1
|
Anari PY, Lay N, Zahergivar A, Firouzabadi FD, Chaurasia A, Golagha M, Singh S, Homayounieh F, Obiezu F, Harmon S, Turkbey E, Merino M, Jones EC, Ball MW, Linehan WM, Turkbey B, Malayeri AA. Deep learning algorithm (YOLOv7) for automated renal mass detection on contrast-enhanced MRI: a 2D and 2.5D evaluation of results. Abdom Radiol (NY) 2024; 49:1194-1201. [PMID: 38368481 DOI: 10.1007/s00261-023-04172-w] [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: 09/29/2023] [Revised: 12/17/2023] [Accepted: 12/19/2023] [Indexed: 02/19/2024]
Abstract
INTRODUCTION Accurate diagnosis and treatment of kidney tumors greatly benefit from automated solutions for detection and classification on MRI. In this study, we explore the application of a deep learning algorithm, YOLOv7, for detecting kidney tumors on contrast-enhanced MRI. MATERIAL AND METHODS We assessed the performance of YOLOv7 tumor detection on excretory phase MRIs in a large institutional cohort of patients with RCC. Tumors were segmented on MRI using ITK-SNAP and converted to bounding boxes. The cohort was randomly divided into ten benchmarks for training and testing the YOLOv7 algorithm. The model was evaluated using both 2-dimensional and a novel in-house developed 2.5-dimensional approach. Performance measures included F1, Positive Predictive Value (PPV), Sensitivity, F1 curve, PPV-Sensitivity curve, Intersection over Union (IoU), and mean average PPV (mAP). RESULTS A total of 326 patients with 1034 tumors with 7 different pathologies were analyzed across ten benchmarks. The average 2D evaluation results were as follows: Positive Predictive Value (PPV) of 0.69 ± 0.05, sensitivity of 0.39 ± 0.02, and F1 score of 0.43 ± 0.03. For the 2.5D evaluation, the average results included a PPV of 0.72 ± 0.06, sensitivity of 0.61 ± 0.06, and F1 score of 0.66 ± 0.04. The best model performance demonstrated a 2.5D PPV of 0.75, sensitivity of 0.69, and F1 score of 0.72. CONCLUSION Using computer vision for tumor identification is a cutting-edge and rapidly expanding subject. In this work, we showed that YOLOv7 can be utilized in the detection of kidney cancers.
Collapse
Affiliation(s)
- Pouria Yazdian Anari
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA
| | - Nathan Lay
- Artificial Intelligence Resource, National Institutes of Health, Bethesda, USA
| | - Aryan Zahergivar
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA
| | - Fatemeh Dehghani Firouzabadi
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA
| | - Aditi Chaurasia
- Urology Oncology Branch, National Cancer Institutes, National Institutes of Health, Bethesda, USA
| | - Mahshid Golagha
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA
| | - Shiva Singh
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA
| | | | - Fiona Obiezu
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA
| | - Stephanie Harmon
- Artificial Intelligence Resource, National Institutes of Health, Bethesda, USA
| | - Evrim Turkbey
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA
| | - Maria Merino
- Pathology Department, National Cancer Institutes, National Institutes of Health, Bethesda, USA
| | - Elizabeth C Jones
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA
| | - Mark W Ball
- Urology Oncology Branch, National Cancer Institutes, National Institutes of Health, Bethesda, USA
| | - W Marston Linehan
- Urology Oncology Branch, National Cancer Institutes, National Institutes of Health, Bethesda, USA
| | - Baris Turkbey
- Artificial Intelligence Resource, National Institutes of Health, Bethesda, USA
| | - Ashkan A Malayeri
- Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA.
| |
Collapse
|
2
|
Guha S, Ibrahim A, Wu Q, Geng P, Chou Y, Yang H, Ma J, Lu L, Wang D, Schwartz LH, Xie CM, Zhao B. Machine learning-based identification of contrast-enhancement phase of computed tomography scans. PLoS One 2024; 19:e0294581. [PMID: 38306329 PMCID: PMC10836663 DOI: 10.1371/journal.pone.0294581] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2023] [Accepted: 11/04/2023] [Indexed: 02/04/2024] Open
Abstract
Contrast-enhanced computed tomography scans (CECT) are routinely used in the evaluation of different clinical scenarios, including the detection and characterization of hepatocellular carcinoma (HCC). Quantitative medical image analysis has been an exponentially growing scientific field. A number of studies reported on the effects of variations in the contrast enhancement phase on the reproducibility of quantitative imaging features extracted from CT scans. The identification and labeling of phase enhancement is a time-consuming task, with a current need for an accurate automated labeling algorithm to identify the enhancement phase of CT scans. In this study, we investigated the ability of machine learning algorithms to label the phases in a dataset of 59 HCC patients scanned with a dynamic contrast-enhanced CT protocol. The ground truth labels were provided by expert radiologists. Regions of interest were defined within the aorta, the portal vein, and the liver. Mean density values were extracted from those regions of interest and used for machine learning modeling. Models were evaluated using accuracy, the area under the curve (AUC), and Matthew's correlation coefficient (MCC). We tested the algorithms on an external dataset (76 patients). Our results indicate that several supervised learning algorithms (logistic regression, random forest, etc.) performed similarly, and our developed algorithms can accurately classify the phase of contrast enhancement.
