensive proteomic profiling of tumour specimens from 321 STS patients representing 11 histological subtypes. Within leiomyosarcomas, we identify three proteomic subtypes with distinct myogenesis and immune features, anatomical site distribution and survival outcomes. Characterisation of undifferentiated pleomorphic sarcomas and dedifferentiated liposarcomas with low infiltrating CD3 + T-lymphocyte levels nominates the complement cascade as a candidate immunotherapeutic target. Comparative analysis of proteomic and transcriptomic profiles highlights the proteomic-specific features for optimal risk stratification in angiosarcomas. Finally, we define functional signatures termed Sarcoma Proteomic Modules which transcend histological subtype classification and show that a vesicle transport protein signature is an independent prognostic factor for distant metastasis. Our study highlights the utility of proteomics for identifying molecular subgroups with implications for risk stratification and therapy selection and provides a rich resource for future sarcoma research.

Multi-task learning-based histologic subtype classification of non-small cell lung cancer.

In clinical applications, accurate histologic subtype classification of lung cancer is important for determining appropriate treatment plans. The purpose of this paper is to evaluate the role of multi-task learning in the classification of adenocarcinoma and squamous cell carcinoma. In this paper, we propose a novel multi-task learning model for histologic subtype classification of non-small cell lung cancer based on computed tomography (CT) images. The model consists of a histologic subtype classification branch and a staging branch, which share a part of the feature extraction layers and are simultaneously trained. By optimizing on the two tasks simultaneously, our model could achieve high accuracy in histologic subtype classification of non-small cell lung cancer without relying on physician's precise labeling of tumor areas. In this study, 402 cases from The Cancer Imaging Archive (TCIA) were used in total, and they were split into training set (n = 258), internal test set (n = 66) and external test set (n = 78). Compared with the radiomics method and single-task networks, our multi-task model could reach an AUC of 0.843 and 0.732 on internal and external test set, respectively. In addition, multi-task network can achieve higher accuracy and specificity than single-task network. Compared with the radiomics methods and single-task networks, our multi-task learning model could improve the accuracy of histologic subtype classification of non-small cell lung cancer by sharing network layers, which no longer relies on the physician's precise labeling of lesion regions and could further reduce the manual workload of physicians.

Advances of pathological diagnosis of lung cancer based on clinical needs

Pathological diagnosis of lung cancer keep updating and developing, in order to meet the clinical needs in the era of precision medicine. It mainly involves the advances of histological subtype classification, molecular testing for targeted therapy, biomarkers detection for immunotherapy and the pathological evaluation for neoadjuvant therapy. Nowadays, pathological diagnosis of lung cancer present a multidisciplinary model including clinical medicine, radiology and pathology. It is gradually moving towards standardization with expection to provide better guidance for clinical treatment and prognosis.

A transformer‐based deep neural network for detection and classification of lung cancer via PET/CT images

AbstractLung cancer is the leading cause of death for men and women worldwide and the second most frequent cancer. Therefore, early detection of the disease increases the cure rate. This paper presents a new approach to evaluate the ability of positron emission tomography/computed tomography (PET/CT) images to classify and detect lung cancer using deep learning techniques. Our approach aims to fully automate lung cancer's anatomical localization from PET/CT images. It also searches to classify the tumor, which is essential as it makes it possible to determine the disease's speed of progression and the best treatments to adopt. We have built, in this work, an approach based on transformers by implementing the DETR model as a tool to detect the tumor and assist physicians in staging patients with lung cancer. The TNM staging system and histologic subtype classification were both taken as a standard for classification. Experimental results demonstrated that our approach achieves sound results on tumor localization, T staging, and histology classification. Our proposed approach detects tumors with an intersection over union (IOU) of 0.8 when tested on the Lung‐PET‐CT‐Dx dataset. It also has yielded better accuracy than state‐of‐the‐art T‐staging and histologic classification methods. It classified T‐stage and histologic subtypes with an accuracy of 0.97 and 0.94, respectively.

