Molecular Classification of Breast Cancer Using Weakly Supervised Learning.

Real-World Surveillance of FDA-Cleared Artificial Intelligence Models: Rationale and Logistics.

BackgroundBreast cancers can be classified by hierarchical clustering using an “intrinsic” gene list into one of at least five molecular subtypes: basal-like, HER2, luminal A, luminal B, and normal breast-like. Five different intrinsic gene lists composed of varying numbers of genes have been used for molecular subtype identification and classification of breast cancers. The aim of this study was to determine the objectivity and interobserver reproducibility of the assignment of molecular subtype classes by hierarchical cluster analysis.MethodsThree publicly available breast cancer datasets (n = 779) were subjected to two-way average-linkage hierarchical cluster analysis using five distinct intrinsic gene lists. We used free-marginal Kappa statistics to analyze interobserver agreement among five breast cancer researchers for the whole classification and for each molecular subtype separately according to each intrinsic gene list for each breast cancer dataset.ResultsNone of the classification systems tested produced almost perfect agreement (Kappa ≥ 0.81) among observers. However, substantial interobserver agreement (70.8% to 76.1% of the samples and free-marginal Kappa scores from 0.635 to 0.701) was consistently observed in all datasets for four molecular subtypes (luminal, basal-like, HER2, and normal breast-like). When luminal cancers were subdivided (luminal A, B, and C), none of the classification systems produced substantial agreement (Kappa ≥ 0.61) in all the datasets analyzed. Analysis of each subtype separately revealed that only two (basal-like and HER2) could be reproducibly identified by independent observers (Kappa ≥ 0.81).ConclusionsAssignment of molecular subtype classes of breast cancer based on the analysis of dendrograms obtained with hierarchical cluster analysis is subjective and shows modest interobserver reproducibility. For the development of a molecular taxonomy, objective definitions for each molecular subtype and standardized methods for their identification are required.

Introduction: Breast cancer has heterogeneous tumor biology. Therefore, breast cancer is divided into molecular subtypes. However, molecular subtypes also show heterogeneity within themselves. In our study, we compared whether there were radiological and pathological differences between breast cancer molecular subtypes. Methods: The data of 569 patients operated on for breast cancer in our General Surgery clinic during an 8-year period were analyzed retrospectively. After dividing the patients into groups consisting of molecular subtypes, their radiological and pathological findings were compared. Results: According to the molecular classification of breast cancer, 47.6% of the patients were in the luminal A group, 23.9% in luminal B, 7.7% in HER2-enriched, and 12% in TN, and 8.8% in normal-like groups. DCIS and LCIS were significantly less common in the TN group than in the others (p=0.015). Tumor diameter and grade were considerably higher in the normal-like, HER2-enriched, and TN groups than in the other groups (p<0.001, p<0.001). LVI was significantly lower in luminal A and significantly higher in luminal B (p<0.001). Mortality was significantly higher in the luminal B and TN groups than in the other groups (p = 0.029). Conclusion: The addition of the basal-like group when classifying breast cancer into molecular subtypes showed histopathological differences. More studies are needed to investigate its effects on treatment and prognosis. Keywords: Breast cancer, Molecular subtype, Genotype, Immunohistochemistry, Survival

Breast cancers have traditionally been classified based on histology. However, with the development in imaging modalities and available treatment options, it is imperative to also focus on the molecular classes of breast cancer. Molecular profile and gene expression are important predictors of treatment response and overall prognosis. Radiologists should have a good understanding of molecular categories of breast cancer along with their imaging hallmarks. Highlights: • To familiarize the readers with the principal biomarkers and molecular classes of breast cancer. • To highlight the characteristic imaging features of each molecular class of breast cancer. • To focus on the pivotal role of molecular classification in the dynamic model of breast cancer treatment.

