Non-small-cell lung cancer classification via RNA-Seq and histology imaging probability fusion

ML3CNet: Non-local means-assisted automatic framework for lung cancer subtypes classification using histopathological images

BACKGROUND AND OBJECTIVE

Lung cancer (LC) has a high fatality rate that continuously affects human lives all over the world. Early detection of LC prolongs human life and helps to prevent the disease. Histopathological inspection is a common method to diagnose LC. Visual inspection of histopathological diagnosis necessitates more inspection time, and the decision depends on the subjective perception of clinicians. Usually, machine learning techniques mostly depend on traditional feature extraction which is labor-intensive and may not be appropriate for enormous data. In this work, a convolutional neural network (CNN)-based architecture is proposed for the more effective classification of lung tissue subtypes using histopathological images.

METHODS

Authors have utilized the first-time nonlocal mean (NLM) filter to suppress the effect of noise from histopathological images. NLM filter efficiently eliminated noise while preserving the edges of images. Then, the obtained denoised images are given as input to the proposed multi-headed lung cancer classification convolutional neural network (ML3CNet). Furthermore, the model quantization technique is utilized to reduce the size of the proposed model for the storage of the data. Reduction in model size requires less memory and speeds up data processing.

RESULTS

The effectiveness of the proposed model is compared with the other existing state-of-the-art methods. The proposed ML3CNet achieved an average classification accuracy of 99.72%, sensitivity of 99.66%, precision of 99.64%, specificity of 99.84%, F-1 score of 0.9965, and area under the curve of 0.9978. The quantized accuracy of 98.92% is attained by the proposed model. To validate the applicability of the proposed ML3CNet, it has also been tested on the colon cancer dataset.

CONCLUSION

The findings reveal that the proposed approach can be beneficial to automatically classify LC subtypes that might assist healthcare workers in making decisions more precisely. The proposed model can be implemented on the hardware using Raspberry Pi for practical realization.

Anlotinib Inhibits Cisplatin Resistance in Non-Small-Cell Lung Cancer Cells by Inhibiting MCL-1 Expression via MET/STAT3/Akt Pathway

Background

Anlotinib is an effective targeted therapy for advanced non-small-cell lung cancer (NSCLC) and has been found to mediate chemoresistance in many cancers. However, the underlying molecular mechanism of anlotinib mediates cisplatin (DDP) resistance in NSCLC remains unclear.

Methods

Cell viability was assessed by the cell counting kit 8 assay. Cell proliferation, migration, and invasion were determined using the colony formation assay and transwell assay. The mRNA expression levels of mesenchymal-epithelial transition factor (MET) and myeloid cell leukemia-1 (MCL-1) were measured by quantitative real-time PCR. Protein expression levels of MET, MCL-1, and STAT3/Akt pathway-related markers were examined using western blot analysis.

Results

Our data showed that anlotinib inhibited the DDP resistance of NSCLC cells by regulating cell proliferation and metastasis. Moreover, MET and MCL-1 expression could be decreased by anlotinib treatment. Silencing of MET suppressed the activity of the STAT3/Akt pathway and MCL-1 expression. Furthermore, MET overexpression reversed the inhibitory effect of anlotinib on the DDP resistance of NSCLC cells, and this effect could be eliminated by MCL-1 knockdown or ACT001 (an inhibitor for STAT3/Akt pathway).

Conclusion

Our results confirmed that anlotinib inhibited DDP resistance in NSCLC cells, which might decrease MCL-1 expression via mediating the MET/STAT3/Akt pathway.

Updates on lung neuroendocrine neoplasm classification

Lung neuroendocrine neoplasms (NENs) are a heterogeneous group of pulmonary neoplasms showing different morphological patterns and clinical and biological characteristics. The World Health Organisation (WHO) classification of lung NENs has been recently updated as part of the broader attempt to uniform the classification of NENs. This much-needed update has come at a time when insights from seminal molecular characterisation studies revolutionised our understanding of the biological and pathological architecture of lung NENs, paving the way for the development of novel diagnostic techniques, prognostic factors and therapeutic approaches. In this challenging and rapidly evolving landscape, the relevance of the 2021 WHO classification has been recently questioned, particularly in terms of its morphology-orientated approach and its prognostic implications. Here, we provide a state-of-the-art review on the contemporary understanding of pulmonary NEN morphology and the potential contribution of artificial intelligence, the advances in NEN molecular profiling with their impact on the classification system and, finally, the key current and upcoming prognostic factors.