Frequency and reliability of histologic subtype classification in invasive and in situ melanoma treated with Mohs micrographic surgery

To the Editor: National Comprehensive Cancer Network (NCCN) guidelines for melanoma state that Mohs micrographic surgery (MMS) may be considered for melanoma in situ (MIS) of lentigo maligna or acral lentiginous subtype or minimally invasive lentigo maligna melanoma subtype. NCCN guidelines also state that MMS may be considered for minimally invasive melanomas on specialty anatomic sites. It is unclear if indications for MMS are histologic subtype, anatomic site, or both.

Reconstruction-Assisted Feature Encoding Network for Histologic Subtype Classification of Non-Small Cell Lung Cancer.

Accurate histological subtype classification between adenocarcinoma (ADC) and squamous cell carcinoma (SCC) using computed tomography (CT) images is of great importance to assist clinicians in determining treatment and therapy plans for non-small cell lung cancer (NSCLC) patients. Although current deep learning approaches have achieved promising progress in this field, they are often difficult to capture efficient tumor representations due to inadequate training data, and in consequence show limited performance. In this study, we propose a novel and effective reconstruction-assisted feature encoding network (RAFENet) for histological subtype classification by leveraging an auxiliary image reconstruction task to enable extra guidance and regularization for enhanced tumor feature representations. Different from existing reconstruction-assisted methods that directly use generalizable features obtained from shared encoder for primary task, a dedicated task-aware encoding module is utilized in RAFENet to perform refinement of generalizable features. Specifically, a cascade of cross-level non-local blocks are introduced to progressively refine generalizable features at different levels with the aid of lower-level task-specific information, which can successfully learn multi-level task-specific features tailored to histological subtype classification. Moreover, in addition to widely adopted pixel-wise reconstruction loss, we introduce a powerful semantic consistency loss function to explicitly supervise the training of RAFENet, which combines both feature consistency loss and prediction consistency loss to ensure semantic invariance during image reconstruction. Extensive experimental results show that RAFENet effectively addresses the difficult issues that cannot be resolved by existing reconstruction-based methods and consistently outperforms other state-of-the-art methods on both public and in-house NSCLC datasets. Supplementary material is available at https://github.com/lhch1994/Rafenet_sup_material.

A Multi-Task Convolutional Neural Network for Lesion Region Segmentation and Classification of Non-Small Cell Lung Carcinoma.

Targeted therapy is an effective treatment for non-small cell lung cancer. Before treatment, pathologists need to confirm tumor morphology and type, which is time-consuming and highly repetitive. In this study, we propose a multi-task deep learning model based on a convolutional neural network for joint cancer lesion region segmentation and histological subtype classification, using magnified pathological tissue images. Firstly, we constructed a shared feature extraction channel to extract abstract information of visual space for joint segmentation and classification learning. Then, the weighted losses of segmentation and classification tasks were tuned to balance the computing bias of the multi-task model. We evaluated our model on a private in-house dataset of pathological tissue images collected from Qilu Hospital of Shandong University. The proposed approach achieved Dice similarity coefficients of 93.5% and 89.0% for segmenting squamous cell carcinoma (SCC) and adenocarcinoma (AD) specimens, respectively. In addition, the proposed method achieved an accuracy of 97.8% in classifying SCC vs. normal tissue and an accuracy of 100% in classifying AD vs. normal tissue. The experimental results demonstrated that our method outperforms other state-of-the-art methods and shows promising performance for both lesion region segmentation and subtype classification.

One-step algorithm for fast-track localization and multi-category classification of histological subtypes in lung cancer

