Radiomics and machine learning analysis based on magnetic resonance imaging in the assessment of liver mucinous colorectal metastases

Granata, Vincenza; Fusco, Roberta; Muzio, Federica De; Cutolo, Carmen; Setola, Sergio Venanzio; Dell’Aversana, Federica; Grassi, Francesca; Belli, Andrea; Silvestro, Lucrezia; Ottaiano, Alessandro; Nasti, Guglielmo; Avallone, Antonio; Flammia, Federica; Miele, Vittorio; Tatangelo, Fabiana; Izzo, Francesco; Petrillo, Antonella

doi:10.1007/s11547-022-01501-9

Cited by 47 publications

(42 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, to avoid the risk of over-diagnosis and to center energy on an early diagnosis, we should define who those subsets of patients are and quantify the degree of risk [115]. Once we have stratified the target population according to risk level, we should define the surveillance timing and the tools (biomarkers and imaging) [115][116][117][118][119][120][121][122][123][124][125][126][127][128]. In the PDAC scenario, we are still interpreting this multi-step process, although definite improvements have been made [115].…”

Section: Risk Factorsmentioning

confidence: 99%

“…In addition the American College of Gastroenterology (ACG) [140] proposed that patients with germline mutations should be subjected to surveillance. For Peutz-Jeghers A clear knowledge of these risk factors allows a correct stratification of patients, in the perspective of a surveillance protocol centered on the patient himself [115][116][117][118][119][120][121][122][123][124][125][126][127][128]. However, to avoid the risk of over-diagnosis and to center energy on an early diagnosis, we should define who those subsets of patients are and quantify the degree of risk [115].…”

Section: Screening Guidelinesmentioning

confidence: 99%

See 1 more Smart Citation

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

Granata

Fusco

Setola

et al. 2023

Cancers

Self Cite

View full text Add to dashboard Cite

Pancreatic cancer (PC) is one of the deadliest cancers, and it is responsible for a number of deaths almost equal to its incidence. The high mortality rate is correlated with several explanations; the main one is the late disease stage at which the majority of patients are diagnosed. Since surgical resection has been recognised as the only curative treatment, a PC diagnosis at the initial stage is believed the main tool to improve survival. Therefore, patient stratification according to familial and genetic risk and the creation of screening protocol by using minimally invasive diagnostic tools would be appropriate. Pancreatic cystic neoplasms (PCNs) are subsets of lesions which deserve special management to avoid overtreatment. The current PC screening programs are based on the annual employment of magnetic resonance imaging with cholangiopancreatography sequences (MR/MRCP) and/or endoscopic ultrasonography (EUS). For patients unfit for MRI, computed tomography (CT) could be proposed, although CT results in lower detection rates, compared to MRI, for small lesions. The actual major limit is the incapacity to detect and characterize the pancreatic intraepithelial neoplasia (PanIN) by EUS and MR/MRCP. The possibility of utilizing artificial intelligence models to evaluate higher-risk patients could favour the diagnosis of these entities, although more data are needed to support the real utility of these applications in the field of screening. For these motives, it would be appropriate to realize screening programs in research settings.

show abstract

Section: Risk Factorsmentioning

confidence: 99%

Section: Screening Guidelinesmentioning

confidence: 99%

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

Granata

Fusco

Setola

et al. 2023

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

“…Accurate diagnosis and staging of HCC can be achieved by CT ( Figure 3 ) or MRI ( Figure 4 ) in the absence of invasive methods, when precise and stringent criteria are applied [ 110 , 111 , 112 , 113 , 114 , 115 , 116 , 117 , 118 , 119 , 120 , 121 , 122 , 123 , 124 , 125 , 126 , 127 , 128 , 129 , 130 ]. Although MRI proves to be more sensitive in the characterization of liver lesions, particularly with hepatospecific contrast agents, there is no unambiguous indication from the pool of experts [ 131 , 132 , 133 , 134 , 135 , 136 , 137 , 138 , 139 , 140 , 141 , 142 , 143 , 144 , 145 , 146 , 147 , 148 ].…”

