Development and validation of a supervised deep learning algorithm for automated whole-slide programmed death-ligand 1 tumour proportion score assessment in non-small cell lung cancer

Artificial Intelligence and Lung Pathology

This manuscript provides a comprehensive overview of the application of artificial intelligence (AI) in lung pathology, particularly in the diagnosis of lung cancer. It discusses various AI models designed to support pathologists and clinicians. AI models supporting pathologists are to standardize diagnosis, score PD-L1 status, supporting tumor cellularity count, and indicating explainability for pathologic judgements. Several models predict outcomes beyond pathologic diagnosis and predict clinical outcomes like patients' survival and molecular alterations. The manuscript emphasizes the potential of AI to enhance accuracy and efficiency in pathology, while also addressing the challenges and future directions for integrating AI into clinical practice.

Clinical Validation of Artificial Intelligence-Powered PD-L1 Tumor Proportion Score Interpretation for Immune Checkpoint Inhibitor Response Prediction in Non-Small Cell Lung Cancer

PURPOSE

Evaluation of PD-L1 tumor proportion score (TPS) by pathologists has been very impactful but is limited by factors such as intraobserver/interobserver bias and intratumor heterogeneity. We developed an artificial intelligence (AI)-powered analyzer to assess TPS for the prediction of immune checkpoint inhibitor (ICI) response in advanced non-small cell lung cancer (NSCLC).

MATERIALS AND METHODS

The AI analyzer was trained with 393,565 tumor cells annotated by board-certified pathologists for PD-L1 expression in 802 whole-slide images (WSIs) stained by 22C3 pharmDx immunohistochemistry. The clinical performance of the analyzer was validated in an external cohort of 430 WSIs from patients with NSCLC. Three pathologists performed annotations of this external cohort, and their consensus TPS was compared with AI-based TPS.

RESULTS

In comparing PD-L1 TPS assessed by AI analyzer and by pathologists, a significant positive correlation was observed (Spearman coefficient = 0.925; P < .001). The concordance of TPS between AI analyzer and pathologists according to TPS ≥50%, 1%-49%, and <1% was 85.7%, 89.3%, and 52.4%, respectively. In median progression-free survival (PFS), AI-based TPS predicted prognosis in the TPS 1%-49% or TPS <1% group better than the pathologist's reading, with the TPS ≥50% group as a reference (hazard ratio [HR], 1.49 [95% CI, 1.19 to 1.86] v HR, 1.36 [95% CI, 1.08 to 1.71] for TPS 1%-49% group, and HR, 2.38 [95% CI, 1.69 to 3.35] v HR, 1.62 [95% CI, 1.23 to 2.13] for TPS <1% group).

CONCLUSION

PD-L1 TPS assessed by AI analyzer correlates with that of pathologists, with clinical performance also being comparable when referenced to PFS. The AI model can accurately predict tumor response and PFS of ICI in advanced NSCLC via assessment of PD-L1 TPS.

Power line fault diagnosis based on convolutional neural networks

With the rapid development of the national economy, power security is very important for the security of the country and people's happiness. Electricity is an important energy source for a country. Even if the power system malfunctions for a short period of time, it would cause incalculable losses to social production and people's lives. Among them, one of the most important reasons for power system faults is the occurrence of power line faults, so diagnosing faulty lines has great research significance. On the basis of analyzing the structure and working principle of the deep learning model convolutional neural network (CNN), this article used the CNN model to diagnose faults in power lines and analyzed the simulation results. It was found that different CNN structures have different fault diagnosis accuracy for power lines. The fewer the number of batches in the network structure and the more the number of training sessions, the higher its fault determination accuracy. In the power line fault diagnosis based on three deep learning algorithms, the CNN has the highest stable fault diagnosis accuracy of 100%; the recursive neural network has the second stable fault diagnosis accuracy of 93.4%; the deep belief network has the lowest stable fault diagnosis accuracy of 91.5%. In the comparison of power line fault diagnosis stability, the accuracy standard deviation of CNN is close to 0, and they are also the most stable in power circuit fault diagnosis. The stability of algorithmic recurrent neural networks is between the two, and the accuracy standard deviation of deep belief networks is 1.84% when trained 12 times. Their fault diagnosis stability is also the worst.

