CT Texture Analysis and Machine Learning Improve Post-ablation Prognostication in Patients with Adrenal Metastases: A Proof of Concept

Daye, Dania; Staziaki, Pedro V.; Furtado, Vanessa Fiorini; Tabari, Azadeh; Fintelmann, Florian J.; Frenk, Nathan E.; Shyn, Paul B.; Tuncalı, Kemal; Silverman, Stuart G.; Arellano, Ronald S.; Gee, Michael S.; Uppot, Raul N.

doi:10.1007/s00270-019-02336-0

Cited by 22 publications

(20 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, only one study has been published recently [26] which investigated pre-ablation radiomics features to predict LTP in adrenal metastases. They reported that a predictive combined model could achieve a significantly higher accuracy than a clinical model.…”

Section: Discussionmentioning

confidence: 99%

CT-Based Radiomics Analysis Before Thermal Ablation to Predict Local Tumor Progression for Colorectal Liver Metastases

Taghavi

Staal

Muñoz

et al. 2021

Cardiovasc Intervent Radiol

View full text Add to dashboard Cite

Purpose Predicting early local tumor progression after thermal ablation treatment for colorectal liver metastases patients is critical for the decision of subsequent follow-up and treatment. Radiomics features derived from medical images show great potential for prediction and prognosis. The aim is to develop and validate a machine learning radiomics model to predict local tumor progression based on the pre-ablation CT scan of colorectal liver metastases patients. Materials and Methods Ninety patients with colorectal liver metastases (140 lesions) treated by ablation were included in the study and were randomly divided into a training (n = 63 patients/n = 94 lesions) and validation (n = 27 patients/n = 46 lesions) cohort. After manual lesion volume segmentation and preprocessing, 1593 radiomics features were extracted for each lesion. Three machine learning survival models were constructed based on (1) radiomics features, (2) clinical features and (3) a combination of clinical and radiomics features to predict local tumor progression free survival. Feature reduction and machine learning modeling were performed and optimized with sequential model-based optimization. Results Median follow-up was 24 months (range 6-115). Thirty-one (22%) lesions developed local tumor progression. The concordance index in the validation set to predict local tumor progression free survival was 0.78 (95% confidence interval [CI]: 0.77-0.79) for the radiomics model, 0.56 (95%CI: 0.55-0.57) for the clinical model and 0.79 (95%CI: 0.78-0.80) for the combined model. Conclusion A machine learning-based radiomics analysis of routine clinical CT imaging pre-ablation could act as a valuable biomarker model to predict local tumor progression with curative intent for colorectal liver metastases patients. Keywords Tomography Á X-ray computed Á Colorectal cancer Á Neoplasm metastasis Á Liver neoplasms Á Liver ablation Á Machine learning Abbreviations CRC Colorectal cancer CRLM Colorectal liver metastases ML Machine learning CI Confidence interval LTP Local tumor progression RFA Radiofrequency ablation MWA Microwave ablation

show abstract

Section: Discussionmentioning

confidence: 99%

CT-Based Radiomics Analysis Before Thermal Ablation to Predict Local Tumor Progression for Colorectal Liver Metastases

Taghavi

Staal

Muñoz

et al. 2021

Cardiovasc Intervent Radiol

View full text Add to dashboard Cite

show abstract

“…Furthermore, TA will improve the work efficiency and reduce the work burden of experienced radiologists. Many artificial intelligence (AI) techniques have been implemented based on TA [26][27][28] , and our research provides a basis for the future application of AI techniques in intestinal diseases.…”

Section: Discussionmentioning

confidence: 99%

The feasibility of differentiating colorectal cancer from normal and inflammatory thickening colon wall using CT texture analysis

