Prediction of Anastomotic Leakage in Esophageal Cancer Surgery: A Multimodal Machine Learning Model Integrating Imaging and Clinical Data.

RATIONALE AND OBJECTIVES: Surgery in combination with chemo/radiotherapy is the standard treatment for locally advanced esophageal cancer. Even after the introduction of minimally invasive techniques, esophagectomy carries significant morbidity and mortality. One of the most common and feared complications of esophagectomy is anastomotic leakage (AL). Our work aimed to develop a multimodal machine-learning model combining CT-derived and clinical data for predicting AL following esophagectomy for esophageal cancer. MATERIAL AND METHODS: A total of 471 patients were prospectively included (Jan 2010-Dec 2022). Preoperative computed tomography (CT) was used to evaluate celia trunk stenosis and vessel calcification. Clinical variables, including demographics, disease stage, operation details, postoperative CRP, and stage, were combined with CT data to build a model for AL prediction. Data was split into 80%:20% for training and testing, and an XGBoost model was developed with 10-fold cross-validation and early stopping. ROC curves and respective areas under the curve (AUC), sensitivity, specificity, PPV, NPV, and F1-scores were calculated. RESULTS: A total of 117 patients (24.8%) exhibited post-operative AL. The XGboost model achieved an AUC of 79.2% (95%CI 69%-89.4%) with a specificity of 77.46%, a sensitivity of 65.22%, PPV of 48.39%, NPV of 87.3%, and F1-score of 56%. Shapley Additive exPlanation analysis showed the effect of individual variables on the result of the model. Decision curve analysis showed that the model was particularly beneficial for threshold probabilities between 15% and 48%. CONCLUSION: A clinically relevant multimodal model can predict AL, which is especially valuable in cases with low clinical probability of AL.

Convolutional neural networks for the differentiation between benign and malignant renal tumors with a multicenter international computed tomography dataset.

OBJECTIVES: To use convolutional neural networks (CNNs) for the differentiation between benign and malignant renal tumors using contrast-enhanced CT images of a multi-institutional, multi-vendor, and multicenter CT dataset. METHODS: A total of 264 histologically confirmed renal tumors were included, from US and Swedish centers. Images were augmented and divided randomly 70%:30% for algorithm training and testing. Three CNNs (InceptionV3, Inception-ResNetV2, VGG-16) were pretrained with transfer learning and fine-tuned with our dataset to distinguish between malignant and benign tumors. The ensemble consensus decision of the three networks was also recorded. Performance of each network was assessed with receiver operating characteristics (ROC) curves and their area under the curve (AUC-ROC). Saliency maps were created to demonstrate the attention of the highest performing CNN. RESULTS: Inception-ResNetV2 achieved the highest AUC of 0.918 (95% CI 0.873-0.963), whereas VGG-16 achieved an AUC of 0.813 (95% CI 0.752-0.874). InceptionV3 and ensemble achieved the same performance with an AUC of 0.894 (95% CI 0.844-0.943). Saliency maps indicated that Inception-ResNetV2 decisions are based on the characteristics of the tumor while in most tumors considering the characteristics of the interface between the tumor and the surrounding renal parenchyma. CONCLUSION: Deep learning based on a diverse multicenter international dataset can enable accurate differentiation between benign and malignant renal tumors. CRITICAL RELEVANCE STATEMENT: Convolutional neural networks trained on a diverse CT dataset can accurately differentiate between benign and malignant renal tumors. KEY POINTS: • Differentiation between benign and malignant tumors based on CT is extremely challenging. • Inception-ResNetV2 trained on a diverse dataset achieved excellent differentiation between tumor types. • Deep learning can be used to distinguish between benign and malignant renal tumors.

A pilot radiometabolomics integration study for the characterization of renal oncocytic neoplasia.

