The ratio of cancer cells to stroma within the invasive area is a histologic prognostic parameter of lung adenocarcinoma

Unveiling the landscape of pathomics in personalized immunotherapy for lung cancer: a bibliometric analysis

Background

Pathomics has emerged as a promising biomarker that could facilitate personalized immunotherapy in lung cancer. It is essential to elucidate the global research trends and emerging prospects in this domain.

Methods

The annual distribution, journals, authors, countries, institutions, and keywords of articles published between 2018 and 2023 were visualized and analyzed using CiteSpace and other bibliometric tools.

Results

A total of 109 relevant articles or reviews were included, demonstrating an overall upward trend; The terms "deep learning", "tumor microenvironment", "biomarkers", "image analysis", "immunotherapy", and "survival prediction", etc. are hot keywords in this field.

Conclusion

In future research endeavors, advanced methodologies involving artificial intelligence and pathomics will be deployed for the digital analysis of tumor tissues and the tumor microenvironment in lung cancer patients, leveraging histopathological tissue sections. Through the integration of comprehensive multi-omics data, this strategy aims to enhance the depth of assessment, characterization, and understanding of the tumor microenvironment, thereby elucidating a broader spectrum of tumor features. Consequently, the development of a multimodal fusion model will ensue, enabling precise evaluation of personalized immunotherapy efficacy and prognosis for lung cancer patients, potentially establishing a pivotal frontier in this domain of investigation.

Mean Apparent Propagator MRI: Quantitative Assessment of Tumor-Stroma Ratio in Invasive Ductal Breast Carcinoma

Purpose To determine whether metrics from mean apparent propagator (MAP) MRI perform better than apparent diffusion coefficient (ADC) value in assessing the tumor-stroma ratio (TSR) status in breast carcinoma. Materials and Methods From August 2021 to October 2022, 271 participants were prospectively enrolled (ClinicalTrials.gov identifier: NCT05159323) and underwent breast diffusion spectral imaging and diffusion-weighted imaging. MAP MRI metrics and ADC were derived from the diffusion MRI data. All participants were divided into high-TSR (stromal component < 50%) and low-TSR (stromal component ≥ 50%) groups based on pathologic examination. Clinicopathologic characteristics were collected, and MRI findings were assessed. Logistic regression was used to determine the independent variables for distinguishing TSR status. The area under the receiver operating characteristic curve (AUC) and sensitivity, specificity, and accuracy were compared between the MAP MRI metrics, either alone or combined with clinicopathologic characteristics, and ADC, using the DeLong and McNemar test. Results A total of 181 female participants (mean age, 49 years ± 10 [SD]) were included. All diffusion MRI metrics differed between the high-TSR and low-TSR groups (P < .001 to P = .01). Radial non-Gaussianity from MAP MRI and lymphovascular invasion were significant independent variables for discriminating the two groups, with a higher AUC (0.81 [95% CI: 0.74, 0.87] vs 0.61 [95% CI: 0.53, 0.68], P < .001) and accuracy (138 of 181 [76%] vs 106 of 181 [59%], P < .001) than that of the ADC. Conclusion MAP MRI may serve as a better approach than conventional diffusion-weighted imaging in evaluating the TSR of breast carcinoma. Keywords: MR Diffusion-weighted Imaging, MR Imaging, Breast, Oncology ClinicalTrials.gov Identifier: NCT05159323 Supplemental material is available for this article. © RSNA, 2024.

Feasibility and effectiveness of automatic deep learning network and radiomics models for differentiating tumor stroma ratio in pancreatic ductal adenocarcinoma

OBJECTIVE

This study aims to compare the feasibility and effectiveness of automatic deep learning network and radiomics models in differentiating low tumor stroma ratio (TSR) from high TSR in pancreatic ductal adenocarcinoma (PDAC).

METHODS

A retrospective analysis was conducted on a total of 207 PDAC patients from three centers (training cohort: n = 160; test cohort: n = 47). TSR was assessed on hematoxylin and eosin-stained specimens by experienced pathologists and divided as low TSR and high TSR. Deep learning and radiomics models were developed including ShuffulNetV2, Xception, MobileNetV3, ResNet18, support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF), and logistic regression (LR). Additionally, the clinical models were constructed through univariate and multivariate logistic regression. Kaplan-Meier survival analysis and log-rank tests were conducted to compare the overall survival time between different TSR groups.

