Written by Satvik Tripathi, Sophie Takmopoulos, & Nikita Kondla
At times, it may feel like the world has only sunk in the sea of 2020. However, there have been great advancements in the medical field on pressing topics—such as cancer. During World Cancer Day, we must celebrate these advancements and keep others knowledgeable of impressive progress. Not only is this day significant to inform people, but it is a day to remember all of the people that the world has lost to this disease.
World Cancer Day every 4 February is the global uniting initiative led by the Union for International Cancer Control (UICC). By raising worldwide awareness, improving education, and catalyzing personal, collective, and government action, we're working together to reimagine a world where millions of preventable cancer deaths are saved and access to life-saving cancer treatment and care is equal for all - no matter who you are or where you live.
World Cancer Day started in 2000 and has created a positive impact in the community for everyone. This is article for everyone to unite to face one of the biggest challenges in history.
World Cancer Day aims to save millions of people from preventable deaths each year by raising awareness to help prevent the disease. Also, pressing governments to help take action and to help others to help cure the disease.’ This is an opportunity to support the international community and to end the injustice of preventing suffering from cancer. Every year, 9.6 million die from cancer. World Cancer Day has been recognized for more than 20 years by groups and organizations across the globe to raise cancer awareness and encourage support, action, and funding.
Cancer rates have dropped every year for the past 20 years. About 40% of people in the United States will get cancer during their lifetime. There are three things to help prevent cancer, one is to quit smoking and stay from other people smoking. Tobacco use can cause cancer throughout the body, not just lung cancer. Keep a healthy weight and exercise regularly. Being overweight and obese can link to cancer. Cancer Awareness has been important in the 21st century. The number of new cancer cases has been diagnosed each year and continues to increase. There were 8.1 million cases that were diagnosed in 1990, 10 million in 2000, 12.4 million in 2008, and 14.1 million in 2008. The number of annual deaths that have been worldwide from cancer from 5.2 million people in 1990 to 8.2 million people in 2012 and has been estimated at 9.6 million people in 2018.
Each year, hundreds of activities and events take place around the world, gathering communities, organizations, and individuals in schools, businesses, hospitals, marketplaces, parks, community halls, places of worship - in the streets and online - acting as a powerful reminder that we all have a role to play in reducing the global impact of
This year's World Cancer Day's theme, 'I Am and I Will', is all about you and your commitment to act. We believe that through our positive actions, together we can reach the target of reducing the number of premature deaths from cancer and non-communicable diseases by one-third by 2030.
State-of-the-Art Research Developments in 2020
Throughout the pandemic, cancer researchers have not sat back but instead have continued to work efficiently on analysis and treatment. Although there have been many advancements, some of the most impressive research that has been conducted consists of the development and launching of Retevmo®️ and CRISPR-Cas9's clinical trial triumph.
In order to treat lung and thyroid cancers, Retevmo®️ (selpercatinib) was created to interact with the RET (rearranged during transfection) gene. The RET gene is a gene responsible for producing signaling proteins which play a role in nerve cell development. Everyone has a RET gene, but everyone does not have a normal RET gene. If the RET gene is mutated, then an overactive RET protein can be synthesized which can cause uncontrollable cell growth and division. Retevmo is a drug that can be utilized to control the rapid cell division as it specifically treats RET-positive metastatic non-small cell lung cancer (NSCLC) or advanced thyroid cancers, and unlike other treatments such as chemotherapies, Retevmo is described as “target cancer therapy”.
Retevmo®️ and NSCLC
Two types of lung cancer exist, non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC) in which 80-85% of patients have NSCLC. When treating NSCLC, in a study, Retevmo helped 144 patients in which 85% of 39 patients who had never received treatment had their tumors shrink by more than 30% or completely dissipated (an objective response) and 64% of 105 patients who in the past had cancer treatment had the same response. In addition, brain tumors of 10 out of 11 NSCLC patients (that received prior treatment) were reduced in size by at least 30% or completely dissipated.
