1
|
Park IA, Noh YK, Min KW, Kim DH, Lee JY, Son BK, Kwon MJ, Han MH, Hur JY, Pyo JS. p27 Cell Cycle Inhibitor and Survival in Luminal-Type Breast Cancer: Gene Ontology, Machine Learning, and Drug Screening Analysis. J Breast Cancer 2024; 27:27.e29. [PMID: 39344410 DOI: 10.4048/jbc.2024.0107] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2024] [Revised: 08/02/2024] [Accepted: 08/25/2024] [Indexed: 10/01/2024] Open
Abstract
PURPOSE A widely distributed cell cycle inhibitor, p27, regulates cyclin-dependent kinase-cyclin complexes. Although the prognostic value of p27 has been established for various types of carcinomas, its role in luminal breast cancer remains poorly understood. This study aimed to explore the functional enrichment of p27 and identify potential drug targets in patients with luminal-type breast cancer. METHODS Clinicopathological data were collected from 868 patients with luminal-type breast cancer. Additionally, publicly available data from the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset (1,500 patients) and the Gene Expression Omnibus database (855 patients) were included in the analysis. Immunohistochemical staining for p27, differential gene expression analysis, disease ontology analysis, survival prediction modeling using machine learning (ML), and in vitro drug screening were also performed. RESULTS Low p27 expression correlated with younger age, advanced tumor stage, estrogen receptor/progesterone receptor negativity, decreased cluster of differentiation 8+ T cell count, and poorer survival outcomes in luminal-type breast cancer. The METABRIC data revealed that reduced cyclin-dependent kinase inhibitor 1B (CDKN1B) expression (encoding p27) was associated with cell proliferation-related pathways and epigenetic polycomb repressive complex 2. Using ML, p27 emerged as the second most significant survival factor after N stage, thereby enhancing survival model performance. Additionally, luminal-type breast cancer cell lines with low CDKN1B expression demonstrated increased sensitivity to specific anticancer drugs such as voxtalisib and serdemetan, implying a potential therapeutic synergy between CDKN1B-targeted approaches and these drugs. CONCLUSION The integration of ML and bioinformatic analyses of p27 has the potential to enhance risk stratification and facilitate personalized treatment strategies for patients with breast cancer.
Collapse
Affiliation(s)
- In Ah Park
- Department of Pathology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Yung-Kyun Noh
- Department of Computer Science, Hanyang University, Seoul, Korea
- School of Computational Sciences, Korea Institute for Advanced Study, Seoul, Korea
| | - Kyueng-Whan Min
- Department of Pathology, Uijeongbu Eulji Medical Center, Eulji University School of Medicine, Uijeongbu, Korea.
| | - Dong-Hoon Kim
- Department of Pathology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Korea.
| | - Jeong-Yeon Lee
- Department of Pathology, Hanyang University College of Medicine, Seoul, Korea
| | - Byoung Kwan Son
- Department of Internal Medicine, Uijeongbu Eulji Medical Center, Eulji University School of Medicine, Uijeongbu, Korea
| | - Mi Jung Kwon
- Department of Pathology, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang, Korea
| | - Myung-Hoon Han
- Department of Neurosurgery, Hanyang University Guri Hospital, Hanyang University College of Medicine, Guri, Korea
| | - Joon Young Hur
- Department of Internal Medicine, Hanyang University Guri Hospital, Hanyang University College of Medicine, Guri, Korea
| | - Jung Soo Pyo
- Department of Pathology, Uijeongbu Eulji Medical Center, Eulji University School of Medicine, Uijeongbu, Korea
| |
Collapse
|
2
|
Whitney HM, Yoeli-Bik R, Abramowicz JS, Lan L, Li H, Longman RE, Lengyel E, Giger ML. AI-based automated segmentation for ovarian/adnexal masses and their internal components on ultrasound imaging. J Med Imaging (Bellingham) 2024; 11:044505. [PMID: 39114540 PMCID: PMC11301525 DOI: 10.1117/1.jmi.11.4.044505] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Revised: 05/21/2024] [Accepted: 07/10/2024] [Indexed: 08/10/2024] Open