We have recently shown that histological phenotypes focusing on clear and eosinophilic cytoplasm in clear cell renal cell carcinoma (ccRCC) correlated with prognosis and the response to angiogenesis inhibition and checkpoint blockade. This study aims to objectively show the diagnostic utility of clear or eosinophilic phenotypes of ccRCC by developing an artificial intelligence (AI) model using the TCGA-ccRCC dataset and to demonstrate if the clear or eosinophilic predicted phenotypes correlate with pathological factors and gene signatures associated with angiogenesis and cancer immunity. Before the development of the AI model, histological evaluation using hematoxylin and eosin whole-slide images of the TCGA-ccRCC cohort (n=435) was performed by a urologic pathologist. The AI model was developed as follows. First, the highest-grade area on each whole slide image was captured for image processing. Second, the selected regions were cropped into tiles. Third, the AI model was trained using transfer learning on a deep convolutional neural network, and clear or eosinophilic predictions were scaled as AI scores. Next, we verified the AI model using a validation cohort (n=95). Finally, we evaluated the accuracy of the prognostic predictions of the AI model and revealed that the AI model detected clear and eosinophilic phenotypes with high accuracy. The AI model stratified the patients' outcomes, and the predicted eosinophilic phenotypes correlated with adverse clinicopathological characteristics and high immune-related gene signatures. In conclusion, the AI-based histologic subclassification accurately predicted clear or eosinophilic phenotypes of ccRCC, allowing for consistently reproducible stratification for prognostic and therapeutic stratification.

This study evaluated if medical doctors could identify more hemorrhage events during chart review in a clinical setting when assisted by an artificial intelligence (AI) model and medical doctors' perception of using the AI model. To develop the AI model, sentences from 900 electronic health records were labeled as positive or negative for hemorrhage and categorized into one of 12 anatomical locations. The AI model was evaluated on a test cohort consisting of 566 admissions. Using eye-tracking technology, we investigated medical doctors' reading workflow during manual chart review. Moreover, we performed a clinical use study where medical doctors read two admissions with and without AI assistance to evaluate performance when using and perception of using the AI model. The AI model had a sensitivity of 93.7% and a specificity of 98.1% on the test cohort. In the use studies, we found that medical doctors missed more than 33% of relevant sentences when doing chart review without AI assistance. Hemorrhage events described in paragraphs were more often overlooked compared with bullet-pointed hemorrhage mentions. With AI-assisted chart review, medical doctors identified 48 and 49 percentage points more hemorrhage events than without assistance in two admissions, and they were generally positive toward using the AI model as a supporting tool. Medical doctors identified more hemorrhage events with AI-assisted chart review and they were generally positive toward using the AI model.

Quantum computing (QC) is not a futuristic notion in agriculture, though its full potential has yet to be realized. QC is an emerging field at the intersection of physics and computer science that holds immense potential to revolutionize various sectors, including agriculture production and artificial intelligence (AI) modeling. While QC is still in the early stages of development and practical applications within agriculture are not yet widespread, researchers are actively exploring its potential benefits in various agricultural domains, including crop optimization, livestock breeding, and environmental monitoring. QC harnesses the principles of quantum mechanics to perform computations using quantum bits or qubits, which can exist in multiple states simultaneously. Unlike classical computers, which rely on binary bits representing 0 or 1, quantum computers exploit phenomena such as superposition and entanglement to process information in parallel, potentially offering exponential speedup for certain types of problems. In agriculture production, particularly in animal science, QC offers promising avenues for optimizing processes and enhancing productivity. Quantum algorithms can analyze vast amounts of genomic data to improve breeding programs, leading to the development of more resilient and productive livestock breeds. Furthermore, QC can facilitate precision farming techniques by modeling complex environmental factors and animal behavior to optimize feeding strategies, disease management, and overall farm management practices. Moreover, QC can significantly benefit AI modeling by accelerating computations and enabling more efficient training of AI models. Quantum algorithms can enhance the performance of AI algorithms in various tasks, including pattern recognition, natural language processing, and predictive analytics. By leveraging quantum-enhanced optimization algorithms, AI models can achieve better convergence and accuracy, leading to more effective decision-making and problem-solving capabilities. While hybrid intelligent models also represent a novel frontier in agriculture, QC has the potential to expedite the merging of mechanistic and AI modeling paradigms, facilitating a more holistic understanding of complex systems in agriculture and beyond. By integrating mechanistic models, which describe the underlying physical processes, with AI models, which learn patterns from data, quantum computing can enable comprehensive simulations and predictions of agricultural systems. This fusion of modeling paradigms can lead to more accurate and robust predictions of crop yields, livestock performance, and environmental impacts, facilitating informed decision-making for farmers and policymakers. The application of QC in agriculture, however, requires interdisciplinary collaborations between physicists, computer scientists, agronomists/animal scientists, and AI researchers. These collaborations can drive the development of quantum algorithms tailored to agricultural applications, the integration of quantum-enhanced AI techniques into existing modeling frameworks, and the deployment of QC resources in real-world agricultural systems. Ultimately, harnessing the power of QC holds the potential to revolutionize agriculture production practices, including regenerative agriculture, and advance AI modeling capabilities, paving the way for a more sustainable and efficient agricultural industry.