A Pipeline for Evaluation of Machine Learning/Artificial Intelligence Models to Quantify Programmed Death Ligand 1 Immunohistochemistry

Immunohistochemistry (IHC) is used to guide treatment decisions in multiple cancer types. For treatment with checkpoint inhibitors, programmed death ligand 1 (PD-L1) IHC is used as a companion diagnostic. However, the scoring of PD-L1 is complicated by its expression in cancer and immune cells. Separation of cancer and noncancer regions is needed to calculate tumor proportion scores (TPS) of PD-L1, which is based on the percentage of PD-L1-positive cancer cells. Evaluation of PD-L1 expression requires highly experienced pathologists and is often challenging and time-consuming. Here, we used a multi-institutional cohort of 77 lung cancer cases stained centrally with the PD-L1 22C3 clone. We developed a 4-step pipeline for measuring TPS that includes the coregistration of hematoxylin and eosin, PD-L1, and negative control (NC) digital slides for exclusion of necrosis, segmentation of cancer regions, and quantification of PD-L1+ cells. As cancer segmentation is a challenging step for TPS generation, we trained DeepLab V3 in the Visiopharm software package to outline cancer regions in PD-L1 and NC images and evaluated the model performance by mean intersection over union (mIoU) against manual outlines. Only 14 cases were required to accomplish a mIoU of 0.82 for cancer segmentation in hematoxylin-stained NC cases. For PD-L1-stained slides, a model trained on PD-L1 tiles augmented by registered NC tiles achieved a mIoU of 0.79. In segmented cancer regions from whole slide images, the digital TPS achieved an accuracy of 75% against the manual TPS scores from the pathology report. Major reasons for algorithmic inaccuracies include the inclusion of immune cells in cancer outlines and poor nuclear segmentation of cancer cells. Our transparent and stepwise approach and performance metrics can be applied to any IHC assay to provide pathologists with important insights on when to apply and how to evaluate commercial automated IHC scoring systems.

A Deep Learning-Based Assay for Programmed Death Ligand 1 Immunohistochemistry Scoring in Non-Small Cell Lung Carcinoma: Does it Help Pathologists Score?

Several studies have developed various artificial intelligence (AI) models for immunohistochemical analysis of programmed death ligand 1 (PD-L1) in patients with non-small cell lung carcinoma; however, none have focused on specific ways by which AI-assisted systems could help pathologists determine the tumor proportion score (TPS). In this study, we developed an AI model to calculate the TPS of the PD-L1 22C3 assay and evaluated whether and how this AI-assisted system could help pathologists determine the TPS and analyze how AI-assisted systems could affect pathologists' assessment accuracy. We assessed the 4 methods of the AI-assisted system: (1 and 2) pathologists first assessed and then referred to automated AI scoring results (1, positive tumor cell percentage; 2, positive tumor cell percentage and visualized overlay image) for final confirmation, and (3 and 4) pathologists referred to the automated AI scoring results (3, positive tumor cell percentage; 4, positive tumor cell percentage and visualized overlay image) while determining TPS. Mixed-model analysis was used to calculate the odds ratios (ORs) with 95% CI for AI-assisted TPS methods 1 to 4 compared with pathologists' scoring. For all 584 samples of the tissue microarray, the OR for AI-assisted TPS methods 1 to 4 was 0.94 to 1.07 and not statistically significant. Of them, we found 332 discordant cases, on which the pathologists' judgments were inconsistent; the ORs for AI-assisted TPS methods 1, 2, 3, and 4 were 1.28 (1.06-1.54; P = .012), 1.29 (1.06-1.55; P = .010), 1.28 (1.06-1.54; P = .012), and 1.29 (1.06-1.55; P = .010), respectively, which were statistically significant. For discordant cases, the OR for each AI-assisted TPS method compared with the others was 0.99 to 1.01 and not statistically significant. This study emphasized the usefulness of the AI-assisted system for cases in which pathologists had difficulty determining the PD-L1 TPS.