Abstract
Purpose Segmentation of ovarian/adnexal masses from surrounding tissue on ultrasound images is a challenging task. The separation of masses into different components may also be important for radiomic feature extraction. Our study aimed to develop an artificial intelligence-based automatic segmentation method for transvaginal ultrasound images that (1) outlines the exterior boundary of adnexal masses and (2) separates internal components. Approach A retrospective ultrasound imaging database of adnexal masses was reviewed for exclusion criteria at the patient, mass, and image levels, with one image per mass. The resulting 54 adnexal masses (36 benign/18 malignant) from 53 patients were separated by patient into training (26 benign/12 malignant) and independent test (10 benign/6 malignant) sets. U-net segmentation performance on test images compared to expert detailed outlines was measured using the Dice similarity coefficient (DSC) and the ratio of the Hausdorff distance to the effective diameter of the outline (R HD - D ) for each mass. Subsequently, in discovery mode, a two-level fuzzy c-means (FCM) unsupervised clustering approach was used to separate the pixels within masses belonging to hypoechoic or hyperechoic components. Results The DSC (median [95% confidence interval]) was 0.91 [0.78, 0.96], andR HD - D was 0.04 [0.01, 0.12], indicating strong agreement with expert outlines. Clinical review of the internal separation of masses into echogenic components demonstrated a strong association with mass characteristics. Conclusion A combined U-net and FCM algorithm for automatic segmentation of adnexal masses and their internal components achieved excellent results compared with expert outlines and review, supporting future radiomic feature-based classification of the masses by components.
Collapse
Affiliation(s)
- Heather M. Whitney
- The University of Chicago, Department of Radiology, Chicago, Illinois, United States
| | - Roni Yoeli-Bik
- The University of Chicago, Department of Obstetrics and Gynecology/Section of Gynecologic Oncology, Chicago, Illinois, United States
| | - Jacques S. Abramowicz
- The University of Chicago, Department of Obstetrics and Gynecology/Section of Ultrasound, Genetics, and Fetal Neonatal Care Center, Chicago, Illinois, United States
| | - Li Lan
- The University of Chicago, Department of Radiology, Chicago, Illinois, United States
| | - Hui Li
- The University of Chicago, Department of Radiology, Chicago, Illinois, United States
| | - Ryan E. Longman
- The University of Chicago, Department of Obstetrics and Gynecology/Section of Ultrasound, Genetics, and Fetal Neonatal Care Center, Chicago, Illinois, United States
| | - Ernst Lengyel
- The University of Chicago, Department of Obstetrics and Gynecology/Section of Gynecologic Oncology, Chicago, Illinois, United States
| | - Maryellen L. Giger
- The University of Chicago, Department of Radiology, Chicago, Illinois, United States
| |
Collapse
|
3
|
Zhang J, Dawkins A. Artificial Intelligence in Ultrasound Imaging: Where Are We Now? Ultrasound Q 2024; 40:93-97. [PMID: 38842384 DOI: 10.1097/ruq.0000000000000680] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/07/2024]
Affiliation(s)
- Jie Zhang
- From the Department of Radiology, University of Kentucky, Lexington, KY
| | | |
Collapse
|
4
|
Guldogan N, Taskin F, Icten GE, Yilmaz E, Turk EB, Erdemli S, Parlakkilic UT, Turkoglu O, Aribal E. Artificial Intelligence in BI-RADS Categorization of Breast Lesions on Ultrasound: Can We Omit Excessive Follow-ups and Biopsies? Acad Radiol 2024; 31:2194-2202. [PMID: 38087719 DOI: 10.1016/j.acra.2023.11.031] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Revised: 11/18/2023] [Accepted: 11/20/2023] [Indexed: 07/01/2024]