Objective To explore the relationship between radiomics signatures based on DWI and dynamic contrast-enhanced MRI (DCE-MRI) and molecular subtypes of breast cancer. Methods A retrospective analysis of 79 female breast cancer patients, with single mass, clear molecular subtypes and preoperative breast MRI scanning (obtaining DCE-MRI and ADC images), of Guangdong General Hospital from June 2015 to June 2016, were performed. Traditional quantitative parameters, including ADC value and initial enhancement rate (IER), were recorded. Texture analysis were performed on ADC map and DCE map, with manual segmentation and extraction of radiomic features, and Manual segmentation was performed on ADC map and DCE map, radiomics features were extracted and 10 radiomics signatures were finally selected after dimension reduction. Four molecular subtypes of breast cancer were classified by immunohistochemical detection of pathological specimens, including Luminal A, Luminal B, human epidermal growth factor receptor 2 (HER2) overexpression and triple negative (TN). Univariate logistic regression analysis was used for assessing the performance of ADC values, IER values and radiomics signatures to independently predict molecular subtypes groups. Multivariate logistic regression analysis was performed to establish predicting models, then receiver operating characteristic curves (ROC) were drawn and areas under ROC curve were calculated to compare the diagnostic performance of each model. The Hosmer-Lemeshow test was performed to test the goodness of model fitness. Results There were 29 cases of Luminal A, 39 cases of Luminal B, 5 cases of HER2 overexpression and 6 cases of TN breast cancer patients. Univariate logistic regression analysis was used to assess the ability of traditonal MRI parameters of ADC and IER values and ten of the radiomics siganitures in classifying molecular subtypes, results showed that the AUC values of ADC and IER values, were both less than 0.70 (range 0.516 to 0.605), which indicated valueless;at least one radiomic signature had AUC greater than 0.70 when identifying each molecular subtype, and AUC of DCE_L_G_2.5_autocorrelation achieved the highest value of 0.941 in identifying TN and non-TN subtypes. Multivariate logistic regression analysis were performed to obtain the best model, results showed that the AUCs for classifying Luminal A and non-Luminal A, Luminal B and non-Luminal B, TN and non-TN subtypes were 0.786 and 0.733 And 0.941, respectively. The Hosmer-Lemeshow test showed that the P values of all models were larger than 0.10 (0.156, 0.204 and 0.820, respectively), indicating that there was no significant difference between the predicted and observed values of each model established, these models were all fitted good. Conclusion The radiomics features based on ADC map and DCE map can help to identify the molecular subtypes of breast cancer, especially for the identification of TN type breast cancer. Key words: Breast neoplasms; Radiomics; Texture analysis; Molecular subtypes; Prediction

e13553 Background: Programmed death-ligand 1 (PD-L1) expression is a predictive marker for immune checkpoint inhibitors (ICI) treatment in various cancer types. The evaluation of PD-L1 expression level by combined positive score (CPS) correlates with immunotherapeutic response in biliary tract, colorectum, liver, pancreas, prostate, and gastric cancers. This study aimed to assess the performance of an artificial intelligence (AI)-powered PD-L1 CPS analyzer on these six cancer types, and to investigate whether the AI assistance could improve concordance among pathologists. Methods: Lunit SCOPE PD-L1 CPS was developed with 1.51 x 106 tumor cells and 8.73 x 105 immune cells from 2,372 PD-L1 stained whole-slide images (WSI) or tissue microarray cores from various cancer and normal tissues. The algorithm consisted of tissue area segmentation and cell detection AI models. The AI models calculated the CPS by detecting tumor cells over the tumor area and immune cells over the tumor and adjacent area. The model performance was validated on 135 PD-L1 stained WSIs including the six cancer types, which were interpreted by three pathologists. The concordant CPS classification (≥1 or <1) by two or more pathologists was considered as the consensus. Each pathologist revisited to evaluate WSIs with AI assistance (including visualization and scoring) if there was a discrepancy between the pathologist and the AI model. Results: Of 135 WSIs, 122 (90.4%) were classified as the same CPS subgroup by all three pathologists. The CPS ≥1 and <1 subgroup included 67 (49.6%) and 68 (50.4%) cases, respectively. The overall percent agreement (OPA) of the AI model to the consensus of pathologists was 84.4%, ranging from 78.3% (liver) to 91.3% (biliary tract). The AI-assisted re-evaluation by three pathologists was performed in 17, 19, and 22 WSIs, respectively. According to the AI-assisted revision, the unanimous agreement level was increased to 92.6% (125 cases). The OPA of the AI model to the consensus of pathologists was also increased to 91.9%, ranging from 82.6% (liver) to 100.0% (pancreas). Conclusions: This study shows that an AI-powered PD-L1 CPS analyzer can evaluate the CPS in the six cancer types analyzed here at a comparable level to pathologists. AI assistance can improve the concordance of pathologists' CPS interpretation.[Table: see text]

