Quantitative prediction of toxicological points of departure using two-stage machine learning models: A new approach methodology (NAM) for chemical risk assessment

Point of departure (POD) is a concept used in risk assessment to calculate the reference dose of exposure that is likely to have no appreciable risk on health. POD can be directly utilized from no observed adverse effect levels (NOAEL) which is the dose or exposure level at which there is little or no risk of adverse effects. However, NOAEL values are unavailable for most of the chemicals due to inconsistent animal toxicity data. Hence, the current study utilizes a two-stage machine learning (ML) model for predicting NOAEL values, based on data curated from diverse toxicity exposures. In the first stage, a random forest regressor is used for supervised outlier detection and removal addressing any variability in data and poor correlations. The refined data is then used for toxicity prediction using several ML models; random forest and XGBoost show relatively higher performance with an R2 value of 0.4 and 0.43, respectively, for predicting NOAEL in chronic toxicity. Similarly, feature combinations with absorption distribution metabolism and excretion (ADME) indicate better NOAEL prediction for acute toxicity. External validation is performed by predicting NOAEL values for cosmetic pigments and calculating reference doses (RfD). Notably, pigments like orange and red show higher RfD values, indicating broader safety margins. This study provides a practical framework for addressing variability and data limitations in toxicity prediction while offering insights into its applicability in risk evaluation.

Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach

BACKGROUND

Computed tomography attenuation correction (CTAC) is commonly used in cardiac SPECT imaging to reduce soft-tissue attenuation artifacts. However, CTAC is prone to inaccuracies due to CT artifacts and SPECT-CT mismatch, along with additional radiation exposure to patients. Thus, these limitations have led to increasing interest in CT-free AC, with deep learning (DL) offering promising solutions. We proposed a new DL-based CT-free AC methods for cardiac SPECT.

METHODS

We developed a feature alignment attenuation correction network (FA-ACNet) based on the 3D U-Net framework to generate predicted DL-based AC SPECT (Deep AC). The network was trained on 167 cardiac SPECT/CT studies using 5-fold cross validation and tested in an independent testing set (n = 35), with CTAC serving as the reference. During training, multi-scale features from non-attenuation-corrected (NAC) SPECT and CT were processed separately and then aligned with the encoded features from NAC SPECT using adversarial learning and distance metric learning techniques. The performance of FA-ACNet was evaluated using mean square error (MSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). Additionally, semi-quantitative evaluation of Deep AC images was performed and compared to CTAC using Bland-Altman plots.

RESULTS

FA-ACNet achieved an MSE of 16.94 ± 2.03 × 10- 6, SSIM of 0.9955 ± 0.0006 and PSNR of 43.73 ± 0.50 after 5-fold cross validation. Compared to U-Net, MSE and PSNR improved by aligning multi-scale features from NAC SPECT and CT with those from NAC SPECT. In the testing set, FA-ACNet achieved an MSE of 11.98 × 10- 6, SSIM of 0.9976 and PSNR of 45.54. The 95% limits of agreement (LoAs) between the Deep AC and CTAC images for the summed stress/rest scores (SSS/SRS) were [- 2.3, 2.8] and [-1.9,2.1] in the training set and testing set respectively. Changes in perfusion categories were observed in 4.19% and 5.9% of studies assessed for global perfusion scores in the training set and testing set.

CONCLUSION

We propose a novel DL-based CT-free AC approach for cardiac SPECT, which can generate AC images without the need for a CT scan. By leveraging multi-scale features from both NAC SPECT and CT, the performance of CT-free AC is significantly enhanced, offering a promising alternative for future DL-based AC strategies.

Automatic image generation and stage prediction of breast cancer immunobiological through a proposed IHC-GAN model

Invasive breast cancer diagnosis and treatment planning require an accurate assessment of human epidermal growth factor receptor 2 (HER2) expression levels. While immunohistochemical techniques (IHC) are the gold standard for HER2 evaluation, their implementation can be resource-intensive and costly. To reduce these obstacles and expedite the procedure, we present an efficient deep-learning model that generates high-quality IHC-stained images directly from Hematoxylin and Eosin (H&E) stained images. We propose a new IHC-GAN that enhances the Pix2PixHD model into a dual generator module, improving its performance and simplifying its structure. Furthermore, to strengthen feature extraction for HE-stained image classification, we integrate MobileNetV3 as the backbone network. The extracted features are then merged with those generated by the generator to improve overall performance. Moreover, the decoder's performance is enhanced by providing the related features from the classified labels by incorporating the adaptive instance normalization technique. The proposed IHC-GAN was trained and validated on a comprehensive dataset comprising 4,870 registered image pairs, encompassing a spectrum of HER2 expression levels. Our findings demonstrate promising results in translating H&E images to IHC-equivalent representations, offering a potential solution to reduce the costs associated with traditional HER2 assessment methods. We extensively validate our model and the current dataset. We compare it with state-of-the-art techniques, achieving high performance using different evaluation metrics, showing 0.0927 FID, 22.87 PSNR, and 0.3735 SSIM. The proposed approach exhibits significant enhancements over current GAN models, including an 88% reduction in Frechet Inception Distance (FID), a 4% enhancement in Learned Perceptual Image Patch Similarity (LPIPS), a 10% increase in Peak Signal-to-Noise Ratio (PSNR), and a 45% reduction in Mean Squared Error (MSE). This advancement holds significant potential for enhancing efficiency, reducing manpower requirements, and facilitating timely treatment decisions in breast cancer care.