Comparing deep learning and pathologist quantification of cell-level PD-L1 expression in non-small cell lung cancer whole-slide images

Programmed death-ligand 1 (PD-L1) expression is currently used in the clinic to assess eligibility for immune-checkpoint inhibitors via the tumor proportion score (TPS), but its efficacy is limited by high interobserver variability. Multiple papers have presented systems for the automatic quantification of TPS, but none report on the task of determining cell-level PD-L1 expression and often reserve their evaluation to a single PD-L1 monoclonal antibody or clinical center. In this paper, we report on a deep learning algorithm for detecting PD-L1 negative and positive tumor cells at a cellular level and evaluate it on a cell-level reference standard established by six readers on a multi-centric, multi PD-L1 assay dataset. This reference standard also provides for the first time a benchmark for computer vision algorithms. In addition, in line with other papers, we also evaluate our algorithm at slide-level by measuring the agreement between the algorithm and six pathologists on TPS quantification. We find a moderately low interobserver agreement at cell-level level (mean reader-reader F1 score = 0.68) which our algorithm sits slightly under (mean reader-AI F1 score = 0.55), especially for cases from the clinical center not included in the training set. Despite this, we find good AI-pathologist agreement on quantifying TPS compared to the interobserver agreement (mean reader-reader Cohen's kappa = 0.54, 95% CI 0.26-0.81, mean reader-AI kappa = 0.49, 95% CI 0.27-0.72). In conclusion, our deep learning algorithm demonstrates promise in detecting PD-L1 expression at a cellular level and exhibits favorable agreement with pathologists in quantifying the tumor proportion score (TPS). We publicly release our models for use via the Grand-Challenge platform.

Artificial Intelligence-Based Treatment Decisions: A New Era for NSCLC

Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related mortality among women and men, in developed countries, despite the public health interventions including tobacco-free campaigns, screening and early detection methods, recent therapeutic advances, and ongoing intense research on novel antineoplastic modalities. Targeting oncogenic driver mutations and immune checkpoint inhibition has indeed revolutionized NSCLC treatment, yet there still remains the unmet need for robust and standardized predictive biomarkers to accurately inform clinical decisions. Artificial intelligence (AI) represents the computer-based science concerned with large datasets for complex problem-solving. Its concept has brought a paradigm shift in oncology considering its immense potential for improved diagnosis, treatment guidance, and prognosis. In this review, we present the current state of AI-driven applications on NSCLC management, with a particular focus on radiomics and pathomics, and critically discuss both the existing limitations and future directions in this field. The thoracic oncology community should not be discouraged by the likely long road of AI implementation into daily clinical practice, as its transformative impact on personalized treatment approaches is undeniable.

Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression

Programmed death-ligand 1 (PD-L1) IHC is the most commonly used biomarker for immunotherapy response. However, quantification of PD-L1 status in pathology slides is challenging. Neither manual quantification nor a computer-based mimicking of manual readouts is perfectly reproducible, and the predictive performance of both approaches regarding immunotherapy response is limited. In this study, we developed a deep learning (DL) method to predict PD-L1 status directly from raw IHC image data, without explicit intermediary steps such as cell detection or pigment quantification. We trained the weakly supervised model on PD-L1-stained slides from the non-small cell lung cancer (NSCLC)-Memorial Sloan Kettering (MSK) cohort (N = 233) and validated it on the pan-cancer-Vall d'Hebron Institute of Oncology (VHIO) cohort (N = 108). We also investigated the performance of the model to predict response to immune checkpoint inhibitors (ICI) in terms of progression-free survival. In the pan-cancer-VHIO cohort, the performance was compared with tumor proportion score (TPS) and combined positive score (CPS). The DL model showed good performance in predicting PD-L1 expression (TPS ≥ 1%) in both NSCLC-MSK and pan-cancer-VHIO cohort (AUC 0.88 ± 0.06 and 0.80 ± 0.03, respectively). The predicted PD-L1 status showed an improved association with response to ICIs [HR: 1.5 (95% confidence interval: 1-2.3), P = 0.049] compared with TPS [HR: 1.4 (0.96-2.2), P = 0.082] and CPS [HR: 1.2 (0.79-1.9), P = 0.386]. Notably, our explainability analysis showed that the model does not just look at the amount of brown pigment in the IHC slides, but also considers morphologic factors such as lymphocyte conglomerates. Overall, end-to-end weakly supervised DL shows potential for improving patient stratification for cancer immunotherapy by analyzing PD-L1 IHC, holistically integrating morphology and PD-L1 staining intensity.