RESULTS

To differentiate low TSR from high TSR, the deep learning models based on ShuffulNetV2, Xception, MobileNetV3, and ResNet18 achieved AUCs of 0.846, 0.924, 0.930, and 0.941, respectively, outperforming the radiomics models based on SVM, KNN, RF, and LR with AUCs of 0.739, 0.717, 0.763, and 0.756, respectively. Resnet 18 achieved the best predictive performance. The clinical model based on T stage alone performed worse than deep learning models and radiomics models. The survival analysis based on 142 of the 207 patients demonstrated that patients with low TSR had longer overall survival.

CONCLUSIONS

Deep learning models demonstrate feasibility and superiority over radiomics in differentiating TSR in PDAC. The tumor stroma ratio in the PDAC microenvironment plays a significant role in determining prognosis.

CRITICAL RELEVANCE STATEMENT

The objective was to compare the feasibility and effectiveness of automatic deep learning networks and radiomics models in identifying the tumor-stroma ratio in pancreatic ductal adenocarcinoma. Our findings demonstrate deep learning models exhibited superior performance compared to traditional radiomics models.

KEY POINTS

• Deep learning demonstrates better performance than radiomics in differentiating tumor-stroma ratio in pancreatic ductal adenocarcinoma. • The tumor-stroma ratio in the pancreatic ductal adenocarcinoma microenvironment plays a protective role in prognosis. • Preoperative prediction of tumor-stroma ratio contributes to clinical decision-making and guiding precise medicine.

Simulating Interclonal Interactions in Diffuse Large B-Cell Lymphoma

Diffuse large B-cell lymphoma (DLBCL) is one of the most common types of cancers, accounting for 37% of B-cell tumor cases globally. DLBCL is known to be a heterogeneous disease, resulting in variable clinical presentations and the development of drug resistance. One underexplored aspect of drug resistance is the evolving dynamics between parental and drug-resistant clones within the same microenvironment. In this work, the effects of interclonal interactions between two cell populations-one sensitive to treatment and the other resistant to treatment-on tumor growth behaviors were explored through a mathematical model. In vitro cultures of mixed DLBCL populations demonstrated cooperative interactions and revealed the need for modifying the model to account for complex interactions. Multiple best-fit models derived from in vitro data indicated a difference in steady-state behaviors based on therapy administrations in simulations. The model and methods may serve as a tool for understanding the behaviors of heterogeneous tumors and identifying the optimal therapeutic regimen to eliminate cancer cell populations using computer-guided simulations.

Significance of Tumor-Stroma Ratio (TSR) in Predicting Outcomes of Malignant Tumors

Background and Objectives: The present study aimed to elucidate the distribution and the prognostic implications of tumor-stroma ratio (TSR) in various malignant tumors through a meta-analysis. Materials and Methods: This meta-analysis included 51 eligible studies with information for overall survival (OS) or disease-free survival (DFS), according to TSR. In addition, subgroup analysis was performed based on criteria for high TSR. Results: The estimated rate of high TSR was 0.605 (95% confidence interval (CI) 0.565-0.644) in overall malignant tumors. The rates of high TSR ranged from 0.276 to 0.865. The highest rate of high TSR was found in endometrial cancer (0.865, 95% CI 0.827-0.895). The estimated high TSR rates of colorectal, esophageal, and stomach cancers were 0.622, 0.529, and 0.448, respectively. In overall cases, patients with high TSR had better OS and DFS than those with low TSR (hazard ratio (HR) 0.631, 95% CI 0.542-0.734, and HR 0.564, 95% CI 0.0.476-0.669, respectively). Significant correlations with OS were found in the breast, cervical, colorectal, esophagus, head and neck, ovary, stomach, and urinary tract cancers. In addition, there were significant correlations of DFS in breast, cervical, colorectal, esophageal, larynx, lung, and stomach cancers. In endometrial cancers, high TSR was significantly correlated with worse OS and DFS. Conclusions: The rate of high TSR was different in various malignant tumors. TSR can be useful for predicting prognosis through a routine microscopic examination of malignant tumors.