Abstract
RATIONALE AND OBJECTIVES Artificial intelligence (AI) systems have been increasingly applied to breast ultrasonography. They are expected to decrease the workload of radiologists and to improve diagnostic accuracy. The aim of this study is to evaluate the performance of an AI system for the BI-RADS category assessment in breast masses detected on breast ultrasound. MATERIALS AND METHODS: A total of 715 masses detected in 530 patients were analyzed. Three breast imaging centers of the same institution and nine breast radiologists participated in this study. Ultrasound was performed by one radiologist who obtained two orthogonal views of each detected lesion. These images were retrospectively reviewed by a second radiologist blinded to the patient's clinical data. A commercial AI system evaluated images. The level of agreement between the AI system and the two radiologists and their diagnostic performance were calculated according to dichotomic BI-RADS category assessment. RESULTS This study included 715 breast masses. Of these, 134 (18.75%) were malignant, and 581 (81.25%) were benign. In discriminating benign and probably benign from suspicious lesions, the agreement between AI and the first and second radiologists was moderate statistically. The sensitivity and specificity of radiologist 1, radiologist 2, and AI were calculated as 98.51% and 80.72%, 97.76% and 75.56%, and 98.51% and 65.40%, respectively. For radiologist 1, the positive predictive value (PPV) was 54.10%, the negative predictive value (NPV) was 99.58%, and the accuracy was 84.06%. Radiologist 2 achieved a PPV of 47.99%, NPV of 99.32%, and accuracy of 79.72%. The AI system exhibited a PPV of 39.64%, NPV of 99.48%, and accuracy of 71.61%. Notably, none of the lesions categorized as BI-RADS 2 by AI were malignant, while 2 of the lesions classified as BI-RADS 3 by AI were subsequently confirmed as malignant. By considering AI-assigned BI-RADS 2 as safe, we could potentially avoid 11% (18 out of 163) of benign lesion biopsies and 46.2% (110 out of 238) of follow-ups. CONCLUSION AI proves effective in predicting malignancy. Integrating it into the clinical workflow has the potential to reduce unnecessary biopsies and short-term follow-ups, which, in turn, can contribute to sustainability in healthcare practices.
Collapse
Affiliation(s)
- Nilgun Guldogan
- Breast Clinic, Acibadem Altunizade Hospital, 34662, Istanbul, Turkey (N.G., E.Y., E.B.T., E.A.).
| | - Fusun Taskin
- Department of Radiology, Acibadem M.A.A. University School of Medicine, Atakent University Hospital, 34755, Istanbul, Turkey (F.T., S.E.); Acibadem M.A.A. University Senology Research Institute, 34457, Sarıyer, Istanbul, Turkey (F.T., G.E.I., U.T.P.)
| | - Gul Esen Icten
- Acibadem M.A.A. University Senology Research Institute, 34457, Sarıyer, Istanbul, Turkey (F.T., G.E.I., U.T.P.); Department of Radiology, Acibadem M.A.A. University School of Medicine, Acıbadem Maslak Hospital, Büyükdere St. 40, 34457, Maslak, Istanbul, Turkey (G.E.I.)
| | - Ebru Yilmaz
- Breast Clinic, Acibadem Altunizade Hospital, 34662, Istanbul, Turkey (N.G., E.Y., E.B.T., E.A.)
| | - Ebru Banu Turk
- Breast Clinic, Acibadem Altunizade Hospital, 34662, Istanbul, Turkey (N.G., E.Y., E.B.T., E.A.)
| | - Servet Erdemli
- Department of Radiology, Acibadem M.A.A. University School of Medicine, Atakent University Hospital, 34755, Istanbul, Turkey (F.T., S.E.)
| | - Ulku Tuba Parlakkilic
- Acibadem M.A.A. University Senology Research Institute, 34457, Sarıyer, Istanbul, Turkey (F.T., G.E.I., U.T.P.)
| | - Ozlem Turkoglu
- Department of Radiology, Taksim Training and Research Hospital, Istanbul, Turkey (O.T.)
| | - Erkin Aribal
- Breast Clinic, Acibadem Altunizade Hospital, 34662, Istanbul, Turkey (N.G., E.Y., E.B.T., E.A.); Department of Radiology, Acibadem M.A.A. University School of Medicine, Istanbul, Turkey (E.A.)