Wang

Yuan

et al. 2020

Sci Rep

View full text Add to dashboard Cite

To investigate the diagnostic value of texture analysis (TA) for differentiating between colorectal cancer (CRC), colonic lesions caused by inflammatory bowel disease (IBD), and normal thickened colon wall (NTC) on computed tomography (CT) and assess which scanning phase has the highest differential diagnostic value. In all, 107 patients with CRC, 113 IBD patients with colonic lesions, and 96 participants with NTC were retrospectively enrolled. All subjects underwent multiphase CT examination, including pre-contrast phase (PCP), arterial phase (AP), and portal venous phase (PVP) scans. Based on these images, classification by TA and visual classification by radiologists were performed to discriminate among the three tissue types. The performance of TA and visual classification was compared. Precise TA classification results (error, 2.03-12.48%) were acquired by nonlinear discriminant analysis for CRC, IBD and NTC, regardless of phase or feature selection. PVP images showed a better ability to discriminate the three tissues by comprising the three scanning phases. TA showed significantly better performance in discriminating CRC, IBD and NTC than visual classification for residents, but there was no significant difference in classification between TA and experienced radiologists. TA could provide useful quantitative information for the differentiation of CRC, IBD and NTC on CT, particularly in PVP images. Colorectal cancer (CRC) is one of the most commonly diagnosed and deadly cancers worldwide 1. The risk of CRC is increased in patients with inflammatory bowel disease (IBD), including ulcerative colitis (UC) and Crohn's disease (CD), compared with that of sporadic CRC, especially in IBD patients with long-term colitis, strictures, fistulae, and right-sided colonic disease 2. Although the incidence of CRC in IBD patients accounts for only 1-2% of all CRC cases, a recent population-based study showed that CRC accounted for 10-15% of all IBD-related deaths 3. Therefore, CRC screening and early detection in IBD patients may reduce the morbidity and mortality rates of CRC in patients with IBD 4. Regular monitoring by endoscopy may allow the early detection of CRC. However, endoscopy usually involves sedation and has associated risks, including perforation and bleeding, especially in patients with active IBD 5. Compared with colonoscopy, computed tomography (CT) is a promising method for CRC screening due to the lower rate of test-related complications, the ability to assess the patient for perforating complications of IBD, and the ability to determine the extent and severity of CRC and IBD 6. On CT images, patterns of wall thickening are helpful for differential diagnosis, with heterogeneous and asymmetrical focal thickening indicating malignancies and homogeneous and symmetrical regular thickening suggesting benign or well-differentiated tumours 2. For experienced gastrointestinal radiologists, it is not very difficult to distinguish CRC from IBD, but for less experienced radiologists or residents, there are still som...

show abstract

“…For instance, the performance of pre-ablation CT texture features may predict post-treatment local progression and survival in patients who undergo tumor ablation, using ML to identifying specific CT texture patterns, as demonstrated by Daye et al for adrenal metastases. During pre-procedural assessment, in fact, when CT-derived texture features were included in addition to clinical variables, there was an increase in accuracy to more than 95% [ 18 ]. Similarly, using MRI texture features and the presence or absence of cirrhosis, Abajian et al assessed a ML algorithm able to predict chemoembolization outcomes in patients with hepatocellular carcinoma, obtaining a very good negative predictive value (88.5%) [ 19 ].…”

Section: Fields Of Applicationmentioning

confidence: 99%

Interventional Radiology ex-machina: impact of Artificial Intelligence on practice

et al. 2021

View full text Add to dashboard Cite

Artificial intelligence (AI) is a branch of Informatics that uses algorithms to tirelessly process data, understand its meaning and provide the desired outcome, continuously redefining its logic. AI was mainly introduced via artificial neural networks, developed in the early 1950s, and with its evolution into "computational learning models." Machine Learning analyzes and extracts features in larger data after exposure to examples; Deep Learning uses neural networks in order to extract meaningful patterns from imaging data, even deciphering that which would otherwise be beyond human perception. Thus, AI has the potential to revolutionize the healthcare systems and clinical practice of doctors all over the world. This is especially true for radiologists, who are integral to diagnostic medicine, helping to customize treatments and triage resources with maximum effectiveness. Related in spirit to Artificial intelligence are Augmented Reality, mixed reality, or Virtual Reality, which are able to enhance accuracy of minimally invasive treatments in image guided therapies by Interventional Radiologists. The potential applications of AI in IR go beyond computer vision and diagnosis, to include screening and modeling of patient selection, predictive tools for treatment planning and navigation, and training tools. Although no new technology is widely embraced, AI may provide opportunities to enhance radiology service and improve patient care, if studied, validated, and applied appropriately.

show abstract

CT Texture Analysis and Machine Learning Improve Post-ablation Prognostication in Patients with Adrenal Metastases: A Proof of Concept

Cited by 22 publications

References 32 publications

CT-Based Radiomics Analysis Before Thermal Ablation to Predict Local Tumor Progression for Colorectal Liver Metastases

CT-Based Radiomics Analysis Before Thermal Ablation to Predict Local Tumor Progression for Colorectal Liver Metastases

The feasibility of differentiating colorectal cancer from normal and inflammatory thickening colon wall using CT texture analysis

Interventional Radiology ex-machina: impact of Artificial Intelligence on practice

Contact Info

Product

Resources

About