Artificial intelligence in predicting recurrence after first-line treatment of liver cancer: a systematic review and meta-analysis

BACKGROUND

The aim of this study was to conduct a systematic review and meta-analysis to comprehensively evaluate the performance and methodological quality of artificial intelligence (AI) in predicting recurrence after single first-line treatment for liver cancer.

METHODS

A rigorous and systematic evaluation was conducted on the AI studies related to recurrence after single first-line treatment for liver cancer, retrieved from the PubMed, Embase, Web of Science, Cochrane Library, and CNKI databases. The area under the curve (AUC), sensitivity (SENC), and specificity (SPEC) of each study were extracted for meta-analysis.

RESULTS

Six percutaneous ablation (PA) studies, 16 surgical resection (SR) studies, and 5 transarterial chemoembolization (TACE) studies were included in the meta-analysis for predicting recurrence after hepatocellular carcinoma (HCC) treatment, respectively. Four SR studies and 2 PA studies were included in the meta-analysis for recurrence after intrahepatic cholangiocarcinoma (ICC) and colorectal cancer liver metastasis (CRLM) treatment. The pooled SENC, SEPC, and AUC of AI in predicting recurrence after primary HCC treatment via PA, SR, and TACE were 0.78, 0.90, and 0.92; 0.81, 0.77, and 0.86; and 0.73, 0.79, and 0.79, respectively. The values for ICC treated with SR and CRLM treated with PA were 0.85, 0.71, 0.86 and 0.69, 0.63,0.74, respectively.

CONCLUSION

This systematic review and meta-analysis demonstrates the comprehensive application value of AI in predicting recurrence after a single first-line treatment of liver cancer, with satisfactory results, indicating the clinical translation potential of AI in predicting recurrence after liver cancer treatment.

Accuracy of deep learning in the differential diagnosis of coronary artery stenosis: a systematic review and meta-analysis

BACKGROUND

In recent years, as deep learning has received widespread attention in the field of heart disease, some studies have explored the potential of deep learning based on coronary angiography (CAG) or coronary CT angiography (CCTA) images in detecting the extent of coronary artery stenosis. However, there is still a lack of a systematic understanding of its diagnostic accuracy, impeding the advancement of intelligent diagnosis of coronary artery stenosis. Therefore, we conducted this study to review the accuracy of image-based deep learning in detecting coronary artery stenosis.

METHODS

We retrieved PubMed, Cochrane, Embase, and Web of Science until April 11, 2023. The risk of bias in the included studies was appraised using the QUADAS-2 tool. We extracted the accuracy of deep learning in the test set and performed subgroup analyses by binary and multiclass classification scenarios. We performed a subgroup analysis based on different degrees of stenosis and applied a double arcsine transformation to process the data. The analysis was done by using R.

RESULTS

Our systematic review finally included 18 studies, involving 3568 patients and 13,362 images. In the included studies, deep learning models were constructed based on CAG and CCTA. In binary classification tasks, the accuracy for detecting > 25%, > 50% and > 70% degrees of stenosis at the vessel level were 0.81 (95% CI: 0.71-0.85), 0.73 (95% CI: 0.58-0.88) and 0.61 (95% CI: 0.56-0.65), respectively. In multiclass classification tasks, the accuracy for detecting 0-25%, 25-50%, 50-70%, and 70-100% degrees of stenosis at the vessel level were 0.78 (95% CI: 0.73-0.84), 0.86 (95% CI: 0.78-0.93), 0.83 (95% CI: 0.70-0.97), and 0.70 (95% CI: 0.42-0.98), respectively.

CONCLUSIONS

Our study shows that deep learning models based on CAG and CCTA appear to be relatively accurate in diagnosing different degrees of coronary artery stenosis. However, for various degrees of stenosis, their accuracy still needs to be further improved.