Tumor-Stroma Ratio in Colorectal Cancer-Comparison between Human Estimation and Automated Assessment

The tumor-stroma ratio (TSR) has been repeatedly shown to be a prognostic factor for survival prediction of different cancer types. However, an objective and reliable determination of the tumor-stroma ratio remains challenging. We present an easily adaptable deep learning model for accurately segmenting tumor regions in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of colon cancer patients into five distinct classes (tumor, stroma, necrosis, mucus, and background). The tumor-stroma ratio can be determined in the presence of necrotic or mucinous areas. We employ a few-shot model, eventually aiming for the easy adaptability of our approach to related segmentation tasks or other primaries, and compare the results to a well-established state-of-the art approach (U-Net). Both models achieve similar results with an overall accuracy of 86.5% and 86.7%, respectively, indicating that the adaptability does not lead to a significant decrease in accuracy. Moreover, we comprehensively compare with TSR estimates of human observers and examine in detail discrepancies and inter-rater reliability. Adding a second survey for segmentation quality on top of a first survey for TSR estimation, we found that TSR estimations of human observers are not as reliable a ground truth as previously thought.

The efficacy of a machine learning algorithm for assessing tumour components as a prognostic marker of surgically resected stage IA lung adenocarcinoma

BACKGROUND

The importance of the stromal components in tumour progression has been discussed widely, but their prognostic role in small size tumours with lepidic components is not fully understood. Applying digital tissue image analysis to whole-slide imaging may enhance the accuracy and reproducibility of pathological assessment. This study aimed to evaluate the prognostic value of tumour components of lung adenocarcinoma by measuring the dimensions of the tumour consisting elements separately, using a machine learning algorithm.

METHODS

Between September 2002 and December 2016, 317 patients with surgically resected, pathological stage IA adenocarcinoma with lepidic components were analysed. We assessed the whole tumour area, including the lepidic components, and measured the epithelium, collagen, elastin areas and alveolar air space. We analysed the prognostic impact of each tumour component.

RESULTS

The dimensions of the epithelium and collagen areas were independent significant risk factors for recurrence-free survival (hazard ratio, 8.38; 95% confidence interval, 1.14-61.88; P = 0.037, and hazard ratio, 2.58; 95% confidence interval, 1.14-5.83; P = 0.022, respectively). According to the subgroup analysis when combining the epithelium and collagen areas as risk factors, patients with tumours consisting of both large epithelium and collagen areas showed significantly poor prognoses (P = 0.002).

CONCLUSIONS

We assessed tumour components using a machine learning algorithm to stratify the post-operative prognosis of surgically resected stage IA adenocarcinomas. This method might guide the selection of patients with a high risk of recurrence.

Application of digital pathology and machine learning in the liver, kidney and lung diseases

The development of rapid and accurate Whole Slide Imaging (WSI) has paved the way for the application of Artificial Intelligence (AI) to digital pathology. The availability of WSI in the recent years allowed the rapid development of various AI technologies to blossom. WSI-based digital pathology combined with neural networks can automate arduous and time-consuming tasks of slide evaluation. Machine Learning (ML)-based AI has been demonstrated to outperform pathologists by eliminating inter- and intra-observer subjectivity, obtaining quantitative data from slide images, and extracting hidden image patterns that are relevant to disease subtype and progression. In this review, we outline the functionality of different AI technologies such as neural networks and deep learning and discover how aspects of different diseases make them benefit from the implementation of AI. AI has proven to be valuable in many different organs, with this review focusing on the liver, kidney, and lungs. We also discuss how AI and image analysis not only can grade diseases objectively but also discover aspects of diseases that have prognostic value. In the end, we review the current status of the integration of AI in pathology and share our vision on the future of digital pathology.

Invasive area to tumor ratio is a significant prognostic factor for non-small cell lung cancer

BACKGROUND

Although T factor is defined as the size of invasive area rather than total tumor size in the eighth edition of the TNM classification, whether the pathological invasive area to tumor ratio (ITR) is a prognostic factor has not yet been evaluated.

METHODS

In total, 432 lung adenocarcinoma patients were analyzed, among which 266 patients with pathological stage IA were used to perform a subanalysis.

