1
|
Jansma CYMN, Wan X, Acem I, Spaanderman DJ, Visser JJ, Hanff D, Taal W, Verhoef C, Klein S, Martin E, Starmans MPA. Preoperative Classification of Peripheral Nerve Sheath Tumors on MRI Using Radiomics. Cancers (Basel) 2024; 16:2039. [PMID: 38893158 PMCID: PMC11170987 DOI: 10.3390/cancers16112039] [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: 04/25/2024] [Revised: 05/21/2024] [Accepted: 05/24/2024] [Indexed: 06/21/2024] Open
Abstract
Malignant peripheral nerve sheath tumors (MPNSTs) are aggressive soft-tissue tumors prevalent in neurofibromatosis type 1 (NF1) patients, posing a significant risk of metastasis and recurrence. Current magnetic resonance imaging (MRI) imaging lacks decisiveness in distinguishing benign peripheral nerve sheath tumors (BPNSTs) and MPNSTs, necessitating invasive biopsies. This study aims to develop a radiomics model using quantitative imaging features and machine learning to distinguish MPNSTs from BPNSTs. Clinical data and MRIs from MPNST and BPNST patients (2000-2019) were collected at a tertiary sarcoma referral center. Lesions were manually and semi-automatically segmented on MRI scans, and radiomics features were extracted using the Workflow for Optimal Radiomics Classification (WORC) algorithm, employing automated machine learning. The evaluation was conducted using a 100× random-split cross-validation. A total of 35 MPNSTs and 74 BPNSTs were included. The T1-weighted (T1w) MRI radiomics model outperformed others with an area under the curve (AUC) of 0.71. The incorporation of additional MRI scans did not enhance performance. Combining T1w MRI with clinical features achieved an AUC of 0.74. Experienced radiologists achieved AUCs of 0.75 and 0.66, respectively. Radiomics based on T1w MRI scans and clinical features show some ability to distinguish MPNSTs from BPNSTs, potentially aiding in the management of these tumors.
Collapse
Affiliation(s)
- Christianne Y. M. N. Jansma
- Department of Surgical Oncology and Gastrointestinal Surgery, Erasmus MC Cancer Institute University Hospital Rotterdam, Dr. Molewaterplein 40, 3015 GD Rotterdam, The Netherlands; (I.A.); (C.V.)
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands;
| | - Xinyi Wan
- Department of Radiology & Nuclear Medicine, Erasmus MC Cancer Institute University Hospital Rotterdam, 3015 GD Rotterdam, The Netherlands; (X.W.); (D.J.S.); (J.J.V.); (D.H.); (S.K.); (M.P.A.S.)
| | - Ibtissam Acem
- Department of Surgical Oncology and Gastrointestinal Surgery, Erasmus MC Cancer Institute University Hospital Rotterdam, Dr. Molewaterplein 40, 3015 GD Rotterdam, The Netherlands; (I.A.); (C.V.)
| | - Douwe J. Spaanderman
- Department of Radiology & Nuclear Medicine, Erasmus MC Cancer Institute University Hospital Rotterdam, 3015 GD Rotterdam, The Netherlands; (X.W.); (D.J.S.); (J.J.V.); (D.H.); (S.K.); (M.P.A.S.)
| | - Jacob J. Visser
- Department of Radiology & Nuclear Medicine, Erasmus MC Cancer Institute University Hospital Rotterdam, 3015 GD Rotterdam, The Netherlands; (X.W.); (D.J.S.); (J.J.V.); (D.H.); (S.K.); (M.P.A.S.)
| | - David Hanff
- Department of Radiology & Nuclear Medicine, Erasmus MC Cancer Institute University Hospital Rotterdam, 3015 GD Rotterdam, The Netherlands; (X.W.); (D.J.S.); (J.J.V.); (D.H.); (S.K.); (M.P.A.S.)
| | - Walter Taal
- Department of Neurology, Erasmus MC Cancer Institute University Hospital Rotterdam, Dr. Molewaterplein 40, 3015 GD Rotterdam, The Netherlands;
| | - Cornelis Verhoef
- Department of Surgical Oncology and Gastrointestinal Surgery, Erasmus MC Cancer Institute University Hospital Rotterdam, Dr. Molewaterplein 40, 3015 GD Rotterdam, The Netherlands; (I.A.); (C.V.)
| | - Stefan Klein
- Department of Radiology & Nuclear Medicine, Erasmus MC Cancer Institute University Hospital Rotterdam, 3015 GD Rotterdam, The Netherlands; (X.W.); (D.J.S.); (J.J.V.); (D.H.); (S.K.); (M.P.A.S.)
| | - Enrico Martin
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands;
| | - Martijn P. A. Starmans
- Department of Radiology & Nuclear Medicine, Erasmus MC Cancer Institute University Hospital Rotterdam, 3015 GD Rotterdam, The Netherlands; (X.W.); (D.J.S.); (J.J.V.); (D.H.); (S.K.); (M.P.A.S.)
