Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study

Deep learning radiomics analysis for prediction of survival in patients with unresectable gastric cancer receiving immunotherapy

Objective

Immunotherapy has become an option for the first-line therapy of advanced gastric cancer (GC), with improved survival. Our study aimed to investigate unresectable GC from an imaging perspective combined with clinicopathological variables to identify patients who were most likely to benefit from immunotherapy.

Method

Patients with unresectable GC who were consecutively treated with immunotherapy at two different medical centers of Chinese PLA General Hospital were included and divided into the training and validation cohorts, respectively. A deep learning neural network, using a multimodal ensemble approach based on CT imaging data before immunotherapy, was trained in the training cohort to predict survival, and an internal validation cohort was constructed to select the optimal ensemble model. Data from another cohort were used for external validation. The area under the receiver operating characteristic curve was analyzed to evaluate performance in predicting survival. Detailed clinicopathological data and peripheral blood prior to immunotherapy were collected for each patient. Univariate and multivariable logistic regression analysis of imaging models and clinicopathological variables was also applied to identify the independent predictors of survival. A nomogram based on multivariable logistic regression was constructed.

Result

A total of 79 GC patients in the training cohort and 97 patients in the external validation cohort were enrolled in this study. A multi-model ensemble approach was applied to train a model to predict the 1-year survival of GC patients. Compared to individual models, the ensemble model showed improvement in performance metrics in both the internal and external validation cohorts. There was a significant difference in overall survival (OS) among patients with different imaging models based on the optimum cutoff score of 0.5 (HR = 0.20, 95 % CI: 0.10-0.37, P < 0.001). Multivariate Cox regression analysis revealed that the imaging models, PD-L1 expression, and lung immune prognostic index were independent prognostic factors for OS. We combined these variables and built a nomogram. The calibration curves showed that the C-index of the nomogram was 0.85 and 0.78 in the training and validation cohorts.

Conclusion

The deep learning model in combination with several clinical factors showed predictive value for survival in patients with unresectable GC receiving immunotherapy.

CT-based radiomics and cluster analysis for the prediction of local progression in stage I NSCLC patients treated with microwave ablation

To predict local progression after microwave ablation (MWA) in patients with stage I non-small cell lung cancer (NSCLC), we developed a CT-based radiomics model. Postoperative CT images were used. The intraclass correlation coefficients, two-sample t-test, least absolute shrinkage and selection operator (LASSO) regression, and Pearson correlation analysis were applied to select radiomics features and establish radiomics score. The Radiomics score was used to classify patients into new radiomics labels. The k-means cluster algorithm was employed to cluster patients into new cluster labels based on radiomics features. Logistic regression was used to build prediction models. The optimal model incorporating clinical risk factors, radiomics labels, and cluster labels achieved the best discrimination. This study proposes a radiomics model that accurately predicts local progression in patients with stage I NSCLC treated with MWA. This prediction tool may be helpful in determining MWA efficacy and individualized risk classification and treatment.

Individualized treatment recommendations for patients with locally advanced head and neck squamous cell carcinoma utilizing deep learning

Background

The conventional treatment for locally advanced head and neck squamous cell carcinoma (LA-HNSCC) is surgery; however, the efficacy of definitive chemoradiotherapy (CRT) remains controversial.

Objective

This study aimed to evaluate the ability of deep learning (DL) models to identify patients with LA-HNSCC who can achieve organ preservation through definitive CRT and provide individualized adjuvant treatment recommendations for patients who are better suited for surgery.

Methods

Five models were developed for treatment recommendations. Their performance was assessed by comparing the difference in overall survival rates between patients whose actual treatments aligned with the model recommendations and those whose treatments did not. Inverse probability treatment weighting (IPTW) was employed to reduce bias. The effect of the characteristics on treatment plan selection was quantified through causal inference.

Results

A total of 7,376 patients with LA-HNSCC were enrolled. Balanced Individual Treatment Effect for Survival data (BITES) demonstrated superior performance in both the CRT recommendation (IPTW-adjusted hazard ratio (HR): 0.84, 95% confidence interval (CI), 0.72-0.98) and the adjuvant therapy recommendation (IPTW-adjusted HR: 0.77, 95% CI, 0.61-0.85), outperforming other models and the National Comprehensive Cancer Network guidelines (IPTW-adjusted HR: 0.87, 95% CI, 0.73-0.96).

Conclusion

BITES can identify the most suitable treatment option for an individual patient from the three most common treatment options. DL models facilitate the establishment of a valid and reliable treatment recommendation system supported by quantitative evidence.

Multi-Centered Pre-Treatment CT-Based Radiomics Features to Predict Locoregional Recurrence of Locally Advanced Esophageal Cancer After Definitive Chemoradiotherapy

Purpose: We constructed a prediction model to predict a 2-year locoregional recurrence based on the clinical features and radiomic features extracted from the machine learning method using computed tomography (CT) before definite chemoradiotherapy (dCRT) in locally advanced esophageal cancer. Patients and methods: A total of 264 patients (156 in Beijing, 87 in Tianjin, and 21 in Jiangsu) were included in this study. All those locally advanced esophageal cancer patients received definite radiotherapy and were randomly divided into five subgroups with a similar number and divided into training groups and validation groups by five cross-validations. The esophageal tumor and extratumoral esophagus were segmented to extract radiomic features from the gross tumor volume (GTV) drawn by radiation therapists before radiotherapy, and six clinical features associated with prognosis were added. T stage, N stage, M stage, total TNM stage, GTV, and GTVnd volume were included to construct a prediction model to predict the 2-year locoregional recurrence of patients after definitive radiotherapy. Results: A total of 264 patients were enrolled from August 2012 to April 2018, with a median age of 62 years and 81% were males. The 2-year locoregional recurrence rate was 52.6%, and the 2-year overall survival rate was 45.6%. About 66% of patients received concurrent chemotherapy. In total, we extracted 786 radiomic features from CT images and the Principal Component Analysis (PCA) method was used to screen out the maximum 30 features. Finally, the Support Vector Machine (SVM) method was used to construct the integrated prediction model combining radiomics and clinical features. In the five training groups for predicting locoregional recurrence, the mean value of C-index was 0.9841 (95%CI, 0.9809-0.9873), and in the five validation groups, the mean value was 0.744 (95%CI, 0.7437-0.7443). Conclusions: The integrated radiomics model could predict the 2-year locoregional recurrence after dCRT. The model showed promising results and could help guide treatment decisions by identifying high-risk patients and enabling strategies to prevent early recurrence.

Predicting the risk of type 2 diabetes mellitus (T2DM) emergence in 5 years using mammography images: a comparison study between radiomics and deep learning algorithm

Purpose

The prevalence of type 2 diabetes mellitus (T2DM) has been steadily increasing over the years. We aim to predict the occurrence of T2DM using mammography images within 5 years using two different methods and compare their performance.

Approach

We examined 312 samples, including 110 positive cases (developed T2DM after 5 years) and 202 negative cases (did not develop T2DM) using two different methods. In the first method, a radiomics-based approach, we utilized radiomics features and machine learning (ML) algorithms. The entire breast region was chosen as the region of interest for extracting radiomics features. Then, a binary breast image was created from which we extracted 668 features and analyzed them using various ML algorithms. In the second method, a complex convolutional neural network (CNN) with a modified ResNet architecture and various kernel sizes was applied to raw mammography images for the prediction task. A nested, stratified five-fold cross-validation was done for both parts A and B to compute accuracy, sensitivity, specificity, and area under the receiver operating curve (AUROC). Hyperparameter tuning was also done to enhance the model's performance and reliability.

Results

The radiomics approach's light gradient boosting model gave 68.9% accuracy, 30.7% sensitivity, 89.5% specificity, and 0.63 AUROC. The CNN method achieved an AUROC of 0.58 over 20 epochs.

Conclusion

Radiomics outperformed CNN by 0.05 in terms of AUROC. This may be due to the more straightforward interpretability and clinical relevance of predefined radiomics features compared with the complex, abstract features learned by CNNs.

Machine learning in image-based outcome prediction after radiotherapy: A review

The integration of machine learning (ML) with radiotherapy has emerged as a pivotal innovation in outcome prediction, bringing novel insights amid unique challenges. This review comprehensively examines the current scope of ML applications in various treatment contexts, focusing on treatment outcomes such as patient survival, disease recurrence, and treatment-induced toxicity. It emphasizes the ascending trajectory of research efforts and the prominence of survival analysis as a clinical priority. We analyze the use of several common medical imaging modalities in conjunction with clinical data, highlighting the advantages and complexities inherent in this approach. The research reflects a commitment to advancing patient-centered care, advocating for expanded research on abdominal and pancreatic cancers. While data collection, patient privacy, standardization, and interpretability present significant challenges, leveraging ML in radiotherapy holds remarkable promise for elevating precision medicine and improving patient care outcomes.