| |
Collapse
|
5
|
Xu P, Zhao J, Wan M, Song Q, Su Q, Wang D. Classification of multi-feature fusion ultrasound images of breast tumor within category 4 using convolutional neural networks. Med Phys 2024; 51:4243-4257. [PMID: 38436433 DOI: 10.1002/mp.16946] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2022] [Revised: 01/03/2024] [Accepted: 01/09/2024] [Indexed: 03/05/2024] Open
Abstract
BACKGROUND Breast tumor is a fatal threat to the health of women. Ultrasound (US) is a common and economical method for the diagnosis of breast cancer. Breast imaging reporting and data system (BI-RADS) category 4 has the highest false-positive value of about 30% among five categories. The classification task in BI-RADS category 4 is challenging and has not been fully studied. PURPOSE This work aimed to use convolutional neural networks (CNNs) for breast tumor classification using B-mode images in category 4 to overcome the dependence on operator and artifacts. Additionally, this work intends to take full advantage of morphological and textural features in breast tumor US images to improve classification accuracy. METHODS First, original US images coming directly from the hospital were cropped and resized. In 1385 B-mode US BI-RADS category 4 images, the biopsy eliminated 503 samples of benign tumor and left 882 of malignant. Then, K-means clustering algorithm and entropy of sliding windows of US images were conducted. Considering the diversity of different characteristic information of malignant and benign represented by original B-mode images, K-means clustering images and entropy images, they are fused in a three-channel form multi-feature fusion images dataset. The training, validation, and test sets are 969, 277, and 139. With transfer learning, 11 CNN models including DenseNet and ResNet were investigated. Finally, by comparing accuracy, precision, recall, F1-score, and area under curve (AUC) of the results, models which had better performance were selected. The normality of data was assessed by Shapiro-Wilk test. DeLong test and independent t-test were used to evaluate the significant difference of AUC and other values. False discovery rate was utilized to ultimately evaluate the advantages of CNN with highest evaluation metrics. In addition, the study of anti-log compression was conducted but no improvement has shown in CNNs classification results. RESULTS With multi-feature fusion images, DenseNet121 has highest accuracy of 80.22 ± 1.45% compared to other CNNs, precision of 77.97 ± 2.89% and AUC of 0.82 ± 0.01. Multi-feature fusion improved accuracy of DenseNet121 by 1.87% from classification of original B-mode images (p < 0.05). CONCLUSION The CNNs with multi-feature fusion show a good potential of reducing the false-positive rate within category 4. The work illustrated that CNNs and fusion images have the potential to reduce false-positive rate in breast tumor within US BI-RADS category 4, and make the diagnosis of category 4 breast tumors to be more accurate and precise.
Collapse
Affiliation(s)
- Pengfei Xu
- Department of Biomedical Engineering, Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China
| | - Jing Zhao
- The Second Hospital of Jilin University, Changchun, China
| | - Mingxi Wan
- Department of Biomedical Engineering, Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China
| | - Qing Song
- The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China
| | - Qiang Su
- Department of Oncology, Beijing Friendship Hospital, Capital Medical University, Beijing, China
| | - Diya Wang
- Department of Biomedical Engineering, Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China
| |
Collapse
|
6
|
Shamir SB, Sasson AL, Margolies LR, Mendelson DS. New Frontiers in Breast Cancer Imaging: The Rise of AI. Bioengineering (Basel) 2024; 11:451. [PMID: 38790318 PMCID: PMC11117903 DOI: 10.3390/bioengineering11050451] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Revised: 04/18/2024] [Accepted: 04/26/2024] [Indexed: 05/26/2024] Open
Abstract
Artificial intelligence (AI) has been implemented in multiple fields of medicine to assist in the diagnosis and treatment of patients. AI implementation in radiology, more specifically for breast imaging, has advanced considerably. Breast cancer is one of the most important causes of cancer mortality among women, and there has been increased attention towards creating more efficacious methods for breast cancer detection utilizing AI to improve radiologist accuracy and efficiency to meet the increasing demand of our patients. AI can be applied to imaging studies to improve image quality, increase interpretation accuracy, and improve time efficiency and cost efficiency. AI applied to mammography, ultrasound, and MRI allows for improved cancer detection and diagnosis while decreasing intra- and interobserver variability. The synergistic effect between a radiologist and AI has the potential to improve patient care in underserved populations with the intention of providing quality and equitable care for all. Additionally, AI has allowed for improved risk stratification. Further, AI application can have treatment implications as well by identifying upstage risk of ductal carcinoma in situ (DCIS) to invasive carcinoma and by better predicting individualized patient response to neoadjuvant chemotherapy. AI has potential for advancement in pre-operative 3-dimensional models of the breast as well as improved viability of reconstructive grafts.
