Elsa Iannicelli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Elsa Iannicelli has a total of 197 co-authors. Here are the top co-authors by number of shared publications:
- Andrea Laghi
Department of Biomedical Sciences, Humanitas University, via Rita Levi Montalcini 4, 20072 Pieve Emanuele, Milan, Italy; IRCCS Humanitas Research Hospital, Department of Diagnostic Imaging, via Manzoni 56, 20089 Rozzano, Milan, Italy; Department of Surgery, The Netherlands Cancer Institute, Plesmanlaan 121, Amsterdam 1066 CX, the Netherlands
14 shared publications - Damiano Caruso
Radiology Unit, Department of Surgical and Medical Sciences and Translational Medicine, Sapienza University of Rome, Sant’Andrea Hospital, 00189 Rome, Italy
13 shared publications - Marta Zerunian
Radiology Unit, Department of Surgical and Medical Sciences and Translational Medicine, Sapienza University of Rome, Sant’Andrea Hospital, 00189 Rome, Italy
12 shared publications - Michela Polici
Radiology Unit, Department of Surgical and Medical Sciences and Translational Medicine, Sapienza University of Rome, Sant’Andrea Hospital, 00189 Rome, Italy
11 shared publications G. Delle Fave
10 shared publications- Francesco Panzuto
Department of Medical-Surgical Sciences and Translational Medicine, Sapienza University of Rome, Digestive Disease Unit, ENETS Center of Excellence, Sant’Andrea University Hospital, Rome, Italy
8 shared publications
Latest Publications
- Open Access
Sarcopenia in Patients with Advanced Gastrointestinal Well-Differentiated Neuroendocrine Tumors
Background: Neuroendocrine neoplasms (NENs) are slow-growing tumors. Sarcopenia is defined as the loss of muscle mass, strength, and physical performance. First-line NEN therapy is somatostatin analogs, which could be responsible for malabsorption conditions, such as pancreatic exocrine insufficiency (EPI) with underlying sarcopenia. Aim: Evaluate the prevalence of sarcopenia in patients with NENs at diagnosis and during follow-up. Methods: A retrospective single-center study was conducted, including patients with advanced intestinal NENs G1/G2 (excluded pancreatic NENs). CT scans were analyzed at diagnosis and after 6 months of therapy, and the skeletal muscle index was assessed. Results: A total of 30 patients (F:M = 6:24) were enrolled, with the following primary tumor sites: 25 in the ileum, 1 stomach, 2 jejunum, and 2 duodenum. At diagnosis, 20 patients (66.6%) showed sarcopenic SMI values, and 10 patients (33.3%) showed non-sarcopenic SMI values. At follow-up, three more patients developed sarcopenic SMI values. Statistical significance in relation to the presence of sarcopenia was found in the group of patients with carcinoid syndrome (p = 0.0178), EPI (p = 0.0018), and weight loss (p = 0.0001). Conclusion: Sarcopenia was present in 2/3 of the patients with advanced intestinal NENs at the diagnosis and during the follow-up. It is reasonable to consider this condition to improve clinical outcomes.
Open AccessSarcopenia in Patients with Advanced Gastrointestinal Well-Differentiated Neuroendocrine Tumors
Background: Neuroendocrine neoplasms (NENs) are slow-growing tumors. Sarcopenia is defined as the loss of muscle mass, strength, and physical performance. First-line NEN therapy is somatostatin analogs, which could be responsible for malabsorption conditions, such as pancreatic exocrine insufficiency (EPI) with underlying sarcopenia. Aim: Evaluate the prevalence of sarcopenia in patients with NENs at diagnosis and during follow-up. Methods: A retrospective single-center study was conducted, including patients with advanced intestinal NENs G1/G2 (excluded pancreatic NENs). CT scans were analyzed at diagnosis and after 6 months of therapy, and the skeletal muscle index was assessed. Results: A total of 30 patients (F:M = 6:24) were enrolled, with the following primary tumor sites: 25 in the ileum, 1 stomach, 2 jejunum, and 2 duodenum. At diagnosis, 20 patients (66.6%) showed sarcopenic SMI values, and 10 patients (33.3%) showed non-sarcopenic SMI values. At follow-up, three more patients developed sarcopenic SMI values. Statistical significance in relation to the presence of sarcopenia was found in the group of patients with carcinoid syndrome (p = 0.0178), EPI (p = 0.0018), and weight loss (p = 0.0001). Conclusion: Sarcopenia was present in 2/3 of the patients with advanced intestinal NENs at the diagnosis and during the follow-up. It is reasonable to consider this condition to improve clinical outcomes.
