Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules

Mokrane, Fatima-Zohra; Lin, Liwu; Vavasseur, Adrien; Otal, Philippe; Péron, Jean‐Marie; Luk, Lyndon; Yang, Hao; Ammari, Samy; Saenger, Yvonne M.; Rousseau, Hervé; Zhao, Binsheng; Schwartz, Lawrence H.; Dercle, Laurent

doi:10.1007/s00330-019-06347-w

Cited by 131 publications

(84 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is therefore not surprising that unlike other similar large organs (such as lungs or the brain) there is a relative paucity of studied using automated diagnostic techniques such as radiomics and deep learning, and all utilizing a manually drawn ROI about the lesion. Zhong et al 18 and Mokrane et al 19 applied texture analysis to their studies to cirrhotic patients using MRI and CT respectively. Both showed improved performance of texture analysis compared to radiologists in determination of benign and malignant cirrhotic www.nature.com/scientificreports/ nodules.…”

Section: Discussionmentioning

confidence: 99%

Convolutional neural networks versus radiologists in characterization of small hypoattenuating hepatic nodules on CT: a critical diagnostic challenge in staging of colorectal carcinoma

Khalili

Pourafkari

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Our objective was to compare the diagnostic performance and diagnostic confidence of convolutional neural networks (CNN) to radiologists in characterizing small hypoattenuating hepatic nodules (SHHN) in colorectal carcinoma (CRC) on CT scans. Retrospective review of CRC CT scans over 6-years yielded 199 patients (550 SHHN) defined as < 1 cm in diameter. The reference standard was established through 1-year stability/MRI for benign or nodule evolution for malignant nodules. Five CNNs underwent supervised training on 150 patients (412 SHHN). The remaining 49 patients (138 SHHN) were used as testing-set to compare performance of 3 radiologists to CNN, measured through ROC AUC analysis of confidence rating assigned to each nodule by the radiologists. Multivariable modeling was used to compensate for radiologist bias from visible findings other than SHHN. In characterizing SHHN as benign or malignant, the radiologists’ mean AUC ROC (0.96) was significantly higher than CNN (0.84, p = 0.0004) but equivalent to CNN adjusted through multivariable modeling for presence of synchronous ≥ 1 cm liver metastases (0.95, p = 0.9). The diagnostic confidence of radiologists and CNN were analyzed. There were significantly lower number of nodules rated with low confidence by CNN (19.6%) and CNN with liver metastatic status (18.1%) than two (38.4%, 44.2%, p < 0.0001) but not a third radiologist (11.1%, p = 0.09). We conclude that in CRC, CNN in combination with liver metastatic status equaled expert radiologists in characterizing SHHN but with better diagnostic confidence.

show abstract

Section: Discussionmentioning

confidence: 99%

Convolutional neural networks versus radiologists in characterization of small hypoattenuating hepatic nodules on CT: a critical diagnostic challenge in staging of colorectal carcinoma

Khalili

Pourafkari

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Radiomic features have been integrated into multivariate models predicting local control and overall survival rates after radiotherapy of HCC with an AUC of 0.80 [ 106 ]. Furthermore, by combining radiomics features with clinical data, survival prediction might even be improved in patients with HCC [ 13 , 107 , 108 ]. Even in case of cholangiocarcinoma, pre-operative MRI was able to predict early recurrence, especially in combination with immunohistochemical markers [ 109 ].…”

Section: Monitoring/follow-upmentioning

confidence: 99%

“…[ 107 ] To predict survival (overall and progression-free survival) CECT 88 A combination of clinical and radiomic features better predicted survival Mokrane et al. [ 108 ] To enhance clinicians’ decision-making by diagnosing HCC in cirrhotic patients with indeterminate liver nodules using quantitative imaging features CECT 178 T: 142 V: 36 Radiomics can be used to non-invasively diagnose HCC in cirrhotic patients with indeterminate liver nodules, which could be used to optimize patient management Donghui et al. [ 13 ] To identify aggressive behaviour and predict recurrence of HCC after liver transplantation (LT) CECT 133 T: 93 V: 40 Radiomics signature extracted from CT images may be a potential imaging biomarker for liver cancer invasion and enable accurate prediction of HCC recurrence after LT Zhao et al.…”

