AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency

International Journal of Multidisciplinary and Innovative Research ISSN(print): 3050-6883, ISSN(online): 3050-6891 Volume 02 Issue 10 October 2025 DOI: 10.58806/ijmir.2025.v2i10n01 Page No: 285-292 285 Volume 02 Issue 10 October 2025 Corresponding Author: Lakshmi Priya Bachina AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency Dr. Kanagala Anusha1, Niveditha Pallerla2, Lakshmi Priya Bachina3* 1Assistant Professor, Koneru Lakshmaiah Education Foundation 2Pharmacy Manager, Crawford Pharmacy of Pleasanton 3Research scholar, Koneru Lakshmaiah Education Foundation ABSTRACT ARTICLE DETAILS Artificial intelligence (AI) has the potential to revolutionize diagnostic imaging, leading to significant improvements in efficiency, accuracy, and patient outcomes. Artificial intelligence (AI) in diagnostic imaging signals the beginning of a revolutionary period in healthcare, characterized by previously unresolved gains in perception and effectiveness. The paper explores how AI addresses longstanding challenges in the field, including human error, time-consuming manual processes, and subjective image interpretation. The paper employed a systematic literature review to assess the impact of AI on diagnostic imaging efficiency and accuracy. Studies published between 2019 and 2023 were reviewed, focusing on peer-reviewed journals and conference proceedings. The initial portion of the paper provides an overview of the classic difficulties associated with diagnostic imaging, such as the possibility of human mistakes, the laborious manual processing process, and the subjective interpretation of pictures. The paper examines how artificial intelligence (AI) technologies are effective diagnostic imaging techniques and how they may improve efficiency and accuracy in clinical settings. By leveraging machine learning techniques like convolutional neural networks (CNNs), AI can analyze complex imaging data with exceptional precision, enabling early disease detection, improved risk assessment, and more timely diagnoses. The paper also discusses challenges associated with AI implementation, such as algorithm interpretability and data privacy. In conclusion, thoughtful integration of AI holds immense promise for transforming diagnostic imaging into a new era of precision medicine. KEYWORDS: Artificial intelligence, Diagnostics, Medical imaging, Accuracy Published On: 06 October 2025 Available on: https://ijmir.com INTRODUCTION: AI has become a potentially useful tool to address these issues as the need for precise and effective medical diagnostics grows. This combination offers previously unheard-of prospects to improve accuracy, efficiency, and patient outcomes, potentially revolutionizing the field of medical imaging. The development of artificial intelligence (AI) in diagnostic imaging can be attributed to its exceptional speed and accuracy in processing large volumes of medical data. AI systems can analyze complicated imaging data, including X-rays, MRIs, and CT scans, and identify tiny anomalies that may be invisible to human eyes by utilizing machine learning algorithms. As an illustration of how AI may improve diagnosis accuracy [14] showed how well deep learning algorithms performed in correctly identifying skin cancer through the analysis of thermoscopic pictures. There are sometimes bottlenecks in traditional diagnostic systems, such as lengthy wait times for imaging interpretation and reporting. AI technology can speed up patient treatment and lessen the workload on healthcare providers by quickly evaluating photos and providing real-time diagnostics support[8]. One prominent instance is the application of AI algorithms to chest X-rays, which has demonstrated impressive results in accelerating the detection of lung disorders, such as diseases.[Fig1]AI-driven diagnostic solutions can fill the gap by offering remote diagnostic support in areas where access to specialized medical knowledge is scarce. It can facilitate prompt diagnosis and treatment, especially in impoverished areas with limited access to medical resources. One promising approach to screening for diabetic retinopathy in resource-constrained situations is the implementation of AI-enabled mobile applications for retinal imaging, which could enable early detection and intervention. AI can completely transform the diagnostic imaging industry by improving accuracy, optimizing workflow efficiency, and addressing healthcare inequities, which would eventually result in better patient outcomes and higher-quality care. AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency 286 Volume 02 Issue 10 October 2025 Corresponding Author: Lakshmi Priya Bachina Fig 1: Diagnostic imaging procedure BACKGROUND OF THE STUDY : AI-based Diagnostic