Machine-Learning Based Hybrid-Feature Analysis for Liver Cancer Classification Using Fused (MR and CT) Images

Prognostic Modeling for Liver Cirrhosis Mortality Prediction and Real-Time Health Monitoring from Electronic Health Data

Liver cirrhosis stands as a prominent contributor to mortality, impacting millions across the United States. Enabling health care providers to predict early mortality among patients with cirrhosis holds the potential to enhance treatment efficacy significantly. Our hypothesis centers on the correlation between mortality and laboratory test results along with relevant diagnoses in this patient cohort. Additionally, we posit that a deep learning model could surpass the predictive capabilities of the existing Model for End-Stage Liver Disease score. This research seeks to advance prognostic accuracy and refine approaches to address the critical challenges posed by cirrhosis-related mortality. This study evaluates the performance of an artificial neural network model for liver disease classification using various training dataset sizes. Through meticulous experimentation, three distinct training proportions were analyzed: 70%, 80%, and 90%. The model's efficacy was assessed using precision, recall, F1-score, accuracy, and support metrics, alongside receiver operating characteristic (ROC) and precision-recall (PR) curves. The ROC curves were quantified using the area under the curve (AUC) metric. Results indicated that the model's performance improved with an increased size of the training dataset. Specifically, the 80% training data model achieved the highest AUC, suggesting superior classification ability over the models trained with 70% and 90% data. PR analysis revealed a steep trade-off between precision and recall across all datasets, with 80% training data again demonstrating a slightly better balance. This is indicative of the challenges faced in achieving high precision with a concurrently high recall, a common issue in imbalanced datasets such as those found in medical diagnostics.

LCRNet: local cross-channel recalibration network for liver cancer classification based on CT images

Liver cancer is the leading cause of mortality in the world. Over the years, researchers have spent much effort in developing computer-aided techniques to improve clinicians' diagnosis efficiency and precision, aiming at helping patients with liver cancer to take treatment early. Recently, attention mechanisms can enhance the representational power of convolutional neural networks (CNNs), which have been widely used in medical image analysis. In this paper, we propose a novel architectural unit, local cross-channel recalibration (LCR) module, dynamically adjusting the relative importance of intermediate feature maps by considering the roles of different global context features and building the local dependencies between channels. LCR first extracts different global context features and integrates them by global context integration operator, then estimates per channel attention weight with a local cross-channel interaction manner. We combine the LCR module with the residual block to form a Residual-LCR module and construct a deep neural network termed local cross-channel recalibration network (LCRNet) based on a stack of Residual-LCR modules to recognize live cancer atomically based on CT images. Furthermore, This paper collects a clinical CT image dataset of liver cancer, AMU-CT, to verify the effectiveness of LCRNet, which will be publicly available. The experiments on the AMU-CT dataset and public SD-OCT dataset demonstrate our LCRNet significantly outperforms state-of-the-art attention-based CNNs. Specifically, our LCRNet improves accuracy by over 11% than ECANet on the AMU-CT dataset.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13755-023-00263-6.

A systematic literature analysis of multi-organ cancer diagnosis using deep learning techniques

Cancer is becoming the most toxic ailment identified among individuals worldwide. The mortality rate has been increasing rapidly every year, which causes progression in the various diagnostic technologies to handle this illness. The manual procedure for segmentation and classification with a large set of data modalities can be a challenging task. Therefore, a crucial requirement is to significantly develop the computer-assisted diagnostic system intended for the initial cancer identification. This article offers a systematic review of Deep Learning approaches using various image modalities to detect multi-organ cancers from 2012 to 2023. It emphasizes the detection of five supreme predominant tumors, i.e., breast, brain, lung, skin, and liver. Extensive review has been carried out by collecting research and conference articles and book chapters from reputed international databases, i.e., Springer Link, IEEE Xplore, Science Direct, PubMed, and Wiley that fulfill the criteria for quality evaluation. This systematic review summarizes the overview of convolutional neural network model architectures and datasets used for identifying and classifying the diverse categories of cancer. This study accomplishes an inclusive idea of ensemble deep learning models that have achieved better evaluation results for classifying the different images into cancer or healthy cases. This paper will provide a broad understanding to the research scientists within the domain of medical imaging procedures of which deep learning technique perform best over which type of dataset, extraction of features, different confrontations, and their anticipated solutions for the complex problems. Lastly, some challenges and issues which control the health emergency have been discussed.