Machine learning-derived peripheral blood transcriptomic biomarkers for early lung cancer diagnosis: Unveiling tumor-immune interaction mechanisms

Lung cancer continues to be the leading cause of cancer-related mortality worldwide. Early detection and a comprehensive understanding of tumor-immune interactions are crucial for improving patient outcomes. This study aimed to develop a novel biomarker panel utilizing peripheral blood transcriptomics and machine learning algorithms for early lung cancer diagnosis, while simultaneously providing insights into tumor-immune crosstalk mechanisms. Leveraging a training cohort (GSE135304), we employed multiple machine learning algorithms to formulate a Lung Cancer Diagnostic Score (LCDS) based on peripheral blood transcriptomic features. The LCDS model's performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) in multiple validation cohorts (GSE42834, GSE157086, and an in-house dataset). Peripheral blood samples were obtained from 20 lung cancer patients and 10 healthy control subjects, representing an in-house cohort recruited at the Sixth People's Hospital of Chengdu. We employed advanced bioinformatics techniques to explore tumor-immune interactions through comprehensive immune infiltration and pathway enrichment analyses. Initial screening identified 844 differentially expressed genes, which were subsequently refined to 87 genes using the Boruta feature selection algorithm. The random forest (RF) algorithm demonstrated the highest accuracy in constructing the LCDS model, yielding a mean AUC of 0.938. Lower LCDS values were significantly associated with elevated immune scores and increased CD4+ and CD8+ T-cell infiltration, indicative of enhanced antitumor-immune responses. Higher LCDS scores correlated with activation of hypoxia, peroxisome proliferator-activated receptor (PPAR), and Toll-like receptor (TLR) signaling pathways, as well as reduced DNA damage repair pathway scores. Our study presents a novel, machine learning-derived peripheral blood transcriptomic biomarker panel with potential applications in early lung cancer diagnosis. The LCDS model not only demonstrates high accuracy in distinguishing lung cancer patients from healthy individuals but also offers valuable insights into tumor-immune interactions and underlying cancer biology. This approach may facilitate early lung cancer detection and contribute to a deeper understanding of the molecular and cellular mechanisms underlying tumor-immune crosstalk. Furthermore, our findings on the relationship between LCDS and immune infiltration patterns may have implications for future research on therapeutic strategies targeting the immune system in lung cancer.

Predicting local control of brain metastases after stereotactic radiotherapy with clinical, radiomics and deep learning features

BACKGROUND AND PURPOSE

Timely identification of local failure after stereotactic radiotherapy for brain metastases allows for treatment modifications, potentially improving outcomes. While previous studies showed that adding radiomics or Deep Learning (DL) features to clinical features increased Local Control (LC) prediction accuracy, their combined potential to predict LC remains unexplored. We examined whether a model using a combination of radiomics, DL and clinical features achieves better accuracy than models using only a subset of these features.

MATERIALS AND METHODS

We collected pre-treatment brain MRIs (TR/TE: 25/1.86 ms, FOV: 210 × 210 × 150, flip angle: 30°, transverse slice orientation, voxel size: 0.82 × 0.82 × 1.5 mm) and clinical data for 129 patients at the Gamma Knife Center of the Elisabeth-TweeSteden Hospital. Radiomics features were extracted using the Python radiomics feature extractor and DL features were obtained using a 3D ResNet model. A Random Forest machine learning algorithm was employed to train four models using: (1) clinical features only; (2) clinical and radiomics features; (3) clinical and DL features; and (4) clinical, radiomics, and DL features. The average accuracy and other metrics were derived using K-fold cross validation.

RESULTS

The prediction model utilizing only clinical variables provided an Area Under the receiver operating characteristic Curve (AUC) of 0.85 and an accuracy of 75.0%. Adding radiomics features increased the AUC to 0.86 and accuracy to 79.33%, while adding DL features resulted in an AUC of 0.82 and accuracy of 78.0%. The best performance came from combining clinical, radiomics, and DL features, achieving an AUC of 0.88 and accuracy of 81.66%. This model's prediction improvement was statistically significant compared to models trained with clinical features alone or with the combination of clinical and DL features. However, the improvement was not statistically significant when compared to the model trained with clinical and radiomics features.

CONCLUSION

Integrating radiomics and DL features with clinical characteristics improves prediction of local control after stereotactic radiotherapy for brain metastases. Models incorporating radiomics features consistently outperformed those utilizing clinical features alone or clinical and DL features. The increased prediction accuracy of our integrated model demonstrates the potential for early outcome prediction, enabling timely treatment modifications to improve patient management.

Real-World and Clinical Trial Validation of a Deep Learning Radiomic Biomarker for PD-(L)1 Immune Checkpoint Inhibitor Response in Advanced Non-Small Cell Lung Cancer

PURPOSE

This study developed and validated a novel deep learning radiomic biomarker to estimate response to immune checkpoint inhibitor (ICI) therapy in advanced non-small cell lung cancer (NSCLC) using real-world data (RWD) and clinical trial data.

MATERIALS AND METHODS

Retrospective RWD of 1,829 patients with advanced NSCLC treated with PD-(L)1 ICIs were collected from 10 academic and community institutions in the United States and Europe. The RWD included data sets for discovery (Data Set A-Discovery, n = 1,173) and independent test (Data Set B, n = 458). A radiomic pipeline, containing a deep learning feature extractor and a survival model, generated the computed tomography (CT) response score (CTRS) applied to the pretreatment routine CT/positron emission tomography (PET)-CT scan. An enhanced CTRS (eCTRS) also incorporated age, sex, treatment line, and lesion annotations. Performance was evaluated against progression-free survival (PFS) and overall survival (OS). Biomarker generalizability was further evaluated using a secondary analysis of a prospective clinical trial (ClinicalTrials.gov identifier: NCT02573259) evaluating the PD-1 inhibitor sasanlimab in second or later line of treatment (Data Set C, n = 54).

RESULTS

In RWD Test Data Set B, the CTRS identified patients with a high probability of response to ICI with a PFS hazard ratio (HR) of 0.46 (95% CI, 0.26 to 0.82) and an OS HR of 0.50 (95% CI, 0.28 to 0.92) in the first-line ICI monotherapy cohort, after adjustment for baseline covariates including the PD-L1 tumor proportion score. In Clinical Trial Data Set C, the CTRS demonstrated an adjusted PFS HR of 1.03 (95% CI, 0.43 to 2.47) and an OS HR of 0.33 (95% CI, 0.14 to 0.91). The CTRS and eCTRS outperformed traditional imaging biomarkers of lesion size in PFS and OS for RWD Test Data Set B and in OS for the Clinical Trial Data Set.

CONCLUSION

The study developed and validated a deep learning radiomic biomarker using pretreatment routine CT/PET-CT scans to identify ICI benefit in advanced NSCLC.

Emerging trends and hotspots in lung cancer-prediction models research

Objective

In recent years, lung cancer-prediction models have become popular. However, few bibliometric analyses have been performed in this field.

Methods

This study aimed to reveal the scientific output and trends in lung cancer-prediction models from a global perspective. In this study, publications were retrieved and extracted from the Web of Science Core Collection (WoSCC) database. CiteSpace 6.1.R3 and VOSviewer 1.6.18 were used to analyze hotspots and theme trends.

Results

A marked increase in the number of publications related to lung cancer-prediction models was observed. A total of 2711 institutions from in 64 countries/regions published 2139 documents in 566 academic journals. China and the United States were the leading country in the field of lung cancer-prediction models. The institutions represented by Fudan University had significant academic influence in the field. Analysis of keywords revealed that lncRNA, tumor microenvironment, immune, cancer statistics, The Cancer Genome Atlas, nomogram, and machine learning were the current focus of research in lung cancer-prediction models.

Conclusions

Over the last two decades, research on risk-prediction models for lung cancer has attracted increasing attention. Prognosis, machine learning, and multi-omics technologies are both current hotspots and future trends in this field. In the future, in-depth explorations using different omics should increase the sensitivity and accuracy of lung cancer-prediction models and reduce the global burden of lung cancer.

Deep Learning of radiology-genomics integration for computational oncology: A mini review

In the field of computational oncology, patient status is often assessed using radiology-genomics, which includes two key technologies and data, such as radiology and genomics. Recent advances in deep learning have facilitated the integration of radiology-genomics data, and even new omics data, significantly improving the robustness and accuracy of clinical predictions. These factors are driving artificial intelligence (AI) closer to practical clinical applications. In particular, deep learning models are crucial in identifying new radiology-genomics biomarkers and therapeutic targets, supported by explainable AI (xAI) methods. This review focuses on recent developments in deep learning for radiology-genomics integration, highlights current challenges, and outlines some research directions for multimodal integration and biomarker discovery of radiology-genomics or radiology-omics that are urgently needed in computational oncology.

Artificial intelligence-based personalized survival prediction using clinical and radiomics features in patients with advanced non-small cell lung cancer

BACKGROUND

Multiple first-line treatment options have been developed for advanced non-small cell lung cancer (NSCLC) in each subgroup determined by predictive biomarkers, specifically driver oncogene and programmed cell death ligand-1 (PD-L1) status. However, the methodology for optimal treatment selection in individual patients is not established. This study aimed to develop artificial intelligence (AI)-based personalized survival prediction model according to treatment selection.

METHODS

The prediction model was built based on random survival forest (RSF) algorithm using patient characteristics, anticancer treatment histories, and radiomics features of the primary tumor. The predictive accuracy was validated with external test data and compared with that of cox proportional hazard (CPH) model.

RESULTS

A total of 459 patients (training, n = 299; test, n = 160) with advanced NSCLC were enrolled. The algorithm identified following features as significant factors associated with survival: age, sex, performance status, Brinkman index, comorbidity of chronic obstructive pulmonary disease, histology, stage, driver oncogene status, tumor PD-L1 expression, administered anticancer agent, six markers of blood test (sodium, lactate dehydrogenase, etc.), and three radiomics features associated with tumor texture, volume, and shape. The C-index of RSF model for test data was 0.841, which was higher than that of CPH model (0.775, P < 0.001). Furthermore, the RSF model enabled to identify poor survivor treated with pembrolizumab because of tumor PD-L1 high expression and those treated with driver oncogene targeted therapy according to driver oncogene status.

CONCLUSIONS

The proposed AI-based algorithm accurately predicted the survival of each patient with advanced NSCLC. The AI-based methodology will contribute to personalized medicine.

TRIAL REGISTRATION

The trial design was retrospectively registered study performed in accordance with the Declaration of Helsinki and approved by the Institutional Review Board of Nagoya University Graduate School of Medicine (approval: 2020 - 0287).