SIGNIFICANCE

The weakly supervised DL model to predict PD-L1 status from raw IHC data, integrating tumor staining intensity and morphology, enables enhanced patient stratification in cancer immunotherapy compared with traditional pathologist assessment.

Correlation Between ImageJ and Conventional Manual Scoring Methods for Programmed Death-Ligand 1 Immuno-Histochemically Stained Sections

Background: One of the most frequently used methods for quantifying PD-L1 (programmed cell death-ligand 1) expression in tumor tissue is IHC (immunohistochemistry). This may predict the patient's response to anti-PD1/PD-L1 therapy in cancer. Methods: ImageJ software was used to score IHC-stained sections for PD-L1 and compare the results with the conventional manual method. Results: In diffuse large B cell lymphoma, no significant difference between the scores obtained by the conventional method and ImageJ scores obtained using the option "RGB" or "Brightness/Contrast." On the other hand, a significant difference was found between the conventional and HSB scoring methods. ImageJ faced some challenges in analyzing head and neck squamous cell carcinoma tissues because of tissue heterogenicity. A significant difference was found between the conventional and ImageJ scores using HSB or RGB but not with the "Brightness/Contrast" option. Scores obtained by ImageJ analysis after taking images using 20 × objective lens gave significantly higher readings compared to 40 × magnification. A significant difference between camera-captured images' scores and scanner whole slide images' scores was observed. Conclusion: ImageJ can be used to score homogeneous tissues. In the case of highly heterogeneous tissues, it is advised to use the conventional method rather than ImageJ scoring.

AI-Powered Segmentation of Invasive Carcinoma Regions in Breast Cancer Immunohistochemical Whole-Slide Images

AIMS

The automation of quantitative evaluation for breast immunohistochemistry (IHC) plays a crucial role in reducing the workload of pathologists and enhancing the objectivity of diagnoses. However, current methods face challenges in achieving fully automated immunohistochemistry quantification due to the complexity of segmenting the tumor area into distinct ductal carcinoma in situ (DCIS) and invasive carcinoma (IC) regions. Moreover, the quantitative analysis of immunohistochemistry requires a specific focus on invasive carcinoma regions.

METHODS AND RESULTS

In this study, we propose an innovative approach to automatically identify invasive carcinoma regions in breast cancer immunohistochemistry whole-slide images (WSIs). Our method leverages a neural network that combines multi-scale morphological features with boundary features, enabling precise segmentation of invasive carcinoma regions without the need for additional H&E and P63 staining slides. In addition, we introduced an advanced semi-supervised learning algorithm, allowing efficient training of the model using unlabeled data. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 618 IHC-stained WSIs from 170 cases, including four types of staining (ER, PR, HER2, and Ki-67). Notably, the model demonstrated an impressive intersection over union (IoU) score exceeding 80% on the test set. Furthermore, to ascertain the practical utility of our model in IHC quantitative evaluation, we constructed a fully automated Ki-67 scoring system based on the model's predictions. Comparative experiments convincingly demonstrated that our system exhibited high consistency with the scores given by experienced pathologists.

CONCLUSIONS

Our developed model excels in accurately distinguishing between DCIS and invasive carcinoma regions in breast cancer immunohistochemistry WSIs. This method paves the way for a clinically available, fully automated immunohistochemistry quantitative scoring system.

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.

Computational pathology in cancer diagnosis, prognosis, and prediction - present day and prospects

Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence (AI) have led to an explosion in innovation in computational pathology, ranging from the prospect of automation of routine diagnostic tasks to the discovery of new prognostic and predictive biomarkers from tissue morphology. Despite the promising potential of computational pathology, its integration in clinical settings has been limited by a range of obstacles including operational, technical, regulatory, ethical, financial, and cultural challenges. Here, we focus on the pathologists' perspective of computational pathology: we map its current translational research landscape, evaluate its clinical utility, and address the more common challenges slowing clinical adoption and implementation. We conclude by describing contemporary approaches to drive forward these techniques. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