- Open Access
- 9 February 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (4) , 379
Liver Magnetic Resonance Elastography: Focus on Methodology, Technique, and Feasibility
Magnetic resonance elastography (MRE) is an imaging technique that combines low-frequency mechanical vibrations with magnetic resonance imaging to create visual maps and quantify liver parenchyma stiffness. As in recent years, diffuse liver diseases have become highly prevalent worldwide and could lead to a chronic condition with different stages of fibrosis. There is a strong necessity for a non-invasive, highly accurate, and standardised quantitative assessment to evaluate and manage patients with different stages of fibrosis from diagnosis to follow-up, as the actual reference standard for the diagnosis and staging of liver fibrosis is biopsy, an invasive method with possible peri-procedural complications and sampling errors. MRE could quantitatively evaluate liver stiffness, as it is a rapid and repeatable method with high specificity and sensitivity. MRE is based on the propagation of mechanical shear waves through the liver tissue that are directly proportional to the organ’s stiffness, expressed in kilopascals (kPa). To obtain a valid assessment of the real hepatic stiffness values, it is mandatory to obtain a high-quality examination. To understand the pearls and pitfalls of MRE, in this review, we describe our experience after one year of performing MRE from indications and patient preparation to acquisition, quality control, and image analysis.
- 9 February 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (4) , 379
Open AccessLiver Magnetic Resonance Elastography: Focus on Methodology, Technique, and Feasibility
Magnetic resonance elastography (MRE) is an imaging technique that combines low-frequency mechanical vibrations with magnetic resonance imaging to create visual maps and quantify liver parenchyma stiffness. As in recent years, diffuse liver diseases have become highly prevalent worldwide and could lead to a chronic condition with different stages of fibrosis. There is a strong necessity for a non-invasive, highly accurate, and standardised quantitative assessment to evaluate and manage patients with different stages of fibrosis from diagnosis to follow-up, as the actual reference standard for the diagnosis and staging of liver fibrosis is biopsy, an invasive method with possible peri-procedural complications and sampling errors. MRE could quantitatively evaluate liver stiffness, as it is a rapid and repeatable method with high specificity and sensitivity. MRE is based on the propagation of mechanical shear waves through the liver tissue that are directly proportional to the organ’s stiffness, expressed in kilopascals (kPa). To obtain a valid assessment of the real hepatic stiffness values, it is mandatory to obtain a high-quality examination. To understand the pearls and pitfalls of MRE, in this review, we describe our experience after one year of performing MRE from indications and patient preparation to acquisition, quality control, and image analysis.
- Open Access
Is CT Radiomics Superior to Morphological Evaluation for pN0 Characterization? A Pilot Study in Colon Cancer
The aim of this study was to compare CT radiomics and morphological features when assessing benign lymph nodes (LNs) in colon cancer (CC). This retrospective study included 100 CC patients (test cohort) who underwent a preoperative CT examination and were diagnosed as pN0 after surgery. Regional LNs were scored with a morphological Likert scale (NODE-SCORE) and divided into two groups: low likelihood (LLM: 0–2 points) and high likelihood (HLM: 3–7 points) of malignancy. The T-test and the Mann–Whitney test were used to compare 107 radiomic features extracted from the two groups. Radiomic features were also extracted from primary lesions (PLs), and the receiver operating characteristic (ROC) was used to test a LN/PL ratio when assessing the LN’s status identified with radiomics and with the NODE-SCORE. An amount of 337 LNs were divided into 167 with LLM and 170 with HLM. Radiomics showed 15/107 features, with a significant difference (p < 0.02) between the two groups. The comparison of selected features between 81 PLs and the corresponding LNs showed all significant differences (p < 0.0001). According to the LN/PL ratio, the selected features recognized a higher number of LNs than the NODE-SCORE (p < 0.001). On validation of the cohort of 20 patients (10 pN0, 10 pN2), significant ROC curves were obtained for LN/PL busyness (AUC = 0.91; 0.69–0.99; 95% C.I.; and p < 0.001) and for LN/PL dependence entropy (AUC = 0.76; 0.52–0.92; 95% C.I.; and p = 0.03). The radiomics ratio between CC and LNs is more accurate for noninvasively discriminating benign LNs compared to CT morphological features.