Diagnostic Performance of Artificial Intelligence in Detection of Hepatocellular Carcinoma: A Meta-analysis

Due to the increasing interest in the use of artificial intelligence (AI) algorithms in hepatocellular carcinoma detection, we performed a systematic review and meta-analysis to pool the data on diagnostic performance metrics of AI and to compare them with clinicians' performance. A search in PubMed and Scopus was performed in January 2024 to find studies that evaluated and/or validated an AI algorithm for the detection of HCC. We performed a meta-analysis to pool the data on the metrics of diagnostic performance. Subgroup analysis based on the modality of imaging and meta-regression based on multiple parameters were performed to find potential sources of heterogeneity. The risk of bias was assessed using Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) and Prediction Model Study Risk of Bias Assessment Tool (PROBAST) reporting guidelines. Out of 3177 studies screened, 44 eligible studies were included. The pooled sensitivity and specificity for internally validated AI algorithms were 84% (95% CI: 81,87) and 92% (95% CI: 90,94), respectively. Externally validated AI algorithms had a pooled sensitivity of 85% (95% CI: 78,89) and specificity of 84% (95% CI: 72,91). When clinicians were internally validated, their pooled sensitivity was 70% (95% CI: 60,78), while their pooled specificity was 85% (95% CI: 77,90). This study implies that AI can perform as a diagnostic supplement for clinicians and radiologists by screening images and highlighting regions of interest, thus improving workflow.

Optimizing Gene Selection and Cancer Classification with Hybrid Sine Cosine and Cuckoo Search Algorithm

Gene expression datasets offer a wide range of information about various biological processes. However, it is difficult to find the important genes among the high-dimensional biological data due to the existence of redundant and unimportant ones. Numerous Feature Selection (FS) techniques have been created to get beyond this obstacle. Improving the efficacy and precision of FS methodologies is crucial in order to identify significant genes amongst complicated complex biological data. In this work, we present a novel approach to gene selection called the Sine Cosine and Cuckoo Search Algorithm (SCACSA). This hybrid method is designed to work with well-known machine learning classifiers Support Vector Machine (SVM). Using a dataset on breast cancer, the hybrid gene selection algorithm's performance is carefully assessed and compared to other feature selection methods. To improve the quality of the feature set, we use minimum Redundancy Maximum Relevance (mRMR) as a filtering strategy in the first step. The hybrid SCACSA method is then used to enhance and optimize the gene selection procedure. Lastly, we classify the dataset according to the chosen genes by using the SVM classifier. Given the pivotal role gene selection plays in unraveling complex biological datasets, SCACSA stands out as an invaluable tool for the classification of cancer datasets. The findings help medical practitioners make well-informed decisions about cancer diagnosis and provide them with a valuable tool for navigating the complex world of gene expression data.

Tile-based microscopic image processing for malaria screening using a deep learning approach

BACKGROUND

Manual microscopic examination remains the golden standard for malaria diagnosis. But it is laborious, and pathologists with experience are needed for accurate diagnosis. The need for computer-aided diagnosis methods is driven by the enormous workload and difficulties associated with manual microscopy based examination. While the importance of computer-aided diagnosis is increasing at an enormous pace, fostered by the advancement of deep learning algorithms, there are still challenges in detecting small objects such as malaria parasites in microscopic images of blood films. The state-of-the-art (SOTA) deep learning-based object detection models are inefficient in detecting small objects accurately because they are underrepresented on benchmark datasets. The performance of these models is affected by the loss of detailed spatial information due to in-network feature map downscaling. This is due to the fact that the SOTA models cannot directly process high-resolution images due to their low-resolution network input layer.

