The Role of Radiomics and AI Technologies in the Segmentation, Detection, and Management of Hepatocellular Carcinoma

Fahmy, Dalia; Alksas, Ahmed; Elnakib, Ahmed; Mahmoud, Ali; Kandil, Heba; Khalil, Ashraf; Ghazal, Mohammed; Bogaert, Eric Van; Contractor, Sohail; El-Baz, Ayman

doi:10.3390/cancers14246123

Cited by 6 publications

(3 citation statements)

References 169 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evolution of deep learning has resulted in significant progress in medical imaging, particularly in the segmentation of liver cancer using CT images 26 . Despite the widespread use of segmentation models, a gap remains in the development of models specifically designed for treatment selection.…”

Section: Discussionmentioning

confidence: 99%

Investigation of deep learning model for predicting immune checkpoint inhibitor treatment efficacy on contrast-enhanced computed tomography images of hepatocellular carcinoma

Nakao,

Nishihara,

Sasaki

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Although the use of immune checkpoint inhibitors (ICIs)-targeted agents for unresectable hepatocellular carcinoma (HCC) is promising, individual response variability exists. Therefore, we developed an artificial intelligence (AI)-based model to predict treatment efficacy using pre-ICIs contrast-enhanced computed tomography (CT) imaging characteristics. We evaluated the efficacy of atezolizumab and bevacizumab in 43 patients at the Nagasaki University Hospital from 2020 to 2022 using the modified Response Evaluation Criteria in Solid Tumors. A total of 197 Progressive Disease (PD), 271 Partial Response (PR), and 342 Stable Disease (SD) contrast CT images of HCC were used for training. We used ResNet-18 as the Convolutional Neural Network (CNN) model and YOLOv5, YOLOv7, YOLOv8 as the You Only Look Once (YOLO) model with precision-recall curves and class activation maps (CAMs) for diagnostic performance evaluation and model interpretation, respectively. The 3D t-distributed Stochastic Neighbor Embedding was used for image feature analysis. The YOLOv7 model demonstrated Precision 53.7%, Recall 100%, F1 score 69.8%, mAP@0.5 99.5% for PD, providing accurate and clinically versatile predictions by identifying decisive points. The ResNet-18 model had Precision 100% and Recall 100% for PD. However, the CAMs sites did not align with the tumors, suggesting the CNN model is not predicting that a given CT slice is PD, PR, or SD, but that it accurately predicts Individual Patient's CT slices. Preparing substantial training data for tumor drug effect prediction models is challenging compared to general tumor diagnosis models; hence, large-scale validation using an efficient YOLO model is warranted.

show abstract

Section: Discussionmentioning

confidence: 99%

Investigation of deep learning model for predicting immune checkpoint inhibitor treatment efficacy on contrast-enhanced computed tomography images of hepatocellular carcinoma

Nakao,

Nishihara,

Sasaki

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The evolution of deep learning has resulted in signi cant progress in medical imaging, particularly in the segmentation of liver cancer using CT images. 10 Despite the widespread use of segmentation models, a gap remains in the development of models speci cally designed for treatment selection. The primary ndings of our study are supported by the differentiation between the existing models and what is urgently required in clinical settings.…”

Section: Discussionmentioning

confidence: 99%

Investigation of optimization model for predicting immune checkpoint inhibitor treatment efficacy on contrast-enhanced computed tomography images of hepatocellular carcinoma using deep learning

Nakao,

Nishihara,

Sasaki

et al. 2023

Preprint

View full text Add to dashboard Cite

Background & Aims Although the use of immune checkpoint inhibitor (ICIs)-targeted agents for unresectable hepatocellular carcinoma (HCC) is promising, individual response variability exists. Therefore, we developed an artificial intelligence (AI)-based model to predict treatment efficacy using pre-ICI contrast-enhanced computed tomography (CT) imaging characteristics. Approach & Results We evaluated the efficacy of atezolizumab and bevacizumab or lenvatinib in 43 patients at the Nagasaki University Hospital from 2020–2022) using the modified Response Evaluation Criteria in Solid Tumors. A total of 197 Progressive Disease (PD), 271 Partial Response (PR), and 342 Stable Disease (SD) contrast CT images of HCC were used for training. We used ResNet18 as the Convolutional Neural Network (CNN) model and YOLOv7 as the You Only LookOnce (YOLO) model with precision-recall curves and class activation maps (CAMs) for diagnostic performance evaluation and model interpretation, respectively. The 3D t-distributed Stochastic Neighbor Embedding was used for image feature analysis. The CNN model had a PD prediction sensitivityof 84 %. However, the CAMs sites did not align with the tumors, suggesting the possible overlearning of non-tumor CT features. In contrast, the YOLO model demonstrated an area under the curve of 0.995 on the precision–recall curve for PD, providing accurate and clinically versatile predictions by identifying decisive points. Conclusions Preparing substantial training data for tumor drug effect prediction models is challenging compared to general tumor diagnosis models; hence, large-scale validation using an efficient YOLO model is warranted.

show abstract

“…With increased research and treatment for HCC, researchers and physicians may change the outcome and treatment of these patients. 62…”

Section: Role Of Radiomics and Artificial Intelligencementioning

confidence: 99%

Advancements in Molecular Imaging for the Diagnosis and Management of Hepatocellular Carcinoma

Gheisari,

Vali

2024

MRAJ

View full text Add to dashboard Cite

Hepatocellular Carcinoma (HCC) is a growing global health burden with high incidence and mortality rates. Despite advances in surgical techniques and perioperative care, outcomes after surgical treatment have not improved over the past three decades. Molecular imaging is an emerging field that enables researchers to study diseases at the molecular and cellular levels, enabling the detection of elevated serum α-fetoprotein (AFP) and abnormal expressions of various HCC-specific and nonspecific cell surface antigens and intracellular targets. Molecular imaging techniques detect liver lesions at the molecular and cellular level, allowing early detection and accurate staging of HCC. Positron emission tomography (PET) imaging offers greater sensitivity and specificity, while hepatobiliary-specific radiotracers with SPECT imaging provide insights into benign and malignant lesion differentiation. Radiomics and artificial intelligence are vital in deciphering molecular imaging data, with machine learning algorithms boosting diagnostic gains and predicting treatment response. Theranostics, a state-of-the-art application, provides diagnostic and therapeutic leverage following a single imaging agent. By understanding tumor biology in real time, radiopharmaceuticals can be transformed into personalized radiotherapies, enabling clinicians to make science-driven decisions throughout the illness. Future directions include developing novel radiotracers and integrating AI into clinical decision-making. Collaboration between academic researchers, clinicians, and industry colleagues is crucial to converting exciting advances into improved clinical outcomes for HCC patients.

show abstract

The Role of Radiomics and AI Technologies in the Segmentation, Detection, and Management of Hepatocellular Carcinoma

Cited by 6 publications

References 169 publications

Investigation of deep learning model for predicting immune checkpoint inhibitor treatment efficacy on contrast-enhanced computed tomography images of hepatocellular carcinoma

Investigation of deep learning model for predicting immune checkpoint inhibitor treatment efficacy on contrast-enhanced computed tomography images of hepatocellular carcinoma

Investigation of optimization model for predicting immune checkpoint inhibitor treatment efficacy on contrast-enhanced computed tomography images of hepatocellular carcinoma using deep learning

Advancements in Molecular Imaging for the Diagnosis and Management of Hepatocellular Carcinoma

Contact Info

Product

Resources

About