Retevmo®️ and Thyroid Cancer
In addition to treating NSCLC with Retevmo, Retevmo also has shown to treat thyroid cancers (including medullary, papillary, poorly differentiated, anaplastic, and Hurthle cell). Retevmo aided 170 patients with their tumors as 69% of 55 patients with RET-positive advanced medullary thyroid cancer (MTC) that has not received care had their tumors shrink in size by 30% or more or have completely dissipated. Also, regarding patients with other times of thyroid cancer, 79% of 19 patients who have had prior treatment had an objective response and 100% of 8 patients who have not had a lot of care had an objective response.
Retevmo is one of the significant prescription cancer tackling drugs that have been created during the last year. It was approved by the FDA in May of 2020, has helped improve many patients’ cancer and will continue to make an impact in the cancer world.
The past few years have been a very exciting time for gene editing therapy! 2019 saw the results from the first human clinical studies whereas 2020 saw the CRISPR gene editing tools inserted directly into the human body for the first time.
The CRISPR-Cas9 gene therapy was administered directly into the body of a person suffering from a rare genetic condition called Leber’s congenital amaurosis 10 (LCA10) which is one of the leading causes of blindness in childhood for the first time, making the treatment a landmark clinical trial of 2020.
Ever since Scientists realized that they have made changes in DNA that causes cancer, they have been searching for an easy way to fix those changes by manipulating the DNA. 2020 has seen the results of CRISPR gene editing tools that were inserted directly into the human body for the first time. The CRISPR-Cas9 Gene therapy was administered directly into the body of a person who was suffering from a rare genetic condition called the Leber’s congenital amaurosis 10 (LCA10) which is one of the leading causes of blindness in childhood for the first time, making the treatment a landmark clinical trial of 2020.
Mark Pennesi, who was a specialist in inherited rental diseases at Oregon Health & Science University in Portland is collaborating with Editas Medicine of Cambridge, Massachusetts, and Allergan of Dublin to conduct the trial, which has been rightly named BRILLIANCE. BRILLIANCE trial is the first to deploy the very popular CRISPR-Cas9 technique which has been hailed for its versatility and the ease of design directly in the body, Gene editing is used to delete a mutation in the gene CEP290 that is responsible for LCA10, in BRILLIANCE. The Royal Swedish Academy of Sciences also decided to award the Nobel Prize in Chemistry 2020 to Emmanuelle Charpentier of the Max Planck Unit for the Science of Pathogens, Germany, and Jennifer Doudna of the University of California, Berkeley, the US for the development of CRISPR-Cas9, a method for genome editing, thus signifying the importance of the CRISPR-Cas9 technique.
Application of CRISPR-Cas9 in Cancer Therapy
CRISPR-Cas9 holds great potential in the field of Cancer research and therapy, providing remarkable discrete cancer-associated mutations in the genome contradicted with the actual ZFNs or TALENs technologies. Also, providing an effective gene-editing method to the cancer biologists enabling them to modify the genetic make-up of cells in various remarkable ways. Moreover, TMEM135-CCDC67 and MAN2A1-FER fusion genes have been recognized as cancer-derived genes in hepatocellular carcinoma and human prostate cancer. Further, the HSV1-TK death-promoting gene, which—as a suicide gene; is a phosphotransferase that blocks DNA synthesis was used to replace the previous genes via the CRISPR-Cas9 technology.
Personalized therapy is another application of the CRISPR/CAS9 system requiring organized screening which would be efficient to identify the genotype-specific changes in a patient’s genome. Therapeutic strategies are constantly being developed based on the results of the gene screening. An example of personalized therapy is the treatment of EGFR-mutant lung cancer. The CRISPR technology is suspected to open the door to effective personalized cancer treatment from specific applications of genome screening to therapeutic strategies with results being achieved in basic research to the development of potential therapies against various diseases. The CRISPR-Cas9 system has the potential to fully revolutionize scientific research providing tremendous resources for greater awareness of cancer biology and treatment.