Clinical applications of radiomics and deep learning in breast and lung cancer: A narrative literature review on current evidence and future perspectives

Radiomics, analysing quantitative features from medical imaging, has rapidly become an emerging field in translational oncology. Radiomics has been investigated in several neoplastic malignancies as it might allow for a non-invasive tumour characterization and for the identification of predictive and prognostic biomarkers. Over the last few years, evidence has been accumulating regarding potential clinical applications of machine learning in many crucial moments of cancer patients' history. However, the incorporation of radiomics in clinical decision-making process is still limited by low data reproducibility and study variability. Moreover, the need for prospective validations and standardizations is emerging. In this narrative review, we summarize current evidence regarding radiomic applications in high-incidence cancers (breast and lung) for screening, diagnosis, staging, treatment choice, response, and clinical outcome evaluation. We also discuss pro and cons of the radiomic approach, suggesting possible solutions to critical issues which might invalidate radiomics studies and propose future perspectives.

radMLBench: A dataset collection for benchmarking in radiomics

BACKGROUND

New machine learning methods and techniques are frequently introduced in radiomics, but they are often tested on a single dataset, which makes it challenging to assess their true benefit. Currently, there is a lack of a larger, publicly accessible dataset collection on which such assessments could be performed. In this study, a collection of radiomics datasets with binary outcomes in tabular form was curated to allow benchmarking of machine learning methods and techniques.

METHODS

A variety of journals and online sources were searched to identify tabular radiomics data with binary outcomes, which were then compiled into a homogeneous data collection that is easily accessible via Python. To illustrate the utility of the dataset collection, it was applied to investigate whether feature decorrelation prior to feature selection could improve predictive performance in a radiomics pipeline.

RESULTS

A total of 50 radiomic datasets were collected, with sample sizes ranging from 51 to 969 and 101 to 11165 features. Using this data, it was observed that decorrelating features did not yield any significant improvement on average.

CONCLUSIONS

A large collection of datasets, easily accessible via Python, suitable for benchmarking and evaluating new machine learning techniques and methods was curated. Its utility was exemplified by demonstrating that feature decorrelation prior to feature selection does not, on average, lead to significant performance gains and could be omitted, thereby increasing the robustness and reliability of the radiomics pipeline.

Deep learning to estimate response of concurrent chemoradiotherapy in non-small-cell lung carcinoma

BACKGROUND

Concurrent chemoradiotherapy (CCRT) is a crucial treatment for non-small cell lung carcinoma (NSCLC). However, the use of deep learning (DL) models for predicting the response to CCRT in NSCLC remains unexplored. Therefore, we constructed a DL model for estimating the response to CCRT in NSCLC and explored the associated biological signaling pathways.

METHODS

Overall, 229 patients with NSCLC were recruited from six hospitals. Based on contrast-enhanced computed tomography (CT) images, a three-dimensional ResNet50 algorithm was used to develop a model and validate the performance in predicting response and prognosis. An associated analysis was conducted on CT image visualization, RNA sequencing, and single-cell sequencing.

RESULTS

The DL model exhibited favorable predictive performance, with an area under the curve of 0.86 (95% confidence interval [CI] 0.79-0·92) in the training cohort and 0.84 (95% CI 0.75-0.94) in the validation cohort. The DL model (low score vs. high score) was an independent predictive factor; it was significantly associated with progression-free survival and overall survival in both the training (hazard ratio [HR] = 0.54 [0.36-0.80], P = 0.002; 0.44 [0.28-0.68], P < 0.001) and validation cohorts (HR = 0.46 [0.24-0.88], P = 0.008; 0.30 [0.14-0.60], P < 0.001). The DL model was also positively related to the cell adhesion molecules, the P53 signaling pathway, and natural killer cell-mediated cytotoxicity. Single-cell analysis revealed that differentially expressed genes were enriched in different immune cells.

CONCLUSION

The DL model demonstrated a strong predictive ability for determining the response in patients with NSCLC undergoing CCRT. Our findings contribute to understanding the potential biological mechanisms underlying treatment responses in these patients.

Artificial intelligence methods available for cancer research

Cancer is a heterogeneous and multifaceted disease with a significant global footprint. Despite substantial technological advancements for battling cancer, early diagnosis and selection of effective treatment remains a challenge. With the convenience of large-scale datasets including multiple levels of data, new bioinformatic tools are needed to transform this wealth of information into clinically useful decision-support tools. In this field, artificial intelligence (AI) technologies with their highly diverse applications are rapidly gaining ground. Machine learning methods, such as Bayesian networks, support vector machines, decision trees, random forests, gradient boosting, and K-nearest neighbors, including neural network models like deep learning, have proven valuable in predictive, prognostic, and diagnostic studies. Researchers have recently employed large language models to tackle new dimensions of problems. However, leveraging the opportunity to utilize AI in clinical settings will require surpassing significant obstacles-a major issue is the lack of use of the available reporting guidelines obstructing the reproducibility of published studies. In this review, we discuss the applications of AI methods and explore their benefits and limitations. We summarize the available guidelines for AI in healthcare and highlight the potential role and impact of AI models on future directions in cancer research.

"Application of CT radiomics in brain metastasis of lung cancer: A systematic review and meta-analysis"

PURPOSE

This study aimed to systematically assess the quality and performance of computed tomography (CT) radiomics studies in predicting brain metastasis (BM) among patients with lung cancer.

METHODS

The PubMed, Embase and Web of Science were searched for studies predicting BM in patients with lung cancer using CT-based radiomics features. Information regarding patients, imaging, and radiomics analysis was extracted from eligible studies. We assessed the quality of included studies using the Radiomics Quality Scoring (RQS) tool and the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). A meta-analysis of studies regarding the prediction of BM in patients with lung cancer was performed.

RESULTS

Thirteen studies were identified, with sample sizes ranging from 75 to 602. The mean RQS of the studies was 12 (range 9-16), and the corresponding percentage of the score was 33.55 % (range 25.00-44.44 %). Four studies (30.8 %) were considered as low risk of bias, while the remaining nine studies (69.2 %) were considered to have unclear risks. The meta-analysis included twelve studies. The pooled sensitivity, specificity and Area Under the Curve (AUC) value with 95 % confidence intervals were 0.75 [0.69, 0.80], 0.76 [0.68, 0.82], and 0.81 [0.77-0.84], respectively.

CONCLUSION

CT radiomics-based models show promising results as a non-invasive method to predict BM in lung cancer patients. However, multicenter and prospective studies are warranted to enhance the stability and acceptance of radiomics.

Organomics: A Concept Reflecting the Importance of PET/CT Healthy Organ Radiomics in Non-Small Cell Lung Cancer Prognosis Prediction Using Machine Learning

PURPOSE

Non-small cell lung cancer is the most common subtype of lung cancer. Patient survival prediction using machine learning (ML) and radiomics analysis proved to provide promising outcomes. However, most studies reported in the literature focused on information extracted from malignant lesions. This study aims to explore the relevance and additional value of information extracted from healthy organs in addition to tumoral tissue using ML algorithms.

PATIENTS AND METHODS

This study included PET/CT images of 154 patients collected from available online databases. The gross tumor volume and 33 volumes of interest defined on healthy organs were segmented using nnU-Net deep learning-based segmentation. Subsequently, 107 radiomic features were extracted from PET and CT images (Organomics). Clinical information was combined with PET and CT radiomics from organs and gross tumor volumes considering 19 different combinations of inputs. Finally, different feature selection (FS; 5 methods) and ML (6 algorithms) algorithms were tested in a 3-fold data split cross-validation scheme. The performance of the models was quantified in terms of the concordance index (C-index) metric.

RESULTS

For an input combination of all radiomics information, most of the selected features belonged to PET Organomics and CT Organomics. The highest C-index (0.68) was achieved using univariate C-index FS method and random survival forest ML model using CT Organomics + PET Organomics as input as well as minimum depth FS method and CoxPH ML model using PET Organomics as input. Considering all 17 combinations with C-index higher than 0.65, Organomics from PET or CT images were used as input in 16 of them.

CONCLUSIONS

The selected features and C-indices demonstrated that the additional information extracted from healthy organs of both PET and CT imaging modalities improved the ML performance. Organomics could be a step toward exploiting the whole information available from multimodality medical images, contributing to the emerging field of digital twins in health care.

Determining individual suitability for neoadjuvant systemic therapy in breast cancer patients through deep learning

BACKGROUND

The survival advantage of neoadjuvant systemic therapy (NST) for breast cancer patients remains controversial, especially when considering the heterogeneous characteristics of individual patients.

OBJECTIVE

To discern the variability in responses to breast cancer treatment at the individual level and propose personalized treatment recommendations utilizing deep learning (DL).

METHODS

Six models were developed to offer individualized treatment suggestions. Outcomes for patients whose actual treatments aligned with model recommendations were compared to those whose did not. The influence of certain baseline features of patients on NST selection was visualized and quantified by multivariate logistic regression and Poisson regression analyses.

RESULTS

Our study included 94,487 female breast cancer patients. The Balanced Individual Treatment Effect for Survival data (BITES) model outperformed other models in performance, showing a statistically significant protective effect with inverse probability treatment weighting (IPTW)-adjusted baseline features [IPTW-adjusted hazard ratio: 0.51, 95% confidence interval (CI), 0.41-0.64; IPTW-adjusted risk difference: 21.46, 95% CI 18.90-24.01; IPTW-adjusted difference in restricted mean survival time: 21.51, 95% CI 19.37-23.80]. Adherence to BITES recommendations is associated with reduced breast cancer mortality and fewer adverse effects. BITES suggests that patients with TNM stage IIB, IIIB, triple-negative subtype, a higher number of positive axillary lymph nodes, and larger tumors are most likely to benefit from NST.