Open AccessIs CT Radiomics Superior to Morphological Evaluation for pN0 Characterization? A Pilot Study in Colon Cancer
The aim of this study was to compare CT radiomics and morphological features when assessing benign lymph nodes (LNs) in colon cancer (CC). This retrospective study included 100 CC patients (test cohort) who underwent a preoperative CT examination and were diagnosed as pN0 after surgery. Regional LNs were scored with a morphological Likert scale (NODE-SCORE) and divided into two groups: low likelihood (LLM: 0–2 points) and high likelihood (HLM: 3–7 points) of malignancy. The T-test and the Mann–Whitney test were used to compare 107 radiomic features extracted from the two groups. Radiomic features were also extracted from primary lesions (PLs), and the receiver operating characteristic (ROC) was used to test a LN/PL ratio when assessing the LN’s status identified with radiomics and with the NODE-SCORE. An amount of 337 LNs were divided into 167 with LLM and 170 with HLM. Radiomics showed 15/107 features, with a significant difference (p < 0.02) between the two groups. The comparison of selected features between 81 PLs and the corresponding LNs showed all significant differences (p < 0.0001). According to the LN/PL ratio, the selected features recognized a higher number of LNs than the NODE-SCORE (p < 0.001). On validation of the cohort of 20 patients (10 pN0, 10 pN2), significant ROC curves were obtained for LN/PL busyness (AUC = 0.91; 0.69–0.99; 95% C.I.; and p < 0.001) and for LN/PL dependence entropy (AUC = 0.76; 0.52–0.92; 95% C.I.; and p = 0.03). The radiomics ratio between CC and LNs is more accurate for noninvasively discriminating benign LNs compared to CT morphological features.
- Open Access
- 24 April 2023
- Published by MDPI AG in Journal of Personalized Medicine
- Vol. 13 (5) , 717
Development and Validation of Artificial-Intelligence-Based Radiomics Model Using Computed Tomography Features for Preoperative Risk Stratification of Gastrointestinal Stromal Tumors
Background: preoperative risk assessment of gastrointestinal stromal tumors (GISTS) is required for optimal and personalized treatment planning. Radiomics features are promising tools to predict risk assessment. The purpose of this study is to develop and validate an artificial intelligence classification algorithm, based on CT features, to define GIST’s prognosis as determined by the Miettinen classification. Methods: patients with histological diagnosis of GIST and CT studies were retrospectively enrolled. Eight morphologic and 30 texture CT features were extracted from each tumor and combined to obtain three models (morphologic, texture and combined). Data were analyzed using a machine learning classification (WEKA). For each classification process, sensitivity, specificity, accuracy and area under the curve were evaluated. Inter- and intra-reader agreement were also calculated. Results: 52 patients were evaluated. In the validation population, highest performances were obtained by the combined model (SE 85.7%, SP 90.9%, ACC 88.8%, and AUC 0.954) followed by the morphologic (SE 66.6%, SP 81.8%, ACC 76.4%, and AUC 0.742) and texture (SE 50%, SP 72.7%, ACC 64.7%, and AUC 0.613) models. Reproducibility was high of all manual evaluations. Conclusions: the AI-based radiomics model using a CT feature demonstrates good predictive performance for preoperative risk stratification of GISTs.