Upcoming Research: Applications and Clinical Challenges of Artificial intelligence in Cancer Imaging
Artificial intelligence (AI), for years, has captured society’s imagination and generated enthusiasm for its potential to improve our lives. Presently, AI already plays an integral role in our daily routines and our interactions with media, transportation, and communications. There is an increasing interest in the applications of AI in healthcare to improve disease diagnosis, management, and the development of effective therapies. Given the large number of patients diagnosed with cancer and the significant amount of data generated during cancer treatment, there is a specific interest in the application of AI to improve oncologic care. In this review, we introduce the fundamentals of AI and provide an overview of its current applications, pitfalls, and future directions in oncology.
What is AI?
Originally formalized in the 1950s, AI refers to the ability of a machine to perform tasks commonly associated with intelligent human behavior. Including disciplines from both computer science and mathematics, AI can be considered a group of iterative, "self-learning" techniques, which discover relationships within data that can evolve and often be performed faster over time. Artificial intelligence refers to the replication of human intelligence in machines that are encoded to think like humans and imitate their actions. The word may also be applied to any machine that displays qualities related to a human mind for example understanding, learning, and problem-solving.
Machine Learning (ML): The Engine That Drives AI
A majority of the AI applications within healthcare involve the utilization of ML algorithms. As ML algorithms are exposed to more training data, they can appreciate hidden patterns within the data which can then be used to perform a task without explicit programming. There are dozens of ML algorithms that have been proposed over the past several decades, and the most traditional forms of ML, such as logistic regression, have proven themselves as valuable tools for general clinical oncology research.
ML tasks are often broadly dichotomized into supervised or unsupervised learning. In supervised learning, a labeled dataset of inputs and outputs is used to train the ML algorithm. The algorithm attempts to learn a general rule that maps input to output. Supervised ML algorithms can learn patterns in data for categorical outputs (classification) and continuous data (regression). Conversely, unsupervised ML algorithms use unlabeled data, intending to discover structure in the input data. Unsupervised ML algorithms are often used to simplify (dimensionality reduction) or organize (clustering) data.
In traditional ML tasks, there is often some pre-engineered organization of raw input data into features that are inferred to have an impact on output.
Artificial Neural Networks and Deep Learning (DL): The Wave Comes to Healthcare
One drawback of traditional ML algorithms has been the need for pre-engineered organization of raw input data into structured datasets. The inability of certain ML algorithms to use unstructured data from the point of generation has limited their utility in clinical practice. One ML algorithm well suited to analyze unstructured data is known as Deep Learning (DL).
DL algorithms are often synonymous with AI. DL is a form of ML that uses layered "artificial neural networks" to develop sophisticated models with the ability to understand data at different levels of abstraction. Artificial neural networks (ANNs) were inspired by human neurobiology and the ability of the brain to use cascading, varying, and layered combinations of neurons to learn complicated patterns with a hierarchy of progressively more complex features Modeling the human neuron in computers yielded the basic design of early ANNs.
While traditional ML algorithms used pre-engineered features to develop predictions, DL algorithms can learn the optimal features that best fit the data through the training process, avoiding the need to use pre-engineering, unstructured data. This ability has allowed DL algorithms to outperform traditional ML algorithms in many common AI problems, including image classification, natural language processing, and sequence prediction. Accordingly, the number of research articles published involving deep learning in the medical field has skyrocketed over the past few years.
Due to this DL renaissance, AI has now generated significant attention in healthcare. In oncology, DL has become a natural partner in the pursuit of precision medicine, leveraging vast, heterogeneous datasets to better diagnose disease burden, predict patient outcomes, and tailor management. AI can also be coupled to a multitude of emerging mobile health interfaces, such as smartphone apps and wearable devices, to develop “digital biomarkers” that can explain, influence, and predict clinical outcomes. In the following sections, we will delve into current AI applications in oncology, their limitations, and future implications.
AI and Cancer Imaging
Seeing better with convolutional neural networks
Image analysis has proven to be among the most effective methods in which AI has impacted society. AI-powered by DL algorithms has provided us self-driving vehicles, mobile check deposits, and multiple other useful technologies. Given the large amount of digital imaging data present within medicine, there is increasing excitement about the application of similar techniques to imaging within oncology.