- Department of Pathology, Erasmus MC Cancer Institute University Hospital Rotterdam, 3015 GD Rotterdam, The Netherlands
| |
Collapse
|
2
|
Debs P, Luna R, Fayad LM, Ahlawat S. MRI features of benign peripheral nerve sheath tumors: how do sporadic and syndromic tumors differ? Skeletal Radiol 2024; 53:709-723. [PMID: 37845504 DOI: 10.1007/s00256-023-04479-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/25/2023] [Revised: 09/20/2023] [Accepted: 10/06/2023] [Indexed: 10/18/2023]
Abstract
OBJECTIVES To compare MRI features of sporadic and neurofibromatosis syndrome-related localized schwannomas and neurofibromas. METHODS In this retrospective study, our pathology database was searched for "neurofibroma" or "schwannoma" from 2014 to 2019. Exclusion criteria were lack of available MRI and intradural or plexiform tumors. Qualitative and quantitative anatomic (location, size, relationship to nerve, signal, muscle denervation) and functional (arterial enhancement, apparent diffusion-weighted coefficient) MRI features of sporadic and syndrome-related tumors were compared. Statistical significance was assumed for p < 0.05. RESULTS A total of 80 patients with 64 schwannomas (sporadic: 42 (65.6%) v. syndrome-related: 22 (34.4%)) and 19 neurofibromas (sporadic: 7 (36.8%) v. syndrome-related: 12 (41.7%)) were included. Only signal heterogeneity (T2W p=0.001, post-contrast p=0.03) and a diffused-weighted imaging target sign (p=0.04) were more frequent with schwannomas than neurofibromas. Sporadic schwannomas were similar in size to syndrome-related schwannomas (2.9±1.2cm vs. 3.7±3.2 cm, p = 0.6), but with greater heterogeneity (T2W p = 0.02, post-contrast p = 0.01). Sporadic neurofibromas were larger (4.6±1.5cm vs. 3.4±2.4 cm, p = 0.03) than syndrome-related neurofibromas, also with greater heterogeneity (T2W p=0.03, post-contrast p=0.04). Additional tumors along an affected nerve were only observed with syndrome-related tumors). There was no difference in apparent diffusion coefficient values or presence of early perfusion between sporadic and syndrome-related tumors (p > 0.05). CONCLUSIONS Although syndrome-related and sporadic schwannomas and neurofibromas overlap in their anatomic, diffusion and perfusion features, signal heterogeneity and presence of multiple lesions along a nerve are differentiating characteristics of syndrome-related tumors.
Collapse
Affiliation(s)
- Patrick Debs
- The Russell H. Morgan Department of Radiology & Radiological Science, The Johns Hopkins Medical Institutions, 600 North Wolfe Street, Baltimore, MD, 21287, USA.
| | - Rodrigo Luna
- The Russell H. Morgan Department of Radiology & Radiological Science, The Johns Hopkins Medical Institutions, 600 North Wolfe Street, Baltimore, MD, 21287, USA
| | - Laura M Fayad
- The Russell H. Morgan Department of Radiology & Radiological Science, The Johns Hopkins Medical Institutions, 600 North Wolfe Street, Baltimore, MD, 21287, USA
- Division of Orthopaedic Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Shivani Ahlawat
- The Russell H. Morgan Department of Radiology & Radiological Science, The Johns Hopkins Medical Institutions, 600 North Wolfe Street, Baltimore, MD, 21287, USA
| |
Collapse
|
3
|
Jin Z, Wang C, Wang D, Li X, Guo W, Chen T. Malignant and Benign Peripheral Nerve Sheath Tumors in a Single Center: Value of Clinical and Ultrasound Features for the Diagnosis of Malignant Peripheral Nerve Sheath Tumor Compared With Magnetic Resonance Imaging. JOURNAL OF ULTRASOUND IN MEDICINE : OFFICIAL JOURNAL OF THE AMERICAN INSTITUTE OF ULTRASOUND IN MEDICINE 2024; 43:21-31. [PMID: 37772628 DOI: 10.1002/jum.16330] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Revised: 08/16/2023] [Accepted: 08/27/2023] [Indexed: 09/30/2023]
Abstract
OBJECTIVES This study aimed to investigate the combined use of ultrasonography and clinical features for the differentiation of malignant peripheral nerve sheath tumors (MPNST) from benign peripheral nerve sheath tumors (BPNST) and to compare the efficacy of ultrasonography with that of magnetic resonance imaging (MRI). METHODS This retrospective study included 28 MPNSTs and a control group of 57 BPNSTs. All patients underwent an ultrasound scan using the Logiq E9 (GE Health Care, Milwaukee, WI) or EPIQ7 equipment (Philips Medical System, Bothell, WA). A 3.0-T MRI machine (Ingenia; Philips Healthcare, Best, the Netherlands) was used for scanning, and conventional MRI was performed on different regions based on the patient's clinical situation. The following variables were evaluated: palpable mass, pain, nerve symptoms, maximum diameter, location, shape, boundary, encapsulation, echogenicity, echo homogeneity, presence of a cystic component, calcification, target sign, posterior echo, and intertumoral vascularity of the tumors. The diagnostic efficacy of ultrasonography and clinical factors was compared with that of MRI. Independent factors for predicting MPNST versus BPNST were also assessed. RESULTS The parameters of location, shape, boundary, encapsulation, and vascularity were significantly different between MPNSTs and BPNSTs. Multiple logistic regression analysis showed that shape, boundary, and vascularity were independent predictors of MPNSTs. The sensitivity, specificity, and Youden index of the three clinical and ultrasound factors (shape, boundary, and vascularity) were 0.89, 0.81, and 0.69, respectively, whereas those of MRI were 0.71, 0.89, and 0.61, respectively. No significant differences in the area under the curve (AUC) of the three combined clinical and ultrasound factors and those of MRI were found (P > .05). CONCLUSIONS MRI was useful in the differential diagnosis between MPNSTs and BPNSTs. However, the combination of clinical and ultrasound diagnoses can achieve the same effect as MRI, including shape, boundary, and vasculature.