Section: Li-radsmentioning

confidence: 99%

“…Accurate diagnosis and staging of HCC can be achieved by CT (Figure 3) or MRI (Figure 4) in the absence of invasive methods, when precise and stringent criteria are applied . Although MRI proves to be more sensitive in the characterization of liver lesions, particularly with hepatospecific contrast agents, there is no unambiguous indication from the pool of experts [131][132][133][134][135][136][137][138][139][140][141][142][143][144][145][146][147][148]. The choice to use CT rather than MRI remains at the discretion of individual institutions.…”

Section: Ct/mri Li-radsmentioning

confidence: 99%

A Narrative Review on LI-RADS Algorithm in Liver Tumors: Prospects and Pitfalls

et al. 2022

Self Cite

View full text Add to dashboard Cite

Liver cancer is the sixth most detected tumor and the third leading cause of tumor death worldwide. Hepatocellular carcinoma (HCC) is the most common primary liver malignancy with specific risk factors and a targeted population. Imaging plays a major role in the management of HCC from screening to post-therapy follow-up. In order to optimize the diagnostic-therapeutic management and using a universal report, which allows more effective communication among the multidisciplinary team, several classification systems have been proposed over time, and LI-RADS is the most utilized. Currently, LI-RADS comprises four algorithms addressing screening and surveillance, diagnosis on computed tomography (CT)/magnetic resonance imaging (MRI), diagnosis on contrast-enhanced ultrasound (CEUS) and treatment response on CT/MRI. The algorithm allows guiding the radiologist through a stepwise process of assigning a category to a liver observation, recognizing both major and ancillary features. This process allows for characterizing liver lesions and assessing treatment. In this review, we highlighted both major and ancillary features that could define HCC. The distinctive dynamic vascular pattern of arterial hyperenhancement followed by washout in the portal-venous phase is the key hallmark of HCC, with a specificity value close to 100%. However, the sensitivity value of these combined criteria is inadequate. Recent evidence has proven that liver-specific contrast could be an important tool not only in increasing sensitivity but also in diagnosis as a major criterion. Although LI-RADS emerges as an essential instrument to support the management of liver tumors, still many improvements are needed to overcome the current limitations. In particular, features that may clearly distinguish HCC from cholangiocarcinoma (CCA) and combined HCC-CCA lesions and the assessment after locoregional radiation-based therapy are still fields of research.

show abstract

“…The importance of Gd-EOB-DTPA has been described in a retrospective analysis by Morin et al, where among 110 patients with liver metastasis, in 43% of patients, Gd-EOB-DTPA revealed a different number of liver lesions, and it potentially modified surgical planning in more than 17% of patients [ 55 ]. Furthermore, as the future of radiology and hepatobiliary surgery will tell us, the role of the radiologist is changing, and a radiologist must be able to use artificial intelligence tools, including 3D reconstruction and radiomics, that surely will be involved in solving the DLM dilemma [ 57 , 58 , 59 ].…”

Section: The Role Of the Radiologistmentioning

confidence: 99%

Disappearing Colorectal Liver Metastases: Do We Really Need a Ghostbuster?

et al. 2022

View full text Add to dashboard Cite

The development of new systemic treatment strategies has resulted in a significant increase in the response rates of colorectal liver metastases (CRLM) in the last few years. Although the radiological response is a favorable prognostic factor, complete shrinkage of CRLM, known as disappearing liver metastases (DLM), presents a therapeutic dilemma, and proper management is still debated in the literature. In fact, DLM is not necessarily equal to cure, and when resected, pathological examination reveals in more than 80% of patients a variable percentage of the tumor as residual disease or early recurrence in situ. Moreover, while a higher incidence of intrahepatic recurrence is documented in small series when surgery is avoided, its clinical significance for long-term OS is still under investigation. In light of this, a multidisciplinary approach and, in particular, radiologists’ role is needed to assist the surgeon in the management of DLM, thanks to emerging technology and strategy. Therefore, the aim of this review is to provide an overview of the DLM phenomenon and current management.

show abstract

Radiomics and machine learning analysis based on magnetic resonance imaging in the assessment of liver mucinous colorectal metastases

Cited by 47 publications

References 83 publications

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

A Narrative Review on LI-RADS Algorithm in Liver Tumors: Prospects and Pitfalls

Disappearing Colorectal Liver Metastases: Do We Really Need a Ghostbuster?

Contact Info

Product

Resources

About