RESULTS

Smoking status (odds ratio [OR]: 0.43, p = 0.01), neutrophil-to-lymphocyte ratio (NLR) (OR: 1.97, p = 0.03), maximum standardized uptake value (SUV_max ) (OR: 3.62, p < 0.01), and ITR (OR: 6.76, p < 0.01) were significantly different in univariate analysis. Smoking status (OR: 0.34, p < 0.01), SUV_max (OR: 3.05, p < 0.01), and ITR (OR: 5.44, p < 0.01) were risk factors for recurrence in multivariate analysis. In patients with pathological stage IA disease, smoking status (OR: 0.34, p = 0.03), NLR (OR: 2.30, p = 0.04), SUV_max (OR: 3.63, p < 0.01), pathological invasive area (OR: 4.00, p < 0.01), and ITR (OR: 6.03, p < 0.01) were significantly different in univariate analysis. Smoking status (OR: 0.27, p = 0.02), SUV_max (OR: 3.93, p < 0.01), and ITR (OR: 4.38, p < 0.01) were significant risk factors for recurrence in multivariate analysis.

CONCLUSIONS

SUV_max and ITR are risk factors for recurrence. These results suggest that SUV_max is important for deciding the indication for limited resection or adjuvant chemotherapy, and ITR is an adaptation criterion for adjuvant chemotherapy for early-stage lung adenocarcinoma patients.

Epithelial cell size dysregulation in human lung adenocarcinoma

Human cells tightly control their dimensions, but in some cancers, normal cell size control is lost. In this study we measure cell volumes of epithelial cells from human lung adenocarcinoma progression in situ. By leveraging artificial intelligence (AI), we reconstruct tumor cell shapes in three dimensions (3D) and find airway type 2 cells display up to 10-fold increases in volume. Surprisingly, cell size increase is not caused by altered ploidy, and up to 80% of near-euploid tumor cells show abnormal sizes. Size dysregulation is not explained by cell swelling or senescence because cells maintain cytoplasmic density and proper organelle size scaling, but is correlated with changes in tissue organization and loss of a novel network of processes that appear to connect alveolar type 2 cells. To validate size dysregulation in near-euploid cells, we sorted cells from tumor single-cell suspensions on the basis of size. Our study provides data of unprecedented detail for cell volume dysregulation in a human cancer. Broadly, loss of size control may be a common feature of lung adenocarcinomas in humans and mice that is relevant to disease and identification of these cells provides a useful model for investigating cell size control and consequences of cell size dysregulation.

Predictive Role of Tumor-Stroma Ratio for Survival of Patients With Non-Small Cell Lung Cancer: A Meta-Analysis

Background: Role of tumor-stroma ratio (TSR) as a predictor of survival in patients with non-small cell lung cancer (NSCLC) remains not clear. A systematic review and meta-analysis was conducted to summarize current evidence for the role of TSR in NSCLC.

Methods: Relevant cohort studies were retrieved via search of Medline, Embase, and Web of Science databases. The data was combined with a random-effect model by incorporating the between-study heterogeneity. Specifically, subgroup and meta-regression analyses were performed to explore the association between TSR and survival in patients with squamous cell carcinoma (SCC) or adenocarcinoma (AC).

Results: Nine cohort studies with 2031 patients with NSCLC were eligible for the meta-analysis. Pooled results showed that compared to those stroma-poor tumor, patients with stroma rich NSCLC were associated with worse recurrence-free survival (RFS, hazard ratio [HR] = 1.52, 95% confidence interval [CI]: 1.07 to 2.16, p = 0.02) and overall survival (OS, HR = 1.48, 95% CI: 1.20 to 1.82, p < 0.001). Subgroup analyses showed that stroma-rich tumor may be associated with a worse survival of SCC (HR = 1.89 and 1.47 for PFS and OS), but a possibly favorable survival of AC (HR = 0.28 and 0.69 for PFS and OS). Results of meta-regression analysis also showed that higher proportion of patients with SCC was correlated with higher HRs for RFS (Coefficient = 0.012, p = 0.03) and OS (Coefficient = 0.014, p = 0.02) in the included patients, while higher proportion of patients with AC was correlated with lower HRs for RFS (Coefficient = −0.012, p = 0.03) and OS (Coefficient = −0.013, p = 0.04), respectively.

Conclusion: Tumor TSR could be used as a predictor of survival in patients with NSCLC. The relative proportion of patients with SCC/AC in the included NSCLC patients may be an important determinant for the association between TSR and survival in NSCLC. Stroma richness may be a predictor of poor survival in patients with lung SCC, but a predictor of better survival in patients with lung AC.

CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma

Purpose

To develop and validate a machine learning classifier based on multidetector computed tomography (MDCT), for the preoperative prediction of tumor-stroma ratio (TSR) expression in patients with pancreatic ductal adenocarcinoma (PDAC).

Materials and Methods

In this retrospective study, 227 patients with PDAC underwent an MDCT scan and surgical resection. We quantified the TSR by using hematoxylin and eosin staining and extracted 1409 arterial and portal venous phase radiomics features for each patient, respectively. Moreover, we used the least absolute shrinkage and selection operator logistic regression algorithm to reduce the features. The extreme gradient boosting (XGBoost) was developed using a training set consisting of 167 consecutive patients, admitted between December 2016 and December 2017. The model was validated in 60 consecutive patients, admitted between January 2018 and April 2018. We determined the XGBoost classifier performance based on its discriminative ability, calibration, and clinical utility.

Results

We observed low and high TSR in 91 (40.09%) and 136 (59.91%) patients, respectively. A log-rank test revealed significantly longer survival for patients in the TSR-low group than those in the TSR-high group. The prediction model revealed good discrimination in the training (area under the curve [AUC]= 0.93) and moderate discrimination in the validation set (AUC= 0.63). While the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the training set were 94.06%, 81.82%, 0.89, 0.89, and 0.90, respectively, those for the validation set were 85.71%, 48.00%, 0.70, 0.70, and 0.71, respectively.

Conclusions

The CT radiomics-based XGBoost classifier provides a potentially valuable noninvasive tool to predict TSR in patients with PDAC and optimize risk stratification.

Pulmonary carcinomas arising in association with scar: Cytomorphologic features in histologically confirmed cases

BACKGROUND

Lung carcinoma arising in association with scar tissue is a well-reported but much debated phenomenon. Scar tissue complicates imaging and pathologic tumor measurement for cancer staging. To the best of our knowledge, the cytological findings in lung scar carcinoma (LSC) have not been described in the literature. Therefore, the aim of this study was to characterize the findings in fine-needle aspirations (FNA) from histologically confirmed LSCs.

METHODS

LSCs were identified on retrospective search. Cases with preoperative FNA material were reviewed, including non-scar cases that were used for comparison. The clinical and histopathology findings were recorded.

RESULTS

Twenty-seven cases associated with scar tissue had material for review and 35 cases not associated with scar tissue were used for comparison. The proportion of fibrosis in resection specimens ranged from 10% to 80%. Five (19%) FNA cases were hypocellular. There was no statistically significant difference between the scar and non-scar groups in terms of overall cellularity and diagnostic categories (P = .113 and P = .17, respectively). There was correlation between cytology and dominant pattern on histology in 19 (79%) adenocarcinoma cases. Spindle cells and fibrous or fibroelastotic fragments were present in 22 (81%) cases.

CONCLUSION

This is the first study describing the cytology associated with LSCs. The presence of fibrosis did not adversely impact cellularity, which is likely due to multiple excursions and selective microdissection of tumor cells by the FNA needle. The cytomorphological and histological patterns correlated in most cases. FNA is able to provide a preoperative diagnosis of carcinoma despite the presence of fibrosis.

The prognostic value of the tumor-stroma ratio in squamous cell lung cancer, a cohort study

OBJECTIVES

The tumor-stroma ratio (TSR) is based on the relative amount of stroma in the primary tumor and has proven to be an independent prognostic factor in various solid tumors. The prognosis of patients and adjuvant treatment decision making in lung squamous cell carcinomas (SqCC) is based on the TNM classification. Currently, no other prognostic biomarkers are available. In this study we evaluated the prognostic value of the TSR in lung SqCC.

MATERIAL AND METHODS

Patients undergoing lung surgery because of lung SqCC between 2000 and 2018 at the Leiden University Medical Center were included. The TSR was scored on hematoxylin & eosin stained tissue sections. Based on the amount of tumor-stroma, two groups were defined: ≤50% was classified as a stroma-low tumor and >50% as stroma-high. The prognostic value of the TSR was determined with survival analysis.