Deep Learning for Predicting Effect of Neoadjuvant Therapies in Non-Small Cell Lung Carcinomas With Histologic Images

Neoadjuvant therapies are used for locally advanced non-small cell lung carcinomas, whereby pathologists histologically evaluate the effect using resected specimens. Major pathological response (MPR) has recently been used for treatment evaluation and as an economical survival surrogate; however, interobserver variability and poor reproducibility are often noted. The aim of this study was to develop a deep learning (DL) model to predict MPR from hematoxylin and eosin-stained tissue images and to validate its utility for clinical use. We collected data on 125 primary non-small cell lung carcinoma cases that were resected after neoadjuvant therapy. The cases were randomly divided into 55 for training/validation and 70 for testing. A total of 261 hematoxylin and eosin-stained slides were obtained from the maximum tumor beds, and whole slide images were prepared. We used a multiscale patch model that can adaptively weight multiple convolutional neural networks trained with different field-of-view images. We performed 3-fold cross-validation to evaluate the model. During testing, we compared the percentages of viable tumor evaluated by annotator pathologists (reviewed data), those evaluated by nonannotator pathologists (primary data), and those predicted by the DL-based model using 2-class confusion matrices and receiver operating characteristic curves and performed a survival analysis between MPR-achieved and non-MPR cases. In cross-validation, accuracy and mean F1 score were 0.859 and 0.805, respectively. During testing, accuracy and mean F1 score with reviewed data and those with primary data were 0.986, 0.985, 0.943, and 0.943, respectively. The areas under the receiver operating characteristic curve with reviewed and primary data were 0.999 and 0.978, respectively. The disease-free survival of MPR-achieved cases with reviewed and primary data was significantly better than that of the non-MPR cases (P<.001 and P=.001), and that predicted by the DL-based model was almost identical (P=.005). The DL model may support pathologist evaluations and can offer accurate determinations of MPR in patients.

Revolutionizing anti-cancer drug discovery against breast cancer and lung cancer by modification of natural genistein: an advanced computational and drug design approach

Breast and lung cancer are two of the most lethal forms of cancer, responsible for a disproportionately high number of deaths worldwide. Both doctors and cancer patients express alarm about the rising incidence of the disease globally. Although targeted treatment has achieved enormous advancements, it is not without its drawbacks. Numerous medicines and chemotherapeutic drugs have been authorized by the FDA; nevertheless, they can be quite costly and often fall short of completely curing the condition. Therefore, this investigation has been conducted to identify a potential medication against breast and lung cancer through structural modification of genistein. Genistein is the active compound in Glycyrrhiza glabra (licorice), and it exhibits solid anticancer efficiency against various cancers, including breast cancer, lung cancer, and brain cancer. Hence, the design of its analogs with the interchange of five functional groups-COOH, NH2 and OCH3, Benzene, and NH-CH2-CH2-OH-have been employed to enhance affinities compared to primary genistein. Additionally, advanced computational studies such as PASS prediction, molecular docking, ADMET, and molecular dynamics simulation were conducted. Firstly, the PASS prediction spectrum was analyzed, revealing that the designed genistein analogs exhibit improved antineoplastic activity. In the prediction data, breast and lung cancer were selected as primary targets. Subsequently, other computational investigations were gradually conducted. The mentioned compounds have shown acceptable results for in silico ADME, AMES toxicity, and hepatotoxicity estimations, which are fundamental for their oral medication. It is noteworthy that the initial binding affinity was only -8.7 kcal/mol against the breast cancer targeted protein (PDB ID: 3HB5). However, after the modification of the functional group, when calculating the binding affinities, it becomes apparent that the binding affinities increase gradually, reaching a maximum of -11.0 and -10.0 kcal/mol. Similarly, the initial binding affinity was only -8.0 kcal/mol against lung cancer (PDB ID: 2P85), but after the addition of binding affinity, it reached -9.5 kcal/mol. Finally, a molecular dynamics simulation was conducted to study the molecular models over 100 ns and examine the stability of the docked complexes. The results indicate that the selected complexes remain highly stable throughout the 100-ns molecular dynamics simulation runs, displaying strong correlations with the binding of targeted ligands within the active site of the selected protein. It is important to further investigate and proceed to clinical or wet lab experiments to determine the practical value of the proposed compounds.