- 24 April 2023
- Published by MDPI AG in Journal of Personalized Medicine
- Vol. 13 (5) , 717
Open AccessDevelopment and Validation of Artificial-Intelligence-Based Radiomics Model Using Computed Tomography Features for Preoperative Risk Stratification of Gastrointestinal Stromal Tumors
Background: preoperative risk assessment of gastrointestinal stromal tumors (GISTS) is required for optimal and personalized treatment planning. Radiomics features are promising tools to predict risk assessment. The purpose of this study is to develop and validate an artificial intelligence classification algorithm, based on CT features, to define GIST’s prognosis as determined by the Miettinen classification. Methods: patients with histological diagnosis of GIST and CT studies were retrospectively enrolled. Eight morphologic and 30 texture CT features were extracted from each tumor and combined to obtain three models (morphologic, texture and combined). Data were analyzed using a machine learning classification (WEKA). For each classification process, sensitivity, specificity, accuracy and area under the curve were evaluated. Inter- and intra-reader agreement were also calculated. Results: 52 patients were evaluated. In the validation population, highest performances were obtained by the combined model (SE 85.7%, SP 90.9%, ACC 88.8%, and AUC 0.954) followed by the morphologic (SE 66.6%, SP 81.8%, ACC 76.4%, and AUC 0.742) and texture (SE 50%, SP 72.7%, ACC 64.7%, and AUC 0.613) models. Reproducibility was high of all manual evaluations. Conclusions: the AI-based radiomics model using a CT feature demonstrates good predictive performance for preoperative risk stratification of GISTs.
- Open Access
- 7 September 2022
- Published by Springer Nature in La radiologia medica
- Vol. 127 (10) , 1098-1105
Artificial intelligence based image quality enhancement in liver MRI: a quantitative and qualitative evaluation
Purpose: To compare liver MRI with AIR Recon Deep Learning™(ARDL) algorithm applied and turned-off (NON-DL) with conventional high-resolution acquisition (NAÏVE) sequences, in terms of quantitative and qualitative image analysis and scanning time. Material and methods: This prospective study included fifty consecutive volunteers (31 female, mean age 55.5 ± 20 years) from September to November 2021. 1.5 T MRI was performed and included three sets of images: axial single-shot fast spin-echo (SSFSE) T2 images, diffusion-weighted images(DWI) and apparent diffusion coefficient(ADC) maps acquired with both ARDL and NAÏVE protocol; the NON-DL images, were also assessed. Two radiologists in consensus drew fixed regions of interest in liver parenchyma to calculate signal-to-noise-ratio (SNR) and contrast to-noise-ratio (CNR). Subjective image quality was assessed by two other radiologists independently with a five-point Likert scale. Acquisition time was recorded. Results: SSFSE T2 objective analysis showed higher SNR and CNR for ARDL vs NAÏVE, ARDL vs NON-DL(all P < 0.013). Regarding DWI, no differences were found for SNR with ARDL vs NAÏVE and, ARDL vs NON-DL (all P > 0.2517).CNR was higher for ARDL vs NON-DL(P = 0.0170), whereas no differences were found between ARDL and NAÏVE(P = 1). No differences were observed for all three comparisons, in terms of SNR and CNR, for ADC maps (all P > 0.32). Qualitative analysis for all sequences showed better overall image quality for ARDL with lower truncation artifacts, higher sharpness and contrast (all P < 0.0070) with excellent inter-rater agreement (k ≥ 0.8143). Acquisition time was lower in ARDL sequences compared to NAÏVE (SSFSE T2 = 19.08 ± 2.5 s vs. 24.1 ± 2 s and DWI = 207.3 ± 54 s vs. 513.6 ± 98.6 s, all P < 0.0001). Conclusion: ARDL applied on upper abdomen showed overall better image quality and reduced scanning time compared with NAÏVE protocol.