METHODS

In this study, an efficient and robust tile-based image processing method is proposed to enhance the performance of malaria parasites detection SOTA models. Three variants of YOLOV4-based object detectors are adopted considering their detection accuracy and speed. These models were trained using tiles generated from 1780 high-resolution P. falciparum-infected thick smear microscopic images. The tiling of high-resolution images improves the performance of the object detection models. The detection accuracy and the generalization capability of these models have been evaluated using three datasets acquired from different regions.

RESULTS

The best-performing model using the proposed tile-based approach outperforms the baseline method significantly (Recall, [95.3%] vs [57%] and Average Precision, [87.1%] vs [76%]). Furthermore, the proposed method has outperformed the existing approaches that used different machine learning techniques evaluated on similar datasets.

CONCLUSIONS

The experimental results show that the proposed method significantly improves P. falciparum detection from thick smear microscopic images while maintaining real-time detection speed. Furthermore, the proposed method has the potential to assist and reduce the workload of laboratory technicians in malaria-endemic remote areas of developing countries where there is a critical skill gap and a shortage of experts.

Clinical stratification improves the diagnostic accuracy of small omics datasets within machine learning and genome-scale metabolic modelling methods

BACKGROUND

Recently, multi-omic machine learning architectures have been proposed for the early detection of cancer. However, for rare cancers and their associated small datasets, it is still unclear how to use the available multi-omics data to achieve a mechanistic prediction of cancer onset and progression, due to the limited data available. Hepatoblastoma is the most frequent liver cancer in infancy and childhood, and whose incidence has been lately increasing in several developed countries. Even though some studies have been conducted to understand the causes of its onset and discover potential biomarkers, the role of metabolic rewiring has not been investigated in depth so far.

METHODS

Here, we propose and implement an interpretable multi-omics pipeline that combines mechanistic knowledge from genome-scale metabolic models with machine learning algorithms, and we use it to characterise the underlying mechanisms controlling hepatoblastoma.

RESULTS AND CONCLUSIONS

While the obtained machine learning models generally present a high diagnostic classification accuracy, our results show that the type of omics combinations used as input to the machine learning models strongly affects the detection of important genes, reactions and metabolic pathways linked to hepatoblastoma. Our method also suggests that, in the context of computer-aided diagnosis of cancer, optimal diagnostic accuracy can be achieved by adopting a combination of omics that depends on the patient's clinical characteristics.

Construction of machine learning-based models for cancer outcomes in low and lower-middle income countries: A scoping review

Background

The impact and utility of machine learning (ML)-based prediction tools for cancer outcomes including assistive diagnosis, risk stratification, and adjunctive decision-making have been largely described and realized in the high income and upper-middle-income countries. However, statistical projections have estimated higher cancer incidence and mortality risks in low and lower-middle-income countries (LLMICs). Therefore, this review aimed to evaluate the utilization, model construction methods, and degree of implementation of ML-based models for cancer outcomes in LLMICs.

Methods

PubMed/Medline, Scopus, and Web of Science databases were searched and articles describing the use of ML-based models for cancer among local populations in LLMICs between 2002 and 2022 were included. A total of 140 articles from 22,516 citations that met the eligibility criteria were included in this study.

Results

ML-based models from LLMICs were often based on traditional ML algorithms than deep or deep hybrid learning. We found that the construction of ML-based models was skewed to particular LLMICs such as India, Iran, Pakistan, and Egypt with a paucity of applications in sub-Saharan Africa. Moreover, models for breast, head and neck, and brain cancer outcomes were frequently explored. Many models were deemed suboptimal according to the Prediction model Risk of Bias Assessment tool (PROBAST) due to sample size constraints and technical flaws in ML modeling even though their performance accuracy ranged from 0.65 to 1.00. While the development and internal validation were described for all models included (n=137), only 4.4% (6/137) have been validated in independent cohorts and 0.7% (1/137) have been assessed for clinical impact and efficacy.