BackgroundsAccumulated evidence has proven that computer-derived features from computed tomography (CT) through radiomics and deep learning technologies can identify extensive characteristics of pulmonary malignancies, such as nodules detection and malignant lesion discrimination. However, there are few studies on whether CT images can reflect histological subtypes of lung cancer through computer-derived features. MethodsContrast-enhanced CT images prior treatment from 417 patients diagnosed with small cell lung cancer (SCLC), lung adenocarcinoma (ADC), or lung squamous cell carcinoma (SCC) were collected. ITK-SNAP software was used by trained radiologists for the manual delineation of tumor volume. Patients of each category (SCLC, ADC, SCC) were then randomly split into training datasets and test datasets in an approximately ratio of 8:2. After image pre-processing and augmentation, 25,042 CT images from the training datasets were used to train our self-developed deep learning model for fast-tracking tumor lesions and classifying corresponding histological subtypes simultaneously. The performance of the network was evaluated by accuracy, F1-score and weighted F1-average using 1,921 testing images based on parameters generated during training. ResultsThe prediction accuracy of SCLC, ADC, and SCC were 0.83, 0.75 and 0.67, respectively. The weighted F1-average was 0.75. ADC obtained the best F1-score of 0.78, which was outperformed SCLC (0.77) and SCC (0.66). The corresponding AUC values of SCLC, ADC, and SCC were 0.87, 0.84, and 0.76, respectively. Only 0.24 s were required to simultaneously achieve functions of tumor localization and histological classification on a thoracic CT image slice. The heat map visualization illustrated the extracted tumor features to classify subtypes of lung cancer by the proposed model. ConclusionsThe newly developed multi-task algorithm provides a CNN-based DL approach in lung cancer for automatically fast-tracking tumor lesions and classifying corresponding histological subtypes in one-step.

Endometrial biopsy under direct hysteroscopic visualisation versus blind endometrial sampling for the diagnosis of endometrial hyperplasia and cancer: Systematic review and meta-analysis.

Endometrial cancer is the most common gynaecological neoplasia in western countries. Diagnosis of endometrial cancer requires an endometrial biopsy. A good quality endometrial biopsy allows not only the identification of the pathology, but also preoperative histologic subtype classification. Endometrial biopsy can be performed under direct hysteroscopic visualisation, but also using blind sampling techniques. To compare endometrial biopsy performed under direct hysteroscopic visualisation versus blind sampling for the diagnosis of endometrial hyperplasia and cancer. Systematic review and meta-analysis. Electronic databases were searched from their inception until March 2022.We included all studies comparing endometrial biopsy performed under direct hysteroscopic visualisation versus blind endometrial sampling. Sample adequacy, failure rate to detect endometrial cancer or endometrial hyperplasia, and rate of detection of endometrial cancer. The summary measures were reported as relative risk (RR) with 95% of confidence interval (CI). Four studies with a total of 1,295 patients were included. Endometrial biopsy under direct hysteroscopic visualisation was associated with a significantly higher rate of sample adequacy (RR 1.13, 95% CI 1.10 to 1.17), and significantly lower risk of failure to detect endometrial cancer or endometrial hyperplasia (RR 0.16, 95% CI 0.03 to 0.92) compared to blind endometrial sampling. However, there was no significant difference between endometrial biopsies taken under direct hysteroscopic visualisation or blindly, with or without a preceding diagnostic hysteroscopy, in the rate of detection of endometrial cancer (RR 0.18, 95% CI 0.03 to 1.06). Hysteroscopic endometrial biopsy under direct visualisation is associated with significantly higher rate of sample adequacy and is comparable to blind endometrial sampling for the diagnosis of endometrial cancer and precancer. Hysteroscopic endometrial biopsy under direct visualisation would be expected to reduce diagnostic failure for endometrial cancer compared to blind endometrial sampling.

MP47-09 THE ADDED VALUE OF HISTOLOGICAL SUBTYPE IN THE PREDICTION OF ONCOLOGIC OUTCOMES IN PATIENTS WITH NON-METASTATIC PAPILLARY RENAL CELL CARCINOMA

MP47-09 THE ADDED VALUE OF HISTOLOGICAL SUBTYPE IN THE PREDICTION OF ONCOLOGIC OUTCOMES IN PATIENTS WITH NON-METASTATIC PAPILLARY RENAL CELL CARCINOMA

Artificial intelligence for histological subtype classification of breast cancer: combining multi-scale feature maps and the recurrent attention model.