Predicting invasion in early-stage ground-glass opacity pulmonary adenocarcinoma: a radiomics-based machine learning approach

BACKGROUND

To design a pulmonary ground-glass nodules (GGN) classification method based on computed tomography (CT) radiomics and machine learning for prediction of invasion in early-stage ground-glass opacity (GGO) pulmonary adenocarcinoma.

METHODS

This retrospective study included pulmonary GGN patients who were histologically confirmed to have adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma cancer (IAC) from 2020 to 2023. CT images of all patients were automatically segmented and 107 radiomic features were obtained for each patient. Classification models were developed using random forest (RF) and cross-validation, including three one-versus-others models and one three-class model. For each model, features were ranked by normalized Gini importance, and a minimal subset was selected with a cumulative importance exceeding 0.9. These selected features were then used to train the final models. The models' performance metrics, including area under the curve (AUC), accuracy, sensitivity, and specificity, were computed. AUC and accuracy were compared to determine the final optimal method.

RESULTS

The study comprised 193 patients (mean age 54 ± 11 years, 65 men), including 65 AIS, 54 MIA, and 74 IAC, divided into one training cohort (N = 154) and one test cohort (N = 39). The final three-class RF model outperformed three individual one-versus-others models in distinguishing each class from the other two. For the multiclass classification model, the AUC, accuracy, sensitivity, and specificity were 0.87, 0.79, 0.62, and 0.88 for AIS; 0.90, 0.79, 0.54, and 0.89 for MIA; and 0.87, 0.69, 0.73, and 0.67 for IAC, respectively.

CONCLUSIONS

A radiomics-based multiclass RF model could effectively differentiate three types of pulmonary GGN, which enabled early diagnosis of GGO pulmonary adenocarcinoma.

Clinical performance of deep learning-enhanced ultrafast whole-body scintigraphy in patients with suspected malignancy

BACKGROUND

To evaluate the clinical performance of two deep learning methods, one utilizing real clinical pairs and the other utilizing simulated datasets, in enhancing image quality for two-dimensional (2D) fast whole-body scintigraphy (WBS).

METHODS

A total of 83 patients with suspected bone metastasis were retrospectively enrolled. All patients underwent single-photon emission computed tomography (SPECT) WBS at speeds of 20 cm/min (1x), 40 cm/min (2x), and 60 cm/min (3x). Two deep learning models were developed to generate high-quality images from real and simulated fast scans, designated 2x-real and 3x-real (images from real fast data) and 2x-simu and 3x-simu (images from simulated fast data), respectively. A 5-point Likert scale was used to evaluate the image quality of each acquisition. Accuracy, sensitivity, specificity, and the area under the curve (AUC) were used to evaluate diagnostic efficacy. Learned perceptual image patch similarity (LPIPS) and the Fréchet inception distance (FID) were used to assess image quality. Additionally, the count-level consistency of WBS was compared between the two models.

RESULTS

Subjective assessments revealed that the 1x images had the highest general image quality (Likert score: 4.40 ± 0.45). The 2x-real, 2x-simu and 3x-real, 3x-simu images demonstrated significantly better quality than the 2x and 3x images (Likert scores: 3.46 ± 0.47, 3.79 ± 0.55 vs. 2.92 ± 0.41, P < 0.0001; 2.69 ± 0.40, 2.61 ± 0.41 vs. 1.36 ± 0.51, P < 0.0001), respectively. Notably, the quality of the 2x-real images was inferior to that of the 2x-simu images (Likert scores: 3.46 ± 0.47 vs. 3.79 ± 0.55, P = 0.001). The diagnostic efficacy for the 2x-real and 2x-simu images was indistinguishable from that of the 1x images (accuracy: 81.2%, 80.7% vs. 84.3%; sensitivity: 77.27%, 77.27% vs. 87.18%; specificity: 87.18%, 84.63% vs. 87.18%. All P > 0.05), whereas the diagnostic efficacy for the 3x-real and 3x-simu was better than that for the 3x images (accuracy: 65.1%, 66.35% vs. 59.0%; sensitivity: 63.64%, 63.64% vs. 64.71%; specificity: 66.67%, 69.23% vs. 55.1%. All P < 0.05). Objectively, both the real and simulated models achieved significantly enhanced image quality from the accelerated scans in the 2x and 3x groups (FID: 0.15 ± 0.18, 0.18 ± 0.18 vs. 0.47 ± 0.34; 0.19 ± 0.23, 0.20 ± 0.22 vs. 0.98 ± 0.59.