Conclusion

Overall, the application of ML for modeling cancer outcomes in LLMICs is increasing. However, model development is largely unsatisfactory. We recommend model retraining using larger sample sizes, intensified external validation practices, and increased impact assessment studies using randomized controlled trial designs.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=308345, identifier CRD42022308345.

Influence of Three-Dimensional Visual Reconstruction Technology Combined with Virtual Surgical Planning of CTA Images on Precise Resection of Liver Cancer in Hepatobiliary Surgery

Hepatobiliary malignancies, such as hepatocellular carcinoma (HCC) and biliary tract cancers, namely, gallbladder carcinoma and cholangiocarcinoma, are linked to a high rate of morbidity and mortality, depending on the phase of the disease. The intricate hepatobiliary anatomy and the need for accurate peroperative management, especially in patients with advanced liver disease, make these tumors difficult to treat. Surgical resection is a notable therapy for hepatobiliary cancers. Unnecessary or excessive liver excision influences patient rehabilitation, normal liver function, and postoperative complications. Hepatobiliary operations must therefore include accurate liver removal. The present advancements in imaging technology are aimed at improving the diagnostic efficacy of liver injury even more. Three-dimensional visual reconstruction is becoming more important in the diagnosis as well as treatment of a variety of disorders. In this paper, we proposed a novel three-dimensional visual reconstruction technology using enhanced nonuniform rational basis spline (ENURBS) combined with virtual surgical planning of Computed Tomography Angiography (CTA) images for precise liver cancer resection. The purpose of this project is to rebuild 2D CTA scan images of liver cancer into a 3D reconstructed model for efficient visualization and diagnosis of liver cancer and to prepare an effective preoperative surgical plan for precise liver excision based on a 3D recreated liver model. This method's performance is compared to that of 2D planning in terms of accuracy and time taken to complete the plan. It is concluded that our proposed technique outperforms the planning technique based on 2D images.

Engineered 2D materials for optical bioimaging and path toward therapy and tissue engineering

Two-dimensional (2D) layered materials as a new class of nanomaterial are characterized by a list of exotic properties. These layered materials are investigated widely in several biomedical applications. A comprehensive understanding of the state-of-the-art developments of 2D materials designed for multiple nanoplatforms will aid researchers in various fields to broaden the scope of biomedical applications. Here, we review the advances in 2D material-based biomedical applications. First, we introduce the classification and properties of 2D materials. Next, we summarize surface and structural engineering methods of 2D materials where we discuss surface functionalization, defect, and strain engineering, and creating heterostructures based on layered materials for biomedical applications. After that, we discuss different biomedical applications. Then, we briefly introduced the emerging role of machine learning (ML) as a technological advancement to boost biomedical platforms. Finally, the current challenges, opportunities, and prospects on 2D materials in biomedical applications are discussed.

Graphical abstract

Recent advancement in cancer diagnosis using machine learning and deep learning techniques: A comprehensive review

Being a second most cause of mortality worldwide, cancer has been identified as a perilous disease for human beings, where advance stage diagnosis may not help much in safeguarding patients from mortality. Thus, efforts to provide a sustainable architecture with proven cancer prevention estimate and provision for early diagnosis of cancer is the need of hours. Advent of machine learning methods enriched cancer diagnosis area with its overwhelmed efficiency & low error-rate then humans. A significant revolution has been witnessed in the development of machine learning & deep learning assisted system for segmentation & classification of various cancers during past decade. This research paper includes a review of various types of cancer detection via different data modalities using machine learning & deep learning-based methods along with different feature extraction techniques and benchmark datasets utilized in the recent six years studies. The focus of this study is to review, analyse, classify, and address the recent development in cancer detection and diagnosis of six types of cancers i.e., breast, lung, liver, skin, brain and pancreatic cancer, using machine learning & deep learning techniques. Various state-of-the-art technique are clustered into same group and results are examined through key performance indicators like accuracy, area under the curve, precision, sensitivity, dice score on benchmark datasets and concluded with future research work challenges.