The aim of this study was to apply a two-stage deep model combining multi-scale feature maps and the recurrent attention model (RAM) to assist with the pathological diagnosis of breast cancer histological subtypes by the use of whole slide images (WSIs). In this article, we propose an integrated framework combining multi-scale feature maps from Inception V3 and the recurrent attention model to classify the six histological subtypes of breast cancer. This model was trained with 194 WSIs, and on 63 validation WSIs the model achieved accuracies of 0.9030 for patch-level classification and 0.8889 for WSI-level classification. In the testing stage, a total of 65 WSIs were used to achieve an accuracy of 0.8462 without any form of datacuration. The t-distributed stochastic neighbour embedding showed that features extracted by the feature network of the RAM from WSIs of the same category can cluster together after training, and the visualization of decision steps showed that the decision-making glimpses are focused on the middle tumour area of an example from test WSIs. Finally, the false classification patches indicated that the morphological similarities between tumour tissues of different subtypes or non-tumour tissues and tumour tissues in patches might contribute to misclassification. This model can imitate the diagnostic process of pathologists, pay attention to a series of local features on the pathology image, and summarize related information, in order to accurately classify breast cancer into its histological subtypes, which is important for treatment and prognosis.

A comprehensive texture feature analysis framework of renal cell carcinoma: pathological, prognostic, and genomic evaluation based on CT images.

We tried to realize accurate pathological classification, assessment of prognosis, and genomic molecular typing of renal cell carcinoma by CT texture feature analysis. To determine whether CT texture features can perform accurate pathological classification and evaluation of prognosis and genomic characteristics in renal cell carcinoma. Patients with renal cell carcinoma from five open-source cohorts were analyzed retrospectively in this study. These data were randomly split to train and test machine learning algorithms to segment the lesion, predict the histological subtype, tumor stage, and pathological grade. Dice coefficient and performance metrics such as accuracy and AUC were calculated to evaluate the segmentation and classification model. Quantitative decomposition of the predictive model was conducted to explore the contribution of each feature. Besides, survival analysis and the statistical correlation between CT texture features, pathological, and genomic signatures were investigated. A total of 569 enhanced CT images of 443 patients (mean age 59.4, 278 males) were included in the analysis. In the segmentation task, the mean dice coefficient was 0.96 for the kidney and 0.88 for the cancer region. For classification of histologic subtype, tumor stage, and pathological grade, the model was on a par with radiologists and the AUC was 0.83 [Formula: see text] 0.1, 0.80 [Formula: see text] 0.1, and 0.77 [Formula: see text] 0.1 at 95% confidence intervals, respectively. Moreover, specific quantitative CT features related to clinical prognosis were identified. A strong statistical correlation (R2 = 0.83) between the feature crosses and genomic characteristics was shown. The structural equation modeling confirmed significant associations between CT features, pathological (β = - 0.75), and molecular subtype (β = - 0.30). The framework illustrates high performance in the pathological classification of renal cell carcinoma. Prognosis and genomic characteristics can be inferred by quantitative image analysis. • The analytical framework exhibits high-performance pathological classification of renal cell carcinoma and is on a par with human radiologists. • Quantitative decomposition of the predictive model shows that specific texture features contribute to histologic subtype and tumor stage classification. • Structural equation modeling shows the associations of genomic characteristics to CT texture features. Overall survival and molecular characteristics can be inferred by quantitative CT texture analysis in renal cell carcinoma.

Comparative analysis of machine learning approaches to classify tumor mutation burden in lung adenocarcinoma using histopathology images