Collapse
Affiliation(s)
- Zhenzhen Jin
- Department of Ultrasound, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| | - Chao Wang
- National Center for Orthopaedics, Beijing Research Institute of Traumatology and Orthopaedics, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| | - Dandan Wang
- Department of Ultrasound, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| | - Xintong Li
- Department of Radiology, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| | - Wen Guo
- Department of Ultrasound, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| | - Tao Chen
- Department of Ultrasound, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| |
Collapse
|
4
|
Ptchelintseva A, Nuutinen H, Salo J, Tukiainen E. Experience of a single center in the treatment of rare malignant peripheral nerve sheath tumors during the years 1991-2021. J Plast Surg Hand Surg 2023; 57:376-382. [PMID: 36244030 DOI: 10.1080/2000656x.2022.2131559] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
Abstract
Malignant peripheral nerve sheath tumor (MPNST) is a rare sarcoma with a poor prognosis, as the aggressive types of this cancer tend to grow rapidly and metastasize frequently. MPNST is associated with neurofibromatosis type 1 gene mutation. The minority of cases arise secondary to radiation therapy or sporadically. The primary treatment for MPNST is early surgical resection of the tumor. The aim of this study was to retrospectively evaluate the outcome of the treatment of MPNST in Helsinki University Hospital from the years 1991 to 2021. Fourteen MPNST cases were evaluated in this study retrospectively. Descriptive statistical analysis was performed on the collected patient data. Marginal resection was completed in nine cases, wide margins were achieved in three cases, and in two cases the final histological examination of the specimen revealed intralesional removal. During the follow-up time of 36.7 ± 12.1 months, all patients who underwent wide margin resection were alive. One patient died 22 months after intralesional resection and six within 38.3 ± 30.9 months of marginal resection. Seventy-one percent of tumor surgeries resulted in Clavien-Dindo class 3b complications, reflecting the complexity of the surgeries. The aggressive nature of MPNST and the large size of these tumors requires extensive surgery, which can lead to complications. The prognosis of MPNST needs improvement.
Collapse
Affiliation(s)
- Anna Ptchelintseva
- Faculty of Medicine, University of Eastern Finland, Kuopio, Finland.,Department of Plastic Surgery, Helsinki University Hospital, Helsinki, Finland
| | - Henrik Nuutinen
- Faculty of Medicine, University of Eastern Finland, Kuopio, Finland.,Department of Plastic Surgery, Kuopio University Hospital, Kuopio, Finland
| | - Juho Salo
- Department of Plastic Surgery, Helsinki University Hospital, Helsinki, Finland
| | - Erkki Tukiainen
- Department of Plastic Surgery, Helsinki University Hospital, Helsinki, Finland
| |
Collapse
|
5
|
KANNO DT, de MATTOS RLM, CAMPOS FG, SIQUEIRA RM, de CARVALHO RB, REAL MARTINEZ CA. MULTIPLE NEUROENDOCRINE NEOPLASIA IN A PATIENT WITH TYPE I NEUROFIBROMATOSIS (NF1): REPORT OF A NEW MUTATION (NF1, EXONS 2-30 DELETION) AND LITERATURE REVIEW. ARQUIVOS BRASILEIROS DE CIRURGIA DIGESTIVA : ABCD = BRAZILIAN ARCHIVES OF DIGESTIVE SURGERY 2023; 35:e1702. [PMID: 36629684 PMCID: PMC9831629 DOI: 10.1590/0102-672020220002e1702] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Accepted: 10/01/2022] [Indexed: 01/11/2023]
Abstract
BACKGROUND Plexiform neurofibromas represent a common neoplasia of type 1 neurofibromatosis in which neurofibromas arise from multiple nerves involving connective tissue and skin and rarely affect the colon and rectum. Co-occurrence of plexiform neurofibromas, neuroendocrine tumors with primary involvement of the rectum, and medullary thyroid carcinoma in patients with neurofibromatosis type 1 is a previously undescribed condition. The aim of this manuscript was to present a case of primary plexiform neurofibroma and neuroendocrine tumors of the upper rectum in a patient with neurofibromatosis type 1 whose genetic sequencing found a novel mutation in the neurofibromatosis type 1 gene and to review the literature. CASE REPORT A 49-year-old woman with a familial history of neurofibromatosis type 1 complained of abdominal cramps for 6 months. She had previously been submitted for a total thyroidectomy due to medullary thyroid carcinoma. She was submitted to a colonoscopy, which identified a submucosa lesion located in the upper rectum. The patient was referred for a laparoscopic rectosigmoidectomy, and the histopathological study of the surgical specimen identified two different tumors. An immunohistochemical panel was done for histopathological confirmation of the etiology of both lesions. The results of the panel showed intense immunoexpression of S100 protein in the largest and superficial lesion, as well as positivity for chromogranin and synaptophysin in the minor and deep lesion confirming the diagnosis of rectal plexiform neurofibromas concomitant with neuroendocrine tumors. The proliferative activity rate using Ki-67 antibodies showed that both tumors had a low rate of mitotic activity (<1%). Genetic sequence panel identified an undescribed mutation in the neurofibromatosis type 1 gene (deletion, exons 2-30). The patient's postoperative evolution was uneventful, and she remains well, without recurrence, 3 years after surgery. CONCLUSION The co-occurrence of medullary thyroid carcinoma, plexiform neurofibromas, and neuroendocrine tumors of the rectum in patients with neurofibromatosis type 1 is an exceptional and undescribed possibility, whose diagnosis can be confirmed by the immunohistochemical staining and genetic panel.