imaging has a revolutionizing phase. Before AI & After AI this diagnostic sector has a lot of changes. Because diagnostic imaging provides medical professionals with information about the structure and functions of the human body, it is crucial to modern healthcare. Medical practitioners can use a range of imaging modalities, such as X-rays, MRIs, CT scans, ultrasounds, and nuclear medicine imaging, to non-invasively view internal organs, tissues, and physiological processes[3]. Diagnostic imaging is to help a wide range of medical illnesses, from cancers and fractures to neurological disorders and cardiovascular ailments. For example, MRI and CT scans provide comprehensive images of soft tissues, organs, and blood vessels, enabling the identification of illnesses like cancers, strokes, and heart disease. X-rays to assess bone fractures. "AI has the potential to revolutionize various aspects of healthcare, including diagnostics, treatment planning, and patient engagement. For instance, [9] explored the use of AIpowered tools to enhance patient engagement, highlighting its potential to improve health outcomes." Abdominal organ evaluation and fetal development examination are two common uses for ultrasound imaging during pregnancy. Screening programs for early disease detection and preventive medicine depend heavily on diagnostic imaging. For example, mammography is frequently used to screen for breast cancer, while colonoscopy and virtual colonoscopy (CT colonography) are used to screen for colorectal cancer. GROWING IMPACT OF AI ON DIAGNOSTIC IMAGING : The increasing influence of artificial intelligence ( AI ) on diagnostic imaging is transforming the way healthcare is delivered by improving patient outcomes, accuracy, and efficiency. Deep learning is becoming incorporated into diagnostic imaging processes, revolutionizing the interpretation and analysis of medical images from modalities, including MRIs, CT scans, ultrasounds, and Xrays. The increase in diagnosis accuracy is one of the effects of AI in diagnostic imaging. A deep learning model surpassed radiologists in identifying breast cancer on mammograms, according to a study by [1] , underscoring the potential of AI to enhance diagnostic capacities. In a similar vein, a meta-analysis conducted in 2020 by McKinney et al. demonstrated the effectiveness of AI algorithms in diagnostic accuracy in critical situations by demonstrating high sensitivity and specificity in identifying cerebral bleeding on head CT scans. Radiologists may concentrate on complex cases and give rapid diagnoses by using AI-powered tools that prioritize urgent findings, triage cases, and shorten the time needed for interpretation. In dermatologists' manual assessment, a study by [3] showed the efficiency gains of an AI system for classifying skin lesions, cutting down on diagnostic time and increasing workflow productivity. AI also makes personalized medicine possible by combining imaging results and clinical data to create customized treatment regimens and forecast patient outcomes. Artificial intelligence (AI) algorithms can help with risk assessment, treatment response prediction, and disease progression tracking by examining imaging biomarkers and patient attributes. For example, [16] study showed that using MRI images, an AI model accurately predicted breast cancer patients' response to neoadjuvant chemotherapy, enabling individualized treatment plans. FUNDAMENTALS OF DIAGNOSTIC IMAGING : The increasing influence of artificial intelligence (AI) on diagnostic imaging is transforming the way healthcare is delivered by improving patient outcomes, accuracy, and efficiency. Deep learning models are becoming more incorporated into diagnostic imaging processes, revolutionizing the interpretation and analysis of medical images from modalities, including MRIs, CT scans, ultrasounds, and X-rays. The increase in diagnosis accuracy is one of the major effects of AI in diagnostic imaging. Large amounts of medical picture data may be quickly analyzed by AI algorithms, which can then spot irregularities and subtle patterns that human radiologists might overlook. A deep learning model surpassed radiologists in identifying breast cancer on mammograms, according to a study by [1], underscoring the potential of AI to enhance diagnostic capacities. In a similar vein, a meta-analysis conducted in AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency 287 Volume 02 Issue 10 October 2025 Corresponding Author: Lakshmi Priya Bachina 2020 by McKinney et al. demonstrated the effectiveness of AI algorithms in diagnostic accuracy in critical situations by demonstrating high sensitivity and specificity in identifying cerebral bleeding on head CT scans. AI is increasing workflow efficiency in diagnostic imaging by speeding