CONCLUSIONS

Our results demonstrated the potential of BITES to aid in clinical treatment decisions and offer quantitative treatment insights. In our further research, these models should be validated in clinical settings and additional patient features as well as outcome measures should be studied in depth.

Identifying cancer risks using spectral subset feature selection based on multi-layer perception neural network for premature treatment

Recently, human beings have been affected mainly by dreadful cancer diseases. Predicting cancer risk levels is a major challenge in biomedical research for feature selection and classification at the margins. To resolve this problem, we propose a Subset Clustering-Based Feature Selection using a Multi-Layer Perception Neural Network (SCFS-MLPNN). Initially, pre-processing is carried out with Intensive Mutual Disease Influence Rate (IMDIR) to identify the relational features. In addition, the Successive Disease Pattern Stimulus Rate (SDPSR) is carried out to create relative feature patterns. Based on the patterns, the features are selected and grouped into clustering. Inter-Class Sub-Space Clustering (ICSSC) is applied to split the features by class labels depending on the marginal rate. From the class labels, marginal features are obtained using spectral subset feature selection (SSFS). The selected features are then trained in a Multi-Layer Perception Neural Network (MLPNN) classifier to classify the patient features by risk. Its contribution is to exploit subset features to improve classification accuracy by clustering relational features. The proposed classifier yields higher classification accuracy than previous methods and observes cancer detection for early detection. Therefore, the proposed method achieved a risk analysis accuracy of 91.8% and an F-measure of 91.3% for early detection, which is recommended for early diagnosis.

Patient-specific cerebral 3D vessel model reconstruction using deep learning

Three-dimensional vessel model reconstruction from patient-specific magnetic resonance angiography (MRA) images often requires some manual maneuvers. This study aimed to establish the deep learning (DL)-based method for vessel model reconstruction. Time of flight MRA of 40 patients with internal carotid artery aneurysms was prepared, and three-dimensional vessel models were constructed using the threshold and region-growing method. Using those datasets, supervised deep learning using 2D U-net was performed to reconstruct 3D vessel models. The accuracy of the DL-based vessel segmentations was assessed using 20 MRA images outside the training dataset. The dice coefficient was used as the indicator of the model accuracy, and the blood flow simulation was performed using the DL-based vessel model. The created DL model could successfully reconstruct a three-dimensional model in all 60 cases. The dice coefficient in the test dataset was 0.859. Of note, the DL-generated model proved its efficacy even for large aneurysms (> 10 mm in their diameter). The reconstructed model was feasible in performing blood flow simulation to assist clinical decision-making. Our DL-based method could successfully reconstruct a three-dimensional vessel model with moderate accuracy. Future studies are warranted to exhibit that DL-based technology can promote medical image processing.

A Survey on Explainable Artificial Intelligence (XAI) Techniques for Visualizing Deep Learning Models in Medical Imaging

The combination of medical imaging and deep learning has significantly improved diagnostic and prognostic capabilities in the healthcare domain. Nevertheless, the inherent complexity of deep learning models poses challenges in understanding their decision-making processes. Interpretability and visualization techniques have emerged as crucial tools to unravel the black-box nature of these models, providing insights into their inner workings and enhancing trust in their predictions. This survey paper comprehensively examines various interpretation and visualization techniques applied to deep learning models in medical imaging. The paper reviews methodologies, discusses their applications, and evaluates their effectiveness in enhancing the interpretability, reliability, and clinical relevance of deep learning models in medical image analysis.

Predicting Gene Comutation of EGFR and TP53 by Radiomics and Deep Learning in Patients With Lung Adenocarcinomas

PURPOSE

This study was designed to construct progressive binary classification models based on radiomics and deep learning to predict the presence of epidermal growth factor receptor (EGFR) and TP53 mutations and to assess the models' capacities to identify patients who are suitable for TKI-targeted therapy and those with poor prognoses.

MATERIALS AND METHODS

A total of 267 patients with lung adenocarcinomas who underwent genetic testing and noncontrast chest computed tomography from our hospital were retrospectively included. Clinical information and imaging characteristics were gathered, and high-throughput feature acquisition on all defined regions of interest (ROIs) was carried out. We selected features and constructed clinical models, radiomics models, deep learning models, and ensemble models to predict EGFR status with all patients and TP53 status with EGFR-positive patients, respectively. The validity and reliability of each model were expressed as the area under the curve (AUC), sensitivity, specificity, accuracy, precision, and F1 score.

RESULTS

We constructed 7 kinds of models for 2 different dichotomies, namely, the clinical model, the radiomics model, the DL model, the rad-clin model, the DL-clin model, the DL-rad model, and the DL-rad-clin model. For EGFR- and EGFR+, the DL-rad-clin model got the highest AUC value of 0.783 (95% CI: 0.677-0.889), followed by the rad-clin model, the DL-clin model, and the DL-rad model. In the group with an EGFR mutation, for TP53- and TP53+, the rad-clin model got the highest AUC value of 0.811 (95% CI: 0.651-0.972), followed by the DL-rad-clin model and the DL-rad model.

CONCLUSION

Our progressive binary classification models based on radiomics and deep learning may provide a good reference and complement for the clinical identification of TKI responders and those with poor prognoses.

Predicting histopathological features of aggressiveness in lung cancer using CT radiomics: a systematic review

PURPOSE

To examine the accuracy of CT radiomics to predict histopathological features of aggressiveness in lung cancer using a systematic review of test accuracy studies.

METHODS

Data sources searched included Medline, Embase, Web of Science, and Cochrane Library from up to 3 November 2023. Included studies reported test accuracy of CT radiomics models to detect the presence of: spread through air spaces (STAS), predominant adenocarcinoma pattern, adenocarcinoma grade, lymphovascular invasion (LVI), tumour infiltrating lymphocytes (TIL) and tumour necrosis, in patients with lung cancer. The primary outcome was test accuracy. Two reviewers independently assessed articles for inclusion and assessed methodological quality using the QUality Assessment of Diagnostic Accuracy Studies-2 tool. A single reviewer extracted data, which was checked by a second reviewer. Narrative data synthesis was performed.

RESULTS

Eleven studies were included in the final analysis. 10/11 studies were in East Asian populations. 4/11 studies investigated STAS, 6/11 investigated adenocarcinoma invasiveness or growth pattern, and 1/11 investigated LVI. No studies investigating TIL or tumour necrosis met inclusion criteria. Studies were of generally mixed to poor methodological quality. Reported accuracies for radiomic models ranged from 0.67 to 0.94.

CONCLUSION

Due to the high risk of bias and concerns regarding applicability, the evidence is inconclusive as to whether radiomic features can accurately predict prognostically important histopathological features of cancer aggressiveness. Many studies were excluded due to lack of external validation. Rigorously conducted prospective studies with sufficient external validity will be required for radiomic models to play a role in improving lung cancer outcomes.

Current status and quality of prognosis prediction models of non-small cell lung cancer constructed using computed tomography (CT)-based radiomics: a systematic review and radiomics quality score 2.0 assessment

Background

Radiomics extracts specific quantitative data from medical images and explores the characteristics of tumors by analyzing these representations and making predictions. The purpose of this paper is to review computed tomography (CT)-based radiomics articles related to prognostic outcomes in non-small cell lung cancer (NSCLC), assess their scientificity and quality by the latest radiomics quality score (RQS) 2.0 scoring criteria, and provide references for subsequent related studies.

Methods

CT-based radiomics studies on NSCLC prognosis published from 1 November 2012 to 30 November 2022 in English were screened through the databases of the Cochrane Library, Embase, and PubMed. By excluding criteria such as non-original studies, small sample sizes studies, positron emission tomography (PET)/CT only, and methodological studies only, 17 studies in English were included. The RQS proposed in 2017 is a quality evaluation index specific to radiomics following the PRISMA guidelines, and the latest update of RQS 2.0 has improved the scientificity and completeness of the score. Each checkpoint either belongs to handcrafted radiomics (HCR), deep learning, or both.

Results

The 17 included studies covered most treatments for NSCLC, including radiotherapy, chemotherapy, surgery, radiofrequency ablation, immunotherapy, and targeted therapy, and predicted outcomes such as overall survival (OS), progression-free survival (PFS), distant metastases, and disease-free survival (DFS). The median score rate for the included studies was 28%, with a range of 12% to 44%. The quality of studies in HCR is not high, and only 4 studies have been validated with independent cohorts.

Conclusions

The value of radiomics studies needs to be increased, such that clinical application will be possible, and the field of radiomics still has much room for growth. To make prediction models more reliable and stable in forecasting the prognosis of NSCLC and advancing the individualized treatment of NSCLC patients, more clinicians must participate in their development and clinical testing.

A dual-radiomics model for overall survival prediction in early-stage NSCLC patient using pre-treatment CT images

Introduction

Radiation therapy (RT) is one of the primary treatment options for early-stage non-small cell lung cancer (ES-NSCLC). Therefore, accurately predicting the overall survival (OS) rate following radiotherapy is crucial for implementing personalized treatment strategies. This work aims to develop a dual-radiomics (DR) model to (1) predict 3-year OS in ES-NSCLC patients receiving RT using pre-treatment CT images, and (2) provide explanations between feature importanceand model prediction performance.