This revolution in image analysis was catalyzed by the development of a particular DL architecture, the Convolutional Neural Network (CNN). CNNs analyze pixel-level information from images. The added benefit of CNNs compared to other DL configurations is the ability to account for the orientation of the pixels to one another. This effectively allows the CNN to appreciate lines, curves, and eventually objects within images. CNN-based models have recently been shown to be equivalent to humans in picture classification and object detection.
One of the initial papers highlighting the promise of DL in cancer imaging was in the identification of skin cancer based on skin photographs. The CNN trained on 130,000 skin images was able to classify malignant lesions with higher sensitivity and specificity than a panel of 21 board-certified dermatologists. Practical applications of detecting skin pathology utilizing patients as the generator of imaging input data have evolved. Further use of CNNs to classify digital photography has been in the automatic detection of polyps during a colonoscopy. One particular study highlights that CNNs can be used not only for image classification but also to detect regions of clinical importance. Researchers found that CNN, which was trained on colonoscopic images from 1,290 patients, had a 94% sensitivity in polyp detection.
Given one of the most effective applications of AI, techniques have been in the field of computer vision, there is natural excitement in the field of radiology, where there exist a number of digitized images. The goals of these AI algorithms have ranged from assisted diagnosis to outcome prediction.
AI algorithms have been found to be effective in streamlining cancer screening and detection. Automated lung nodule detection and classification has attracted significant attention and formed the basis of the 2017 Kaggle Data Science Bowl, an international competition for ML scientists. Several successful CNN-based models resulted from this competition and other research groups, demonstrating accuracies in the 80% to 95% range and showing promise for lung cancer screening. Additionally, CNNs have been shown to be successful in segmenting tumor volumes, which may have implications for radiotherapy treatment planning. Improvement of breast cancer screening with AI has also been an active area of investigation, with its own data science competitions, resulting in a CNN algorithm able to detect breast malignancy with a sensitivity of 90%.
AI has also shown promise in detecting radiographic anatomic features of malignancies that goes beyond what can be reliably achieved by clinicians. While extranodal extension (ENE) of tumors in the head and neck cancer lymph nodes has been notoriously difficult to diagnosis radiographically by clinicians, a CNN-based model showed >85% accuracy in identifying this feature on diagnostic, contrast-enhanced CT scans. Identification of ENE has high importance in prognostication and management for head and neck cancer patients, and thus this model shows promise as a clinical decision-making tool.
Going further than anatomic characterization, AI has shown promise in the burgeoning field of radiogenomics, where radiographic image analysis is used to predict underlying genotypic traits. This has recently been demonstrated using CNNs on brain MRIs of patients with low-grade glioma. CNNs have been able to predict both IDH mutation and MGMT methylation status with 85% to 95% and 83% accuracy, respectively, based on raw imaging data alone.
DL also has the potential to predict response to treatment based on imaging findings. Recently, a CNN model showed success in predicting complete response to neoadjuvant chemoradiation with 80% accuracy. Additionally, a radionics signature using extracted features from CT data and an ML algorithm was able to predict underlying CD8 cell tumor infiltration and, remarkably, response to immunotherapy for a variety of advanced cancers.
The increasing digitization of histopathologic tumor specimen slides provides a robust 2D image suitable for DL analysis. DL CNN algorithms have now been shown to diagnose breast cancer metastasis in lymph nodes with at least equivalent performance compared to a panel of pathologists and in a more time-efficient manner. DL has also been shown to be useful in automated Gleason grading of prostate adenocarcinoma Hematoxylin and Eosin–stained specimens, with a 75% rate of agreement between the algorithm and pathologists.