Collapse
Affiliation(s)
- Siddharth Guha
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | - Abdalla Ibrahim
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | - Qian Wu
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | - Pengfei Geng
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | - Yen Chou
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | - Hao Yang
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | - Jingchen Ma
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | - Lin Lu
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | - Delin Wang
- Sun Yat-Sen University Cancer Center, Guangzhou, China
| | - Lawrence H. Schwartz
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| | | | - Binsheng Zhao
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States of America
| |
Collapse
|
3
|
Yilmaz EC, Belue MJ, Turkbey B, Reinhold C, Choyke PL. A Brief Review of Artificial Intelligence in Genitourinary Oncological Imaging. Can Assoc Radiol J 2023; 74:534-547. [PMID: 36515576 DOI: 10.1177/08465371221135782] [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] [Indexed: 12/15/2022] Open
Abstract
Genitourinary (GU) system is among the most commonly involved malignancy sites in the human body. Imaging plays a crucial role not only in diagnosis of cancer but also in disease management and its prognosis. However, interpretation of conventional imaging methods such as CT or MR imaging (MRI) usually demonstrates variability across different readers and institutions. Artificial intelligence (AI) has emerged as a promising technology that could improve the patient care by providing helpful input to human readers through lesion detection algorithms and lesion classification systems. Moreover, the robustness of these models may be valuable in automating time-consuming tasks such as organ and lesion segmentations. Herein, we review the current state of imaging and existing challenges in GU malignancies, particularly for cancers of prostate, kidney and bladder; and briefly summarize the recent AI-based solutions to these challenges.
Collapse
Affiliation(s)
- Enis C Yilmaz
- Molecular Imaging Branch, National Cancer Institute, NIH, Bethesda, MD, USA
| | - Mason J Belue
- Molecular Imaging Branch, National Cancer Institute, NIH, Bethesda, MD, USA
| | - Baris Turkbey
- Molecular Imaging Branch, National Cancer Institute, NIH, Bethesda, MD, USA
| | - Caroline Reinhold
- McGill University Health Center, McGill University, Montreal, Canada
| | - Peter L Choyke
- Molecular Imaging Branch, National Cancer Institute, NIH, Bethesda, MD, USA
| |
Collapse
|
4
|
Shamija Sherryl RMR, Jaya T. Semantic Multiclass Segmentation and Classification of Kidney Lesions. Neural Process Lett 2022. [DOI: 10.1007/s11063-022-11034-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/10/2022]
|
5
|
Radiology Imaging Scans for Early Diagnosis of Kidney Tumors: A Review of Data Analytics-Based Machine Learning and Deep Learning Approaches. BIG DATA AND COGNITIVE COMPUTING 2022. [DOI: 10.3390/bdcc6010029] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
Plenty of disease types exist in world communities that can be explained by humans’ lifestyles or the economic, social, genetic, and other factors of the country of residence. Recently, most research has focused on studying common diseases in the population to reduce death risks, take the best procedure for treatment, and enhance the healthcare level of the communities. Kidney Disease is one of the common diseases that have affected our societies. Sectionicularly Kidney Tumors (KT) are the 10th most prevalent tumor for men and women worldwide. Overall, the lifetime likelihood of developing a kidney tumor for males is about 1 in 466 (2.02 percent) and it is around 1 in 80 (1.03 percent) for females. Still, more research is needed on new diagnostic, early, and innovative methods regarding finding an appropriate treatment method for KT. Compared to the tedious and time-consuming traditional diagnosis, automatic detection algorithms of machine learning can save diagnosis time, improve test accuracy, and reduce costs. Previous studies have shown that deep learning can play a role in dealing with complex tasks, diagnosis and segmentation, and classification of Kidney Tumors, one of the most malignant tumors. The goals of this review article on deep learning in radiology imaging are to summarize what has already been accomplished, determine the techniques used by the researchers in previous years in diagnosing Kidney Tumors through medical imaging, and identify some promising future avenues, whether in terms of applications or technological developments, as well as identifying common problems, describing ways to expand the data set, summarizing the knowledge and best practices, and determining remaining challenges and future directions.