Clinical Efficacy of Interventional Chemotherapy Embolization Combined with Monopolar Radiofrequency Ablation on Patients with Liver Cancer

Due to the greater prevalence of chronic hepatitis B infection, liver tumor is especially popular in China. In China, it is the 4th most prevalent tumor and the 3rd main reason for cancer fatalities. Hepatocellular carcinomas (HCCs) account for more than 91% of every liver tumor case, and chemotherapy and immunotherapy are the better therapy choices. It is a serious threat to the lives and health of Chinese citizens. Patients diagnosed with liver tumors have a bad prognosis. Surgical resection, liver transplantation, chemotherapeutic embolization, and radiofrequency ablation (RFA) are all choices for patients who are detected early. More effective therapies can result in a better prognosis. This paper analyzes the clinical efficiency of interventional transarterial chemoembolization (TACE) integrated with monopolar radiofrequency ablation (RFA) on patients with a liver tumor. Initially, the dataset is collected and the patients are treated with combined TACE and RFA. The computed tomography (CT) images are obtained using three-phase CT imaging. The images are segmented using adaptive U-Net-based segmentation. The clinical efficiency of the patients is evaluated using Robust Residual Convolutional Neural Network (RR-CNN) which is optimized using Firefly Particle Swarm Optimization (FPSO) algorithm. The performance of the system is analyzed using the MATLAB simulation tool. In performance analysis, the proposed method of RR-CNN is high when compared to the existing method of CNN, logistic regression using genetic algorithm and KNN in overall parameters are accuracy, sensitivity, F1-score, and specificity. These integrated treatments have a suggested greater response frequency, indicating a synergistic impact by combination treatment in the initial stages.

An Improved Brain MRI Classification Methodology Based on Statistical Features and Machine Learning Algorithms

In this paper, we have proposed a novel methodology based on statistical features and different machine learning algorithms. The proposed model can be divided into three main stages, namely, preprocessing, feature extraction, and classification. In the preprocessing stage, the median filter has been used in order to remove salt-and-pepper noise because MRI images are normally affected by this type of noise, the grayscale images are also converted to RGB images in this stage. In the preprocessing stage, the histogram equalization has also been used to enhance the quality of each RGB channel. In the feature extraction stage, the three channels, namely, red, green, and blue, are extracted from the RGB images and statistical measures, namely, mean, variance, skewness, kurtosis, entropy, energy, contrast, homogeneity, and correlation, are calculated for each channel; hence, a total of 27 features, 9 for each channel, are extracted from an RGB image. After the feature extraction stage, different machine learning algorithms, such as artificial neural network, k-nearest neighbors' algorithm, decision tree, and Naïve Bayes classifiers, have been applied in the classification stage on the features extracted in the feature extraction stage. We recorded the results with all these algorithms and found that the decision tree results are better as compared to the other classification algorithms which are applied on these features. Hence, we have considered decision tree for further processing. We have also compared the results of the proposed method with some well-known algorithms in terms of simplicity and accuracy; it was noted that the proposed method outshines the existing methods.

A novel ResNet101 model based on dense dilated convolution for image classification

Image classification plays an important role in computer vision. The existing convolutional neural network methods have some problems during image classification process, such as low accuracy of tumor classification and poor ability of feature expression and feature extraction. Therefore, we propose a novel ResNet101 model based on dense dilated convolution for medical liver tumors classification. The multi-scale feature extraction module is used to extract multi-scale features of images, and the receptive field of the network is increased. The depth feature extraction module is used to reduce background noise information and focus on effective features of the focal region. To obtain broader and deeper semantic information, a dense dilated convolution module is deployed in the network. This module combines the advantages of Inception, residual structure, and multi-scale dilated convolution to obtain a deeper level of feature information without causing gradient explosion and gradient disappearance. To solve the common feature loss problems in the classification network, the up- down-sampling module in the network is improved, and multiple convolution kernels with different scales are cascaded to widen the network, which can effectively avoid feature loss. Finally, experiments are carried out on the proposed method. Compared with the existing mainstream classification networks, the proposed method can improve the classification performance, and finally achieve accurate classification of liver tumors. The effectiveness of the proposed method is further verified by ablation experiments.

