Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets

Yang, Ching-Juei; Wang, Chien-Kuo; Fang, Yueh‐Fu; Wang, Jingyao; Su, Fong-Chin; Tsai, Hong‐Ming; Lin, Ying‐Ting; Tsai, Hung‐Wen; Yeh, Lee‐Ren

doi:10.1371/journal.pone.0255605

Cited by 11 publications

(7 citation statements)

References 51 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sixty studies had lesion segmentation as a primary or secondary study aim. Thirty-six are journal articles [ 24 , 29 , 31 , 32 , 38 , 46 , 47 , 55 , 56 , 62 , 72 , 78 , 84 , 91 , 93 , 94 , 97 , 98 , 102 , 111 , 115 , 117 , 118 , 122 , 124 , 125 , 130 , 133 – 135 , 137 , 138 , 140 , 201 ], and twenty-four [ 22 , 37 , 42 , 64 , 65 , 68 , 82 , 88 , 92 , 96 , 99 , 103 , 108 , 121 , 124 , 126 – 129 , 131 , 132 , 136 , 139 , 200 ] are proceedings papers.…”

Section: Resultsmentioning

confidence: 99%

Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review

Radiya,

Joakimsen,

Mikalsen

et al. 2023

Eur Radiol

View full text Add to dashboard Cite

Objectives Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field by answering the following questions: (1) How is ML applied in liver computed tomography (CT) imaging? (2) How well do ML systems perform in liver CT imaging? (3) What are the clinical applications of ML in liver CT imaging? Methods A systematic review was carried out according to the guidelines from the PRISMA-P statement. The search string focused on studies containing content relating to artificial intelligence, liver, and computed tomography. Results One hundred ninety-one studies were included in the study. ML was applied to CT liver imaging by image analysis without clinicians’ intervention in majority of studies while in newer studies the fusion of ML method with clinical intervention have been identified. Several were documented to perform very accurately on reliable but small data. Most models identified were deep learning-based, mainly using convolutional neural networks. Potentially many clinical applications of ML to CT liver imaging have been identified through our review including liver and its lesion segmentation and classification, segmentation of vascular structure inside the liver, fibrosis and cirrhosis staging, metastasis prediction, and evaluation of chemotherapy. Conclusion Several studies attempted to provide transparent result of the model. To make the model convenient for a clinical application, prospective clinical validation studies are in urgent call. Computer scientists and engineers should seek to cooperate with health professionals to ensure this. Key Points • ML shows great potential for CT liver image tasks such as pixel-wise segmentation and classification of liver and liver lesions, fibrosis staging, metastasis prediction, and retrieval of relevant liver lesions from similar cases of other patients. • Despite presenting the result is not standardized, many studies have attempted to provide transparent results to interpret the machine learning method performance in the literature. • Prospective studies are in urgent call for clinical validation of ML method, preferably carried out by cooperation between clinicians and computer scientists.

show abstract

Section: Resultsmentioning

confidence: 99%

Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review

Radiya,

Joakimsen,

Mikalsen

et al. 2023

Eur Radiol

View full text Add to dashboard Cite

show abstract

“…Among the selected studies, we found that the mean age of patients across the studies was 56 years, with the study size ranging between 16 [12] and 7512 [13] subjects with HCC. Many of the studies (n=24, 67%) used either Computed Tomography (CT) or Magnetic Resonance Imaging (MRI) scans as the basis of their algorithm development [12][13][14]16,17,[19][20][21][22][23][24][25][28][29][30][31][33][34][35]39,40,[42][43][44]. A modest number of images (100 to 1000) were used for these studies, except for Kim et.…”

Section: Resultsmentioning

confidence: 99%

“…As seen in Table 1, 16 studies (44%) were extracted that focused on different AI tools used for the diagnostic purposes of HCC or liver tumors. Many of the studies (n=12, 33%) used CT or MRI scans as the foundation of their technique and developed an AI algorithm to improve various characteristics of the images acquired [12][13][14]16,17,[20][21][22][23][24][25]. Among the studies, the Fully Automated Pipeline based on Machine learning had the highest accuracy of 98.8% for differentiating HCC from normal tissue [18]).…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence Used for the Diagnosis, Treatment and Surveillance of Hepatocellular Carcinoma: A Systematic Review