Differentiating benign renal oncocytic tumors and malignant renal cell carcinoma (RCC) on imaging and histopathology is a critical problem that presents an everyday clinical challenge. This manuscript aims to demonstrate a novel methodology integrating metabolomics with radiomics features (RF) to differentiate between benign oncocytic neoplasia and malignant renal tumors. For this purpose, thirty-three renal tumors (14 renal oncocytic tumors and 19 RCC) were prospectively collected and histopathologically characterised. Matrix-assisted laser desorption/ionisation mass spectrometry imaging (MALDI-MSI) was used to extract metabolomics data, while RF were extracted from CT scans of the same tumors. Statistical integration was used to generate multilevel network communities of -omics features. Metabolites and RF critical for the differentiation between the two groups (delta centrality > 0.1) were used for pathway enrichment analysis and machine learning classifier (XGboost) development. Receiver operating characteristics (ROC) curves and areas under the curve (AUC) were used to assess classifier performance. Radiometabolomics analysis demonstrated differential network node configuration between benign and malignant renal tumors. Fourteen nodes (6 RF and 8 metabolites) were crucial in distinguishing between the two groups. The combined radiometabolomics model achieved an AUC of 86.4%, whereas metabolomics-only and radiomics-only classifiers achieved AUC of 72.7% and 68.2%, respectively. Analysis of significant metabolite nodes identified three distinct tumour clusters (malignant, benign, and mixed) and differentially enriched metabolic pathways. In conclusion, radiometabolomics integration has been presented as an approach to evaluate disease entities. In our case study, the method identified RF and metabolites important in differentiating between benign oncocytic neoplasia and malignant renal tumors, highlighting pathways differentially expressed between the two groups. Key metabolites and RF identified by radiometabolomics can be used to improve the identification and differentiation between renal neoplasms.

Machine Learning Integrating 99mTc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors.

The increasing evidence of oncocytic renal tumors positive in 99mTc Sestamibi Single Photon Emission Tomography/Computed Tomography (SPECT/CT) examination calls for the development of diagnostic tools to differentiate these tumors from more aggressive forms. This study combined radiomics analysis with the uptake of 99mTc Sestamibi on SPECT/CT to differentiate benign renal oncocytic neoplasms from renal cell carcinoma. A total of 57 renal tumors were prospectively collected. Histopathological analysis and radiomics data extraction were performed. XGBoost classifiers were trained using the radiomics features alone and combined with the results from the visual evaluation of 99mTc Sestamibi SPECT/CT examination. The combined SPECT/radiomics model achieved higher accuracy (95%) with an area under the curve (AUC) of 98.3% (95% CI 93.7-100%) than the radiomics-only model (71.67%) with an AUC of 75% (95% CI 49.7-100%) and visual evaluation of 99mTc Sestamibi SPECT/CT alone (90.8%) with an AUC of 90.8% (95%CI 82.5-99.1%). The positive predictive values of SPECT/radiomics, radiomics-only, and 99mTc Sestamibi SPECT/CT-only models were 100%, 85.71%, and 85%, respectively, whereas the negative predictive values were 85.71%, 55.56%, and 94.6%, respectively. Feature importance analysis revealed that 99mTc Sestamibi uptake was the most influential attribute in the combined model. This study highlights the potential of combining radiomics analysis with 99mTc Sestamibi SPECT/CT to improve the preoperative characterization of benign renal oncocytic neoplasms. The proposed SPECT/radiomics classifier outperformed the visual evaluation of 99mTc Sestamibii SPECT/CT and the radiomics-only model, demonstrating that the integration of 99mTc Sestamibi SPECT/CT and radiomics data provides improved diagnostic performance, with minimal false positive and false negative results.

Radiomics Analysis for Multiple Myeloma: A Systematic Review with Radiomics Quality Scoring.