DL algorithms have also gone a step further than pathologic diagnosis automation and have been used to characterize the underlying genotype-phenotype correlation within a tumor specimen. Using raw input data consisting of digitized formalin-fixed, paraffin-embedded tissue from lung cancer biopsies, a CNN was trained to predict six different genetic mutations (STK11, EGFR, FAT1, SETBP1, KRAS, and TP53), establishing that genotypic information may be gleaned from histopathologic architectural patterns. These methods may assist pathologists in the detection of cancer gene mutations and may be cost-effective compared to direct mutational analysis.
AI and Clinical Outcomes
Within clinical oncology, AI has increasingly been applied to harness the power of the electronic health record (EHR). Specifically, AI-based natural language processing techniques have shown promise in predicting the development of diseases across large healthcare systems. A notable example from a group at Mount Sinai, a DL-based AI algorithm modeling EHR, was able to predict the development of a variety of diseases with 93% accuracy overall, including cancers of the prostate, rectum, and liver.
There have additionally been interests in using DL to predict cancer treatment toxicity. Recently, a CNN approach was used to predict the side effects of polypharmacy combinations based on databases of protein-protein and drug-protein interactions. This study led to the discovery of at least five novel drug-drug interaction predictions, which were subsequently found to have supporting literature evidence. The use of AI to predict radiotherapy toxicity has generated significant interest over the past few years. Basic neural networks, CNNs, and other ML methods have been explored, using clinical and dosimetric data to predict urinary and rectal toxicity resulting from prostate radiotherapy results, hepatobiliary toxicity after liver radiotherapy, and rectal toxicity for patients receiving radiotherapy for cervical cancer.
AI and Translational Oncology
Translational oncology is an area where AI is beginning to emerge. Over the past decade, there has been an expansion of biological quantitative or “-omic” data. Given the complexities and heterogeneity within this data, the use of DL in analysis has been appealing. DL neural networks have been utilized to predict protein structure, classify cells into a distinct stage of mitosis, and even predict the future lineage of progenitor cells based on microscopy images.
Drug development and repurposing have become an attractive target for DL. One group used DL ANNs trained on transcriptomic response signatures to drugs to predict with high accuracy the likelihood of failure of a clinical trial of over 200 example drugs. Another used an ANN to predict cancer cell sensitivity to therapeutics using a combination of genomic and chemical properties. CNNs have also been employed to predict peptide-major histocompatibility complex binding, which may have implications for oncologic immunotherapy development.
AI and Clinical Decision Making
Given the increasing amount and pace of published research, clinical trial enrollment, drug development, and biomarker discovery in oncology in recent years, there is more opportunity than ever for AI to assist in synthesizing this data and to guide decision-making. Several commercial applications in development utilize DL and natural language processing to this aim. These applications are being designed to link patient data to clinical trial databases and to match patients to appropriate clinical trials nationwide. Another algorithm utilizes ML to select the appropriate investigational drugs in development for a given patient. There have also been interests in utilizing AI coupled with patient data and national treatment guidelines to guide cancer management, with the most prominent example being IBM’s Watson for Oncology (WFO). WFO has demonstrated high concordance with tumor board recommendations for breast cancer patients, though has fallen short in other areas of oncologic decision-making. While this area of AI application is in its nascent stages, performance continues to improve, and there is great potential to improve clinical practice.
AI Limitations and Future Directions
Proving generalizability and real-world applications
While AI is rapidly being incorporated into oncologic research, work remains to be done to translate these studies into real-world, clinically meaningful applications. One of the biggest barriers is in external validation and proving the generalizability of DL applications. Given the complexity of neural networks and the extremely large number of parameters (often in the millions), there is a high tendency for neural networks to create overfitted models that do not generalize across different populations. Additionally, because there is a significant amount of heterogeneity of medical data across institutions, multiple external validation sets may be required to prove the performance of an application.
