1
|
Anari PY, Lay N, Gopal N, Chaurasia A, Samimi S, Harmon S, Firouzabadi FD, Merino MJ, Wakim P, Turkbey E, Jones EC, Ball MW, Turkbey B, Linehan WM, Malayeri AA. An MRI-based radiomics model to predict clear cell renal cell carcinoma growth rate classes in patients with von Hippel-Lindau syndrome. Abdom Radiol (NY) 2022; 47:3554-3562. [PMID: 35869307 PMCID: PMC10645140 DOI: 10.1007/s00261-022-03610-5] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2022] [Revised: 06/28/2022] [Accepted: 07/03/2022] [Indexed: 01/18/2023]
Abstract
PURPOSE Upfront knowledge of tumor growth rates of clear cell renal cell carcinoma in von Hippel-Lindau syndrome (VHL) patients can allow for a more personalized approach to either surveillance imaging frequency or surgical planning. In this study, we implement a machine learning algorithm utilizing radiomic features of renal tumors identified on baseline magnetic resonance imaging (MRI) in VHL patients to predict the volumetric growth rate category of these tumors. MATERIALS AND METHODS A total of 73 VHL patients with 173 pathologically confirmed Clear Cell Renal Cell Carcinoma (ccRCCs) underwent MRI at least at two different time points between 2015 and 2021. Each tumor was manually segmented in excretory phase contrast T1 weighed MRI and co-registered on pre-contrast, corticomedullary and nephrographic phases. Radiomic features and volumetric data from each tumor were extracted using the PyRadiomics library in Python (4544 total features). Tumor doubling time (DT) was calculated and patients were divided into two groups: DT < = 1 year and DT > 1 year. Random forest classifier (RFC) was used to predict the DT category. To measure prediction performance, the cohort was randomly divided into 100 training and test sets (80% and 20%). Model performance was evaluated using area under curve of receiver operating characteristic curve (AUC-ROC), as well as accuracy, F1, precision and recall, reported as percentages with 95% confidence intervals (CIs). RESULTS The average age of patients was 47.2 ± 10.3 years. Mean interval between MRIs for each patient was 1.3 years. Tumors included in this study were categorized into 155 Grade 2; 16 Grade 3; and 2 Grade 4. Mean accuracy of RFC model was 79.0% [67.4-90.6] and mean AUC-ROC of 0.795 [0.608-0.988]. The accuracy for predicting DT classes was not different among the MRI sequences (P-value = 0.56). CONCLUSION Here we demonstrate the utility of machine learning in accurately predicting the renal tumor growth rate category of VHL patients based on radiomic features extracted from different T1-weighted pre- and post-contrast MRI sequences.
Collapse
Affiliation(s)
- Pouria Yazdian Anari
- Radiology and Imaging Sciences, Clinical Center (CC), National Institutes of Health, Bethesda, MD, USA
| | - Nathan Lay
- Artificial Intelligence Resource, Clinical Center, National Institutes of Health, Bethesda, MD, USA
| | - Nikhil Gopal
- Urologic Oncology Branch, Clinical Center, National Cancer Institute (NCI), National Institutes of Health, Bethesda, MD, USA
| | - Aditi Chaurasia
- Radiology and Imaging Sciences, Clinical Center (CC), National Institutes of Health, Bethesda, MD, USA
| | - Safa Samimi
- Radiology and Imaging Sciences, Clinical Center (CC), National Institutes of Health, Bethesda, MD, USA
| | - Stephanie Harmon
- Artificial Intelligence Resource, Clinical Center, National Institutes of Health, Bethesda, MD, USA
| | | | - Maria J Merino
- Pathology Department, Clinical Center, National Cancer Institutes (NCI), National Institutes of Health, Bethesda, MD, USA
| | - Paul Wakim
- Biostatistics and Clinical Epidemiology Service, Clinical Center, National Institutes of Health, Bethesda, MD, USA
| | - Evrim Turkbey
- Radiology and Imaging Sciences, Clinical Center (CC), National Institutes of Health, Bethesda, MD, USA
| | - Elizabeth C Jones
- Radiology and Imaging Sciences, Clinical Center (CC), National Institutes of Health, Bethesda, MD, USA
| | - Mark W Ball
- Urologic Oncology Branch, Clinical Center, National Cancer Institute (NCI), National Institutes of Health, Bethesda, MD, USA
| | - Baris Turkbey
- Artificial Intelligence Resource, Clinical Center, National Institutes of Health, Bethesda, MD, USA
| | - W Marston Linehan
- Urologic Oncology Branch, Clinical Center, National Cancer Institute (NCI), National Institutes of Health, Bldg. 10, Room 2 W-5940 and Room 1-5940, 10 Center Drive, Bethesda, MD, 20892, USA.
| | - Ashkan A Malayeri
- Radiology and Imaging Sciences, Clinical Center (CC), National Institutes of Health, 10 Center Drive, Bethesda, MD, 20892-1109, USA.