RESULTS

A total of 174 stage I-III patients were included. Of them, 79 (45%) were stroma-low and 95 (55%) stroma-high. Separately analyzed for tumor stages, the TSR showed to be an independent prognostic biomarker in stage II (n = 68) for 5-year overall survival (HR=3.0; 95% CI, 1.1-8.6; p = 0.035) and 5-year disease free survival (DFS) (HR=3.6; 95% CI, 1.3-9.9; p = 0.014). Patients with a stroma-high tumor had a worse 5-year DFS in the whole cohort (HR 1.6; 95% CI, 1.0-2.4; p = 0.048), but no independent prognostic value was found.

CONCLUSION

In stage II lung SqCC patients, stroma-low tumors have a better prognosis compared to stroma-high tumors. Moreover, adjuvant chemotherapy could be spared for these stroma-low patients.

Computational Staining of Pathology Images to Study the Tumor Microenvironment in Lung Cancer

The spatial organization of different types of cells in tumor tissues reveals important information about the tumor microenvironment (TME). To facilitate the study of cellular spatial organization and interactions, we developed Histology-based Digital-Staining, a deep learning-based computation model, to segment the nuclei of tumor, stroma, lymphocyte, macrophage, karyorrhexis, and red blood cells from standard hematoxylin and eosin-stained pathology images in lung adenocarcinoma. Using this tool, we identified and classified cell nuclei and extracted 48 cell spatial organization-related features that characterize the TME. Using these features, we developed a prognostic model from the National Lung Screening Trial dataset, and independently validated the model in The Cancer Genome Atlas lung adenocarcinoma dataset, in which the predicted high-risk group showed significantly worse survival than the low-risk group (P = 0.001), with a HR of 2.23 (1.37-3.65) after adjusting for clinical variables. Furthermore, the image-derived TME features significantly correlated with the gene expression of biological pathways. For example, transcriptional activation of both the T-cell receptor and programmed cell death protein 1 pathways positively correlated with the density of detected lymphocytes in tumor tissues, while expression of the extracellular matrix organization pathway positively correlated with the density of stromal cells. In summary, we demonstrate that the spatial organization of different cell types is predictive of patient survival and associated with the gene expression of biological pathways. SIGNIFICANCE: These findings present a deep learning-based analysis tool to study the TME in pathology images and demonstrate that the cell spatial organization is predictive of patient survival and is associated with gene expression.See related commentary by Rodriguez-Antolin, p. 1912.

ConvPath: A software tool for lung adenocarcinoma digital pathological image analysis aided by a convolutional neural network

BACKGROUND

The spatial distributions of different types of cells could reveal a cancer cell's growth pattern, its relationships with the tumor microenvironment and the immune response of the body, all of which represent key "hallmarks of cancer". However, the process by which pathologists manually recognize and localize all the cells in pathology slides is extremely labor intensive and error prone.

METHODS

In this study, we developed an automated cell type classification pipeline, ConvPath, which includes nuclei segmentation, convolutional neural network-based tumor cell, stromal cell, and lymphocyte classification, and extraction of tumor microenvironment-related features for lung cancer pathology images. To facilitate users in leveraging this pipeline for their research, all source scripts for ConvPath software are available at https://qbrc.swmed.edu/projects/cnn/.

FINDINGS

The overall classification accuracy was 92.9% and 90.1% in training and independent testing datasets, respectively. By identifying cells and classifying cell types, this pipeline can convert a pathology image into a "spatial map" of tumor, stromal and lymphocyte cells. From this spatial map, we can extract features that characterize the tumor micro-environment. Based on these features, we developed an image feature-based prognostic model and validated the model in two independent cohorts. The predicted risk group serves as an independent prognostic factor, after adjusting for clinical variables that include age, gender, smoking status, and stage.

INTERPRETATION

The analysis pipeline developed in this study could convert the pathology image into a "spatial map" of tumor cells, stromal cells and lymphocytes. This could greatly facilitate and empower comprehensive analysis of the spatial organization of cells, as well as their roles in tumor progression and metastasis.

Artificial Intelligence in Lung Cancer Pathology Image Analysis

OBJECTIVE

Accurate diagnosis and prognosis are essential in lung cancer treatment selection and planning. With the rapid advance of medical imaging technology, whole slide imaging (WSI) in pathology is becoming a routine clinical procedure. An interplay of needs and challenges exists for computer-aided diagnosis based on accurate and efficient analysis of pathology images. Recently, artificial intelligence, especially deep learning, has shown great potential in pathology image analysis tasks such as tumor region identification, prognosis prediction, tumor microenvironment characterization, and metastasis detection.