up picture analysis and automating repetitive processes. Radiologists may concentrate on complex cases and give rapid diagnoses by using AI-powered tools that prioritize urgent findings, triage cases, and shorten the time needed for interpretation. In dermatologists' manual assessment, a study by [3] showed the efficiency gains of an AI system for classifying skin lesions, cutting down on diagnostic time and increasing workflow productivity. AI also makes personalized medicine possible by combining imaging results and clinical data to create customized treatment regimens and forecast patient outcomes. Artificial intelligence (AI) algorithms can help with risk assessment, treatment response prediction, and disease progression tracking by examining imaging biomarkers and patient attributes. For example, [16] study showed that using MRI images, an AI model accurately predicted breast cancer patients' response to neoadjuvant chemotherapy, enabling individualized treatment plans. Fig 2: Diagnostic imaging workflow process Fig 2 represents A patient or clinical issue as the first step in the process. The patient needs an imaging scan for this reason. The Imaging Scan is the following stage. The exact type of diagnostic imaging procedure, such as a CT or MRI scan, will be performed. Next, the RIS/PACS receives the scan's images. These software applications handle the storage and management of medical images. After examining the pictures, a radiologist or other licensed medical professional will prepare a report. The stage for clinical reporting. The Imaging Report is the last stage. The referring physician receives this report and discusses the findings with the patient. Digital Imaging and Communications in Medicine is referred to as DICOM. It is a standard that guarantees the interchangeability of medical images between various software applications and imaging systems. INTRODUCTION TO AI IN DIAGNOSTIC IMAGING : Considering the promise of improved accessibility, efficiency, and accuracy in illness diagnosis and patient care, the introduction of Artificial Intelligence (AI) into diagnostic imaging has signaled a paradigm shift in healthcare. AI-powered solutions provide a revolutionary approach to image interpretation. AI APPLICATIONS FOR DIAGNOSTIC IMAGING: By automating operations that radiologists once did, artificial intelligence (AI) algorithms are changing diagnostic imaging across many modalities, including MRI, CT scan, ultrasound, and X-ray. Large volumes of imaging data may be quickly analyzed by these algorithms, which can identify abnormalities and help identify diseases remarkably accurately. For example, [3] showed the effectiveness of a deep learning system in diagnosing skin cancer with a performance level comparable to dermatologists in a study published in Nature Medicine. Like this, AI models have demonstrated potential in the diagnosis of neurological illnesses through brain imaging, the interpretation of retinal pictures for diabetic retinopathy, and the detection of breast cancer on mammograms. These applications are as follows : 1. Image Recognition and analysis 2. Automated segmentation 3. Quantitative Analysis 4. Decision support system 5. Predictive analysis 6. Quality Control 7. Personalized medicine ENHANCING ACCURACY WITH AI: AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency 288 Volume 02 Issue 10 October 2025 Corresponding Author: Lakshmi Priya Bachina Through previously unheard-of improvements in accuracy and efficiency, artificial intelligence is transforming diagnostic imaging. Artificial intelligence (AI) algorithms have become indispensable tools for radiologists and clinicians due to their rapid and accurate analysis of large amounts of medical imaging data. Artificial intelligence ( AI) may detect minute irregularities and trends in medical images that can go unnoticed by humans by utilizing sophisticated machine learning algorithms. This ability leads to better patient outcomes and prompt interventions by enabling earlier disease diagnosis and improving diagnostic accuracy. AI also expedites the diagnostic procedure, thus increasing the effectiveness of healthcare services. AI-powered decision support technologies also help radiologists streamline workflow, guaranteeing that patients receive timely and appropriate care and offering real-time insights and recommendations. Healthcare practitioners can increase throughput, lower diagnostic mistakes, and ultimately enhance the standard of patient care by incorporating AI into diagnostic imaging workflows. IMPROVING EFFICIENCY AND DIAGNOSTIC WORKFLOW : Through dramatically increased productivity and streamlined diagnostic workflows, AI is transforming diagnostic imaging. AI systems enable radiologists to focus on cases and judgments by