Methods

The publicly available TCIA Lung1 dataset with 132 ES-NSCLC patients received RT were studied: 89/43 patients in the under/over 3-year OS group. For each patient, two types of radiomic features were examined: 56 handcrafted radiomic features (HRFs) extracted within gross tumor volume, and 512 image deep features (IDFs) extracted using a pre-trained U-Net encoder. They were combined as inputs to an explainable boosting machine (EBM) model for OS prediction. The EBM's mean absolute scores for HRFs and IDFs were used as feature importance explanations. To evaluate identified feature importance, the DR model was compared with EBM using either (1) key or (2) non-key feature type only. Comparison studies with other models, including supporting vector machine (SVM) and random forest (RF), were also included. The performance was evaluated by the area under the receiver operating characteristic curve (AUCROC), accuracy, sensitivity, and specificity with a 100-fold Monte Carlo cross-validation.

Results

The DR model showed highestperformance in predicting 3-year OS (AUCROC=0.81 ± 0.04), and EBM scores suggested that IDFs showed significantly greater importance (normalized mean score=0.0019) than HRFs (score=0.0008). The comparison studies showed that EBM with key feature type (IDFs-only demonstrated comparable AUCROC results (0.81 ± 0.04), while EBM with non-key feature type (HRFs-only) showed limited AUCROC (0.64 ± 0.10). The results suggested that feature importance score identified by EBM is highly correlated with OS prediction performance. Both SVM and RF models were unable to explain key feature type while showing limited overall AUCROC=0.66 ± 0.07 and 0.77 ± 0.06, respectively. Accuracy, sensitivity, and specificity showed a similar trend.

Discussion

In conclusion, a DR model was successfully developed to predict ES-NSCLC OS based on pre-treatment CT images. The results suggested that the feature importance from DR model is highly correlated to the model prediction power.

End-to-end reproducible AI pipelines in radiology using the cloud

Artificial intelligence (AI) algorithms hold the potential to revolutionize radiology. However, a significant portion of the published literature lacks transparency and reproducibility, which hampers sustained progress toward clinical translation. Although several reporting guidelines have been proposed, identifying practical means to address these issues remains challenging. Here, we show the potential of cloud-based infrastructure for implementing and sharing transparent and reproducible AI-based radiology pipelines. We demonstrate end-to-end reproducibility from retrieving cloud-hosted data, through data pre-processing, deep learning inference, and post-processing, to the analysis and reporting of the final results. We successfully implement two distinct use cases, starting from recent literature on AI-based biomarkers for cancer imaging. Using cloud-hosted data and computing, we confirm the findings of these studies and extend the validation to previously unseen data for one of the use cases. Furthermore, we provide the community with transparent and easy-to-extend examples of pipelines impactful for the broader oncology field. Our approach demonstrates the potential of cloud resources for implementing, sharing, and using reproducible and transparent AI pipelines, which can accelerate the translation into clinical solutions.

Cancer genetics and deep learning applications for diagnosis, prognosis, and categorization

Gene expression data are used to discover meaningful hidden information in gene datasets. Cancer and other disorders may be diagnosed based on differences in gene expression profiles, and this information can be gleaned by gene sequencing. Thanks to the tremendous power of artificial intelligence (AI), healthcare has become a significant user of deep learning (DL) for predicting cancer diseases and categorizing gene expression. Gene expression Microarrays have been proved effective in predicting cancer diseases and categorizing gene expression. Gene expression datasets contain only limited samples, but the features of cancer are diverse and complex. To overcome their dimensionality, gene expression datasets must be enhanced. By learning and analyzing features of input data, it is possible to extract features, as multidimensional arrays, from the data. Synthetic samples are needed to strengthen the range of information. DL strategies may be used when gene expression data are used to diagnose and classify cancer diseases.

Application of artificial intelligence in cancer diagnosis and tumor nanomedicine

Cancer is a major health concern due to its high incidence and mortality rates. Advances in cancer research, particularly in artificial intelligence (AI) and deep learning, have shown significant progress. The swift evolution of AI in healthcare, especially in tools like computer-aided diagnosis, has the potential to revolutionize early cancer detection. This technology offers improved speed, accuracy, and sensitivity, bringing a transformative impact on cancer diagnosis, treatment, and management. This paper provides a concise overview of the application of artificial intelligence in the realms of medicine and nanomedicine, with a specific emphasis on the significance and challenges associated with cancer diagnosis. It explores the pivotal role of AI in cancer diagnosis, leveraging structured, unstructured, and multimodal fusion data. Additionally, the article delves into the applications of AI in nanomedicine sensors and nano-oncology drugs. The fundamentals of deep learning and convolutional neural networks are clarified, underscoring their relevance to AI-driven cancer diagnosis. A comparative analysis is presented, highlighting the accuracy and efficiency of traditional methods juxtaposed with AI-based approaches. The discussion not only assesses the current state of AI in cancer diagnosis but also delves into the challenges faced by AI in this context. Furthermore, the article envisions the future development direction and potential application of artificial intelligence in cancer diagnosis, offering a hopeful prospect for enhanced cancer detection and improved patient prognosis.

Application of computed tomography-based radiomics analysis combined with lung cancer serum tumor markers in the identification of lung squamous cell carcinoma and lung adenocarcinoma

OBJECTIVE

To establish a prediction model of lung cancer classification by computed tomography (CT) radiomics with the serum tumor markers (STM) of lung cancer.

MATERIALS AND METHODS

Two-hundred NSCLC patients were enrolled in our study. Clinical data including age, sex, and STM (squamous cell carcinoma [SCC], neuron-specific enolase [NSE], carcinoembryonic antigen [CEA], pro-gastrin-releasing peptide [PRO-GRP], and cytokeratin 19 fragment [cYFRA21-1]) were collected. A radiomics signature was generated from the training set using the least absolute shrinkage and selection operator (LASSO) algorithm. The risk factors were identified using multivariate logistic regression analysis, and a radiomics nomogram based on the radiomics signature and clinical features was constructed. The capability of the nomogram was evaluated using the training set and validated using the validation set. A correction curve and the Hosmer-Lemeshow test were used to evaluate the predictive performance of the radiomics model for the training and test sets.

RESULTS

Twenty-nine of 1234 radiomics parameters were screened as important factors for establishing the radiomics model. The training (area under the curve [AUC] = 0.925; 95% confidence interval [CI]: 0.885-0.966) and validation sets (AUC = 0.921; 95% CI: 0.854-0.989) showed that the CT radiomics signature, combined with STM, accurately predicted lung squamous cell carcinoma and lung adenocarcinoma. Moreover, the logistic regression model showed good performance based on the Hosmer-Lemeshow test in the training (P = 0.954) and test sets (P = 0.340). Good calibration curve consistency also indicated the good performance of the nomogram.

CONCLUSION

The combination of the CT radiomics signature and lung cancer STM performed well for the pathological classification of NSCLC. Compared with the radiomics signature method, the nomogram based on the radiomics signature and clinical factors had better performance for the differential diagnosis of NSCLC.

Systematic review and meta-analysis of deep learning applications in computed tomography lung cancer segmentation

BACKGROUND

Accurate segmentation of lung tumors on chest computed tomography (CT) scans is crucial for effective diagnosis and treatment planning. Deep Learning (DL) has emerged as a promising tool in medical imaging, particularly for lung cancer segmentation. However, its efficacy across different clinical settings and tumor stages remains variable.

METHODS

We conducted a comprehensive search of PubMed, Embase, and Web of Science until November 7, 2023. We assessed the quality of these studies by using the Checklist for Artificial Intelligence in Medical Imaging and the Quality Assessment of Diagnostic Accuracy Studies-2 tools. This analysis included data from various clinical settings and stages of lung cancer. Key performance metrics, such as the Dice similarity coefficient, were pooled, and factors affecting algorithm performance, such as clinical setting, algorithm type, and image processing techniques, were examined.

RESULTS

Our analysis of 37 studies revealed a pooled Dice score of 79 % (95 % CI: 76 %-83 %), indicating moderate accuracy. Radiotherapy studies had a slightly lower score of 78 % (95 % CI: 74 %-82 %). A temporal increase was noted, with recent studies (post-2022) showing improvement from 75 % (95 % CI: 70 %-81 %). to 82 % (95 % CI: 81 %-84 %). Key factors affecting performance included algorithm type, resolution adjustment, and image cropping. QUADAS-2 assessments identified ambiguous risks in 78 % of studies due to data interval omissions and concerns about generalizability in 8 % due to nodule size exclusions, and CLAIM criteria highlighted areas for improvement, with an average score of 27.24 out of 42.

CONCLUSION

This meta-analysis demonstrates DL algorithms' promising but varied efficacy in lung cancer segmentation, particularly higher efficacy noted in early stages. The results highlight the critical need for continued development of tailored DL models to improve segmentation accuracy across diverse clinical settings, especially in advanced cancer stages with greater challenges. As recent studies demonstrate, ongoing advancements in algorithmic approaches are crucial for future applications.

Development of a CT-Based comprehensive model combining clinical, radiomics with deep learning for differentiating pulmonary metastases from noncalcified pulmonary hamartomas: a retrospective cohort study

BACKGROUND

Clinical differentiation between pulmonary metastases and noncalcified pulmonary hamartomas (NCPH) often presents challenges, leading to potential misdiagnosis. However, the efficacy of a comprehensive model that integrates clinical features, radiomics, and deep learning (CRDL) for differential diagnosis of these two diseases remains uncertain.

OBJECTIVE

This study evaluated the diagnostic efficacy of a CRDL model in differentiating pulmonary metastases from NCPH.

METHODS

The authors retrospectively analyzed the clinical and imaging data of 256 patients from the First Medical Centre of the General Hospital of the People's Liberation Army (PLA) and 85 patients from Shanghai Changhai Hospital, who were pathologically confirmed pulmonary hamartomas or pulmonary metastases after thoracic surgery. Employing Python 3.7 software suites, the authors extracted radiomic features and deep learning (DL) attributes from patient datasets. The cohort was divided into training set, internal validation set, and external validation set. The diagnostic performance of the constructed models was evaluated using receiver operating characteristic (ROC) curve analysis to determine their effectiveness in differentiating between pulmonary metastases and NCPH.