Collapse
Affiliation(s)
- Stephanie B. Shamir
- Department of Diagnostic, Molecular and Interventional Radiology, The Icahn School of Medicine at Mount Sinai, 1 Gustave L. Levy Pl, New York, NY 10029, USA
| | | | | | | |
Collapse
|
7
|
Mundinger A, Mundinger C. Artificial Intelligence in Senology - Where Do We Stand and What Are the Future Horizons? Eur J Breast Health 2024; 20:73-80. [PMID: 38571686 PMCID: PMC10985572 DOI: 10.4274/ejbh.galenos.2024.2023-12-13] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2023] [Accepted: 01/16/2024] [Indexed: 04/05/2024]
Abstract
Artificial Intelligence (AI) is defined as the simulation of human intelligence by a digital computer or robotic system and has become a hype in current conversations. A subcategory of AI is deep learning, which is based on complex artificial neural networks that mimic the principles of human synaptic plasticity and layered brain architectures, and uses large-scale data processing. AI-based image analysis in breast screening programmes has shown non-inferior sensitivity, reduces workload by up to 70% by pre-selecting normal cases, and reduces recall by 25% compared to human double reading. Natural language programs such as ChatGPT (OpenAI) achieve 80% and higher accuracy in advising and decision making compared to the gold standard: human judgement. This does not yet meet the necessary requirements for medical products in terms of patient safety. The main advantage of AI is that it can perform routine but complex tasks much faster and with fewer errors than humans. The main concerns in healthcare are the stability of AI systems, cybersecurity, liability and transparency. More widespread use of AI could affect human jobs in healthcare and increase technological dependency. AI in senology is just beginning to evolve towards better forms with improved properties. Responsible training of AI systems with meaningful raw data and scientific studies to analyse their performance in the real world are necessary to keep AI on track. To mitigate significant risks, it will be necessary to balance active promotion and development of quality-assured AI systems with careful regulation. AI regulation has only recently included in transnational legal frameworks, as the European Union's AI Act was the first comprehensive legal framework to be published, in December 2023. Unacceptable AI systems will be banned if they are deemed to pose a clear threat to people's fundamental rights. Using AI and combining it with human wisdom, empathy and affection will be the method of choice for further, fruitful development of tomorrow's senology.
Collapse
Affiliation(s)
- Alexander Mundinger
- Breast Imaging and Interventions; Breast Centre Osnabrück; FHH Niels-Stensen-Kliniken; Franziskus-Hospital Harderberg, Georgsmarienhütte, Germany
| | - Carolin Mundinger
- Department of Behavioural Biology, Institute for Neuro- and Behavioural Biology, University of Muenster, Muenster, Germany
| |
Collapse
|
8
|
Fusco R, Granata V, Simonetti I, Setola SV, Iasevoli MAD, Tovecci F, Lamanna CMP, Izzo F, Pecori B, Petrillo A. An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies. Curr Oncol 2024; 31:403-424. [PMID: 38248112 PMCID: PMC10814313 DOI: 10.3390/curroncol31010027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2023] [Revised: 01/04/2024] [Accepted: 01/09/2024] [Indexed: 01/23/2024] Open
Abstract
The aim of this informative review was to investigate the application of radiomics in cancer imaging and to summarize the results of recent studies to support oncological imaging with particular attention to breast cancer, rectal cancer and primitive and secondary liver cancer. This review also aims to provide the main findings, challenges and limitations of the current methodologies. Clinical studies published in the last four years (2019-2022) were included in this review. Among the 19 studies analyzed, none assessed the differences between scanners and vendor-dependent characteristics, collected images of individuals at additional points in time, performed calibration statistics, represented a prospective study performed and registered in a study database, conducted a cost-effectiveness analysis, reported on the cost-effectiveness of the clinical application, or performed multivariable analysis with also non-radiomics features. Seven studies reached a high radiomic quality score (RQS), and seventeen earned additional points by using validation steps considering two datasets from two distinct institutes and open science and data domains (radiomics features calculated on a set of representative ROIs are open source). The potential of radiomics is increasingly establishing itself, even if there are still several aspects to be evaluated before the passage of radiomics into routine clinical practice. There are several challenges, including the need for standardization across all stages of the workflow and the potential for cross-site validation using real-world heterogeneous datasets. Moreover, multiple centers and prospective radiomics studies with more samples that add inter-scanner differences and vendor-dependent characteristics will be needed in the future, as well as the collecting of images of individuals at additional time points, the reporting of calibration statistics and the performing of prospective studies registered in a study database.