Section: Monitoring/follow-upmentioning

confidence: 99%

“…Survival could be predicted using a radiomics signature made by a single shape-based feature Kim et al [107] To predict survival (overall and progression-free survival) CECT 88 A combination of clinical and radiomic features better predicted survival Mokrane et al [108] To enhance clinicians' decision-making by diagnosing HCC in cirrhotic patients with indeterminate liver nodules using quantitative imaging features CECT 178 T: 142 V: 36…”

mentioning

confidence: 99%

“…Radiomics can be used to non-invasively diagnose HCC in cirrhotic patients with indeterminate liver nodules, which could be used to optimize patient management Donghui et al [13] To identify aggressive behaviour and predict recurrence of HCC after liver transplantation (LT) tures have been integrated into multivariate models predicting local control and overall survival rates after radiotherapy of HCC with an AUC of 0.80 [106]. Furthermore, by combining radiomics features with clinical data, survival prediction might even be improved in patients with HCC [13,107,108]. Even in case of cholangiocarcinoma, preoperative MRI was able to predict early recurrence, especially in combination with immunohistochemical markers [109].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Radiomics for liver tumours

et al. 2020

View full text Add to dashboard Cite

Current research, especially in oncology, increasingly focuses on the integration of quantitative, multiparametric and functional imaging data. In this fast-growing field of research, radiomics may allow for a more sophisticated analysis of imaging data, far beyond the qualitative evaluation of visible tissue changes. Through use of quantitative imaging data, more tailored and tumour-specific diagnostic work-up and individualized treatment concepts may be applied for oncologic patients in the future. This is of special importance in cross-sectional disciplines such as radiology and radiation oncology, with already high and still further increasing use of imaging data in daily clinical practice. Liver targets are generally treated with stereotactic body radiotherapy (SBRT), allowing for local dose escalation while preserving surrounding normal tissue. With the introduction of online target surveillance with implanted markers, 3D-ultrasound on conventional linacs and hybrid magnetic resonance imaging (MRI)-linear accelerators, individualized adaptive radiotherapy is heading towards realization. The use of big data such as radiomics and the integration of artificial intelligence techniques have the potential to further improve image-based treatment planning and structured follow-up, with outcome/toxicity prediction and immediate detection of (oligo)progression. The scope of current research in this innovative field is to identify and critically discuss possible application forms of radiomics, which is why this review tries to summarize current knowledge about interdisciplinary integration of radiomics in oncologic patients, with a focus on investigations of radiotherapy in patients with liver cancer or oligometastases including multiparametric, quantitative data into (radio)-oncologic workflow from disease diagnosis, treatment planning, delivery and patient follow-up.

show abstract

Clinical care in hepatocellular carcinoma: A mixed methods assessment of experiences and challenges of oncology professionals

Jacobs¹,

Boyle

El–Serag

et al. 2022

Cancer Medicine

View full text Add to dashboard Cite

Introduction Healthcare providers (HCPs) may face numerous dilemmas in optimally screening, diagnosing, and treating patients with, and/or at risk for, hepatocellular carcinoma (HCC). This study aimed to achieve a greater understanding of the challenges in HCC care which in turn could delineate HCP educational opportunities within this oncologic sub‐specialty. Methods A mixed‐methods approach was used to identify practice gaps and clinical barriers experienced by US‐based medical oncologists, hepatologists, oncology physician assistants, oncology nurse practitioners, and interventional radiologists involved in HCC care. The qualitative (semi‐structured interview) and quantitative (survey) data collection approaches were deployed sequentially with findings subsequently triangulated. Results A total of 214 HCPs participated in this study. Analysis revealed challenges related to screening and diagnosing HCC, specifically in applying appropriate screening guidelines, and the optimal use and decisions related to diagnostic imaging and biopsy. Issues related to treatment selection included the application of existing HCC guidelines in treatment decision‐making, weighing risk/benefit ratios of various antineoplastics regimens (i.e., tyrosine kinase inhibitors‐TKIs, immunotherapy agents, chemotherapy), sequencing therapies, potential toxicity management, and optimally educating patients about their HCC. Conclusion These findings highlight the educational needs of those involved in HCC care and provide a starting point for clinicians to both reflect on their practice and identify opportunities to enhance communication within the HCC team and between provider and patient. There is an opportunity to optimize continuing professional development interventions that address the identified gaps in clinical practice specifically related to teamwork and interdisciplinary communication.

show abstract

Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules

Cited by 131 publications

References 31 publications

Convolutional neural networks versus radiologists in characterization of small hypoattenuating hepatic nodules on CT: a critical diagnostic challenge in staging of colorectal carcinoma

Convolutional neural networks versus radiologists in characterization of small hypoattenuating hepatic nodules on CT: a critical diagnostic challenge in staging of colorectal carcinoma

Radiomics for liver tumours

Clinical care in hepatocellular carcinoma: A mixed methods assessment of experiences and challenges of oncology professionals

Contact Info

Product

Resources

About