RESULTS

Clinical features such as white blood cell count (WBC), platelet count (PLT), history of cancer, carcinoembryonic antigen (CEA) level, tumor marker status, lesion margin characteristics (smooth or blurred), and maximum diameter were found to have diagnostic value in differentiating between the two diseases. In the domains of radiomics and DL. Of the 1130 radiomics features and 512 DL features, 24 and 7, respectively, were selected for model development. The area under the ROC curve (AUC) values for the four groups were 0.980, 0.979, 0.999, and 0.985 in the training set, 0.947, 0.816, 0.934, and 0.952 in the internal validation set, and 0.890, 0.904, 0.923, and 0.938 in the external validation set. This demonstrated that the CRDL model showed the greatest efficacy.

CONCLUSIONS

The comprehensive model incorporating clinical features, radiomics, and DL shows promise for aiding in the differentiation between pulmonary metastases and hamartomas.

An extensive review on lung cancer therapeutics using machine learning techniques: state-of-the-art and perspectives

There are over 100 types of human cancer, accounting for millions of deaths every year. Lung cancer alone claims over 1.8 million lives per year and is expected to surpass 3.2 million by 2050, which underscores the urgent need for rapid drug development and repurposing initiatives. The application of AI emerges as a pivotal solution to developing anti-cancer therapeutics. This state-of-the-art review aims to explore the various applications of AI in lung cancer therapeutics. Predictive models can analyse large datasets, including clinical data, genetic information, and treatment outcomes, for novel drug design and to generate personalised treatment recommendations, potentially optimising therapeutic strategies, enhancing treatment efficacy, and minimising adverse effects. A thorough literature review study was conducted based on articles indexed in PubMed and Scopus. We compiled the use of various machine learning approaches, including CNN, RNN, GAN, VAEs, and other AI techniques, enhancing efficiency with accuracy exceeding 95%, which is validated through a computer-aided drug design process. AI can revolutionise lung cancer therapeutics, streamlining processes and saving biological scientists' time and effort-however, further research is needed to overcome challenges and fully unlock AI's potential in Lung Cancer Therapeutics.

Deep Learning-Guided Dosimetry for Mitigating Local Failure of Patients With Non-Small Cell Lung Cancer Receiving Stereotactic Body Radiation Therapy

PURPOSE

Non-small cell lung cancer (NSCLC) stereotactic body radiation therapy with 50 Gy/5 fractions is sometimes considered controversial, as the nominal biologically effective dose (BED) of 100 Gy is felt by some to be insufficient for long-term local control of some lesions. In this study, we analyzed such patients using explainable deep learning techniques and consequently proposed appropriate treatment planning criteria. These novel criteria could help planners achieve optimized treatment plans for maximal local control.

METHODS AND MATERIALS

A total of 535 patients treated with 50 Gy/5 fractions were used to develop a novel deep learning local response model. A multimodality approach, incorporating computed tomography images, 3-dimensional dose distribution, and patient demographics, combined with a discrete-time survival model, was applied to predict time to failure and the probability of local control. Subsequently, an integrated gradient-weighted class activation mapping method was used to identify the most significant dose-volume metrics predictive of local failure and their optimal cut-points.

RESULTS

The model was cross-validated, showing an acceptable performance (c-index: 0.72, 95% CI, 0.68-0.75); the testing c-index was 0.69. The model's spatial attention was concentrated mostly in the tumors' periphery (planning target volume [PTV] - internal gross target volume [IGTV]) region. Statistically significant dose-volume metrics in improved local control were BED Dnear-min ≥ 103.8 Gy in IGTV (hazard ratio [HR], 0.31; 95% CI, 015-0.63), V104 ≥ 98% in IGTV (HR, 0.30; 95% CI, 0.15-0.60), gEUD ≥ 103.8 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.50), and Dmean ≥ 104.5 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.51).

CONCLUSIONS

Deep learning-identified dose-volume metrics have shown significant prognostic power (log-rank, P = .003) and could be used as additional actionable criteria for treatment planning in NSCLC stereotactic body radiation therapy patients receiving 50 Gy in 5 fractions. Although our data do not confirm or refute that a significantly higher BED for the prescription dose is necessary for tumor control in NSCLC, it might be clinically effective to escalate the nominal prescribed dose from BED 100 to 105 Gy.

Brain metastasis magnetic resonance imaging-based deep learning for predicting epidermal growth factor receptor (EGFR) mutation and subtypes in metastatic non-small cell lung cancer

Background

The preoperative identification of epidermal growth factor receptor (EGFR) mutations and subtypes based on magnetic resonance imaging (MRI) of brain metastases (BM) is necessary to facilitate individualized therapy. This study aimed to develop a deep learning model to preoperatively detect EGFR mutations and identify the location of EGFR mutations in patients with non-small cell lung cancer (NSCLC) and BM.

Methods

We included 160 and 72 patients who underwent contrast-enhanced T1-weighted (T1w-CE) and T2-weighted (T2W) MRI at Liaoning Cancer Hospital and Institute (center 1) and Shengjing Hospital of China Medical University (center 2) to form a training cohort and an external validation cohort, respectively. A multiscale feature fusion network (MSF-Net) was developed by adaptively integrating features based on different stages of residual network (ResNet) 50 and by introducing channel and spatial attention modules. The external validation set from center 2 was used to assess the performance of MSF-Net and to compare it with that of handcrafted radiomics features. Receiver operating characteristic (ROC) curves, accuracy, precision, recall, and F1-score were used to evaluate the effectiveness of the models. Gradient-weighted class activation mapping (Grad-CAM) was used to demonstrate the attention of the MSF-Net model.

Results

The developed MSF-Net generated a better diagnostic performance than did the handcrafted radiomics in terms of the microaveraged area under the curve (AUC) (MSF-Net: 0.91; radiomics: 0.80) and macroaveraged AUC (MSF-Net: 0.90; radiomics: 0.81) for predicting EGFR mutations and subtypes.

Conclusions

This study provides an end-to-end and noninvasive imaging tool for the preoperative prediction of EGFR mutation status and subtypes based on BM, which may be helpful for facilitating individualized clinical treatment plans.

EfficientNet-Based System for Detecting EGFR-Mutant Status and Predicting Prognosis of Tyrosine Kinase Inhibitors in Patients with NSCLC

We aimed to develop and validate a deep learning-based system using pre-therapy computed tomography (CT) images to detect epidermal growth factor receptor (EGFR)-mutant status in patients with non-small cell lung cancer (NSCLC) and predict the prognosis of advanced-stage patients with EGFR mutations treated with EGFR tyrosine kinase inhibitors (TKI). This retrospective, multicenter study included 485 patients with NSCLC from four hospitals. Of them, 339 patients from three centers were included in the training dataset to develop an EfficientNetV2-L-based model (EME) for predicting EGFR-mutant status, and the remaining patients were assigned to an independent test dataset. EME semantic features were extracted to construct an EME-prognostic model to stratify the prognosis of EGFR-mutant NSCLC patients receiving EGFR-TKI. A comparison of EME and radiomics was conducted. Additionally, we included patients from The Cancer Genome Atlas lung adenocarcinoma dataset with both CT images and RNA sequencing data to explore the biological associations between EME score and EGFR-related biological processes. EME obtained an area under the curve (AUC) of 0.907 (95% CI 0.840-0.926) on the test dataset, superior to the radiomics model (P = 0.007). The EME and radiomics fusion model showed better (AUC, 0.941) but not significantly increased performance (P = 0.895) compared with EME. In prognostic stratification, the EME-prognostic model achieved the best performance (C-index, 0.711). Moreover, the EME-prognostic score showed strong associations with biological pathways related to EGFR expression and EGFR-TKI efficacy. EME demonstrated a non-invasive and biologically interpretable approach to predict EGFR status, stratify survival prognosis, and correlate biological pathways in patients with NSCLC.

Pathological image profiling identifies onco-microbial, tumor immune microenvironment, and prognostic subtypes of colorectal cancer

Histology slide, tissue microbes, and the host gene expression can be independent prognostic factors of colorectal cancer (CRC), but the underlying associations and biological significance of these multimodal omics remain unknown. Here, we comprehensively profiled the matched pathological images, intratumoral microbes, and host gene expression characteristics in 527 patients with CRC. By clustering these patients based on histology slide features, we classified the patients into two histology slide subtypes (HSS). Onco-microbial community and tumor immune microenvironment (TIME) were also significantly different between the two subtypes (HSS1 and HSS2) of patients. Furthermore, variation in intratumoral microbes-host interaction was associated with the prognostic heterogeneity between HSS1 and HSS2. This study proposes a new CRC classification based on pathological image features and elucidates the process by which tumor microbes-host interactions are reflected in pathological images through the TIME.