Multiple myeloma (MM) is one of the most common hematological malignancies affecting the bone marrow. Radiomics analysis has been employed in the literature in an attempt to evaluate the bone marrow of MM patients. This manuscript aimed to systematically review radiomics research on MM while employing a radiomics quality score (RQS) to accurately assess research quality in the field. A systematic search was performed on Web of Science, PubMed, and Scopus. The selected manuscripts were evaluated (data extraction and RQS scoring) by three independent readers (R1, R2, and R3) with experience in radiomics analysis. A total of 23 studies with 2682 patients were included, and the median RQS was 10 for R1 (IQR 5.5-12) and R3 (IQR 8.3-12) and 11 (IQR 7.5-12.5) for R2. RQS was not significantly correlated with any of the assessed bibliometric data (impact factor, quartile, year of publication, and imaging modality) (p > 0.05). Our results demonstrated the low quality of published radiomics research in MM, similarly to other fields of radiomics research, highlighting the need to tighten publication standards.

Current Imaging Diagnosis of Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is the fourth leading cause of cancer related death worldwide. Radiology has traditionally played a central role in HCC management, ranging from screening of high-risk patients to non-invasive diagnosis, as well as the evaluation of treatment response and post-treatment follow-up. From liver ultrasonography with or without contrast to dynamic multiple phased CT and dynamic MRI with diffusion protocols, great progress has been achieved in the last decade. Throughout the last few years, pathological, biological, genetic, and immune-chemical analyses have revealed several tumoral subtypes with diverse biological behavior, highlighting the need for the re-evaluation of established radiological methods. Considering these changes, novel methods that provide functional and quantitative parameters in addition to morphological information are increasingly incorporated into modern diagnostic protocols for HCC. In this way, differential diagnosis became even more challenging throughout the last few years. Use of liver specific contrast agents, as well as CT/MRI perfusion techniques, seem to not only allow earlier detection and more accurate characterization of HCC lesions, but also make it possible to predict response to treatment and survival. Nevertheless, several limitations and technical considerations still exist. This review will describe and discuss all these imaging modalities and their advances in the imaging of HCC lesions in cirrhotic and non-cirrhotic livers. Sensitivity and specificity rates, method limitations, and technical considerations will be discussed.

Role of Radiology in the Preoperative Detection of Arterial Calcification and Celiac Trunk Stenosis and Its Association with Anastomotic Leakage Post Esophagectomy, an Up-to-Date Review of the Literature.

Surgical resection of the esophagus remains a critical component of the multimodal treatment of esophageal cancer. Anastomotic leakage (AL) is the most significant complication following esophagectomy, in terms of clinical implications. Identifying risk factors for AL is important for modifying patient management and improving surgical outcomes. This review aims to examine the role of radiological risk factors for AL after esophagectomy, and in particular, arterial calcification and celiac trunk stenosis. Eligible publications prior to 25 August 2021 were retrieved from Medline and Google Scholar using a predefined search algorithm. A total of 68 publications were identified, of which 9 original studies remained for in-depth analysis. The majority of these studies found correlations between calcifications in the aorta, celiac trunk, and right post-celiac arteries and AL following esophagectomy. Some studies suggest celiac trunk stenosis as a more appropriate surrogate. Our up-to-date review highlights the need for automated quantification of aortic calcifications, as well as the degree of celiac trunk stenosis in preoperative computed tomography in patients undergoing esophagectomy, to obtain robust and reproducible measurements that can be used for a definite correlation.

Combining contrast-enhanced ultrasound, CT perfusion and 99mTc-Sestamibi SPECT/CT to guide diagnosis in a case of solid renal tumour.

Definitive, pre-operative differentiation of solid renal lesions by ultrasound, contrast-enhanced multiphasic CT or MRI examinations is often not possible. An increasing amount of literature indicates the added value of 99mTc-Sestamibi SPECT/CT, CT perfusion and contrast-enhanced ultrasound in the pre-operative characterisation of solid renal tumours. This case report presents the diagnostic approach of a solid renal tumour that turned out to be a hybrid oncocytic chromophobe tumour in a patient with Stage 3 renal failure by combining the three aforementioned modern examination techniques.

CT liver perfusion in patients with hepatocellular carcinoma: can we modify acquisition protocol to reduce patient exposure?