automating segmentation and analysis, freeing them from manual activities. To further improve diagnostic confidence and accuracy, AI-powered decision systems give radiologists access to pertinent clinical data, real-time insights, and proposed differential diagnoses. AI integration in diagnostic imaging boosts productivity, raises throughput, and ultimately improves patient outcomes by streamlining workflow and lessening the difficulty of repetitive activities. REVIEW OF PREVIOUS RESEARCH : AI could significantly increase the precision and effectiveness of diagnostic imaging [10] emphasize how AI may enhance workflow, yield repeatable outcomes, and facilitate real-time risk assessment and diagnosis for applications related to the heart and lungs, where AI can automate the detection and characterization of characteristics, standardize picture capture and processing, and forecast individual results[5] underscores the capacity of deep learning and machine learning methodologies to augment the precision of medical picture analysis, specifically in brain tumor identification. Research on artificial intelligence in diagnostic imaging has significantly increased, according to a comprehensive survey between 2019 and 2023. The Scopus database yielded 1750 documents, of which 480 were judged significant to the medical and health fields (Figure 3). Because AI-powered diagnostic imaging has the potential to transform clinical practice and enhance patient outcomes, there is a growing amount of literature that reflects this interest and investment [15]. Examine and explore the ways that artificial intelligence is being used in various medical fields, including neurology, pulmonology, and cardiology. Examine how AI algorithms are customized to handle diagnostic issues particular to each specialty. Provide quantifiable statistics to demonstrate the growing research around AI-powered diagnostic imaging. Figure 3: Scopus database (2019-2023) Growing graph There is no doubting the rise in AI research in diagnostic imaging. A good indication is the 1750 records were found in just four years (Figure 3). As the potential of AI to enhance patient outcomes and healthcare delivery becomes increasingly evident, this number continues climbing. AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency 289 Volume 02 Issue 10 October 2025 Corresponding Author: Lakshmi Priya Bachina Source: Web of science Bar chart The above bar chart shows the following things: Neurology: Artificial intelligence (AI) can examine brain scans for indications of neurodegenerative illnesses like Parkinson's and Alzheimer's. Additionally, it can help in the diagnosis of strokes. Pulmonology: By examining CT scans and chest X-rays, AI is used to identify lung cancer. Cardiology: AI can identify irregularities in the rhythm and shape of the heart by analyzing echocardiograms, a form of ultrasound used to evaluate heart function. Oncology: AI is being used to diagnose breast cancer and other cancers by analyzing pictures from CT scans, mammograms, and other tests. Radiology: AI can help radiologists understand a variety of medical pictures, including CT scans, MRIs, and X-rays[2] The Bibliometric analysis is executed with the keywords used with AI. From the analysis AI diagnostic related articles significantly with analyze, design, and coordination (Figure 4) Source : Vos Viewer The above diagram shows a network of areas connected by lines. Words about artificial intelligence (AI) in diagnostics and imaging for medicine can be found in these areas. The "pathology," "imaging," and "diagnosis" spheres are at the center of the network, indicating that these are fundamental ideas in AI-powered medical diagnostics. The fact that phrases like "machine learning," "decision support systems," and "computer-aided diagnosis" are near the core concepts suggests that they are crucial parts of AI diagnostics. The picture also illustrates the possibility for AI to integrate different kinds of medical data for diagnosis by using more general categories like "genomics," "proteomics," and "phenotype." The network includes security and privacy features, emphasizing when developing and utilizing AI diagnostics. AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency 290 Volume 02 Issue 10 October 2025 Corresponding Author: Lakshmi Priya Bachina EXPLORATION OF AI TECHNIQUES SUCH AS MACHINE LEARNING, DEEP LEARNING, AND NEURAL NETWORKS: Artificial intelligence (AI) methods like machine learning, deep learning, and neural networks have become revolutionary tools for increasing precision and productivity in diagnostic imaging. Systems may learn from data and make predictions or judgements without explicit programming algorithms that can be trained on massive datasets of medical pictures in the context of