| |
Collapse
|
2
|
de Souza PL, Aslan P, Clark W, Nour R, de Silva S. RESIRT: A Phase 1 Study of Selective Internal Radiation Therapy Using Yttrium-90 Resin Microspheres in Patients With Primary Renal Cell Carcinoma. Clin Genitourin Cancer 2022; 20:442-451. [PMID: 35710899 DOI: 10.1016/j.clgc.2022.05.006] [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: 09/17/2021] [Revised: 05/13/2022] [Accepted: 05/13/2022] [Indexed: 12/24/2022]
Abstract
INTRODUCTION Selective internal radiation therapy (SIRT) is a potential treatment of primary renal cell carcinoma (RCC) deemed unsuitable for conventional therapy. RESIRT is the first-in-human study to evaluate safety and feasibility of SIRT for primary RCC. PATIENTS AND METHODS Patients with RCC, unsuitable for, or who declined conventional therapy, were eligible. A single transfemoral micro-catheter administration of yttrium-90 (Y-90) resin microspheres (SIR-Spheres) was delivered super selectively via the renal artery to the tumour at intended radiation doses of 75, 100, 150, 200, 300 Gy and a final cohort with a procedural endpoint of "imminent stasis," in a dose-escalation design. Post-SIRT follow-up was 12 months. Study endpoints included safety and toxicity 30-days and 12-months post-SIRT and tumour response (RECIST v1.1). RESULTS In total, 21 patients were enrolled, mean (SD) age was 75 (9.3) years, WHO performance status was 0 in 81%, 12 (57%) had stage 3 chronic kidney disease, and 7 (33%) had prior contralateral nephrectomy. Overall, 71% of patients completed 12 months of follow-up. Intended doses were delivered without any dose-limiting toxicity. Seventeen out of 21 (81%) patients experienced an adverse event (AE) from any cause within 30 days post-SIRT; all SIRT-related AEs were grade 1 to 2. Best overall tumour responses were partial response 1/21 (4.8%), stable disease 19/21 (90.5%) and progressive disease 1/21 (4.8%). CONCLUSION This study demonstrated good tolerability of SIRT at all dose levels including "imminent stasis" in treating primary tumours in RCC patients otherwise unsuitable for conventional therapy. SIRT with Y-90 resin microspheres may be a feasible treatment option for RCC.
Collapse
Affiliation(s)
- Paul L de Souza
- University of Western Sydney School of Medicine, Sydney, Australia.
| | - Peter Aslan
- Department of Urology, St George Hospital, Sydney, Australia
| | - William Clark
- Department of Interventional Radiology, St. George Private Hospital, Sydney, Australia
| | - Ramy Nour
- Department of Nuclear Medicine, St. George Hospital, Sydney, Australia
| | - Suresh de Silva
- Department of Medicine, University of New South Wales, Sydney, Australia
| |
Collapse
|
3
|
Abstract
Kidney cancer accounts for 2% of cancer related deaths. Historically, a patient with a solid renal mass would undergo surgery without biopsy given the previously low diagnostic yield of biopsy and the fear of tumor seeding. This led to a high rate of resection for benign masses. With the rising incidence of renal masses discovered on imaging, improvements in biopsy technique and advancements in pathologic evaluation of biopsy samples of renal masses, renal mass biopsy now plays an important role in selected patients with renal masses. Coaxial core needle biopsy is the preferred technique with a low rate of complications and a high diagnostic yield. This article will discuss indications, methods, utility, limitations and complications of renal mass biopsy.
Collapse
Affiliation(s)
- Keith B Quencer
- Department of Radiology, University of Utah, Salt Lake City, UT.
| |
Collapse
|
4
|
Abstract
PURPOSE OF REVIEW With this review, we describe the most recent advances in active surveillance as well as diagnosis and management of small renal masses (SRMs). RECENT FINDINGS We discuss diagnosis, differentiation of solid from cystic lesions, risk prediction and treatment of the SRM. A better understanding of the disease facilitates the use of more conservatory treatments, such as active surveillance. Active surveillance has been increasingly accepted not only for SRM, but also for larger tumors and even metastatic patients. Exiting advances in risk prediction will help us define which patients can be safely managed with active surveillance and which require immediate treatment. Meanwhile, the use of renal tumor biopsies is still an important tool for these cases. SUMMARY Active surveillance is an option for many patients with renal masses. Noninvasive methods for diagnosis and risk prediction are being developed, but meanwhile, renal tumor biopsy is a useful tool. A better understanding of the disease increases the number of patients who can undergo active surveillance fully certain of the safety of their management.