Reporting Standards for Complication Studies of Radiation Therapy for Pediatric Cancer: Lessons From PENTEC

The major aim of Pediatric Normal Tissue Effects in the Clinic (PENTEC) was to synthesize quantitative published dose/-volume/toxicity data in pediatric radiation therapy. Such systematic reviews are often challenging because of the lack of standardization and difficulty of reporting outcomes, clinical factors, and treatment details in journal articles. This has clinical consequences: optimization of treatment plans must balance between the risks of toxicity and local failure; counseling patients and their parents requires knowledge of the excess risks encountered after a specific treatment. Studies addressing outcomes after pediatric radiation therapy are particularly challenging because: (a) survivors may live for decades after treatment, and the latency time to toxicity can be very long; (b) children's maturation can be affected by radiation, depending on the developmental status of the organs involved at time of treatment; and (c) treatment regimens frequently involve chemotherapies, possibly modifying and adding to the toxicity of radiation. Here we discuss: basic reporting strategies to account for the actuarial nature of the complications; the reporting of modeling of abnormal development; and the need for standardized, comprehensively reported data sets and multivariate models (ie, accounting for the simultaneous effects of radiation dose, age, developmental status at time of treatment, and chemotherapy dose). We encourage the use of tools that facilitate comprehensive reporting, for example, electronic supplements for journal articles. Finally, we stress the need for clinicians to be able to trust artificial intelligence models of outcome of radiation therapy, which requires transparency, rigor, reproducibility, and comprehensive reporting. Adopting the reporting methods discussed here and in the individual PENTEC articles will increase the clinical and scientific usefulness of individual reports and associated pooled analyses.

Implementation of Artificial Intelligence in Personalized Prognostic Assessment of Lung Cancer: A Narrative Review

Artificial Intelligence (AI) has revolutionized the management of non-small-cell lung cancer (NSCLC) by enhancing different aspects, including staging, prognosis assessment, treatment prediction, response evaluation, recurrence/prognosis prediction, and personalized prognostic assessment. AI algorithms may accurately classify NSCLC stages using machine learning techniques and deep imaging data analysis. This could potentially improve precision and efficiency in staging, facilitating personalized treatment decisions. Furthermore, there are data suggesting the potential application of AI-based models in predicting prognosis in terms of survival rates and disease progression by integrating clinical, imaging and molecular data. In the present narrative review, we will analyze the preliminary studies reporting on how AI algorithms could predict responses to various treatment modalities, such as surgery, radiotherapy, chemotherapy, targeted therapy, and immunotherapy. There is robust evidence suggesting that AI also plays a crucial role in predicting the likelihood of tumor recurrence after surgery and the pattern of failure, which has significant implications for tailoring adjuvant treatments. The successful implementation of AI in personalized prognostic assessment requires the integration of different data sources, including clinical, molecular, and imaging data. Machine learning (ML) and deep learning (DL) techniques enable AI models to analyze these data and generate personalized prognostic predictions, allowing for a precise and individualized approach to patient care. However, challenges relating to data quality, interpretability, and the ability of AI models to generalize need to be addressed. Collaboration among clinicians, data scientists, and regulators is critical for the responsible implementation of AI and for maximizing its benefits in providing a more personalized prognostic assessment. Continued research, validation, and collaboration are essential to fully exploit the potential of AI in NSCLC management and improve patient outcomes. Herein, we have summarized the state of the art of applications of AI in lung cancer for predicting staging, prognosis, and pattern of recurrence after treatment in order to provide to the readers a large comprehensive overview of this challenging issue.

Prognostication of lung adenocarcinomas using CT-based deep learning of morphological and histopathological features: a retrospective dual-institutional study

OBJECTIVES

To develop and validate CT-based deep learning (DL) models that learn morphological and histopathological features for lung adenocarcinoma prognostication, and to compare them with a previously developed DL discrete-time survival model.

METHODS

DL models were trained to simultaneously predict five morphological and histopathological features using preoperative chest CT scans from patients with resected lung adenocarcinomas. The DL score was validated in temporal and external test sets, with freedom from recurrence (FFR) and overall survival (OS) as outcomes. Discrimination was evaluated using the time-dependent area under the receiver operating characteristic curve (TD-AUC) and compared with the DL discrete-time survival model. Additionally, we performed multivariable Cox regression analysis.

RESULTS

In the temporal test set (640 patients; median age, 64 years), the TD-AUC was 0.79 for 5-year FFR and 0.73 for 5-year OS. In the external test set (846 patients; median age, 65 years), the TD-AUC was 0.71 for 5-year OS, equivalent to the pathologic stage (0.71 vs. 0.71 [p = 0.74]). The prognostic value of the DL score was independent of clinical factors (adjusted per-percentage hazard ratio for FFR (temporal test), 1.02 [95% CI: 1.01-1.03; p < 0.001]; OS (temporal test), 1.01 [95% CI: 1.002-1.02; p = 0.01]; OS (external test), 1.01 [95% CI: 1.005-1.02; p < 0.001]). Our model showed a higher TD-AUC than the DL discrete-time survival model, but without statistical significance (2.5-year OS: 0.73 vs. 0.68; p = 0.13).

CONCLUSION

The CT-based prognostic score from collective deep learning of morphological and histopathological features showed potential in predicting survival in lung adenocarcinomas.

CLINICAL RELEVANCE STATEMENT

Collective CT-based deep learning of morphological and histopathological features presents potential for enhancing lung adenocarcinoma prognostication and optimizing pre-/postoperative management.

KEY POINTS

• A CT-based prognostic model was developed using collective deep learning of morphological and histopathological features from preoperative CT scans of 3181 patients with resected lung adenocarcinoma. • The prognostic performance of the model was comparable-to-higher performance than the pathologic T category or stage. • Our approach yielded a higher discrimination performance than the direct survival prediction model, but without statistical significance (0.73 vs. 0.68; p=0.13).

[Prediction of recurrence-free survival in lung adenocarcinoma based on self-supervised pre-training and multi-task learning]

Computed tomography (CT) imaging is a vital tool for the diagnosis and assessment of lung adenocarcinoma, and using CT images to predict the recurrence-free survival (RFS) of lung adenocarcinoma patients post-surgery is of paramount importance in tailoring postoperative treatment plans. Addressing the challenging task of accurate RFS prediction using CT images, this paper introduces an innovative approach based on self-supervised pre-training and multi-task learning. We employed a self-supervised learning strategy known as "image transformation to image restoration" to pretrain a 3D-UNet network on publicly available lung CT datasets to extract generic visual features from lung images. Subsequently, we enhanced the network's feature extraction capability through multi-task learning involving segmentation and classification tasks, guiding the network to extract image features relevant to RFS. Additionally, we designed a multi-scale feature aggregation module to comprehensively amalgamate multi-scale image features, and ultimately predicted the RFS risk score for lung adenocarcinoma with the aid of a feed-forward neural network. The predictive performance of the proposed method was assessed by ten-fold cross-validation. The results showed that the consistency index (C-index) of the proposed method for predicting RFS and the area under curve (AUC) for predicting whether recurrence occurs within three years reached 0.691 ± 0.076 and 0.707 ± 0.082, respectively, and the predictive performance was superior to that of existing methods. This study confirms that the proposed method has the potential of RFS prediction in lung adenocarcinoma patients, which is expected to provide a reliable basis for the development of individualized treatment plans.

Machine Learning in Diagnosis and Prognosis of Lung Cancer by PET-CT

As a disease with high morbidity and high mortality, lung cancer has seriously harmed people's health. Therefore, early diagnosis and treatment are more important. PET/CT is usually used to obtain the early diagnosis, staging, and curative effect evaluation of tumors, especially lung cancer, due to the heterogeneity of tumors and the differences in artificial image interpretation and other reasons, it also fails to entirely reflect the real situation of tumors. Artificial intelligence (AI) has been applied to all aspects of life. Machine learning (ML) is one of the important ways to realize AI. With the help of the ML method used by PET/CT imaging technology, there are many studies in the diagnosis and treatment of lung cancer. This article summarizes the application progress of ML based on PET/CT in lung cancer, in order to better serve the clinical. In this study, we searched PubMed using machine learning, lung cancer, and PET/CT as keywords to find relevant articles in the past 5 years or more. We found that PET/CT-based ML approaches have achieved significant results in the detection, delineation, classification of pathology, molecular subtyping, staging, and response assessment with survival and prognosis of lung cancer, which can provide clinicians a powerful tool to support and assist in critical daily clinical decisions. However, ML has some shortcomings such as slightly poor repeatability and reliability.

Deep learning model for predicting postoperative survival of patients with gastric cancer

Background

Prognostic prediction for surgical treatment of gastric cancer remains valuable in clinical practice. This study aimed to develop survival models for postoperative gastric cancer patients.

Methods

Eleven thousand seventy-five patients from the Surveillance, Epidemiology, and End Results (SEER) database were included, and 122 patients from the Chinese database were used for external validation. The training cohort was created to create three separate models, including Cox regression, RSF, and DeepSurv, using data from the SEER database split into training and test cohorts with a 7:3 ratio. Test cohort was used to evaluate model performance using c-index, Brier scores, calibration, and the area under the curve (AUC). The new risk stratification based on the best model will be compared with the AJCC stage on the test and Chinese cohorts using decision curve analysis (DCA), the net reclassification index (NRI), and integrated discrimination improvement (IDI).

Results

It was discovered that the DeepSurv model predicted postoperative gastric cancer patients' overall survival (OS) with a c-index of 0.787; the area under the curve reached 0.781, 0.798, 0.868 at 1-, 3- and 5- years, respectively; the Brier score was below 0.25 at different time points; showing an advantage over the Cox and RSF models. The results are also validated in the China cohort. The calibration plots demonstrated good agreement between the DeepSurv model's forecast and actual results. The NRI values (test cohort: 0.399, 0.288, 0.267 for 1-, 3- and 5-year OS prediction; China cohort:0.399, 0.288 for 1- and 3-year OS prediction) and IDI (test cohort: 0.188, 0.169, 0.157 for 1-, 3- and 5-year OS prediction; China cohort: 0.189, 0.169 for 1- and 3-year OS prediction) indicated that the risk score stratification performed significantly better than the AJCC staging alone (P < 0.05). DCA showed that the risk score stratification was clinically useful and had better discriminative ability than the AJCC staging. Finally, an interactive native web-based prediction tool was constructed for the survival prediction of patients with postoperative gastric cancer.