2022

URNCST Journal

View full text Add to dashboard Cite

Introduction: Hepatocellular Carcinoma (HCC) is the most common type of liver cancer, compromising about 75% of all liver cancers. The advancement in artificial intelligence (AI) has paved the way in the field of liver cancers to help clinicians with early diagnosis, treatment guidance and surveillance for HCC. The aim of this review was to summarize different AI-assisted methods that could be used in the diagnosis, treatment, and surveillance of HCC throughout the literature. Methods: PubMed and MEDLINE OVID databases were searched for primary studies involving AI and HCC published from 2012 to February 2022. Data was obtained, including study characteristics and outcome measures: accuracy, area under curve (AUC), specificity, sensitivity, and errors. A narrative synthesis was used to summarize the findings. Results: The systematic search produced 340 studies, of which 36 met the pre-determined eligibility criteria. The studies were published between 2012 to 2020. All the studies with their respective AI models/algorithms were described and summarized in the tables according to their role in the diagnosis, treatment, or surveillance of HCC. All the studies included used different AI algorithms, out of which, most were used for diagnostic purposes (44%), followed by treatment prediction (38%) and then surveillance of HCC (18%). Among studies, 38% reported their results as AUC, 33% of the studies reported accuracy, 19% reported sensitivity and specificity, 4% reported concordance indices (C-indices), 3% reported the mean errors and 2% reported AUROC values for respective AI models used. The accuracy of the diagnostic, treatment and surveillance tools range from 40% to 99%, 50% to 90% and 70% to 95% respectively. Conclusion: Many AI models are available that show promising results for the different applications in diagnosis, treatment, and surveillance of HCC. However, the demand for the generalization of these results remains. Future research should focus on improving the results and accuracy of these algorithms used for HCC to reduce the risks in complicated procedures.

show abstract

“…The U-net is a convolutional neural network (CNN) architecture specifically designed for biomedical image segmentation, which also takes into account the spatial context [ 13 ]. CNN architectures such as U-nets have recently shown their value in many medical applications, e.g., in detection, classification, and segmentation tasks based on radiological images [ 28 , 29 ], as they are robust to variations in shape, orientation, and position. Even though the achieved accuracy of 75% of the U-net seems low at first glance, it must be taken into account that this result was achieved with a limited number of samples ( n = 12), a specific marker panel was used, and the calculation of the accuracy is based on the classification of each individual cell.…”

Section: Discussionmentioning

confidence: 99%

A Deep-Learning-Computed Cancer Score for the Identification of Human Hepatocellular Carcinoma Area Based on a Six-Colour Multiplex Immunofluorescence Panel

Dievernich

Stegmaier

Achenbach

et al. 2023

Cells

View full text Add to dashboard Cite

Liver cancer is one of the most frequently diagnosed and fatal cancers worldwide, with hepatocellular carcinoma (HCC) being the most common primary liver cancer. Hundreds of studies involving thousands of patients have now been analysed across different cancer types, including HCC, regarding the effects of immune infiltrates on the prognosis of cancer patients. However, for these analyses, an unambiguous delineation of the cancer area is paramount, which is difficult due to the strong heterogeneity and considerable inter-operator variability induced by qualitative visual assessment and manual assignment. Nowadays, however, multiplex analyses allow the simultaneous evaluation of multiple protein markers, which, in conjunction with recent machine learning approaches, may offer great potential for the objective, enhanced identification of cancer areas with further in situ analysis of prognostic immune parameters. In this study, we, therefore, used an exemplary five-marker multiplex immunofluorescence panel of commonly studied markers for prognosis (CD3 T, CD4 T helper, CD8 cytotoxic T, FoxP3 regulatory T, and PD-L1) and DAPI to assess which analytical approach is best suited to combine morphological and immunohistochemical data into a cancer score to identify the cancer area that best matches an independent pathologist’s assignment. For each cell, a total of 68 individual cell features were determined, which were used as input for 4 different approaches for computing a cancer score: a correlation-based selection of individual cell features, a MANOVA-based selection of features, a multilayer perceptron, and a convolutional neural network (a U-net). Accuracy was used to evaluate performance. With a mean accuracy of 75%, the U-net was best capable of identifying the cancer area. Although individual cell features showed a strong heterogeneity between patients, the spatial representations obtained with the computed cancer scores delineate HCC well from non-cancer liver tissues. Future analyses with larger sample sizes will help to improve the model and enable direct, in-depth investigations of prognostic parameters, ultimately enabling precision medicine.

show abstract

Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets

Cited by 11 publications

References 51 publications

Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review

Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review

Artificial Intelligence Used for the Diagnosis, Treatment and Surveillance of Hepatocellular Carcinoma: A Systematic Review

A Deep-Learning-Computed Cancer Score for the Identification of Human Hepatocellular Carcinoma Area Based on a Six-Colour Multiplex Immunofluorescence Panel

Contact Info

Product

Resources

About