Synthetic whole-slide image tile generation with gene expression profile-infused deep generative models

In this work, we propose an approach to generate whole-slide image (WSI) tiles by using deep generative models infused with matched gene expression profiles. First, we train a variational autoencoder (VAE) that learns a latent, lower-dimensional representation of multi-tissue gene expression profiles. Then, we use this representation to infuse generative adversarial networks (GANs) that generate lung and brain cortex tissue tiles, resulting in a new model that we call RNA-GAN. Tiles generated by RNA-GAN were preferred by expert pathologists compared with tiles generated using traditional GANs, and in addition, RNA-GAN needs fewer training epochs to generate high-quality tiles. Finally, RNA-GAN was able to generalize to gene expression profiles outside of the training set, showing imputation capabilities. A web-based quiz is available for users to play a game distinguishing real and synthetic tiles: https://rna-gan.stanford.edu/, and the code for RNA-GAN is available here: https://github.com/gevaertlab/RNA-GAN.

Deep Learning for Lung Cancer Diagnosis, Prognosis and Prediction Using Histological and Cytological Images: A Systematic Review

Lung cancer is one of the deadliest cancers worldwide, with a high incidence rate, especially in tobacco smokers. Lung cancer accurate diagnosis is based on distinct histological patterns combined with molecular data for personalized treatment. Precise lung cancer classification from a single H&E slide can be challenging for a pathologist, requiring most of the time additional histochemical and special immunohistochemical stains for the final pathology report. According to WHO, small biopsy and cytology specimens are the available materials for about 70% of lung cancer patients with advanced-stage unresectable disease. Thus, the limited available diagnostic material necessitates its optimal management and processing for the completion of diagnosis and predictive testing according to the published guidelines. During the new era of Digital Pathology, Deep Learning offers the potential for lung cancer interpretation to assist pathologists' routine practice. Herein, we systematically review the current Artificial Intelligence-based approaches using histological and cytological images of lung cancer. Most of the published literature centered on the distinction between lung adenocarcinoma, lung squamous cell carcinoma, and small cell lung carcinoma, reflecting the realistic pathologist's routine. Furthermore, several studies developed algorithms for lung adenocarcinoma predominant architectural pattern determination, prognosis prediction, mutational status characterization, and PD-L1 expression status estimation.

An emerging era of computational cytology

BACKGROUND

The significant advancement in digital imaging, data management, advanced computational power, and artificial neural network have an immense impact on the field of cytology. The amalgamation of these areas has generated a newer discipline known as computational cytology.

AIMS AND OBJECTIVE

In To discuss the various important aspects of computational cytology.

MATERIALS AND METHODS

We reviewed the different studies published in English during the last few years on computational cytology.

RESULT

Computational cytology is a newer and emerging discipline in pathology that deals with the patient's meta-data and digital image data to make a mathematical model to produce diagnostic interpretations and predictions. The role of the cytologist is now changing from a simple observational scientist and slide interpreter to a dynamic and integrated multi-parametric prediction-based scientist.

CONCLUSION

In the current stage, the cytologist must understand the situation and should have a vision of the complete scenario on computational cytology.

Binary classification of multi-magnification histopathological breast cancer images using late fusion and transfer learning

Purpose

Histopathology biopsy imaging is currently the gold standard for the diagnosis of breast cancer in clinical practice. Pathologists examine the images at various magnifications to identify the type of tumor because if only one magnification is taken into account, the decision may not be accurate. This study explores the performance of transfer learning and late fusion to construct multi-scale ensembles that fuse different magnification-specific deep learning models for the binary classification of breast tumor slides.

Design/methodology/approach

Three pretrained deep learning techniques (DenseNet 201, MobileNet v2 and Inception v3) were used to classify breast tumor images over the four magnification factors of the Breast Cancer Histopathological Image Classification dataset (40×, 100×, 200× and 400×). To fuse the predictions of the models trained on different magnification factors, different aggregators were used, including weighted voting and seven meta-classifiers trained on slide predictions using class labels and the probabilities assigned to each class. The best cluster of the outperforming models was chosen using the Scott–Knott statistical test, and the top models were ranked using the Borda count voting system.

Findings

This study recommends the use of transfer learning and late fusion for histopathological breast cancer image classification by constructing multi-magnification ensembles because they perform better than models trained on each magnification separately.

Originality/value

The best multi-scale ensembles outperformed state-of-the-art integrated models and achieved an accuracy mean value of 98.82 per cent, precision of 98.46 per cent, recall of 100 per cent and F1-score of 99.20 per cent.