Data access and equity
Directly contributing to this problem of overfitting are limitations with data access and quality. DL neural networks, more than any other ML algorithm, require large amounts of data. This can pose a problem in healthcare when attempting to apply AI to disease processes with less prevalence. Furthermore, data is often siloed within individual institutions. Contributing to this relative data drought are concerns with the transmission of protected patient health information, along with lack of data-sharing infrastructure to link institutions, heterogeneity and incompleteness in the collection of data, and competition between institutions. These obstacles are beginning to be addressed, with more and more emphasis on streamlined data capture, and a number of multi-institutional data-sharing agreements Guidelines have been proposed to support FAIR (findable, accessible, interoperable, reusable) data use, and there are now opportunities for research groups to publish their data itself, which may incentivize openness.
Interpretability and the black box problem
One of the central limitations to the adoption of AI in healthcare is the concern that these models, despite regularly achieving high performance, are somewhat opaque. For instance, a DL model may correctly predict that a patient will develop pancreatic cancer based on his past 2 years of EHR data, but why did it make that prediction? At the present, we are limited in our ability to determine the precise logic behind DL-based predictions. This is often referred to as the “black box” problem. In medical practice, it has traditionally been essential in clinical decision-making to know the rationale for each decision. Traditional ML algorithms, like linear regression, have limited ability to model complex relationships, but offer this easy interpretability-in these algorithms, we have a set of predefined features and the resulting feature weights that characterize their effect sizes. In contrast, DL utilizes unstructured input data, and the bulk of knowledge generation occurs within the hidden layers. It thus becomes difficult to determine which specific characteristic(s) of the input data contributed to the outcome. This interpretability challenge has large implications for the adoption of AI-based algorithms in healthcare, both from the practitioner and regulatory perspectives.
Tackling the black box problem has now become a major focus of research. In AI image analysis algorithms, several methods have been developed, including feature visualization, saliency maps, class activation mapping, and sensitivity analyses, where certain parts of the image are hidden to the effect on prediction. While these methods have advanced over the past few years, further work is needed to better elucidate the decision-making logic with deep neural networks.
Education and expertise
To successfully merge AI with clinical oncology and maximize its impact, there are knowledge gaps that need to be addressed. Currently, physicians receive little training in data science and ML, limiting their ability to understand DL mechanisms, adopt algorithms appropriately, and conduct research. Similarly, most data scientists have little experience with oncologic workup and management, limiting the ability to identify important and suitable clinical use cases. Further collaboration should be pursued between clinical oncologic departments and bioinformatics and data science divisions, and strategic partnerships with technology firms should be formed where appropriate.
Promoting AI in Oncology: Professional Societies and National Initiatives
In response to these challenges, several national professional societies have launched initiatives to bridge these knowledge gaps and promote the dissemination of AI in oncology. These societies and medical institutions have been the backbone of various research projects and have contributed to advancing healthcare and patient care facilities. Some of the most active societies/institutions in translational cancer research are-
American College of Radiology (ACR)
The ACR has founded a Data Science Institute (ACR-DSI) with the mission of collaborating with radiologists, industry, and government agencies to facilitate the development of AI in imaging. Within the ACR-DSI are several core goals: 1) providing standards for measuring the performance of AI algorithms (“Touch-AI”), 2) independent, external validation of algorithms and navigating the regulatory landscape (“Certify-AI”), and longitudinal, prospective evaluation of deployed algorithm performance “(Assess-AI”). The ACR-DSI has additionally set up a series of use cases for recommended AI imaging applications with the unmet clinical need.
American Society of Clinical Oncology (ASCO) & American Society for Radiation Oncology (ASTRO)
ASCO has launched a big data initiative named CancerLinQ, in partnership with oncologists, industry, and academia, with the goals of real-time quality of care tracking and treatment evaluation, as well as knowledge dissemination to oncologists in user-friendly ways. The initiative’s backbone is a constantly growing database of de-identified patient information that can be mined and analyzed. In 2017, ASTRO partnered with CancerLinQ to provide radiation oncology expertise and uses for the database. In addition, Big Data Analytics and Bioinformatics are one of the core initiatives of the ASTRO Research Agenda for 2018.