- 7 September 2022
- Published by Springer Nature in La radiologia medica
- Vol. 127 (10) , 1098-1105
Open AccessArtificial intelligence based image quality enhancement in liver MRI: a quantitative and qualitative evaluation
Purpose: To compare liver MRI with AIR Recon Deep Learning™(ARDL) algorithm applied and turned-off (NON-DL) with conventional high-resolution acquisition (NAÏVE) sequences, in terms of quantitative and qualitative image analysis and scanning time. Material and methods: This prospective study included fifty consecutive volunteers (31 female, mean age 55.5 ± 20 years) from September to November 2021. 1.5 T MRI was performed and included three sets of images: axial single-shot fast spin-echo (SSFSE) T2 images, diffusion-weighted images(DWI) and apparent diffusion coefficient(ADC) maps acquired with both ARDL and NAÏVE protocol; the NON-DL images, were also assessed. Two radiologists in consensus drew fixed regions of interest in liver parenchyma to calculate signal-to-noise-ratio (SNR) and contrast to-noise-ratio (CNR). Subjective image quality was assessed by two other radiologists independently with a five-point Likert scale. Acquisition time was recorded. Results: SSFSE T2 objective analysis showed higher SNR and CNR for ARDL vs NAÏVE, ARDL vs NON-DL(all P < 0.013). Regarding DWI, no differences were found for SNR with ARDL vs NAÏVE and, ARDL vs NON-DL (all P > 0.2517).CNR was higher for ARDL vs NON-DL(P = 0.0170), whereas no differences were found between ARDL and NAÏVE(P = 1). No differences were observed for all three comparisons, in terms of SNR and CNR, for ADC maps (all P > 0.32). Qualitative analysis for all sequences showed better overall image quality for ARDL with lower truncation artifacts, higher sharpness and contrast (all P < 0.0070) with excellent inter-rater agreement (k ≥ 0.8143). Acquisition time was lower in ARDL sequences compared to NAÏVE (SSFSE T2 = 19.08 ± 2.5 s vs. 24.1 ± 2 s and DWI = 207.3 ± 54 s vs. 513.6 ± 98.6 s, all P < 0.0001). Conclusion: ARDL applied on upper abdomen showed overall better image quality and reduced scanning time compared with NAÏVE protocol.
- Open Access
- 19 August 2022
- Published by MDPI AG in Tomography
- Vol. 8 (4) , 2059-2072
Performance of Machine Learning and Texture Analysis for Predicting Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer with 3T MRI
Background: To evaluate the diagnostic performance of a Machine Learning (ML) algorithm based on Texture Analysis (TA) parameters in the prediction of Pathological Complete Response (pCR) to Neoadjuvant Chemoradiotherapy (nChRT) in Locally Advanced Rectal Cancer (LARC) patients. Methods: LARC patients were prospectively enrolled to undergo pre- and post-nChRT 3T MRI for initial loco-regional staging. TA was performed on axial T2-Weighted Images (T2-WI) to extract specific parameters, including skewness, kurtosis, entropy, and mean of positive pixels. For the assessment of TA parameter diagnostic performance, all patients underwent complete surgical resection, which served as a reference standard. ROC curve analysis was carried out to determine the discriminatory accuracy of each quantitative TA parameter to predict pCR. A ML-based decisional tree was implemented combining all TA parameters in order to improve diagnostic accuracy. Results: Forty patients were considered for final study population. Entropy, kurtosis and MPP showed statistically significant differences before and after nChRT in patients with pCR; in particular, when patients with Pathological Partial Response (pPR) and/or Pathological Non-Response (pNR) were considered, entropy and skewness showed significant differences before and after nChRT (all p < 0.05). In terms of absolute value changes, pre- and post-nChRT entropy, and kurtosis showed significant differences (0.31 ± 0.35, in pCR, −0.02 ± 1.28 in pPR/pNR, (p = 0.04); 1.87 ± 2.19, in pCR, −0.06 ± 3.78 in pPR/pNR (p = 0.0005); 107.91 ± 274.40, in pCR, −28.33 ± 202.91 in pPR/pNR, (p = 0.004), respectively). According to ROC curve analysis, pre-treatment kurtosis with an optimal cut-off value of ≤3.29 was defined as the best discriminative parameter, resulting in a sensitivity and specificity in predicting pCR of 81.5% and 61.5%, respectively. Conclusions: TA parameters extracted from T2-WI MRI images could play a key role as imaging biomarkers in the prediction of response to nChRT in LARC patients. ML algorithms can be used to efficiently combine all TA parameters in order to improve diagnostic accuracy.