We aimed to compare the distribution of different molecular subtypes of invasive breast cancer (BC) between patients whose samples were obtained by core needle biopsy (CB) and surgical specimens (SS) and to assess the reliability of CB as a diagnostic method in this context. All patients (222) diagnosed with invasive BC were examined. Immunohistochemistry was performed on 40 samples obtained by CB and on 148 SS, while in 34 patients, the analysis was performed on both CB and SS. Molecular classification of BC was performed based on estrogen receptor (ER), progesterone receptor (PgR), Human epidermal growth factor receptor 2 (HER2), and Ki67 proliferative index status. The most common molecular subtypes were Luminal A (43.2%) and Luminal B HER2- (29.7%). When comparing the frequencies of determined molecular subtypes, no difference was observed between samples obtained by CB and SS (p>0.05). Concordance analysis of molecular subtypes determined by immunohistochemistry on CB and SS was performed in 34 patients whose samples were obtained using both methods. No significant difference was observed in the designation of molecular subtype in relation to the sampling method (p>0.05). Results of immunohistochemistry analysis on CB and SS demonstrated good statistical agreement (Concordance rate=85.29%, Kappa=0.771, p<0.001). CB might be a reliable method for the determination of the molecular subtype of invasive BC.

Aim: The majority of machine learning (ML) models in healthcare are built on retrospective data, much of which is collected without explicit patient consent for use in artificial intelligence (AI) and ML applications. The primary aim of this study was to evaluate whether clinicians and scientific researchers themselves consent to provide their own data for the training of ML models. Materials and Methods: This survey was conducted through an anonymous online survey, utilizing platforms such as Telegram, LinkedIn, and Viber. The target audience comprised specific international groups, primarily Russian, German, and English-speaking, of clinicians and scientific researchers. These participants ranged in their levels of expertise and experience, from beginners to veterans. The survey centered on a singular, pivotal question: “Do You Consent to the Use of Your Biological and Private Data for Training Machine Learning and AI Models?” Respondents had the option to choose from three responses: “Yes” and “No”. Results: The survey was conducted in January 2024. A total of 119 unique and verified individuals participated in the survey. The results revealed that only 50% of respondents (63 persons) expressed consent to provide their own data for the training of ML and AI models. Conclusion: In the development of ML and AI models, particularly open-source ones, it is crucial to ascertain whether participants are willing to provide their private data. While ML algorithms can transform the nature of data, it is important to remember that the primary owner of this data is the individual. Our findings show that in 50% of the cases, even participants from scientific research and clinical backgrounds – individuals typically accountable for ensuring data quality in AI and ML model development – do not consent to the use of their data in AI and ML settings. This highlights the need for more stringent consent processes and ethical considerations in the utilization of personal data in AI and ML research.