Identification of a apoptosis-related LncRNA signature to improve prognosis prediction and immunotherapy response in lung adenocarcinoma patients

Apoptosis is closely associated with the development of various cancers, including lung adenocarcinoma (LUAD). However, the prognostic value of apoptosis-related lncRNAs (ApoRLs) in LUAD has not been fully elucidated. In the present study, we screened 2, 960 ApoRLs by constructing a co-expression network of mRNAs-lncRNAs associated with apoptosis, and identified 421 ApoRLs that were differentially expressed between LUAD samples and normal lung samples. Sixteen differentially expressed apoptosis-related lncRNAs (DE-ApoRLs) with prognostic relevance to LUAD patients were screened using univariate Cox regression analysis. An apoptosis-related lncRNA signature (ApoRLSig ) containing 10 ApoRLs was constructed by applying the Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression method, and all LUAD patients in the TCGA cohort were divided into high or low risk groups. Moreover, patients in the high-risk group had a worse prognosis (p < 0.05). When analyzed in conjunction with clinical features, we found ApoRLSig to be an independent predictor of LUAD patients and established a prognostic nomogram combining ApoRLSig and clinical features. Gene set enrichment analysis (GSEA) revealed that ApoRLSig is involved in many malignancy-associated immunomodulatory pathways. In addition, there were significant differences in the immune microenvironment and immune cells between the high-risk and low-risk groups. Further analysis revealed that the expression levels of most immune checkpoint genes (ICGs) were higher in the high-risk group, which suggested that the immunotherapy effect was better in the high-risk group than in the low-risk group. And we found that the high-risk group was also better than the low-risk group in terms of chemotherapy effect. In conclusion, we successfully constructed an ApoRLSig which could predict the prognosis of LUAD patients and provide a novel strategy for the antitumor treatment of LUAD patients.

Machine-Learning-Based Late Fusion on Multi-Omics and Multi-Scale Data for Non-Small-Cell Lung Cancer Diagnosis

Differentiation between the various non-small-cell lung cancer subtypes is crucial for providing an effective treatment to the patient. For this purpose, machine learning techniques have been used in recent years over the available biological data from patients. However, in most cases this problem has been treated using a single-modality approach, not exploring the potential of the multi-scale and multi-omic nature of cancer data for the classification. In this work, we study the fusion of five multi-scale and multi-omic modalities (RNA-Seq, miRNA-Seq, whole-slide imaging, copy number variation, and DNA methylation) by using a late fusion strategy and machine learning techniques. We train an independent machine learning model for each modality and we explore the interactions and gains that can be obtained by fusing their outputs in an increasing manner, by using a novel optimization approach to compute the parameters of the late fusion. The final classification model, using all modalities, obtains an F1 score of 96.81±1.07, an AUC of 0.993±0.004, and an AUPRC of 0.980±0.016, improving those results that each independent model obtains and those presented in the literature for this problem. These obtained results show that leveraging the multi-scale and multi-omic nature of cancer data can enhance the performance of single-modality clinical decision support systems in personalized medicine, consequently improving the diagnosis of the patient.

Deep Learning Facilitates Distinguishing Histologic Subtypes of Pulmonary Neuroendocrine Tumors on Digital Whole-Slide Images

Simple Summary

Challenges persist in diagnosing pulmonary neuroendocrine tumors. Our case study shows that deep learning combined with convolutional neural networks has the potential to assist in the diagnosis of pulmonary neuroendocrine tumors from digital whole-slide images.

Abstract

The histological distinction of lung neuroendocrine carcinoma, including small cell lung carcinoma (SCLC), large cell neuroendocrine carcinoma (LCNEC) and atypical carcinoid (AC), can be challenging in some cases, while bearing prognostic and therapeutic significance. To assist pathologists with the differentiation of histologic subtyping, we applied a deep learning classifier equipped with a convolutional neural network (CNN) to recognize lung neuroendocrine neoplasms. Slides of primary lung SCLC, LCNEC and AC were obtained from the Laboratory of Clinical and Experimental Pathology (University Hospital Nice, France). Three thoracic pathologists blindly established gold standard diagnoses. The HALO-AI module (Indica Labs, UK) trained with 18,752 image tiles extracted from 60 slides (SCLC = 20, LCNEC = 20, AC = 20 cases) was then tested on 90 slides (SCLC = 26, LCNEC = 22, AC = 13 and combined SCLC with LCNEC = 4 cases; NSCLC = 25 cases) by F1-score and accuracy. A HALO-AI correct area distribution (AD) cutoff of 50% or more was required to credit the CNN with the correct diagnosis. The tumor maps were false colored and displayed side by side to original hematoxylin and eosin slides with superimposed pathologist annotations. The trained HALO-AI yielded a mean F1-score of 0.99 (95% CI, 0.939–0.999) on the testing set. Our CNN model, providing further larger validation, has the potential to work side by side with the pathologist to accurately differentiate between the different lung neuroendocrine carcinoma in challenging cases.