Highlights

A Systematic Review of Artificial Intelligence Techniques in Cancer Prediction and Diagnosis

Artificial intelligence has aided in the advancement of healthcare research. The availability of open-source healthcare statistics has prompted researchers to create applications that aid cancer detection and prognosis. Deep learning and machine learning models provide a reliable, rapid, and effective solution to deal with such challenging diseases in these circumstances. PRISMA guidelines had been used to select the articles published on the web of science, EBSCO, and EMBASE between 2009 and 2021. In this study, we performed an efficient search and included the research articles that employed AI-based learning approaches for cancer prediction. A total of 185 papers are considered impactful for cancer prediction using conventional machine and deep learning-based classifications. In addition, the survey also deliberated the work done by the different researchers and highlighted the limitations of the existing literature, and performed the comparison using various parameters such as prediction rate, accuracy, sensitivity, specificity, dice score, detection rate, area undercover, precision, recall, and F1-score. Five investigations have been designed, and solutions to those were explored. Although multiple techniques recommended in the literature have achieved great prediction results, still cancer mortality has not been reduced. Thus, more extensive research to deal with the challenges in the area of cancer prediction is required.

Statistical features analysis and discrimination of maize seeds utilizing machine vision approach

The purpose of this study is the statistical analysis and discrimination of maize seed using a machine vision (MV) approach. The foundation of the digital image dataset holds six maize seed varieties named as Kargal K-9803, Gujjar Khan, Desi White, Pioner 30Y87, Syngenta ST-6142, and Pioner 31R88. The digital image dataset acquired via a digital imaging laboratory. For preprocessing, we crop the image into a size of 600×600 pixels, and convert it into a gray level image format. After that, line and edge detection are performed by using a Prewitt filter, and five non-overlapping areas of interest (AOIs) size of (200×200), and (250×250) are drawn. A total of 56 statistical features, containing texture features, histogram features, and spectral features, is extracted from each AOI. The 11 optimized statistical features have been selected by deploying “Correlation-based Feature Selection” (CFS) with the Greedy algorithm. For the discrimination analysis, four MV classifiers named as “Support Vector Machine” (SVM), “Logistic” (Lg), “Bagging” (B), and “LogitBoost” (LB) have been deployed on optimized statistical features dataset. After analysis, the SVM classifier has shown a promising accuracy of 99.93% on AOIs size (250×250). The obtained accuracy by SVM classifier on six maize seed varieties, namely Kargal K-9803, Gujjar Khan, Desi White, Pioner 30Y87, Syngenta ST-6142, and Pioner 31R88, were 99.9%, 99.8%, 100%, 100%, 99.9%, and 99.8%, respectively.

Discrimination of sunflower seeds using multispectral and texture dataset in combination with region selection and supervised classification methods

The purpose of this study is to discriminate sunflower seeds with the help of a dataset having spectral and textural features. The production of crop based on seed purity and quality other hand sunflower seed used for oil content worldwide. In this regard, the foundation of a dataset categorizes sunflower seed varieties (Syngenta CG, HS360, S278, HS30, Armani, and High Sun 33), which were acquired from the agricultural farms of The Islamia University of Bahawalpur, Pakistan, into six classes. For preprocessing, a new region-oriented seed-based segmentation was deployed for the automatic selection of regions and extraction of 53 multi-features from each region, while 11 optimized fused multi-features were selected using the chi-square feature selection technique. For discrimination, four supervised classifiers, namely, deep learning J4, support vector machine, random committee, and Bayes net, were employed to optimize the multi-feature dataset. We observe very promising accuracies of 98.2%, 97.5%, 96.6%, and 94.8%, respectively, when the size of a region is (180 × 180).