- 19 August 2022
- Published by MDPI AG in Tomography
- Vol. 8 (4) , 2059-2072
Open AccessPerformance of Machine Learning and Texture Analysis for Predicting Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer with 3T MRI
Background: To evaluate the diagnostic performance of a Machine Learning (ML) algorithm based on Texture Analysis (TA) parameters in the prediction of Pathological Complete Response (pCR) to Neoadjuvant Chemoradiotherapy (nChRT) in Locally Advanced Rectal Cancer (LARC) patients. Methods: LARC patients were prospectively enrolled to undergo pre- and post-nChRT 3T MRI for initial loco-regional staging. TA was performed on axial T2-Weighted Images (T2-WI) to extract specific parameters, including skewness, kurtosis, entropy, and mean of positive pixels. For the assessment of TA parameter diagnostic performance, all patients underwent complete surgical resection, which served as a reference standard. ROC curve analysis was carried out to determine the discriminatory accuracy of each quantitative TA parameter to predict pCR. A ML-based decisional tree was implemented combining all TA parameters in order to improve diagnostic accuracy. Results: Forty patients were considered for final study population. Entropy, kurtosis and MPP showed statistically significant differences before and after nChRT in patients with pCR; in particular, when patients with Pathological Partial Response (pPR) and/or Pathological Non-Response (pNR) were considered, entropy and skewness showed significant differences before and after nChRT (all p < 0.05). In terms of absolute value changes, pre- and post-nChRT entropy, and kurtosis showed significant differences (0.31 ± 0.35, in pCR, −0.02 ± 1.28 in pPR/pNR, (p = 0.04); 1.87 ± 2.19, in pCR, −0.06 ± 3.78 in pPR/pNR (p = 0.0005); 107.91 ± 274.40, in pCR, −28.33 ± 202.91 in pPR/pNR, (p = 0.004), respectively). According to ROC curve analysis, pre-treatment kurtosis with an optimal cut-off value of ≤3.29 was defined as the best discriminative parameter, resulting in a sensitivity and specificity in predicting pCR of 81.5% and 61.5%, respectively. Conclusions: TA parameters extracted from T2-WI MRI images could play a key role as imaging biomarkers in the prediction of response to nChRT in LARC patients. ML algorithms can be used to efficiently combine all TA parameters in order to improve diagnostic accuracy.
- Open Access
Radiomic Cancer Hallmarks to Identify High-Risk Patients in Non-Metastatic Colon Cancer
The study was aimed to develop a radiomic model able to identify high-risk colon cancer by analyzing pre-operative CT scans. The study population comprised 148 patients: 108 with non-metastatic colon cancer were retrospectively enrolled from January 2015 to June 2020, and 40 patients were used as the external validation cohort. The population was divided into two groups—High-risk and No-risk—following the presence of at least one high-risk clinical factor. All patients had baseline CT scans, and 3D cancer segmentation was performed on the portal phase by two expert radiologists using open-source software (3DSlicer v4.10.2). Among the 107 radiomic features extracted, stable features were selected to evaluate the inter-class correlation (ICC) (cut-off ICC > 0.8). Stable features were compared between the two groups (T-test or Mann–Whitney), and the significant features were selected for univariate and multivariate logistic regression to build a predictive radiomic model. The radiomic model was then validated with an external cohort. In total, 58/108 were classified as High-risk and 50/108 as No-risk. A total of 35 radiomic features were stable (0.81 ≤ ICC < 0.92). Among these, 28 features were significantly different between the two groups (p < 0.05), and only 9 features were selected to build the radiomic model. The radiomic model yielded an AUC of 0.73 in the internal cohort and 0.75 in the external cohort. In conclusion, the radiomic model could be seen as a performant, non-invasive imaging tool to properly stratify colon cancers with high-risk disease.