Collapse
Affiliation(s)
- Danilo Toshio KANNO
- Universidade São Francisco, Graduate Program in Health Sciences – Bragança Paulista (SP), Brazil
| | | | - Fábio Guilherme CAMPOS
- Universidade São Francisco, Graduate Program in Health Sciences – Bragança Paulista (SP), Brazil
| | - Rayama Moreira SIQUEIRA
- Universidade São Francisco, Graduate Program in Health Sciences – Bragança Paulista (SP), Brazil
| | | | - Carlos Augusto REAL MARTINEZ
- Universidade São Francisco, Graduate Program in Health Sciences – Bragança Paulista (SP), Brazil;,Universidade Estadual de Campinas, Department of Surgery, Gastrocenter – Campinas (SP), Brazil
| |
Collapse
|
6
|
Tang H, He Y, Chen Y, Xu W, Xu Y, Li X, Guo D. Sinonasal mucosal melanoma with smooth muscle differentiation: a potential pathological diagnostic pitfall. Diagn Pathol 2022; 17:95. [PMID: 36564790 PMCID: PMC9784021 DOI: 10.1186/s13000-022-01280-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2022] [Accepted: 12/19/2022] [Indexed: 12/24/2022] Open
Abstract
BACKGROUND Sinonasal mucosal melanoma (SNMM) is a rare malignant melanoma originating from melanocytes derived from multipotent neural crest cells. Its incidence accounts for less than 1 % of all malignant melanomas, with five-year survival rate about 25 %. Occasionally, it is incredibly formidable to make a compelling diagnosis when malignant melanoma with other diverse differentiation. CASE PRESENTATION Herein, we presented a 54-year-old male case of SNMM with smooth muscle differentiation, defined by histopathology and positive immunostaining for the smooth muscle specific markers of a-SMA, H-caldesmon, calponin and Desmin, as well as specific melanocyte markers of HMB-45, Melan-A, SOX10, and PNL2. CONCLUSIONS Mucosal melanoma with smooth muscle differentiation is remarkably infrequent, and reported only 4 cases to date. It would be a potential pathological diagnostic pitfall. It is important to understand this variation of malignant melanoma for avoiding misdiagnosis.
Collapse
Affiliation(s)
- Hao Tang
- Department of Pathology, Guiqian International General Hospital, Guiyang, Guizhou Province China
| | - Yutao He
- grid.412787.f0000 0000 9868 173XSchool of Public Health, Medical College, Wuhan University of Science and Technology, Wuhan, Hubei Province China
| | - Ying Chen
- Department of Pathology, Guiqian International General Hospital, Guiyang, Guizhou Province China
| | - Wenfeng Xu
- Department of Pathology, Guiqian International General Hospital, Guiyang, Guizhou Province China
| | - Yujuan Xu
- Department of Pathology, Guiqian International General Hospital, Guiyang, Guizhou Province China
| | - Xianyun Li
- Department of Pathology, Guiqian International General Hospital, Guiyang, Guizhou Province China
| | - Deyu Guo
- Department of Pathology, Guiqian International General Hospital, Guiyang, Guizhou Province China
| |
Collapse
|
7
|
Jin Z, Zhao K, Guo W, Wang D, Deng Y, Chen T. Investigation of Ultrasound Parameters for the Differential Diagnosis of Malignant and Benign Peripheral Nerve Sheath Tumors. JOURNAL OF ULTRASOUND IN MEDICINE : OFFICIAL JOURNAL OF THE AMERICAN INSTITUTE OF ULTRASOUND IN MEDICINE 2022; 41:3091-3101. [PMID: 36082840 DOI: 10.1002/jum.16089] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/10/2022] [Revised: 07/05/2022] [Accepted: 07/31/2022] [Indexed: 06/15/2023]
Abstract
OBJECTIVES The objectives were to identify the key features of malignant and benign peripheral nerve sheath tumors (PNSTs) and determine a strategy for differentiating them using sonography. METHODS Forty-six malignant peripheral nerve sheath tumors (MPNSTs) and 83 benign peripheral nerve sheath tumors (BPNSTs) confirmed by pathology from April 2010 to July 2021 were included. The general data and grayscale and color Doppler ultrasonic manifestations were compared between the two groups. We used single factor, multifactor, and area under the receiver operating characteristic (ROC) curve analyses to extract significant malignant risk factors and then established a scoring system with these factors. RESULTS The significant variables identified in univariate analysis (P < .05) were maximum diameter, location, shape, boundary, encapsulation, echogenicity, texture pattern, calcification, entering or exiting nerve, and vascularity. Shape, boundary and vascularity were significant risk factors, and a scoring system was established. The area under the ROC curve (0.925) confirmed the usefulness of the scoring system for differentiating MPNSTs and BPNSTs. CONCLUSIONS Ultrasonography is an effective method for differentiating MPNSTs from BPNSTs.