Both histologic subtypes and tumor mutation burden (TMB) represent important biomarkers in lung cancer, with implications for patient prognosis and treatment decisions. Typically, TMB is evaluated by comprehensive genomic profiling but this requires use of finite tissue specimens and costly, time-consuming laboratory processes. Histologic subtype classification represents an established component of lung adenocarcinoma histopathology, but can be challenging and is associated with substantial inter-pathologist variability. Here we developed a deep learning system to both classify histologic patterns in lung adenocarcinoma and predict TMB status using de-identified Hematoxylin and Eosin (H&E) stained whole slide images. We first trained a convolutional neural network to map histologic features across whole slide images of lung cancer resection specimens. On evaluation using an external data source, this model achieved patch-level area under the receiver operating characteristic curve (AUC) of 0.78–0.98 across nine histologic features. We then integrated the output of this model with clinico-demographic data to develop an interpretable model for TMB classification. The resulting end-to-end system was evaluated on 172 held out cases from TCGA, achieving an AUC of 0.71 (95% CI 0.63–0.80). The benefit of using histologic features in predicting TMB is highlighted by the significant improvement this approach offers over using the clinical features alone (AUC of 0.63 [95% CI 0.53–0.72], p = 0.002). Furthermore, we found that our histologic subtype-based approach achieved performance similar to that of a weakly supervised approach (AUC of 0.72 [95% CI 0.64–0.80]). Together these results underscore that incorporating histologic patterns in biomarker prediction for lung cancer provides informative signals, and that interpretable approaches utilizing these patterns perform comparably with less interpretable, weakly supervised approaches.

Deep learning for predicting subtype classification and survival of lung adenocarcinoma on computed tomography

ObjectivesThe subtype classification of lung adenocarcinoma is important for treatment decision. This study aimed to investigate the deep learning and radiomics networks for predicting histologic subtype classification and survival of lung adenocarcinoma diagnosed through computed tomography (CT) images. MethodsA dataset of 1222 patients with lung adenocarcinoma were retrospectively enrolled from three medical institutions. The anonymised preoperative CT images and pathological labels of atypical adenomatous hyperplasia, adenocarcinoma in situ, minimally invasive adenocarcinoma, invasive adenocarcinoma (IAC) with five predominant components were obtained. These pathological labels were divided into 2-category classification (IAC; non-IAC), 3-category and 8-category. We modeled the classification task of histological subtypes based on modified ResNet-34 deep learning network, radiomics strategies and deep radiomics combined algorithm. Then we established the prognostic models in lung adenocarcinoma patients with survival outcomes. The accuracy (ACC), area under ROC curves (AUCs) and C-index were primarily performed to evaluate the algorithms. ResultsThis study included a training set (n = 802) and two validation cohorts (internal, n = 196; external, n = 224). The ACC of deep radiomics algorithm in internal validation achieved 0.8776, 0.8061 in the 2-category, 3-category classification, respectively. Even in 8 classifications, the AUC ranged from 0.739 to 0.940 in internal set. Further, we constructed a prognosis model that C-index was 0.892(95% CI: 0.846–0.937) in internal validation set. ConclusionsThe automated deep radiomics based triage system has achieved the great performance in the subtype classification and survival predictability in patients with CT-detected lung adenocarcinoma nodules, providing the clinical guide for treatment strategies.

Diagnostic Value of Conventional PET Parameters and Radiomic Features Extracted from 18F-FDG-PET/CT for Histologic Subtype Classification and Characterization of Lung Neuroendocrine Neoplasms.

Aim: To evaluate if conventional Positron emission tomography (PET) parameters and radiomic features (RFs) extracted by 18F-FDG-PET/CT can differentiate among different histological subtypes of lung neuroendocrine neoplasms (Lu-NENs). Methods: Forty-four naïve-treatment patients on whom 18F-FDG-PET/CT was performed for histologically confirmed Lu-NEN (n = 46) were retrospectively included. Manual segmentation was performed by two operators allowing for extraction of four conventional PET parameters (SUVmax, SUVmean, metabolic tumor volume (MTV), and total lesion glycolysis (TLG)) and 41 RFs. Lu-NENs were classified into two groups: lung neuroendocrine tumors (Lu-NETs) vs. lung neuroendocrine carcinomas (Lu-NECs). Lu-NETs were classified according to histological subtypes (typical (TC)/atypical carcinoid (AC)), Ki67-level, and TNM staging. The least absolute shrink age and selection operator (LASSO) method was used to select the most predictive RFs for classification and Pearson correlation analysis was performed between conventional PET parameters and selected RFs. Results: PET parameters, in particular, SUVmax (area under the curve (AUC) = 0.91; cut-off = 5.16) were higher in Lu-NECs vs. Lu-NETs (p < 0.001). Among RFs, HISTO_Entropy_log10 was the most predictive (AUC = 0.90), but correlated with SUVmax/SUVmean (r = 0.95/r = 0.94, respectively). No statistical differences were found between conventional PET parameters and RFs (p > 0.05) and TC vs. AC classification. Conventional PET parameters were correlated with N+ status in Lu-NETs. Conclusion: In our study, conventional PET parameters were able to distinguish Lu-NECs from Lu-NETs, but not TC from AC. RFs did not provide additional information.