The secondary use of health data for training Artificial Intelligence (AI) models holds immense potential for advancing medical research and healthcare delivery. However, ensuring patient consent for such utilization is paramount to uphold ethical standards and data privacy. Patient informed consent means patients are fully informed about how their data will be collected, used, and protected, and they voluntarily agree to allow their data to be used for AI models. In addition to formal consent frameworks, establishing a social license is critical to foster public trust and societal acceptance for the secondary use of health data in AI systems. This study examines patient consent practices in this domain. In this scoping review, we searched Web of Science, PubMed, and Scopus. We included studies in English that addressed the core issues of interest, namely, privacy, security, legal, and ethical issues related to the secondary use of health data in AI models. Articles not addressing the core issues, as well as systematic reviews, meta-analyses, books, letters, conference abstracts, and study protocols were excluded. Two authors independently screened titles, abstracts, and full texts, resolving disagreements with a third author. Data was extracted using a data extraction form. After screening 774 articles, a total of 38 articles were ultimately included in the review. Across these studies, a total of 178 barriers and 193 facilitators were identified. We consolidated similar codes and extracted 65 barriers and 101 facilitators, which we then categorized into four themes: "Structure," "People," "Physical system," and "Task." We identified notable emphasis on "Legal and Ethical Challenges" and "Interoperability and Data Governance." Key barriers included concerns over privacy and security breaches, inadequacies in informed consent processes, and unauthorized data sharing. Critical facilitators included enhancing patient consent procedures, improving data privacy through anonymization, and promoting ethical standards for data usage. Our study underscores the complexity of patient consent for the secondary use of health data in AI models, highlighting significant barriers and facilitators within legal, ethical, and technological domains. We recommend the development of specific guidelines and actionable strategies for policymakers, practitioners, and researchers to improve informed consent, ensuring privacy, trust, and ethical use of data, thereby facilitating the responsible advancement of AI in healthcare.

Artificial Intelligence: The Future of Maxillofacial Prognosis and Diagnosis?

Background: Breast cancer is a heterogeneous disease with different biological and histological properties due to genetics and epigenetic changes with varying clinical features and treatment responses. This study was planned and carried out with the objective to classify breast cancers molecularly using surrogate markers, ER, PgR, Her2/neu and Ki67 and correlate the various types with conventional prognostic markers. Materials and Methods: 70 cases of invasive breast carcinomas were subjected to routine staining and immunohistochemistry with estrogen receptors(ER), progesterone receptors (PgR), Her2/neu and Ki67and classified into molecular subtypes as defined in various studies. These were correlated with other conventional prognostic parameters and analyzed statistically. Result: 70 cases of invasive breast cancer were classified into 18(22%) cases of luminal B, 16(25%) cases of Her2/neu and triple negative each and 14(22%) cases of luminal A subtypes. There was an even distribution of molecular subtypes varying from 22 to 28%. Luminal B and Her subtype were commoner in the Indian setting as compare to other studies. Luminal A and Luminal B subtypes were commoner in patients older than 50 years. Her2/neu and TNBC cases were more commonly of higher histological grade and pathological stage, while Luminal A and B subtypes showed lower grade and stages. Luminal B subtype and Her2/neu subtypes showed DCIS more often and Luminal B and TNBC subtypes, more frequent lymph node metastasis. Conclusion: The molecular classification of breast cancer by IHC in this study population showed an almost equal distribution of the 4 subtypes. The association of tumor grade and LVI with the molecular subtypes showed a significant correlation. Keywords: ER, PR, Her2/neu, Ki67.

Solar energy-based technologies have developed rapidly in recent years, however, the inability to appropriately estimate solar energy resources is still a major drawback for these technologies. In this study, eight different artificial intelligence (AI) models namely; convolutional neural network (CNN), artificial neural network (ANN), long short-term memory recurrent model (LSTM), eXtreme gradient boost algorithm (XG Boost), multiple linear regression (MLR), polynomial regression (PLR), decision tree regression (DTR), and random forest regression (RFR) are designed and compared for solar irradiance prediction. Additionally, two hybrid deep neural network models (ANN-CNN and CNN-LSTM-ANN) are developed in this study for the same task. This study is novel as each of the AI models developed was used to estimate solar irradiance considering different timesteps (hourly, every minute, and daily average). Also, different solar irradiance datasets (from six countries in Africa) measured with various instruments were used to train/test the AI models. With the aim to check if there is a universal AI model for solar irradiance estimation in developing countries, the results of this study show that various AI models are suitable for different solar irradiance estimation tasks. However, XG boost has a consistently high performance for all the case studies and is the best model for 10 of the 13 case studies considered in this paper. The result of this study also shows that the prediction of hourly solar irradiance is more accurate for the models when compared to daily average and minutes timestep. The specific performance of each model for all the case studies is explicated in the paper.