Machine Learning: Applications and Advanced Progresses of Radiomics in Endocrine Neoplasms

Table 3

Different clinical applications of radiomic models (features) in pancreatic neuroendocrine tumors.

References	Case numbers	Radiomic method	Results
[96]	164	CT	CT-based radiomic classifiers had the potential to differentiate serous cystadenoma from IPMN and MCN
[97]	38	CT	Radiomic method may more accurately predict IPMNs pathology than radiologic features considered in consensus guidelines
[98]	53	CT	Radiomics could predict the malignant potential of intraductal papillary mucinous neoplasms and had important application values in clinical decision making
[99]	260	CT	The proposed radiomic-based computer-aided diagnosis scheme could increase preoperative diagnostic accuracy and assist clinicians in making accurate management decisions
[100]	78	CT	Radiomics made a contribution to the differentiation of pancreatic serous cystadenomas and mucinous cystadenomas
[101]	225	CT	Radiomic features were independently and positively associated with the risk of LN metastasis in PDAC
[102]	159	CT	CT radiomic signature could be conveniently used for preoperative prediction of lymph node metastasis in patients with PDAC
[105]	20	CT	CT radiomic features may be potentially used for early assessment of treatment response and stratification for therapeutic intensification
[106]	90	CT	Radiomics may develop into a biomarker for early prediction of treatment response
[107]	74	CT	Overall survival and recurrence could be better predicted with models based on radiomic features than with those based on clinical features for pancreatic cancer
[108]	24	CT	Combining radiomics with CA19-9 could improve the ability to predict posttreatment responses
[112]	Not mentioned	MRI	Radiomics could be used as an imaging biomarker for early immunotherapy response assessment in a KPC transgenic mouse model of PDAC
[114]	301	CT	CT radiomic signature showed moderate predictive accuracy for differentiating low-grade from high-grade PDAC and should become a new noninvasive method for the preoperative prediction of histological grades of PDAC
[115]	86	CT	Radiomics was rewarding for the aided diagnosis of R0 and R1. Texture features could potentially enhance physicians’ diagnostic ability
[116]	88	CT	CT radiomics could be used for predicting the prognosis in pancreas head cancer patients who underwent curative resection
[117]	63	MRI	MRI-based radiomic features were associated with overall survival in patients with pancreatic cancer
[118]	132	MRI	Radiomic models had the potential to predict tumor subtypes and overall survival in PDAC
[119]	100	CT	A CT-based radiomic signature was correlated with overall survival and local control after stereotactic body radiation therapy and allowed to identify low and high-risk groups of patients
[120]	98	CT	The proposed survival model outperforms Cox proportional hazard model-based radiomic pipeline in PDAC prognosis
[121]	106	CT	Radiomics was assisted in selecting an appropriate candidate for irradiation stents in patients with unresectable pancreatic cancer
[122]	117	CT	Radiomics had the potential to predict pancreatic fistula operatively in patients who would receive pancreaticoduodenectomy