Collapse
Affiliation(s)
- Zhenzhen Jin
- Department of Ultrasound, Beijing Jishuitan Hospital, Beijing, China
| | - Kaiping Zhao
- Department of Medical Record Management and Statistics, Beijing Jishuitan Hospital, Beijing, China
| | - Wen Guo
- Department of Ultrasound, Beijing Jishuitan Hospital, Beijing, China
| | - Dandan Wang
- Department of Ultrasound, Beijing Jishuitan Hospital, Beijing, China
| | - Yukun Deng
- Department of Ultrasound, Beijing Jishuitan Hospital, Beijing, China
| | - Tao Chen
- Department of Ultrasound, Beijing Jishuitan Hospital, Beijing, China
| |
Collapse
|
8
|
Geitenbeek RTJ, Martin E, Graven LH, Broen MPG, Anten MHME, van der Pol JAJ, Verhoef C, Taal W. Diagnostic value of 18F-FDG PET-CT in detecting malignant peripheral nerve sheath tumors among adult and pediatric neurofibromatosis type 1 patients. J Neurooncol 2022; 156:559-567. [PMID: 35025020 PMCID: PMC8860956 DOI: 10.1007/s11060-021-03936-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2021] [Accepted: 12/24/2021] [Indexed: 11/26/2022]
Abstract
Purpose Detecting malignant peripheral nerve sheath tumors (MPNSTs) remains difficult. 18F-FDG PET-CT has been shown helpful, but ideal threshold values of semi-quantitative markers remain unclear, partially because of variation among scanners. Using EU-certified scanners diagnostic accuracy of ideal and commonly used 18F-FDG PET-CT thresholds were investigated and differences between adult and pediatric lesions were evaluated. Methods A retrospective cohort study was performed including patients from two hospitals with a clinical or radiological suspicion of MPNST between 2013 and 2019. Several markers were studied for ideal threshold values and differences among adults and children. A diagnostic algorithm was subsequently developed. Results Sixty patients were included (10 MPNSTs). Ideal threshold values were 5.8 for SUVmax (sensitivity 0.70, specificity 0.92), 5.0 for SUVpeak (sensitivity 0.70, specificity 0.97), 1.7 for TLmax (sensitivity 0.90, specificity 0.86), and 2.3 for TLmean (sensitivity 0.90, specificity 0.79). The standard TLmean threshold value of 2.0 yielded a sensitivity of 0.90 and specificity of 0.74, while the standard SUVmax threshold value of 3.5 yielded a sensitivity of 0.80 and specificity of 0.63. SUVmax and adjusted SUV for lean body mass (SUL) were lower in children, but tumor-to-liver ratios were similar in adult and pediatric lesions. Using TLmean > 2.0 or TLmean < 2.0 and SUVmax > 3.5, a sensitivity and specificity of 1.00 and 0.63 can be achieved. Conclusion 18F-FDG PET-CT offers adequate accuracy to detect MPNSTs. SUV values in pediatric MPNSTs may be lower, but tumor-to-liver ratios are not. By combining TLmean and SUVmax values, a 100% sensitivity can be achieved with acceptable specificity. Supplementary Information The online version contains supplementary material available at 10.1007/s11060-021-03936-y.
Collapse
Affiliation(s)
- Ritch T J Geitenbeek
- Department of Plastic and Reconstructive Surgery G04.126, University Medical Center Utrecht, PO Box 85060, 3508 AB, Utrecht, The Netherlands.,Department of Surgical Oncology, Erasmus Medical Center Cancer Institute, Rotterdam, Netherlands
| | - Enrico Martin
- Department of Plastic and Reconstructive Surgery G04.126, University Medical Center Utrecht, PO Box 85060, 3508 AB, Utrecht, The Netherlands. .,Department of Surgical Oncology, Erasmus Medical Center Cancer Institute, Rotterdam, Netherlands.