The artificial intelligence and machine learning in lung cancer immunotherapy

Since the past decades, more lung cancer patients have been experiencing lasting benefits from immunotherapy. It is imperative to accurately and intelligently select appropriate patients for immunotherapy or predict the immunotherapy efficacy. In recent years, machine learning (ML)-based artificial intelligence (AI) was developed in the area of medical-industrial convergence. AI can help model and predict medical information. A growing number of studies have combined radiology, pathology, genomics, proteomics data in order to predict the expression levels of programmed death-ligand 1 (PD-L1), tumor mutation burden (TMB) and tumor microenvironment (TME) in cancer patients or predict the likelihood of immunotherapy benefits and side effects. Finally, with the advancement of AI and ML, it is believed that "digital biopsy" can replace the traditional single assessment method to benefit more cancer patients and help clinical decision-making in the future. In this review, the applications of AI in PD-L1/TMB prediction, TME prediction and lung cancer immunotherapy are discussed.

See Lung Cancer with an AI

A lot has happened in the field of lung cancer screening in recent months. The ongoing discussion and documentation published by the scientific community and policymakers are of great importance to the entire European community and perhaps beyond. Lung cancer is the main worldwide killer. Low-dose computed tomography-based screening, together with smoking cessation, is the only tool to fight lung cancer, as it has already been proven in the United States of America but also European randomized controlled trials. Screening requires a lot of well-organized specialized work, but it can be supported by artificial intelligence (AI). Here we discuss whether and how to use AI for patients, radiologists, pulmonologists, thoracic surgeons, and all hospital staff supporting screening process benefits.

PD-L1 testing by immunohistochemistry in immuno-oncology

Immunotherapy, based on immune checkpoint inhibitors targeting the Programmed cell death ligand 1 (PD-L1) and/or Programmed Death Receptor 1 (PD-1), has substantially improved the outcomes of patients with various cancers. However, only ~30% of patients benefit from immune checkpoint inhibitors. Tumor PD-L1 expression, assessed by immunohistochemistry, is the most widely validated and used predictive biomarker to guide the selection of patients for immune checkpoint inhibitors. PD-L1 assessment may be challenging due to the necessity for different companion diagnostic assays for required specific immune checkpoint inhibitors and a relatively high level of inter-assay variability in terms of performance and cutoff levels. In this review, we discuss the role of PD-L1 immunohistochemistry as a predictive test in immunotherapy (immuno-oncology), highlight the complexity of the PD-L1 testing landscape, discuss various preanalytical, analytical and clinical issues that are associated with PD-L1 assays, and provide some insights into optimization of PD-L1 as a predictive biomarker in immuno-oncology.

Detection of abnormal extraocular muscles in small datasets of computed tomography images using a three-dimensional variational autoencoder

We sought to establish an unsupervised algorithm with a three-dimensional (3D) variational autoencoder model (VAE) for the detection of abnormal extraocular muscles in small datasets of orbital computed tomography (CT) images. 334 CT images of normal orbits and 96 of abnormal orbits diagnosed as thyroid eye disease were used for training and validation; 24 normal and 11 abnormal orbits were used for the test. A 3D VAE was developed and trained. All images were preprocessed to emphasize extraocular muscles and to suppress background noise (e.g., high signal intensity from bones). The optimal cut-off value was identified through receiver operating characteristic (ROC) curve analysis. The ability of the model to detect muscles of abnormal size was assessed by visualization. The model achieved a sensitivity of 79.2%, specificity of 72.7%, accuracy of 77.1%, F1-score of 0.667, and AUROC of 0.801. Abnormal CT images correctly identified by the model showed differences in the reconstruction of extraocular muscles. The proposed model showed potential to detect abnormalities in extraocular muscles using a small dataset, similar to the diagnostic approach used by physicians. Unsupervised learning could serve as an alternative detection method for medical imaging studies in which annotation is difficult or impossible to perform.