Open AccessRadiomic Cancer Hallmarks to Identify High-Risk Patients in Non-Metastatic Colon Cancer
The study was aimed to develop a radiomic model able to identify high-risk colon cancer by analyzing pre-operative CT scans. The study population comprised 148 patients: 108 with non-metastatic colon cancer were retrospectively enrolled from January 2015 to June 2020, and 40 patients were used as the external validation cohort. The population was divided into two groups—High-risk and No-risk—following the presence of at least one high-risk clinical factor. All patients had baseline CT scans, and 3D cancer segmentation was performed on the portal phase by two expert radiologists using open-source software (3DSlicer v4.10.2). Among the 107 radiomic features extracted, stable features were selected to evaluate the inter-class correlation (ICC) (cut-off ICC > 0.8). Stable features were compared between the two groups (T-test or Mann–Whitney), and the significant features were selected for univariate and multivariate logistic regression to build a predictive radiomic model. The radiomic model was then validated with an external cohort. In total, 58/108 were classified as High-risk and 50/108 as No-risk. A total of 35 radiomic features were stable (0.81 ≤ ICC < 0.92). Among these, 28 features were significantly different between the two groups (p < 0.05), and only 9 features were selected to build the radiomic model. The radiomic model yielded an AUC of 0.73 in the internal cohort and 0.75 in the external cohort. In conclusion, the radiomic model could be seen as a performant, non-invasive imaging tool to properly stratify colon cancers with high-risk disease.
- Open Access
- 3 October 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (19) , 9211
Perioperative Chemotherapy with FLOT Scheme in Resectable Gastric Adenocarcinoma: A Preliminary Correlation between TRG and Radiomics
Perioperative chemotherapy (p-ChT) with a fluorouracil plus leucovorin, oxaliplatin, and docetaxel (FLOT) scheme is the gold standard of care for locally advanced gastric cancer. We aimed to test CT radiomics performance in early response prediction for p-ChT. Patients with advanced gastric cancer who underwent contrast enhanced CT prior to and post p-ChT were retrospectively enrolled. Histologic evaluation of resected specimens was used as the reference standard, and patients were divided into responders (TRG 1a-1b) and non-responders (TRG 2-3) according to their Becker tumor regression grade (TRG). A volumetric region of interest including the whole tumor tissue was drawn from a CT portal-venous phase before and after p-ChT; 120 radiomic features, both first and second order, were extracted. CT radiomics performances were derived from baseline CT radiomics alone and ΔRadiomics to predict response to p-ChT according to the TRG and tested using a receiver operating characteristic (ROC) curve. The final population comprised 15 patients, 6 (40%) responders and 9 (60%) non-responders. Among pre-treatment CT radiomics parameters, Shape, GLCM, First order, and NGTDM features showed a significant ability to discriminate between responders and non-responders (p < 0.011), with Cluster Shade and Autocorrelation (GLCM features) having AUC = 0.907. ΔRadiomics showed significant differences for Shape, GLRLM, GLSZM, and NGTDM features (p < 0.007). MeshVolume (Shape feature) and LongRunEmphasis (GLRLM feature) had AUC = 0.889. In conclusion, CT radiomics may represent an important supportive approach for the radiologic evaluation of advanced gastric cancer patients.
- 3 October 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (19) , 9211
Open AccessPerioperative Chemotherapy with FLOT Scheme in Resectable Gastric Adenocarcinoma: A Preliminary Correlation between TRG and Radiomics
Perioperative chemotherapy (p-ChT) with a fluorouracil plus leucovorin, oxaliplatin, and docetaxel (FLOT) scheme is the gold standard of care for locally advanced gastric cancer. We aimed to test CT radiomics performance in early response prediction for p-ChT. Patients with advanced gastric cancer who underwent contrast enhanced CT prior to and post p-ChT were retrospectively enrolled. Histologic evaluation of resected specimens was used as the reference standard, and patients were divided into responders (TRG 1a-1b) and non-responders (TRG 2-3) according to their Becker tumor regression grade (TRG). A volumetric region of interest including the whole tumor tissue was drawn from a CT portal-venous phase before and after p-ChT; 120 radiomic features, both first and second order, were extracted. CT radiomics performances were derived from baseline CT radiomics alone and ΔRadiomics to predict response to p-ChT according to the TRG and tested using a receiver operating characteristic (ROC) curve. The final population comprised 15 patients, 6 (40%) responders and 9 (60%) non-responders. Among pre-treatment CT radiomics parameters, Shape, GLCM, First order, and NGTDM features showed a significant ability to discriminate between responders and non-responders (p < 0.011), with Cluster Shade and Autocorrelation (GLCM features) having AUC = 0.907. ΔRadiomics showed significant differences for Shape, GLRLM, GLSZM, and NGTDM features (p < 0.007). MeshVolume (Shape feature) and LongRunEmphasis (GLRLM feature) had AUC = 0.889. In conclusion, CT radiomics may represent an important supportive approach for the radiologic evaluation of advanced gastric cancer patients.