Collapse
|
6
|
Lee S, Summers RM. Clinical Artificial Intelligence Applications in Radiology: Chest and Abdomen. Radiol Clin North Am 2021; 59:987-1002. [PMID: 34689882 DOI: 10.1016/j.rcl.2021.07.001] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
Organ segmentation, chest radiograph classification, and lung and liver nodule detections are some of the popular artificial intelligence (AI) tasks in chest and abdominal radiology due to the wide availability of public datasets. AI algorithms have achieved performance comparable to humans in less time for several organ segmentation tasks, and some lesion detection and classification tasks. This article introduces the current published articles of AI applied to chest and abdominal radiology, including organ segmentation, lesion detection, classification, and predicting prognosis.
Collapse
Affiliation(s)
- Sungwon Lee
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Building 10, Room 1C224D, 10 Center Drive, Bethesda, MD 20892-1182, USA
| | - Ronald M Summers
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Building 10, Room 1C224D, 10 Center Drive, Bethesda, MD 20892-1182, USA.
| |
Collapse
|
7
|
Lee M, Wei S, Anaokar J, Uzzo R, Kutikov A. Kidney cancer management 3.0: can artificial intelligence make us better? Curr Opin Urol 2021; 31:409-415. [PMID: 33882560 DOI: 10.1097/mou.0000000000000881] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
PURPOSE OF REVIEW Artificial intelligence holds tremendous potential for disrupting clinical medicine. Here we review the current role of artificial intelligence in the kidney cancer space. RECENT FINDINGS Machine learning and deep learning algorithms have been developed using information extracted from radiomic, histopathologic, and genomic datasets of patients with renal masses. SUMMARY Although artificial intelligence applications in medicine are still in their infancy, they already hold immediate promise to improve accuracy of renal mass characterization, grade, and prognostication. As algorithms become more robust and generalizable, artificial intelligence is poised to significantly disrupt kidney cancer care.
Collapse
Affiliation(s)
| | | | - Jordan Anaokar
- Department of Diagnostic Imaging, Fox Chase Cancer Center, Philadelphia, Pennsylvania, USA
| | | | | |
Collapse
|
8
|
Wilson MP, Patel D, Katlariwala P, Low G. A review of clinical and MR imaging features of renal lipid-poor angiomyolipomas. Abdom Radiol (NY) 2021; 46:2072-2078. [PMID: 33151360 DOI: 10.1007/s00261-020-02835-6] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2020] [Revised: 10/13/2020] [Accepted: 10/20/2020] [Indexed: 12/19/2022]
Abstract
BACKGROUND Lipid-poor angiomyolipomas (lpAMLs) constitute up to 5% of renal angiomyolipomas and are challenging to differentiate from malignant renal lesions on imaging alone. This review aims to identify clinical and MRI features which can be utilized to improve specificity and diagnostic accuracy for detecting lpAMLs in patients being considered for active surveillance rather than intervention. FINDINGS Young age, female sex, and small lesion size are associated with lpAMLs in studies evaluating indeterminate renal lesions. The accuracy of criteria using T2-weighted imaging, diffusion-weighted imaging, chemical shift imaging, dynamic contrast enhancement, multiparametric imaging, and radiomics are reviewed. Low T2 signal intensity is a particularly important MRI feature for lpAML. In studies with low T2 signal intensity, homogeneous early enhancement is a typical feature with an arterial-to-delay enhancement ratio > 1.5. Intratumoral hemorrhage with decrease in signal intensity on in-phase chemical shift imaging may be particularly useful for differentiating papillary renal cell carcinomas from lpAMLs in low T2 signal intensity lesions. Combining clinical and multiparametric MRI features can result in near-perfect specificity for lpAML. In select patients, clinical and MRI features can result in a high specificity and diagnostic accuracy for lpAMLs. These lesions can be considered for active surveillance rather than invasive diagnostic and therapeutic procedures such as biopsy or surgery.
Collapse
|
9
|
Butwick AJ, McCarthy RJ. Machine learning: the next frontier in obstetric anesthesiology? Int J Obstet Anesth 2020; 45:8-10. [PMID: 33129657 DOI: 10.1016/j.ijoa.2020.09.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/14/2020] [Revised: 08/25/2020] [Accepted: 09/06/2020] [Indexed: 11/15/2022]
Affiliation(s)
- A J Butwick
- Department of Anesthesiology, Perioperative, and Pain Medicine, Stanford University School of Medicine Stanford, CA, USA.
| | - R J McCarthy
- Department of Anesthesiology, Rush University, Jelke, Chicago, IL, USA
| |
Collapse
|