Conclusion

In this study, a high-performance prediction model for the postoperative prognosis of gastric cancer was developed using DeepSurv, which offers essential benefits for risk stratification and prognosis prediction for each patient.

Lung cancer detection in perioperative patients' exhaled breath with nanomechanical sensor array

INTRODUCTION

Breath analysis using a chemical sensor array combined with machine learning algorithms may be applicable for detecting and screening lung cancer. In this study, we examined whether perioperative breath analysis can predict the presence of lung cancer using a Membrane-type Surface stress Sensor (MSS) array and machine learning.

METHODS

Patients who underwent lung cancer surgery at an academic medical center, Japan, between November 2018 and November 2019 were included. Exhaled breaths were collected just before surgery and about one month after surgery, and analyzed using an MSS array. The array had 12 channels with various receptor materials and provided 12 waveforms from a single exhaled breath sample. Boxplots of the perioperative changes in the expiratory waveforms of each channel were generated and Mann-Whitney U test were performed. An optimal lung cancer prediction model was created and validated using machine learning.

RESULTS

Sixty-six patients were enrolled of whom 57 were included in the analysis. Through the comprehensive analysis of the entire dataset, a prototype model for predicting lung cancer was created from the combination of array five channels. The optimal accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were 0.809, 0.830, 0.807, 0.806, and 0.812, respectively.

CONCLUSION

Breath analysis with MSS and machine learning with careful control of both samples and measurement conditions provided a lung cancer prediction model, demonstrating its capacity for non-invasive screening of lung cancer.

Methodology for Good Machine Learning with Multi-Omics Data

In 2020, Novartis Pharmaceuticals Corporation and the U.S. Food and Drug Administration (FDA) started a 4-year scientific collaboration to approach complex new data modalities and advanced analytics. The scientific question was to find novel radio-genomics-based prognostic and predictive factors for HR+/HER- metastatic breast cancer under a Research Collaboration Agreement. This collaboration has been providing valuable insights to help successfully implement future scientific projects, particularly using artificial intelligence and machine learning. This tutorial aims to provide tangible guidelines for a multi-omics project that includes multidisciplinary expert teams, spanning across different institutions. We cover key ideas, such as "maintaining effective communication" and "following good data science practices," followed by the four steps of exploratory projects, namely (1) plan, (2) design, (3) develop, and (4) disseminate. We break each step into smaller concepts with strategies for implementation and provide illustrations from our collaboration to further give the readers actionable guidance.

The development of a prediction model based on deep learning for prognosis prediction of gastrointestinal stromal tumor: a SEER-based study

Accurately predicting the prognosis of Gastrointestinal stromal tumor (GIST) patients is an important task. The goal of this study was to create and assess models for GIST patients' survival patients using the Surveillance, Epidemiology, and End Results Program (SEER) database based on the three different deep learning models. Four thousand five hundred thirty-eight patients were enrolled in this study and divided into training and test cohorts with a 7:3 ratio; the training cohort was used to develop three different models, including Cox regression, RSF, and DeepSurv model. Test cohort was used to evaluate model performance using c-index, Brier scores, calibration, and the area under the curve (AUC). The net benefits at risk score stratification of GIST patients based on the optimal model was compared with the traditional AJCC staging system using decision curve analysis (DCA). The clinical usefulness of risk score stratification compared to AJCC tumor staging was further assessed using the Net Reclassification Index (NRI) and Integrated Discrimination Improvement (IDI). The DeepSurv model predicted cancer-specific survival (CSS) in GIST patients showed a higher c-index (0.825), lower Brier scores (0.142), and greater AUC of receiver operating characteristic (ROC) analysis (1-year ROC:0.898; 3-year:0.853, and 5-year ROC: 0.856). The calibration plots demonstrated good agreement between the DeepSurv model's forecast and actual results. The NRI values ( training cohort: 0.425 for 1-year, 0.329 for 3-year and 0.264 for 5-year CSS prediction; test cohort:0.552 for 1-year,0.309 for 3-year and 0.255 for 5-year CSS prediction) and IDI (training cohort: 0.130 for 1-year,0.141 for 5-year and 0.155 for 10-year CSS prediction; test cohort: 0.154 for 1-year,0.159 for 3-year and 0.159 for 5-year CSS prediction) indicated that the risk score stratification performed significantly better than the AJCC staging alone (P < 0.001). DCA demonstrated the risk score stratification as more clinically beneficial and discriminatory than AJCC staging. Finally, an interactive native web-based prediction tool was constructed for the survival prediction of GIST patients. This study established a high-performance prediction model for projecting GIST patients based on deep learning, which has advantages in predicting each person's prognosis and risk stratification.

Foundation model for cancer imaging biomarkers

Foundation models in deep learning are characterized by a single large-scale model trained on vast amounts of data serving as the foundation for various downstream tasks. Foundation models are generally trained using self-supervised learning and excel in reducing the demand for training samples in downstream applications. This is especially important in medicine, where large labelled datasets are often scarce. Here, we developed a foundation model for cancer imaging biomarker discovery by training a convolutional encoder through self-supervised learning using a comprehensive dataset of 11,467 radiographic lesions. The foundation model was evaluated in distinct and clinically relevant applications of cancer imaging-based biomarkers. We found that it facilitated better and more efficient learning of imaging biomarkers and yielded task-specific models that significantly outperformed conventional supervised and other state-of-the-art pretrained implementations on downstream tasks, especially when training dataset sizes were very limited. Furthermore, the foundation model was more stable to input variations and showed strong associations with underlying biology. Our results demonstrate the tremendous potential of foundation models in discovering new imaging biomarkers that may extend to other clinical use cases and can accelerate the widespread translation of imaging biomarkers into clinical settings.

Efficient 18F-fluorodeoxyglucose positron emission tomography/computed tomography-based machine learning model for predicting epidermal growth factor receptor mutations in non-small cell lung cancer

BACKGROUND

Beyond the human eye's limitations, radiomics provides more information that can be used for diagnosis. We develop a personalized and efficient model based on 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) to predict epidermal growth factor receptor (EGFR) mutations to help identify which non-small cell cancer (NSCLC) patients are candidates for EGFR-tyrosine kinase inhibitors (TKIs) therapy.

METHODS

We retrospectively included 100 patients with NSCLC and randomized them according to 70 patients in the training group and 30 patients in the validation group. The least absolute shrinkage and selection operator logistic regression (LLR) algorithm and support vector machine (SVM) classifier were used to build the models and predict whether EGFR is mutated or not. The predictive efficacy of the LLR algorithm-based model and the SVM classifier-based model was evaluated by plotting the receiver operating characteristic (ROC) curves and calculating the area under the curve (AUC).

RESULTS

The AUC, sensitivity and specificity of our radiomics model by LLR algorithm were 0.792, 0.967, and 0.600 for the training group and 0.643, 1.00, and 0.378 for the validation group, respectively, in predicting EGFR mutations. The AUC was 0.838 for the training group and 0.696 for the validation group after combining radiomics features with clinical features. The prediction results based on the SVM classifier showed that the validation group had the best performance when based on radial kernel function with AUC, sensitivity, and specificity of 0.741, 0.667, and 0.825, respectively.

CONCLUSIONS

Radiomics models based on 18F-FDG PET/CT modeled with different machine learning algorithms can improve the predictive efficacy of the models. Models that combine clinical features are more clinically valuable.

AI in medical diagnosis: AI prediction & human judgment

AI has long been regarded as a panacea for decision-making and many other aspects of knowledge work; as something that will help humans get rid of their shortcomings. We believe that AI can be a useful asset to support decision-makers, but not that it should replace decision-makers. Decision-making uses algorithmic analysis, but it is not solely algorithmic analysis; it also involves other factors, many of which are very human, such as creativity, intuition, emotions, feelings, and value judgments. We have conducted semi-structured open-ended research interviews with 17 dermatologists to understand what they expect from an AI application to deliver to medical diagnosis. We have found four aggregate dimensions along which the thinking of dermatologists can be described: the ways in which our participants chose to interact with AI, responsibility, 'explainability', and the new way of thinking (mindset) needed for working with AI. We believe that our findings will help physicians who might consider using AI in their diagnosis to understand how to use AI beneficially. It will also be useful for AI vendors in improving their understanding of how medics want to use AI in diagnosis. Further research will be needed to examine if our findings have relevance in the wider medical field and beyond.

Deep representation learning of tissue metabolome and computed tomography annotates NSCLC classification and prognosis

The rich chemical information from tissue metabolomics provides a powerful means to elaborate tissue physiology or tumor characteristics at cellular and tumor microenvironment levels. However, the process of obtaining such information requires invasive biopsies, is costly, and can delay clinical patient management. Conversely, computed tomography (CT) is a clinical standard of care but does not intuitively harbor histological or prognostic information. Furthermore, the ability to embed metabolome information into CT to subsequently use the learned representation for classification or prognosis has yet to be described. This study develops a deep learning-based framework -- tissue-metabolomic-radiomic-CT (TMR-CT) by combining 48 paired CT images and tumor/normal tissue metabolite intensities to generate ten image embeddings to infer metabolite-derived representation from CT alone. In clinical NSCLC settings, we ascertain whether TMR-CT results in an enhanced feature generation model solving histology classification/prognosis tasks in an unseen international CT dataset of 742 patients. TMR-CT non-invasively determines histological classes - adenocarcinoma/squamous cell carcinoma with an F1-score = 0.78 and further asserts patients' prognosis with a c-index = 0.72, surpassing the performance of radiomics models and deep learning on single modality CT feature extraction. Additionally, our work shows the potential to generate informative biology-inspired CT-led features to explore connections between hard-to-obtain tissue metabolic profiles and routine lesion-derived image data.