Facts and Hopes on the Use of Artificial Intelligence for Predictive Immunotherapy Biomarkers in Cancer

Immunotherapy by immune checkpoint inhibitors has become a standard treatment strategy for many types of solid tumors. However, the majority of patients with cancer will not respond, and predicting response to this therapy is still a challenge. Artificial intelligence (AI) methods can extract meaningful information from complex data, such as image data. In clinical routine, radiology or histopathology images are ubiquitously available. AI has been used to predict the response to immunotherapy from radiology or histopathology images, either directly or indirectly via surrogate markers. While none of these methods are currently used in clinical routine, academic and commercial developments are pointing toward potential clinical adoption in the near future. Here, we summarize the state of the art in AI-based image biomarkers for immunotherapy response based on radiology and histopathology images. We point out limitations, caveats, and pitfalls, including biases, generalizability, and explainability, which are relevant for researchers and health care providers alike, and outline key clinical use cases of this new class of predictive biomarkers.

Artificial intelligence for prediction of response to cancer immunotherapy

Artificial intelligence (AI) indicates the application of machines to imitate intelligent behaviors for solving complex tasks with minimal human intervention, including machine learning and deep learning. The use of AI in medicine improves health-care systems in multiple areas such as diagnostic confirmation, risk stratification, analysis, prognosis prediction, treatment surveillance, and virtual health support, which has considerable potential to revolutionize and reshape medicine. In terms of immunotherapy, AI has been applied to unlock underlying immune signatures to associate with responses to immunotherapy indirectly as well as predict responses to immunotherapy responses directly. The AI-based analysis of high-throughput sequences and medical images can provide useful information for management of cancer immunotherapy considering the excellent abilities in selecting appropriate subjects, improving therapeutic regimens, and predicting individualized prognosis. In present review, we aim to evaluate a broad framework about AI-based computational approaches for prediction of response to cancer immunotherapy on both indirect and direct manners. Furthermore, we summarize our perspectives about challenges and opportunities of further AI applications on cancer immunotherapy relating to clinical practicability.

Artificial Intelligence-Powered Prediction of ALK Gene Rearrangement in Patients With Non-Small-Cell Lung Cancer

PURPOSE

Several studies reported the possibility of predicting genetic abnormalities in non-small-cell lung cancer by deep learning (DL). However, there are no data of predicting ALK gene rearrangement (ALKr) using DL. We evaluated the ALKr predictability using the DL platform.

MATERIALS AND METHODS

We selected 66 ALKr-positive cases and 142 ALKr-negative cases, which were diagnosed by ALKr immunohistochemical staining in our institution from January 2009 to March 2019. We generated virtual slide of 300 slides (150 ALKr-positive slides and 150 ALKr-negative slides) using NanoZoomer. HALO-AI was used to analyze the whole-slide imaging data, and the DenseNet network was used to build the learning model. Of the 300 slides, we randomly assigned 172 slides to the training cohort and 128 slides to the test cohort to ensure no duplication of cases. In four resolutions (16.0/4.0/1.0/0.25 μm/pix), ALKr prediction models were built in the training cohort and ALKr prediction performance was evaluated in the test cohort. We evaluated the diagnostic probability of ALKr by receiver operating characteristic analysis in each ALKr probability threshold (50%, 60%, 70%, 80%, 90%, and 95%). We expected the area under the curve to be 0.64-0.85 in the model of a previous study. Furthermore, in the test cohort data, an expert pathologist also evaluated the presence of ALKr by hematoxylin and eosin staining on whole-slide imaging.

RESULTS

The maximum area under the curve was 0.73 (50% threshold: 95% CI, 0.65 to 0.82) in the resolution of 1.0 μm/pix. In this resolution, with an ALKr probability of 50% threshold, the sensitivity and specificity were 73% and 73%, respectively. The expert pathologist's sensitivity and specificity in the same test cohort were 13% and 94%.

CONCLUSION

The ALKr prediction by DL was feasible. Further study should be addressed to improve accuracy of ALKr prediction.