| | - Laura H Graven
- Department of Radiology and Nuclear Medicine, Erasmus Medical Center Cancer Institute, Rotterdam, Netherlands
| | - Martijn P G Broen
- Department of Neurology, Maastricht University Medical Center, Maastricht, Netherlands
| | - Monique H M E Anten
- Department of Neurology, Maastricht University Medical Center, Maastricht, Netherlands
| | - Jochem A J van der Pol
- Department of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, Netherlands
| | - Cornelis Verhoef
- Department of Surgical Oncology, Erasmus Medical Center Cancer Institute, Rotterdam, Netherlands
| | - Walter Taal
- Department of Neurology, Erasmus Medical Center Cancer Institute, Rotterdam, Netherlands
| |
Collapse
|
9
|
Zhang M, Tong E, Hamrick F, Lee EH, Tam LT, Pendleton C, Smith BW, Hug NF, Biswal S, Seekins J, Mattonen SA, Napel S, Campen CJ, Spinner RJ, Yeom KW, Wilson TJ, Mahan MA. Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study. Neurosurgery 2021; 89:509-517. [PMID: 34131749 PMCID: PMC8364819 DOI: 10.1093/neuros/nyab212] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2020] [Accepted: 04/27/2021] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Clinicoradiologic differentiation between benign and malignant peripheral nerve sheath tumors (PNSTs) has important management implications. OBJECTIVE To develop and evaluate machine-learning approaches to differentiate benign from malignant PNSTs. METHODS We identified PNSTs treated at 3 institutions and extracted high-dimensional radiomics features from gadolinium-enhanced, T1-weighted magnetic resonance imaging (MRI) sequences. Training and test sets were selected randomly in a 70:30 ratio. A total of 900 image features were automatically extracted using the PyRadiomics package from Quantitative Imaging Feature Pipeline. Clinical data including age, sex, neurogenetic syndrome presence, spontaneous pain, and motor deficit were also incorporated. Features were selected using sparse regression analysis and retained features were further refined by gradient boost modeling to optimize the area under the curve (AUC) for diagnosis. We evaluated the performance of radiomics-based classifiers with and without clinical features and compared performance against human readers. RESULTS A total of 95 malignant and 171 benign PNSTs were included. The final classifier model included 21 imaging and clinical features. Sensitivity, specificity, and AUC of 0.676, 0.882, and 0.845, respectively, were achieved on the test set. Using imaging and clinical features, human experts collectively achieved sensitivity, specificity, and AUC of 0.786, 0.431, and 0.624, respectively. The AUC of the classifier was statistically better than expert humans (P = .002). Expert humans were not statistically better than the no-information rate, whereas the classifier was (P = .001). CONCLUSION Radiomics-based machine learning using routine MRI sequences and clinical features can aid in evaluation of PNSTs. Further improvement may be achieved by incorporating additional imaging sequences and clinical variables into future models.
Collapse
Affiliation(s)
- Michael Zhang
- Department of Neurosurgery, Stanford University, Stanford, California, USA
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Elizabeth Tong
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Forrest Hamrick
- Department of Neurosurgery, Clinical Neurosciences Center, University of Utah, Salt Lake City, Utah, USA
| | - Edward H Lee
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Lydia T Tam
- Stanford School of Medicine, Stanford University, Stanford, California, USA
| | | | - Brandon W Smith
- Department of Neurosurgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Nicholas F Hug
- Stanford School of Medicine, Stanford University, Stanford, California, USA
| | - Sandip Biswal
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Jayne Seekins
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Sarah A Mattonen
- Department of Medical Biophysics, Western University, London, Canada
| | - Sandy Napel
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Cynthia J Campen
- Department of Neurology and Neurological Sciences, Stanford University, Stanford, California, USA
| | - Robert J Spinner
- Department of Neurosurgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Kristen W Yeom
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Thomas J Wilson
- Department of Neurosurgery, Stanford University, Stanford, California, USA
| | - Mark A Mahan
- Department of Neurosurgery, Clinical Neurosciences Center, University of Utah, Salt Lake City, Utah, USA
| |
Collapse
|
10
|
Prabhu VC, Pappu S, Borys E, Ormston L, Lomasney LM. Commentary: Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study. Neurosurgery 2021; 89:E156-E157. [PMID: 34131751 DOI: 10.1093/neuros/nyab224] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2021] [Accepted: 05/02/2021] [Indexed: 11/14/2022] Open
Affiliation(s)
- Vikram C Prabhu
- Department of Neurological Surgery, Loyola University Medical Center, Maywood, Illinois, USA
| | - Suguna Pappu
- Section of Neurosurgery, Department of Surgery, Edward Hines Veterans Administration Hospital, Hines, Illinois, USA
| | - Ewa Borys
- Department of Pathology, Loyola University Medical Center, Maywood, Illinois, USA
| | - Leighanne Ormston
- Department of Oncology, Loyola University Medical Center, Maywood, Illinois, USA
| | - Laurie M Lomasney
- Department of Radiology, Loyola University Medical Center, Maywood, Illinois, USA