Collapse
Affiliation(s)
- Roberta Fusco
- Medical Oncology Division, Igea SpA, 80013 Naples, Italy;
| | - Vincenza Granata
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy (S.V.S.); (M.A.D.I.); (F.T.); (C.M.P.L.); (A.P.)
| | - Igino Simonetti
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy (S.V.S.); (M.A.D.I.); (F.T.); (C.M.P.L.); (A.P.)
| | - Sergio Venanzio Setola
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy (S.V.S.); (M.A.D.I.); (F.T.); (C.M.P.L.); (A.P.)
| | - Maria Assunta Daniela Iasevoli
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy (S.V.S.); (M.A.D.I.); (F.T.); (C.M.P.L.); (A.P.)
| | - Filippo Tovecci
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy (S.V.S.); (M.A.D.I.); (F.T.); (C.M.P.L.); (A.P.)
| | - Ciro Michele Paolo Lamanna
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy (S.V.S.); (M.A.D.I.); (F.T.); (C.M.P.L.); (A.P.)
| | - Francesco Izzo
- Division of Epatobiliary Surgical Oncology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy;
| | - Biagio Pecori
- Division of Radiation Protection and Innovative Technology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy;
| | - Antonella Petrillo
- Division of Radiology, Istituto Nazionale Tumori IRCCS Fondazione Pascale—IRCCS di Napoli, 80131 Naples, Italy (S.V.S.); (M.A.D.I.); (F.T.); (C.M.P.L.); (A.P.)
| |
Collapse
|
9
|
Adam R, Dell'Aquila K, Hodges L, Maldjian T, Duong TQ. Deep learning applications to breast cancer detection by magnetic resonance imaging: a literature review. Breast Cancer Res 2023; 25:87. [PMID: 37488621 PMCID: PMC10367400 DOI: 10.1186/s13058-023-01687-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 07/11/2023] [Indexed: 07/26/2023] Open
Abstract
Deep learning analysis of radiological images has the potential to improve diagnostic accuracy of breast cancer, ultimately leading to better patient outcomes. This paper systematically reviewed the current literature on deep learning detection of breast cancer based on magnetic resonance imaging (MRI). The literature search was performed from 2015 to Dec 31, 2022, using Pubmed. Other database included Semantic Scholar, ACM Digital Library, Google search, Google Scholar, and pre-print depositories (such as Research Square). Articles that were not deep learning (such as texture analysis) were excluded. PRISMA guidelines for reporting were used. We analyzed different deep learning algorithms, methods of analysis, experimental design, MRI image types, types of ground truths, sample sizes, numbers of benign and malignant lesions, and performance in the literature. We discussed lessons learned, challenges to broad deployment in clinical practice and suggested future research directions.
Collapse
Affiliation(s)
- Richard Adam
- Department of Radiology, Albert Einstein College of Medicine and the Montefiore Medical Center, 1300 Morris Park Avenue, Bronx, NY, 10461, USA
| | - Kevin Dell'Aquila
- Department of Radiology, Albert Einstein College of Medicine and the Montefiore Medical Center, 1300 Morris Park Avenue, Bronx, NY, 10461, USA
| | - Laura Hodges
- Department of Radiology, Albert Einstein College of Medicine and the Montefiore Medical Center, 1300 Morris Park Avenue, Bronx, NY, 10461, USA
| | - Takouhie Maldjian
- Department of Radiology, Albert Einstein College of Medicine and the Montefiore Medical Center, 1300 Morris Park Avenue, Bronx, NY, 10461, USA
| | - Tim Q Duong
- Department of Radiology, Albert Einstein College of Medicine and the Montefiore Medical Center, 1300 Morris Park Avenue, Bronx, NY, 10461, USA.