Artificial intelligence-based prediction of clinical outcome in immunotherapy and targeted therapy of lung cancer

Lung cancer accounts for the main proportion of malignancy-related deaths and most patients are diagnosed at an advanced stage. Immunotherapy and targeted therapy have great advances in application in clinics to treat lung cancer patients, yet the efficacy is unstable. The response rate of these therapies varies among patients. Some biomarkers have been proposed to predict the outcomes of immunotherapy and targeted therapy, including programmed cell death-ligand 1 (PD-L1) expression and oncogene mutations. Nevertheless, the detection tests are invasive, time-consuming, and have high demands on tumor tissue. The predictive performance of conventional biomarkers is also unsatisfactory. Therefore, novel biomarkers are needed to effectively predict the outcomes of immunotherapy and targeted therapy. The application of artificial intelligence (AI) can be a possible solution, as it has several advantages. AI can help identify features that are unable to be used by humans and perform repetitive tasks. By combining AI methods with radiomics, pathology, genomics, transcriptomics, proteomics, and clinical data, the integrated model has shown predictive value in immunotherapy and targeted therapy, which significantly improves the precision treatment of lung cancer patients. Herein, we reviewed the application of AI in predicting the outcomes of immunotherapy and targeted therapy in lung cancer patients, and discussed the challenges and future directions in this field.

Graph-Embedded Online Learning for Cell Detection and Tumour Proportion Score Estimation

Cell detection in microscopy images can provide useful clinical information. Most methods based on deep learning for cell detection are fully supervised. Without enough labelled samples, the accuracy of these methods would drop rapidly. To handle limited annotations and massive unlabelled data, semi-supervised learning methods have been developed. However, many of these are trained off-line, and are unable to process new incoming data to meet the needs of clinical diagnosis. Therefore, we propose a novel graph-embedded online learning network (GeoNet) for cell detection. It can locate and classify cells with dot annotations, saving considerable manpower. Trained by both historical data and reliable new samples, the online network can predict nuclear locations for upcoming new images while being optimized. To be more easily adapted to open data, it engages dynamic graph regularization and learns the inherent nonlinear structures of cells. Moreover, GeoNet can be applied to downstream tasks such as quantitative estimation of tumour proportion score (TPS), which is a useful indicator for lung squamous cell carcinoma treatment and prognostics. Experimental results for five large datasets with great variability in cell type and morphology validate the effectiveness and generalizability of the proposed method. For the lung squamous cell carcinoma (LUSC) dataset, the detection F1-scores of GeoNet for negative and positive tumour cells are 0.734 and 0.769, respectively, and the relative error of GeoNet for TPS estimation is 11.1%.

Application of Artificial Intelligence in Lung Cancer

Simple Summary

Lung cancer is the leading cause of malignancy-related mortality worldwide. AI has the potential to help to treat lung cancer from detection, diagnosis and decision making to prognosis prediction. AI could reduce the labor work of LDCT, CXR, and pathology slides reading. AI as a second reader in LDCT and CXR reading reduces the effort of radiologists and increases the accuracy of nodule detection. Introducing AI to WSI in digital pathology increases the Kappa value of the pathologist and help to predict molecular phenotypes with radiomics and H&E staining. By extracting radiomics from image data and WSI from the histopathology field, clinicians could use AI to predict tumor properties such as gene mutation and PD-L1 expression. Furthermore, AI could help clinicians in decision-making by predicting treatment response, side effects, and prognosis prediction in medical treatment, surgery, and radiotherapy. Integrating AI in the future clinical workflow would be promising.

Abstract

Lung cancer is the leading cause of malignancy-related mortality worldwide due to its heterogeneous features and diagnosis at a late stage. Artificial intelligence (AI) is good at handling a large volume of computational and repeated labor work and is suitable for assisting doctors in analyzing image-dominant diseases like lung cancer. Scientists have shown long-standing efforts to apply AI in lung cancer screening via CXR and chest CT since the 1960s. Several grand challenges were held to find the best AI model. Currently, the FDA have approved several AI programs in CXR and chest CT reading, which enables AI systems to take part in lung cancer detection. Following the success of AI application in the radiology field, AI was applied to digitalized whole slide imaging (WSI) annotation. Integrating with more information, like demographics and clinical data, the AI systems could play a role in decision-making by classifying EGFR mutations and PD-L1 expression. AI systems also help clinicians to estimate the patient’s prognosis by predicting drug response, the tumor recurrence rate after surgery, radiotherapy response, and side effects. Though there are still some obstacles, deploying AI systems in the clinical workflow is vital for the foreseeable future.