| |
Collapse
|
11
|
Martin E, Geitenbeek RTJ, Coert JH, Hanff DF, Graven LH, Grünhagen DJ, Verhoef C, Taal W. A Bayesian approach for diagnostic accuracy of malignant peripheral nerve sheath tumors: a systematic review and meta-analysis. Neuro Oncol 2021; 23:557-571. [PMID: 33326583 PMCID: PMC8041346 DOI: 10.1093/neuonc/noaa280] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022] Open
Abstract
Background Malignant peripheral nerve sheath tumors (MPNST) carry a dismal prognosis and require early detection and complete resection. However, MPNSTs are prone to sampling errors and biopsies or resections are cumbersome and possibly damaging in benign peripheral nerve sheath tumor (BPNST). This study aimed to systematically review and quantify the diagnostic accuracy of noninvasive tests for distinguishing MPNST from BPNST. Methods Studies on accuracy of MRI, FDG-PET (fluorodeoxyglucose positron emission tomography), and liquid biopsies were identified in PubMed and Embase from 2000 to 2019. Pooled accuracies were calculated using Bayesian bivariate meta-analyses. Individual level-patient data were analyzed for ideal maximum standardized uptake value (SUVmax) threshold on FDG-PET. Results Forty-three studies were selected for qualitative synthesis including data on 1875 patients and 2939 lesions. Thirty-five studies were included for meta-analyses. For MRI, the absence of target sign showed highest sensitivity (0.99, 95% CI: 0.94-1.00); ill-defined margins (0.94, 95% CI: 0.88-0.98); and perilesional edema (0.95, 95% CI: 0.83-1.00) showed highest specificity. For FDG-PET, SUVmax and tumor-to-liver ratio show similar accuracy; sensitivity 0.94, 95% CI: 0.91-0.97 and 0.93, 95% CI: 0.87-0.97, respectively, specificity 0.81, 95% CI: 0.76-0.87 and 0.79, 95% CI: 0.70-0.86, respectively. SUVmax ≥3.5 yielded the best accuracy with a sensitivity of 0.99 (95% CI: 0.93-1.00) and specificity of 0.75 (95% CI: 0.56-0.90). Conclusions Biopsies may be omitted in the presence of a target sign and the absence of ill-defined margins or perilesional edema. Because of diverse radiological characteristics of MPNST, biopsies may still commonly be required. In neurofibromatosis type 1, FDG-PET scans may further reduce biopsies. Ideal SUVmax threshold is ≥3.5.
Collapse
Affiliation(s)
- Enrico Martin
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Utrecht, the Netherlands.,Department of Surgical Oncology, Erasmus Medical Center, Rotterdam, the Netherlands
| | - Ritchie T J Geitenbeek
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Utrecht, the Netherlands.,Department of Surgical Oncology, Erasmus Medical Center, Rotterdam, the Netherlands
| | - J Henk Coert
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Utrecht, the Netherlands
| | - David F Hanff
- Department of Radiology and Nuclear Medicine, Erasmus Medical Center, Rotterdam, the Netherlands
| | - Laura H Graven
- Department of Radiology and Nuclear Medicine, Erasmus Medical Center, Rotterdam, the Netherlands
| | - Dirk J Grünhagen
- Department of Surgical Oncology, Erasmus Medical Center, Rotterdam, the Netherlands
| | - Cornelis Verhoef
- Department of Surgical Oncology, Erasmus Medical Center, Rotterdam, the Netherlands
| | - Walter Taal
- Department of Neuro-Oncology/Neurology, Erasmus Medical Center Cancer Institute, Rotterdam, the Netherlands
| |
Collapse
|
12
|
Diagnostic Accuracy of MRI for the Detection of Malignant Peripheral Nerve Sheath Tumors: A Systematic Review and Meta-Analysis. AJR Am J Roentgenol 2021; 217:31-39. [PMID: 33909462 DOI: 10.2214/ajr.20.23403] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Abstract
OBJECTIVE. This systematic review and meta-analysis evaluates the diagnostic accuracy of MRI for differentiating malignant (MPNSTs) from benign peripheral nerve sheath tumors (BPNSTs). MATERIALS AND METHODS. A systematic review of MEDLINE, Embase, Scopus, the Cochrane Library, and the gray literature from inception to December 2019 was performed. Original articles that involved at least 10 patients and that evaluated the accuracy of MRI for detecting MPNSTs were included. Two reviewers independently extracted clinical and radiologic data from included articles to calculate sensitivity, specificity, PPV, NPV, and accuracy. A meta-analysis was performed using a bivariate mixed-effects regression model. Risk of bias was evaluated using QUADAS-2. RESULTS. Fifteen studies involving 798 lesions (252 MPNSTs and 546 BPNSTs) were included in the analysis. Pooled and weighted sensitivity, specificity, and AUC values for MRI in detecting MPNSTs were 68% (95% CI, 52-80%), 93% (95% CI, 85-97%), and 0.89 (95% CI, 0.86-0.92) when using feature combination and 88% (95% CI, 74-95%), 94% (95% CI, 89-96%), and 0.97 (95% CI, 0.95-0.98) using diffusion restriction with or without feature combination. Subgroup analysis, such as patients with neurofibromatosis type 1 (NF1) versus those without NF1, could not be performed because of insufficient data. Risk of bias was predominantly high or unclear for patient selection, mixed for index test, low for reference standard, and unclear for flow and timing. CONCLUSION. Combining features such as diffusion restriction optimizes the diagnostic accuracy of MRI for detecting MPNSTs. However, limitations in the literature, including variability and risk of bias, necessitate additional methodologically rigorous studies to allow subgroup analysis and further evaluate the combination of clinical and MRI features for MPNST diagnosis.