Deep Learning for Predicting Subtype Classification and Survival of Lung Adenocarcinoma on Computed Tomography

Background: The subtype classification of lung adenocarcinoma is of paramount importance for preoperative adjuvant therapy. The precise evaluation in histopathologic classification of lung adenocarcinoma depends on full nodule lesion resection. This study aimed to investigate the deep learning and radiomics networks for predicting histologic subtype classification and survival of lung adenocarcinoma diagnosed with small biopsy specimen through computed tomography (CT) images. Methods: A dataset of 1222 lung adenocarcinoma patients including the clinicopathological data were retrospectively enrolled from three institutions. The anonymised preoperative CT images and pathological labels of atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), invasive adenocarcinoma (IAC) with predominant components classified into lepidic (pLAC), acinar(pAAC), papillary(pPAC), micropapillary(pMAC), and solid (pSAC) ones were obtained. These pathological labels were divided into 2-category classification (IAC; non-IAC), 3-category (Non-MAC/SAC, Non-pMAC/pSAC and pMAC/pSAC) and 8-category as aforementioned. We modeled the classification task of histological subtypes based on modified ResNet-34 deep learning network, radiomics strategies and deep radiomics combined algorithm. Then we established the prognostic models in lung adenocarcinoma patients with survival outcomes. The accuracy (ACC), area under ROC curves (AUCs) and C-index were primarily performed to evaluate the algorithms. Findings: This study included the a training set (n=802) and two validation cohorts (internal, n=196; external, n=224). The ACC of deep radiomics algorithm in internal validation achieved 0.8776, 0.8061 in the 2-category, 3-category classification, respectively. Even in 8 classifications, the AUC ranged from 0.739 to 0.940 in internal test. Further, we constructed a prognosis model that C-index was 0.892(95% Confidence Intervals: 0.846-0.937) in internal validation set. Interpretation: Our results reveal that the automated deep radiomics based triage system has achieved the great performance in the subtype classification and survival predictability in patients with CT-detected lung adenocarcinoma nodules, providing the clinical guide for preoperative adjuvant therapy. Funding Statement: National Natural Science Foundation of China, Science and Technology Project of Chengdu, and Science and Technology Project of Sichuan Declaration of Interests: The authors declare no conflict of interest. Ethics Approval Statement: This study was approved by the institutional ethics committee of participating institutions.

Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study.

BackgroundHistologic phenotype identification of Non-Small Cell Lung Cancer (NSCLC) is essential for treatment planning and prognostic prediction. The prediction model based on radiomics analysis has the potential to quantify tumor phenotypic characteristics non-invasively. However, most existing studies focus on relatively small datasets, which limits the performance and potential clinical applicability of their constructed models.MethodsTo fully explore the impact of different datasets on radiomics studies related to the classification of histological subtypes of NSCLC, we retrospectively collected three datasets from multi-centers and then performed extensive analysis. Each of the three datasets was used as the training dataset separately to build a model and was validated on the remaining two datasets. A model was then developed by merging all the datasets into a large dataset, which was randomly split into a training dataset and a testing dataset. For each model, a total of 788 radiomic features were extracted from the segmented tumor volumes. Then three widely used features selection methods, including minimum Redundancy Maximum Relevance Feature Selection (mRMR), Sequential Forward Selection (SFS), and Least Absolute Shrinkage and Selection Operator (LASSO) were used to select the most important features. Finally, three classification methods, including Logistics Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) were independently evaluated on the selected features to investigate the prediction ability of the radiomics models.ResultsWhen using a single dataset for modeling, the results on the testing set were poor, with AUC values ranging from 0.54 to 0.64. When the merged dataset was used for modeling, the average AUC value in the testing set was 0.78, showing relatively good predictive performance.ConclusionsModels based on radiomics analysis have the potential to classify NSCLC subtypes, but their generalization capabilities should be carefully considered.