MATERIALS AND METHODS

In this review, we aim to provide an overview of current and potential applications for AI methods in pathology image analysis, with an emphasis on lung cancer.

RESULTS

We outlined the current challenges and opportunities in lung cancer pathology image analysis, discussed the recent deep learning developments that could potentially impact digital pathology in lung cancer, and summarized the existing applications of deep learning algorithms in lung cancer diagnosis and prognosis.

DISCUSSION AND CONCLUSION

With the advance of technology, digital pathology could have great potential impacts in lung cancer patient care. We point out some promising future directions for lung cancer pathology image analysis, including multi-task learning, transfer learning, and model interpretation.

Adjustment of Microvessel Area by Stromal Area to Improve Survival Prediction in Non-Small Cell Lung Cancer

Background: Sustained tumor growth and metastasis require sufficient blood supply, and microvessel area (MVA) has been reported that is related to prognosis of cancer patients. However, tumor cells may not be nourished enough by blood vessels when the cells are separated from vessels by thick stroma. Therefore we investigated whether stroma-area normalized MVA (SnMVA) is a more important prognostic factor than MVA.

Materials and Methods: 100 NSCLC patients who underwent resection between July 2011 and October 2012 were randomly selected. We determined the MVA of the tumor tissues by anti-CD31 immunostaining of microvessels. Stroma-area normalized MVA (SnMVA) was a ratio of MVA to stromal area. Correlation of MVA and SnMVA with overall survival (OS) or progression-free survival (PFS) was assessed using multivariate analysis.

Results: Median MVA was 0.0228 (range, 0.00393 to 0.172), and median SnMVA was 0.0441 × 10^-6 (range, 0.00393 × 10^-6 to 0.259 × 10^-6). There was no significant difference in OS between groups of different MVA (HR 0.58, 95%CI 0.28 to 1.19, p = 0.148). In contrast, the risk of death was significantly decreased in high SnMVA group (at or below the median) than in group with low SnMVA (HR 0.47, 95%CI 0.23 to 0.97, p = 0.046). Furthermore, in multivariate analysis, high SnMVA, but not MVA, was an independent prognostic factor after adjusting for age, sex, tumor stage and other factors. OS was significantly associated with SnMVA in six of seven subgroup analysis, but with MVA in only three.

Conclusions: Our study showed that the NSCLC patients with high SnMVA had higher OS. And SnMVA is a prognostic factor with greater accuracy than MVA. Since stroma exists widely in a variety of cancer tissues, we infer that SnMVA may also predict the prognostic of other types of cancers.

New revisions and current issues in the eighth edition of the TNM classification for non-small cell lung cancer

In the eighth edition of the TNM classification of lung cancer, the prognostic impact of tumor size is emphasized as a descriptor of all T categories. Especially in lung cancer where tumor size is 5 cm or less, the 1-cm cutoff point significantly differentiated the survival outcome. In addition, the new staging categories were assigned, namely, Tis (adenocarcinoma in situ) and T1mi (minimally invasive adenocarcinoma). Furthermore, the measurement of a radiological solid component size excluding the ground glass opacity component or pathological invasive size without a lepidic component was proposed for deciding the cT/pT categories for lung adenocarcinoma. The N descriptors were kept the same as in the eventh edition on the whole, however, quantification of nodal disease had a prognostic impact based on the number of nodal stations involved in the eighth edition, i.e. N1a as a single N1 station, N1b as a multiple N1 station, N2a1 as a single N2 station without N1 (skip metastasis), N2a2 as a single N2 station with N1 disease, and N2b as a multiple N2 station. In the M descriptors, subclassification was performed based on the location or numbers of distantly metastatic lesions, i.e. M1a as any intrathoracic metastases, M1b as a single distant metastatic lesion in one organ, and M1c as multiple distant metastases in either a single organ or multiple organs. Survival analysis of the eighth edition of the TNM classification clearly separated the distinct groups, however, unsolved issues still remain that should be discussed and further revised for the forthcoming TNM staging system.