Collapse
|
13
|
Dare AJ, Gupta AA, Thipphavong S, Miettinen M, Gladdy RA. Abdominal neoplastic manifestations of neurofibromatosis type 1. Neurooncol Adv 2020; 2:i124-i133. [PMID: 32642738 PMCID: PMC7317050 DOI: 10.1093/noajnl/vdaa032] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022] Open
Abstract
Neurofibromatosis type 1 (NF1) is an autosomal dominant hereditary tumor syndrome, with a wide clinicopathologic spectrum. It is defined by characteristic central nervous system, cutaneous and osseous manifestations, and by mutations in the NF1 gene, which is involved in proliferation via p21, RAS, and MAP kinase pathways. Up to 25% of NF1 patients develop intra-abdominal neoplastic manifestations including neurogenic (commonly plexiform neurofibromas and malignant peripheral nerve sheath tumors), interstitial cells of Cajal (hyperplasia, gastrointestinal stromal tumors), neuroendocrine, and embryonal tumors (rhabdomyosarcoma). Nonspecific symptoms, multifocal disease, or coexistence of 2 or more tumor types make patients challenging to diagnose and manage. Screening for intra-abdominal tumors in NF1 patients remains controversial, and currently no guidelines are established. Management decisions are complex and often informed by single-center experiences or case studies in the literature, though the field is rapidly evolving. Thus, NF1 patients should be followed in specialist centers familiar with their wide spectrum of pathology and with multidisciplinary care including specialized pathology and radiology. This review will (1) provide a contemporaneous synthesis of the literature and our multi-institutional clinical experiences with intra-abdominal neoplasms in NF1 patients, (2) present a classification framework for this heterogeneous group of disorders, and (3) outline approaches to screening, surveillance, diagnosis, and management.
Collapse
Affiliation(s)
- Anna J Dare
- Department of Surgery, Mount Sinai Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Abha A Gupta
- Division of Pediatric Hematology/Oncology, Department of Pediatrics, The Hospital for Sick Children, University of Toronto, Toronto, Ontario, Canada.,Department of Medical Oncology, Princess Margaret Cancer Centre, Toronto, Ontario, Canada
| | - Seng Thipphavong
- Department of Medical Imaging, Women's College Hospital, Toronto, Ontario, Canada
| | - Markku Miettinen
- Laboratory of Pathology, National Cancer Institute/Center for Cancer Research, Bethesda, Maryland, USA
| | - Rebecca A Gladdy
- Department of Surgery, Mount Sinai Hospital, University of Toronto, Toronto, Ontario, Canada.,Department of Surgical Oncology, Princess Margaret Hospital, Toronto, Ontario, Canada
| |
Collapse
|
14
|
Martin E, Flucke UE, Coert JH, van Noesel MM. Treatment of malignant peripheral nerve sheath tumors in pediatric NF1 disease. Childs Nerv Syst 2020; 36:2453-2462. [PMID: 32494969 PMCID: PMC7575473 DOI: 10.1007/s00381-020-04687-3] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/30/2020] [Accepted: 05/14/2020] [Indexed: 12/11/2022]
Abstract
BACKGROUND Malignant peripheral nerve sheath tumors (MPNSTs) are rare yet highly aggressive soft tissue sarcomas. Children with neurofibromatosis type 1 (NF1) have a 10% lifetime risk for development of MPNST. Prognosis remains poor and survival seems worse for NF1 patients. METHODS This narrative review highlights current practices and pitfalls in the management of MPNST in pediatric NF1 patients. RESULTS Preoperative diagnostics can be challenging, but PET scans have shown to be useful tools. More recently, functional MRI holds promise as well. Surgery remains the mainstay treatment for these patients, but careful planning is needed to minimize postoperative morbidity. Functional reconstructions can play a role in improving functional status. Radiotherapy can be administered to enhance local control in selected cases, but care should be taken to minimize radiation effects as well as reduce the risk of secondary malignancies. The exact role of chemotherapy has yet to be determined. Reports on the efficacy of chemotherapy vary as some report lower effects in NF1 populations. Promisingly, survival seems to ameliorate in the last few decades and response rates of chemotherapy may increase in NF1 populations when administering it as part of standard of care. However, in metastasized disease, response rates remain poor. New systemic therapies are therefore desperately warranted and multiple trials are currently investigating the role of drugs. Targeted drugs are nevertheless not yet included in first line treatment. CONCLUSION Both research and clinical efforts benefit from multidisciplinary approaches with international collaborations in this rare malignancy.
Collapse
Affiliation(s)
- Enrico Martin
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, G04.126, PO Box 85060, 3508, AB, Utrecht, the Netherlands.
| | - Uta E. Flucke
- Department of Solid Tumors, Princess Máxima Center for Pediatric Oncology, Utrecht, the Netherlands ,Department of Pathology, Radboud University Medical Center, Nijmegen, the Netherlands
| | - J. Henk Coert
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, G04.126, PO Box 85060, 3508 AB Utrecht, the Netherlands
| | - Max M. van Noesel
- Department of Solid Tumors, Princess Máxima Center for Pediatric Oncology, Utrecht, the Netherlands
| |
Collapse
|