OBJECTIVES: To investigate the potential of decreasing the number of scans and associated radiation exposure involved in CT liver perfusion (CTLP) dynamic studies for hepatocellular carcinoma (HCC) assessment. METHODS: Twenty-four CTLP image datasets of patients with HCC were retrospectively analyzed. All examinations were performed on a modern CT system using a standard acquisition protocol involving 35 scans with 1.7 s interval. A deconvolution-based or a standard algorithm was employed to compute ten perfusion parametric maps. 3D ROIs were positioned on 33 confirmed HCCs and non-malignant parenchyma. Analysis was repeated for two subsampled datasets generated from the original dataset by including only the (a) 18 odd-numbered scans with 3.4 s interval and (b) 18 first scans with 1.7 s interval. Standard and modified datasets were compared regarding the (a) accuracy of calculated perfusion parameters, (b) power of parametric maps to discriminate HCCs from liver parenchyma, and (c) associated radiation exposure. RESULTS: When the time interval between successive scans was doubled, perfusion parameters of HCCs were found unaffected (p > 0.05) and the discriminating efficiency of parametric maps was preserved (p < 0.05). In contrast, significant differences were found for all perfusion parameters of HCCs when acquisition duration was reduced to half (p < 0.05), while the discriminating efficiency of four parametric maps was significantly deteriorated (p < 0.05). Modified CTLP acquisition protocols were found to involve 48.5% less patient exposure. CONCLUSIONS: Doubling the interscan time interval may considerably reduce radiation exposure from CTLP studies performed for HCC evaluation without affecting the diagnostic efficiency of perfusion maps generated with either standard or deconvolution-based mathematical model. KEY POINTS: • CT liver perfusion for HCC diagnosis/assessment is not routinely used in clinical practice mainly due to the associated high radiation exposure. • Two alternative acquisition protocols involving 18 scans of the liver were compared with the standard 35-scan protocol. • Increasing the time interval between successive scans to 3.4 s was found to preserve the accuracy of computed perfusion parameters derived with a standard or a deconvolution-based model and to reduce radiation exposure by 48.5%.

Perfusion-CT analysis for assessment of hepatocellular carcinoma lesions: diagnostic value of different perfusion maps.

BACKGROUND: Computed tomography liver perfusion (CTLP) has been improved in recent years, offering a variety of perfusion-parametric maps. A map that better discriminates hepatocellular carcinoma (HCC) is still to be found. PURPOSE: To compare different CTLP maps, regarding their ability to differentiate cirrhotic or non-cirrhotic parenchyma from malignant HCC. MATERIAL AND METHODS: Twenty-six patients (11 cirrhotic) with 50 diagnosed HCC lesions, underwent CTLP on a 128-row dual-energy CT system. Nine different maps were generated. Regions of interest (ROIs) were positioned on non-tumorous parenchyma and on HCCs found on previous magnetic resonance imaging. Perfusion parameters for non-cirrhotic and cirrhotic livers were compared. Receiver operating characteristic (ROC) analysis was employed to evaluate each map's ability to discriminate HCCs from non-tumorous livers. Comparison of ROC curves was performed to evaluate statistical significance of differences in the discriminating efficiency of derived perfusion maps. RESULTS: Perfusion parameters for non-tumorous liver and HCCs recorded in cirrhotic patients did not significantly differ from corresponding values recorded in non-cirrhotic patients ( P > 0.05). The highest power for HCC discrimination was found for the maximum-slope-of-increase (MSI) parametric map, with estimated the area under ROC curve of 0.997. An MSI cut-off criterion of 2.2 HU/s was found to provide 96% sensitivity and 100% specificity. Time to peak, blood flow, and transit time to peak were also found to have high discriminating power. CONCLUSION: Among available CTLP-derived perfusion parameters, MSI was found to provide the highest diagnostic accuracy in discriminating HCCs from non-tumorous parenchyma. Perfusion parameters for non-tumorous livers and HCCs were not found to significantly differ between cirrhotic and non-cirrhotic patients.