Selection of Representative Histologic Slides in Interobserver Reproducibility Studies: Insights from Expert Review for Ovarian Carcinoma Subtype Classification

Background: Observer studies in pathology often utilize a limited number of representative slides per case, selected and reported in a nonstandardized manner. Reference diagnoses are commonly assumed to be generalizable to all slides of a case. We examined these issues in the context of pathologist concordance for histologic subtype classification of ovarian carcinomas (OCs). Materials and Methods: A cohort of 114 OCs consisting of 72 cases with a single representative slide (Group 1) and 42 cases with multiple representative slides (148 slides, 2–6 sections per case, Group 2) was independently reviewed by three experts in gynecologic pathology (case-based review). In a follow-up study, each individual slide was independently reviewed in a randomized order by the same pathologists (section-based review). Results: Average interobserver concordance varied from 100% for Group 1 to 64.3% for Group 2 (86.8% across all cases). Across Group 2, 19 cases (45.2%) had at least one slide classified as a different subtype than the subtype assigned from case-based review, demonstrating the impact of intratumoral heterogeneity. Section-based concordance across individual sections from Group 2 was comparable to case-based concordance for those cases indicating diagnostic challenges at the individual section level. Findings demonstrate the increased diagnostic complexity of heterogeneous tumors that require multiple section sampling and its impact on pathologist performance. Conclusions: The proportion of cases with multiple representative slides in cohorts used in validation studies, such as those conducted to evaluate artificial intelligence/machine learning tools, can influence diagnostic performance, and if not accounted for, can cause disparities between research and real-world observations and between research studies. Case selection in validation studies should account for tumor heterogeneity to create balanced datasets in terms of diagnostic complexity.

Stage-Specific PET Radiomic Prediction Model for the Histological Subtype Classification of Non-Small-Cell Lung Cancer.

PurposeTo investigate the impact of staging on differences in glucose metabolic heterogeneity between lung adenocarcinoma (ADC) and squamous cell carcinoma (SCC) by 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) textural analysis and to develop a stage-specific PET radiomic prediction model to distinguish lung ADC from SCC.Patients and MethodsPatients who were histologically diagnosed with lung ADC or SCC and underwent pretreatment 18F-FDG PET/CT scans were retrospectively identified. Radiomic features were extracted from a semiautomatically outlined tumor region in the Chang-Gung Image Texture Analysis (CGITA) software package. The differences in radiomic parameters between lung ADC and SCC were compared stage-by-stage in 253 consecutive NSCLC patients with stages I to III disease. The least absolute shrinkage and selection operator (LASSO) algorithm was used for feature selection. A radiomic signature for each stage was subsequently constructed and evaluated. Then, an individual nomogram incorporating the radiomic signature and clinical risk factors was established and evaluated. The performance of the constructed models was assessed by receiver operating characteristic (ROC) curve analysis, and the nomogram was further validated by calibration curve analysis.ResultsThe performance of the radiomic signature for distinguishing lung ADC and SCC in both the training and validation cohorts was good, with AUCs of 0.883, 0.854, and 0.895 in the training cohort and 0.932, 0.944, and 0.886 in the validation cohort for stages I, II, and III NSCLC, respectively. The radiomic-clinical nomogram integrating radiomic features with independent clinical predictors exhibited more favorable discriminative performance, with AUCs of 0.982, 0.963, and 0.979 in the training cohort and 0.989, 0.984, and 0.978 in the validation cohort for stages I, II, and III, respectively.ConclusionDifferences in PET radiomic features between lung ADC and SCC varied in different stages. Stage-specific PET radiomic prediction models provided more favorable performance for discriminating the histological subtype of NSCLC.