| |
Collapse
|
10
|
Ozcan BB, Patel BK, Banerjee I, Dogan BE. Artificial Intelligence in Breast Imaging: Challenges of Integration Into Clinical Practice. JOURNAL OF BREAST IMAGING 2023; 5:248-257. [PMID: 38416888 DOI: 10.1093/jbi/wbad007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Indexed: 03/01/2024]
Abstract
Artificial intelligence (AI) in breast imaging is a rapidly developing field with promising results. Despite the large number of recent publications in this field, unanswered questions have led to limited implementation of AI into daily clinical practice for breast radiologists. This paper provides an overview of the key limitations of AI in breast imaging including, but not limited to, limited numbers of FDA-approved algorithms and annotated data sets with histologic ground truth; concerns surrounding data privacy, security, algorithm transparency, and bias; and ethical issues. Ultimately, the successful implementation of AI into clinical care will require thoughtful action to address these challenges, transparency, and sharing of AI implementation workflows, limitations, and performance metrics within the breast imaging community and other end-users.
Collapse
Affiliation(s)
- B Bersu Ozcan
- The University of Texas Southwestern Medical Center, Department of Radiology, Dallas, TX, USA
| | | | - Imon Banerjee
- Mayo Clinic, Department of Radiology, Scottsdale, AZ, USA
| | - Basak E Dogan
- The University of Texas Southwestern Medical Center, Department of Radiology, Dallas, TX, USA
| |
Collapse
|
11
|
Vedantham S, Shazeeb MS, Chiang A, Vijayaraghavan GR. Artificial Intelligence in Breast X-Ray Imaging. Semin Ultrasound CT MR 2023; 44:2-7. [PMID: 36792270 PMCID: PMC9932302 DOI: 10.1053/j.sult.2022.12.002] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
This topical review is focused on the clinical breast x-ray imaging applications of the rapidly evolving field of artificial intelligence (AI). The range of AI applications is broad. AI can be used for breast cancer risk estimation that could allow for tailoring the screening interval and the protocol that are woman-specific and for triaging the screening exams. It also can serve as a tool to aid in the detection and diagnosis for improved sensitivity and specificity and as a tool to reduce radiologists' reading time. AI can also serve as a potential second 'reader' during screening interpretation. During the last decade, numerous studies have shown the potential of AI-assisted interpretation of mammography and to a lesser extent digital breast tomosynthesis; however, most of these studies are retrospective in nature. There is a need for prospective clinical studies to evaluate these technologies to better understand their real-world efficacy. Further, there are ethical, medicolegal, and liability concerns that need to be considered prior to the routine use of AI in the breast imaging clinic.
Collapse
Affiliation(s)
| | | | - Alan Chiang
- Department of Medical Imaging, University of Arizona, Tucson, AZ
| | | |
Collapse
|
12
|
Bahl M. Updates in Artificial Intelligence for Breast Imaging. Semin Roentgenol 2022; 57:160-167. [PMID: 35523530 PMCID: PMC9077006 DOI: 10.1053/j.ro.2021.12.005] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2021] [Accepted: 12/23/2021] [Indexed: 12/19/2022]
Abstract
Artificial intelligence (AI) for breast imaging has rapidly moved from the experimental to implementation phase. As of this writing, Food and Drug Administration (FDA)-approved mammographic applications are available for triage, lesion detection and classification, and breast density assessment. For sonography and MRI, FDA-approved applications are available for lesion classification. Numerous other interpretive and noninterpretive AI applications are in the development phase. This article reviews AI applications for mammography, sonography, and MRI that are currently available for clinical use. In addition, clinical implementation and the future of AI for breast imaging are discussed.