National Institutes of Health (NIH)
As part of the NIH Common Fund, the Big Data to Knowledge (BD2K) initiative was launched to support the research and development of tools to integrate big data and data science into biomedical research. One of the central components of the initiative involves leveraging existing national datasets, such as the Library of Integrated Network-based Cellular Signatures (LINCS) and The Cancer Genome Atlas (TCGA), and applying ML techniques to discover patterns in the data that may result in heretofore unknown compounds for cancer therapeutics.
Not that long ago, a cancer diagnosis was a death sentence. Over the last two centuries, though, scientists have worked hard to understand how cancer forms, how it can be prevented, and how to treat it. Today, with many types of cancer, the prognosis for those who receive early treatment is positive, with 14 million cancer survivors living in the United States alone.
Research continues into all aspects of cancer and includes a broad swath of sciences, including mathematics, immunology, nanotechnology, epigenetics, engineering, and biotechnology. Hopefully, with the latest additions of AI-aided diagnosis and prognosis, we will be able to fight this deadly curse and save millions of lives.
2021 – the ultimate year of the ‘I Am and I Will’ campaign – shows us that our actions have an impact on everyone around us, within our neighborhoods, communities and cities. And that more than ever, our actions are also being felt across borders and oceans. This year is a reminder of the enduring power of cooperation and collective action. When we choose to come together, we can achieve what we all wish for: a healthier, brighter world without cancer. Together, all of our actions matter. This World Cancer Day, who are you, and what will you do?
This World Cancer Day join us on 4 February and speak out and stand up for a cancer-free world.
References (online publications)-
References (research articles/chapters)-
Tripathi, Satvik. "Artificial Intelligence: A Brief Review." Analyzing Future Applications of AI, Sensors, and Robotics in Society, IGI Global, 2021, pp. 1-16. http://doi:10.4018/978-1-7998-3499-1.ch001
Ding MQ, Chen L, Cooper GF, et al. Precision oncology beyond targeted therapy: combining omics data with machine learning matches the majority of cancer cells to effective therapeutics. Mol Cancer Res. 2018;16:269-78.
Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115:211-52.
Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115-8.
Pella A, Cambria R, Riboldi M, et al. Use of machine learning methods for prediction of acute toxicity in organs at risk following prostate radiotherapy. Med Phys. 2011;38:2859-67.
Carrara M, Massari E, Cicchetti A, et al. Development of a ready-to-use graphical tool based on artificial neural network classification: application for the prediction of late fecal incontinence after prostate cancer radiation therapy. Int J Radiat Oncol. 2018 Aug 6.
Lee S, Kerns S, Ostrer H, et al. Machine learning on a genome-wide association study to predict late genitourinary toxicity after prostate radiation therapy. Int J Radiat Oncol Biol Phys. 2018;101:128-35.
Ibragimov B, Toesca D, Chang D, et al. Development of deep neural networks for individualized hepatobiliary toxicity prediction after liver SBRT. Med Phys. 2018;45:4763-74.
Zhen X, Chen J, Zhong Z, et al. Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study. Phys Med Biol. 2017;62:8246-63.
Zhao W, Yang J, Sun Y, et al. 3D deep learning from CT scans predicts tumor invasiveness of subcentimeter pulmonary adenocarcinomas. Cancer Res. 2018;78:6881-9.
Abdelhafiz D, Yang C, Ammar R, Nabavi S. Deep convolutional neural networks for mammography: advances, challenges, and applications. BMC Bioinformatics. 2019 Jun 6;20(Suppl 11):281. doi: 10.1186/s12859-019-2823-4. PMID: 31167642; PMCID: PMC6551243.
Ciompi F, Chung K, van Riel SJ, et al. Towards automatic pulmonary nodule management in lung cancer screening with deep learning. Sci Rep. 2017;7:46479.
Kang G, Liu K, Hou B, Zhang N. 3D multi-view convolutional neural networks for lung nodule classification. PLOS One. 2017;12:e0188290.
Wang S, Zhou M, Gevaert O, et al. A multi-view deep convolutional neural networks for lung nodule segmentation. Conf Proc IEEE Eng Med Biol Soc. 2017;2017:1752-5.