diagnostic imaging to identify patterns and abnormalities, assisting in the identification and diagnosis of illnesses. Deep learning is a subfield of Machine learning that has gained notoriety due to its ability to hierarchical data representations. One kind of deep learning model that has demonstrated remarkable performance in tasks like object detection, segmentation, and picture categorization is the convolutional neural network (CNN). In diagnostic imaging, CNNs can precisely identify and define anomalies with pixel-level accuracy. A neural network’s basic structure, which is in deep learning, is shown in the image you submitted. Machine learning, a subset of artificial intelligence (AI), includes deep learning as a subfield. Some key AI techniques regarding Machine and deep learning. Algorithms are used in machine learning to learn from data without explicit programming. It can be applied to applications like clustering, regression, and classification. Algorithms are used in machine learning to learn from data without explicit programming. It can be applied to applications like clustering, regression, and classification. Three primary categories of machine learning exist. Labeled data is used in supervised to train a model. Un supervised learning looks for patterns in data by utilizing unlabeled data. An unsupervised learning model. For instance, might client base into various groups according to the consumers past purchases. Trial and error are how reinforcement learning. A reward signal is a reinforcement learning model for activities that it deems desirable and a punishment signal for acts that it deems undesirable. The model gains the ability to behave in a way that maximizes the reward signal over time. METHODOLOGY: To determine how AI will affect the precision and effectiveness of diagnostic imaging. The paper employed a systematic literature review to assess the impact of AI on diagnostic imaging efficiency and accuracy. A systematic literature review will be conducted to identify relevant studies published between 2019 and 2023 (expanding the timeframe for a more robust analysis). Peer-reviewed journals and conference proceedings will be searched using electronic databases such as PubMed, Scopus, and Web of Science. The keywords included ‘’AI,’’ ‘’artificial intelligence,’’ ‘’machine learning,’ ‘’deep learning,’’ ‘’diagnostic imaging,’’ ‘’medical imaging,’’ ‘’radiology’’’, ‘’accuracy’’, as well as ‘’efficiency’’. Techniques are utilized to improve accuracy and efficiency in the quickly developing field of AI applications in diagnostic imaging [4]. Among these techniques are evidence-based algorithms, which are created, tested, and trained using benchmark datasets [8]. AI can streamline processes and produce unbiased outcomes in cardiovascular imaging [10]. To prevent overdiagnosis, AI imaging research must concentrate on clinically significant goals like survival and symptoms [12]. Furthermore, the results of a few selected studies were examined using the qualitative analysis method. The data extraction procedure includes the AI algorithms, imaging modalities, sample size, study design, performance indicators, and findings on diagnostic accuracy and efficiency. To ascertain the possibility of bias and confirm the validity and reliability of the synthesis evidence, a critical assessment of the included studies was conducted. CHALLENGES & LIMITATIONS: Artificial intelligence (AI) has the potential to revolutionize diagnostic imaging and is widely adopted. Especially those containing detailed medical images are essential for AI models to identify trends and generate precise predictions, but obtaining them can be difficult because of data silos, privacy issues, and the requirement for standardized formats. The interpretability and explainability of AI algorithms provide another difficulty. Deep learning models are frequently employed in diagnostic imaging, but they function as "black boxes," making it challenging to decipher the logic underlying their predictions. Without understanding how decisions are formed, radiologists and other medical professionals could be hesitant to trust diagnoses produced by AI. Building confidence and acceptability among healthcare professionals requires ensuring that AI algorithms are transparent. Additionally, AI systems work with current healthcare IT systems and electronic health records (EHRs) to seamlessly integrate into clinical workflows. AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency 291 Volume 02 Issue 10 October 2025 Corresponding Author: Lakshmi Priya Bachina FINDINGS: The findings from the AI-revolutionary diagnostic imaging are 1. Enhanced accuracy 2. Efficiency Gains 3. Early disease detection 4. Personalized Medicine 5. Remote diagnosis 6. Quality Control FUTURE SCOPE: The future of diagnostic imaging lies in the advancement of artificial intelligence (AI) technology. Advances in machine learning and artificial intelligence enhance patient outcomes by raising the precision and efficacy of diagnostic procedures. Also, the development of customized AI models suited to certain imaging modalities and clinical applications by innovative multidisciplinary cooperation involving radiologists, medical professionals, and AI experts. As AI becomes more widely used in diagnostic imaging, it will be critical to address ethical and legal issues related to patient permission, algorithm openness, and data protection to ensure its responsible and equitable application in healthcare procedures. CONCLUSION: These developments enhance patient outcomes and healthcare inequities with medical professionals with strong diagnostic and therapeutic instruments. The issues of data privacy, algorithm transparency, and regulatory compliance must be acknowledged and addressed as we embrace the transformative promise of AI in diagnostic imaging. For AI researchers, clinicians, legislators, and industry stakeholders to effectively navigate these obstacles and guarantee the ethical and responsible application of AI technology in clinical practice, cooperation is essential. We can create a future where diagnostic imaging sets new benchmarks for accuracy, efficiency, and accessibility in healthcare by utilizing AI while putting patient safety, privacy, and equity first. In summary, artificial intelligence (AI) in diagnostic imaging is a game-changer for the healthcare industry, presenting to improve patient care, efficiency, and accuracy. Artificial intelligence (AI)-driven algorithms have proven remarkably effective at identifying minute irregularities, optimizing workflow procedures, and supporting early illness identification. REFERENCES: 1) Ardila, D.et al. (2020). End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nature Medicine, 26(6),782-789. 2) Albano, Domenico (2024). Artificial intelligence for radiographic imaging detection of caries lesions: a systematic review, BMC Oral Health, doi: 10.1186/s12903-024-04046-7 3) Esteva, A., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542 (7639), 115-118 4) JOSEPH, SANIL, (2024), Diagnostic Accuracy of Artificial Intelligence-Based Automated Diabetic Retinopathy Screening in Real-World Settings: A Systematic Review and Meta-Analysis, American Journal of Ophthalmology, doi: 10.1016/j.ajo.2024.02.012 5) Katharina Wenderott (2024), Radiologists’ perspectives on the workflow integration of an artificial intelligence-based computer-aided detection system: A qualitative study, Applied Ergonomics, doi: 10.1016/j.apergo.2024.104243 6) Kayarian, Fae,(2024), Artificial intelligence and point-of-care ultrasound: Benefits, limitations, and implications for the future, American Journal of Emergency Medicine, doi: 10.1016/j.ajem.2024.03.023 7) Khalighi, Sirvan(2024), Artificial intelligence in neuro-oncology: advances and challenges in brain tumor diagnosis, prognosis, and precision treatment, npj Precision Oncology, doi: 10.1038/s41698-024-00575-0 8) Lakhani, P., & Sundaram, B. (2017). Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology, 284(2), 574-582. 9) Lakshmipriya BACHINA, Anusha KANAGALA,(2023). Health revolution: AI-powered patient engagement, IJCBS, 24(5) (2023): 722-731 10) Lin, (2020). Artificial intelligence (AI): Improving the efficiency of Cardiovascular imaging, Expert Review of medical devices, Doi: https://doi.org/10.1080/17434440.2020.1777855 11) Lindner, Cristian,(2024), Improving the radiological diagnosis of hepatic artery thrombosis after liver transplantation: Current approaches and future challenges, World Journal of Transplantation, doi: 10.5500/wjt.v14.i1.88938 12) Oren, Artificial Intelligence (AI) in Medical Imaging : Switching from radiographic pathological data to clinically meaningful end points, doi: https://doi.org/10.1016/s2589-7500(20)30160-6 13) Tayebi Arasteh, Soroosh (2024), Enhancing diagnostic deep learning via self-supervised pretraining on large-scale, unlabeled non-medical images, European Radiology Experimental, doi: 10.1186/s41747-023-00411-3 AI Revolutionizing Diagnostic Imaging: Enhancing Accuracy and Efficiency 292 Volume 02 Issue 10 October 2025 Corresponding Author: Lakshmi Priya Bachina 14) Ting, D.S., et al.(2019). Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA, 318(22), 2211-2223. 15) Xiaoli Tang, (2020). The role of AI in medical imaging research, BJRi open, doi : http://doi.org/10.1259/bjro.20190031 16) Zhang, B.et al. (2019). Deep learning based on MRI data identifies breast cancer patients eligible for neoadjuvant chemotherapy independent of clinical factors. Breast Cancer Research and Treatment, 174 (2), 1-10.