Collapse
|
5
|
The Natural History of Wilms Tumor–A Case Comparison of Two Different Tumors. Urology 2019; 130:151-154. [DOI: 10.1016/j.urology.2019.02.015] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2019] [Revised: 02/05/2019] [Accepted: 02/11/2019] [Indexed: 11/17/2022]
|
6
|
Peng X, Chen J, Wang J, Peng S, Liu S, Ma K, Zhou J, Hong B, Zhou B, Zhang J, Cai L, Gong K. Natural history of renal tumours in von Hippel-Lindau disease: a large retrospective study of Chinese patients. J Med Genet 2019; 56:380-387. [DOI: 10.1136/jmedgenet-2018-105567] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2018] [Revised: 01/10/2019] [Accepted: 01/19/2019] [Indexed: 12/20/2022]
Abstract
BackgroundHistorically, renal cell carcinoma (RCC) is one of the main causes of death in von Hippel-Lindau (VHL) disease. However, the natural history of VHL-related RCC has not been thoroughly elucidated to date. This report described the natural history of VHL-related RCC in a large Chinese VHL cohort and might be helpful in the surveillance and treatment of VHL disease.MethodsIn this retrospective study, we included 196 renal tumours from 150 patients with VHL disease. Statistical analysis was used to evaluate the influence of age of onset, sex, family history, unilateral or bilateral tumour, VHL disease type, mutation type, mutation location, and tumour size on tumour growth, metastasis and survival in patients with VHL disease.ResultsThe mean age of onset was 38.8 years, and the mean initial tumour size was 3.1 cm. The mean linear growth rate was 0.49 cm/year. Patients experienced faster tumour growth when they had later age of onset, larger initial tumour size, missense mutation, mutations locating in exon 3, and when they were not affected by cerebral or retinal haemangioblastomas. Tumours larger than 4 cm grew faster than those smaller than 4 cm. Bilateral tumours, large initial tumours, fast tumour growth and metastasis were risk factors for poor prognosis in VHL-related RCC.ConclusionThis large study demonstrated that age of onset, initial tumour size, concomitant tumours, mutation type and mutation location had an effect on growth rate in VHL-related RCC. Active surveillance may be safe for patients with tumour size less than 4 cm, which is helpful in clinical decision-making.
Collapse
|
7
|
Active Surveillance of Small Renal Masses. Urology 2019; 123:157-166. [DOI: 10.1016/j.urology.2018.09.017] [Citation(s) in RCA: 20] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2018] [Revised: 09/10/2018] [Accepted: 09/18/2018] [Indexed: 01/12/2023]
|
8
|
Sadigh G, Nandwana SB, Moreno C, Cox KL, Baumgarten DA, Switchenko J, Easter T, Applegate KE. Assessment of Added Value of Noncontrast to Contrast-Enhanced Abdominal Computed Tomography Scan for Characterization of Hypervascular Liver Metastases. Curr Probl Diagn Radiol 2016; 45:373-379. [PMID: 27397022 PMCID: PMC5655799 DOI: 10.1067/j.cpradiol.2016.05.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2016] [Accepted: 05/20/2016] [Indexed: 12/21/2022]
Abstract
Assess the added value of nonenhanced computed tomography (NECT) to contrast-enhanced CT (CECT) of the abdomen for characterization of hypervascular liver metastases and incidental findings. Institutional review board approved, Health Insurance Probability and Accountability Act compliant, retrospective study of patients with melanoma, neuroendocrine tumor, or thyroid cancer. First available triphasic abdomen CT after initial diagnosis was reviewed by 3 radiologists. The 3 most suspicious lesions were characterized on the CECT as benign or malignant and then recharacterized after reviewing the NECT with CECT. Incidental renal and adrenal lesions were characterized similarly. Diagnostic performance of CECT vs its combination with NECT was assessed. Statistical significance level was set at P < 0.05. A total of 81 patients were included (mean age = 55 years; 52% male; 64% with liver lesions; 27% and 11% with incidental renal and adrenal lesions, respectively). Percentage area under the curve and 95% CI of CECT vs combination with NECT for characterization of liver metastases was 98(94-100) vs 99(96-100) for reviewer 1 (P = 0.35), 93(86-100) vs 94(87-100) for reviewer 2 (P = 0.23), and 96(90-100) vs 99(97-100) for reviewer 3 (P = 0.32). Mean difference in area under the curve and 95% CI between 2 protocols for characterization of liver, renal, and adrenal lesions were -0.007(-0.05 to 0.04) (P = 0.63), -0.09(-0.25 to 0.07) (P = 0.22), and -0.01(-0.05 to 0.02) (P = 0.27), respectively. After addition of NECT, confidence level for lesion characterization increased 4%-15% for liver metastases, 18%-59% and 33%-67% for renal and adrenal lesions, respectively. In conclusion, while addition of NECT to CECT improved radiologist' confidence, there was no statistically significant change in characterization of hypervascular liver metastases or incidental renal and adrenal lesions.
Collapse
Affiliation(s)
- Gelareh Sadigh
- Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA.
| | - Sadhna B Nandwana
- Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA
| | - Courtney Moreno
- Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA
| | - Kelly L Cox
- Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA
| | - Deborah A Baumgarten
- Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA
| | - Jeffrey Switchenko
- Department of Biostatistics & Bioinformatics, Rollins School of Public Health, Atlanta, GA
| | - Tiffany Easter
- Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA
| | - Kimberly E Applegate
- Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA; Department of Radiology, Children's Hospital of Atlanta, Atlanta, GA
| |
Collapse
|