- Open Access
- 31 May 2021
- Published by MDPI AG in Diagnostics
- Vol. 11 (6) , 1000
Influence of Adaptive Statistical Iterative Reconstructions on CT Radiomic Features in Oncologic Patients
Iterative reconstructions (IR) might alter radiomic features extraction. We aim to evaluate the influence of Adaptive Statistical Iterative Reconstruction-V (ASIR-V) on CT radiomic features. Patients who underwent unenhanced abdominal CT (Revolution Evo, GE Healthcare, USA) were retrospectively enrolled. Raw data of filtered-back projection (FBP) were reconstructed with 10 levels of ASIR-V (10–100%). CT texture analysis (CTTA) of liver, kidney, spleen and paravertebral muscle for all datasets was performed. Six radiomic features (mean intensity, standard deviation (SD), entropy, mean of positive pixel (MPP), skewness, kurtosis) were extracted and compared between FBP and all ASIR-V levels, with and without altering the spatial scale filter (SSF). CTTA of all organs revealed significant differences between FBP and all ASIR-V reconstructions for mean intensity, SD, entropy and MPP (all p < 0.0001), while no significant differences were observed for skewness and kurtosis between FBP and all ASIR-V reconstructions (all p > 0.05). A per-filter analysis was also performed comparing FBP with all ASIR-V reconstructions for all six SSF separately (SSF0-SSF6). Results showed significant differences between FBP and all ASIR-V reconstruction levels for mean intensity, SD, and MPP (all filters p < 0.0315). Skewness and kurtosis showed no differences for all comparisons performed (all p > 0.05). The application of incremental ASIR-V levels affects CTTA across various filters. Skewness and kurtosis are not affected by IR and may be reliable quantitative parameters for radiomic analysis.
- 31 May 2021
- Published by MDPI AG in Diagnostics
- Vol. 11 (6) , 1000
Open AccessInfluence of Adaptive Statistical Iterative Reconstructions on CT Radiomic Features in Oncologic Patients
Iterative reconstructions (IR) might alter radiomic features extraction. We aim to evaluate the influence of Adaptive Statistical Iterative Reconstruction-V (ASIR-V) on CT radiomic features. Patients who underwent unenhanced abdominal CT (Revolution Evo, GE Healthcare, USA) were retrospectively enrolled. Raw data of filtered-back projection (FBP) were reconstructed with 10 levels of ASIR-V (10–100%). CT texture analysis (CTTA) of liver, kidney, spleen and paravertebral muscle for all datasets was performed. Six radiomic features (mean intensity, standard deviation (SD), entropy, mean of positive pixel (MPP), skewness, kurtosis) were extracted and compared between FBP and all ASIR-V levels, with and without altering the spatial scale filter (SSF). CTTA of all organs revealed significant differences between FBP and all ASIR-V reconstructions for mean intensity, SD, entropy and MPP (all p < 0.0001), while no significant differences were observed for skewness and kurtosis between FBP and all ASIR-V reconstructions (all p > 0.05). A per-filter analysis was also performed comparing FBP with all ASIR-V reconstructions for all six SSF separately (SSF0-SSF6). Results showed significant differences between FBP and all ASIR-V reconstruction levels for mean intensity, SD, and MPP (all filters p < 0.0315). Skewness and kurtosis showed no differences for all comparisons performed (all p > 0.05). The application of incremental ASIR-V levels affects CTTA across various filters. Skewness and kurtosis are not affected by IR and may be reliable quantitative parameters for radiomic analysis.