Collapse
Affiliation(s)
- Manisha Bahl
- Massachusetts General Hospital, Department of Radiology, Boston, MA.
| |
Collapse
|
13
|
Zhu Y, Zhan W, Jia X, Liu J, Zhou J. Clinical Application of Computer-Aided Diagnosis for Breast Ultrasonography: Factors That Lead to Discordant Results in Radial and Antiradial Planes. Cancer Manag Res 2022; 14:751-760. [PMID: 35237075 PMCID: PMC8882474 DOI: 10.2147/cmar.s348463] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Accepted: 01/27/2022] [Indexed: 01/30/2023] Open
Affiliation(s)
- Ying Zhu
- Department of Ultrasound, Shanghai Ruijin Hospital Affiliated to Medical School of Shanghai Jiaotong University, Shanghai, People’s Republic of China
| | - Weiwei Zhan
- Department of Ultrasound, Shanghai Ruijin Hospital Affiliated to Medical School of Shanghai Jiaotong University, Shanghai, People’s Republic of China
| | - Xiaohong Jia
- Department of Ultrasound, Shanghai Ruijin Hospital Affiliated to Medical School of Shanghai Jiaotong University, Shanghai, People’s Republic of China
| | - Juan Liu
- Department of Ultrasound, Shanghai Ruijin Hospital Affiliated to Medical School of Shanghai Jiaotong University, Shanghai, People’s Republic of China
| | - Jianqiao Zhou
- Department of Ultrasound, Shanghai Ruijin Hospital Affiliated to Medical School of Shanghai Jiaotong University, Shanghai, People’s Republic of China
- Correspondence: Jianqiao Zhou, Department of Ultrasound, Shanghai Ruijin Hospital Affiliated to Medical School of Shanghai Jiaotong University, 197 Ruijin Er Road, Shanghai, 200025, People’s Republic of China, Email
| |
Collapse
|
14
|
A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of Ultrasound-Detected Suspicious Breast Masses. Diagnostics (Basel) 2022; 12:diagnostics12010187. [PMID: 35054354 PMCID: PMC8774734 DOI: 10.3390/diagnostics12010187] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2021] [Revised: 01/07/2022] [Accepted: 01/10/2022] [Indexed: 01/01/2023] Open
Abstract
We developed a machine learning model based on radiomics to predict the BI-RADS category of ultrasound-detected suspicious breast lesions and support medical decision-making towards short-interval follow-up versus tissue sampling. From a retrospective 2015–2019 series of ultrasound-guided core needle biopsies performed by four board-certified breast radiologists using six ultrasound systems from three vendors, we collected 821 images of 834 suspicious breast masses from 819 patients, 404 malignant and 430 benign according to histopathology. A balanced image set of biopsy-proven benign (n = 299) and malignant (n = 299) lesions was used for training and cross-validation of ensembles of machine learning algorithms supervised during learning by histopathological diagnosis as a reference standard. Based on a majority vote (over 80% of the votes to have a valid prediction of benign lesion), an ensemble of support vector machines showed an ability to reduce the biopsy rate of benign lesions by 15% to 18%, always keeping a sensitivity over 94%, when externally tested on 236 images from two image sets: (1) 123 lesions (51 malignant and 72 benign) obtained from two ultrasound systems used for training and from a different one, resulting in a positive predictive value (PPV) of 45.9% (95% confidence interval 36.3–55.7%) versus a radiologists’ PPV of 41.5% (p < 0.005), combined with a 98.0% sensitivity (89.6–99.9%); (2) 113 lesions (54 malignant and 59 benign) obtained from two ultrasound systems from vendors different from those used for training, resulting into a 50.5% PPV (40.4–60.6%) versus a radiologists’ PPV of 47.8% (p < 0.005), combined with a 94.4% sensitivity (84.6–98.8%). Errors in BI-RADS 3 category (i.e., assigned by the model as BI-RADS 4) were 0.8% and 2.7% in the Testing set I and II, respectively. The board-certified breast radiologist accepted the BI-RADS classes assigned by the model in 114 masses (92.7%) and modified the BI-RADS classes of 9 breast masses (7.3%). In six of nine cases, the model performed better than the radiologist did, since it assigned a BI-RADS 3 classification to histopathology-confirmed benign masses that were classified as BI-RADS 4 by the radiologist.
Collapse
|