LPIPS

0.17 ± 0.05, 0.16 ± 0.04 vs. 0.19 ± 0.05; 0.18 ± 0.05, 0.19 ± 0.05 vs. 0.23 ± 0.04. All P < 0.05). The count-level consistency with the 1x images was excellent for all four sets of model-generated images (P < 0.0001).

CONCLUSIONS

Ultrafast 2x speed (real and simulated) images achieved comparable diagnostic value to that of standardly acquired images, but the simulation algorithm does not necessarily reflect real data.

nnU-Net based segmentation and 3D reconstruction of uterine fibroids with MRI images for HIFU surgery planning

High-Intensity Focused Ultrasound (HIFU) ablation represents a rapidly advancing non-invasive treatment modality that has achieved considerable success in addressing uterine fibroids, which constitute over 50% of benign gynecological tumors. Preoperative Magnetic Resonance Imaging (MRI) plays a pivotal role in the planning and guidance of HIFU surgery for uterine fibroids, wherein the segmentation of tumors holds critical significance. The segmentation process was previously manually executed by medical experts, entailing a time-consuming and labor-intensive procedure heavily reliant on clinical expertise. This study introduced deep learning-based nnU-Net models, offering a cost-effective approach for their application in the segmentation of uterine fibroids utilizing preoperative MRI images. Furthermore, 3D reconstruction of the segmented targets was implemented to guide HIFU surgery. The evaluation of segmentation and 3D reconstruction performance was conducted with a focus on enhancing the safety and effectiveness of HIFU surgery. Results demonstrated the nnU-Net's commendable performance in the segmentation of uterine fibroids and their surrounding organs. Specifically, 3D nnU-Net achieved Dice Similarity Coefficients (DSC) of 92.55% for the uterus, 95.63% for fibroids, 92.69% for the spine, 89.63% for the endometrium, 97.75% for the bladder, and 90.45% for the urethral orifice. Compared to other state-of-the-art methods such as HIFUNet, U-Net, R2U-Net, ConvUNeXt and 2D nnU-Net, 3D nnU-Net demonstrated significantly higher DSC values, highlighting its superior accuracy and robustness. In conclusion, the efficacy of the 3D nnU-Net model for automated segmentation of the uterus and its surrounding organs was robustly validated. When integrated with intra-operative ultrasound imaging, this segmentation method and 3D reconstruction hold substantial potential to enhance the safety and efficiency of HIFU surgery in the clinical treatment of uterine fibroids.

Fractional differentiation based image enhancement for automatic detection of malignant melanoma

Recent improvements in artificial intelligence and computer vision make it possible to automatically detect abnormalities in medical images. Skin lesions are one broad class of them. There are types of lesions that cause skin cancer, again with several types. Melanoma is one of the deadliest types of skin cancer. Its early diagnosis is at utmost importance. The treatments are greatly aided with artificial intelligence by the quick and precise diagnosis of these conditions. The identification and delineation of boundaries inside skin lesions have shown promise when using the basic image processing approaches for edge detection. Further enhancements regarding edge detections are possible. In this paper, the use of fractional differentiation for improved edge detection is explored on the application of skin lesion detection. A framework based on fractional differential filters for edge detection in skin lesion images is proposed that can improve automatic detection rate of malignant melanoma. The derived images are used to enhance the input images. Obtained images then undergo a classification process based on deep learning. A well-studied dataset of HAM10000 is used in the experiments. The system achieves 81.04% accuracy with EfficientNet model using the proposed fractional derivative based enhancements whereas accuracies are around 77.94% when using original images. In almost all the experiments, the enhanced images improved the accuracy. The results show that the proposed method improves the recognition performance.

Vascular liver segmentation: a narrative review on methods and new insights brought by artificial intelligence

Liver vessel segmentation from routinely performed medical imaging is a useful tool for diagnosis, treatment planning and delivery, and prognosis evaluation for many diseases, particularly liver cancer. A precise representation of liver anatomy is crucial to define the extent of the disease and, when suitable, the consequent resective or ablative procedure, in order to guarantee a radical treatment without sacrificing an excessive volume of healthy liver. Once mainly performed manually, with notable cost in terms of time and human energies, vessel segmentation is currently realized through the application of artificial intelligence (AI), which has gained increased interest and development of the field. Many different AI-driven models adopted for this aim have been described and can be grouped into different categories: thresholding methods, edge- and region-based methods, model-based methods, and machine learning models. The latter includes neural network and deep learning models that now represent the principal algorithms exploited for vessel segmentation. The present narrative review describes how liver vessel segmentation can be realized through AI models, with a summary of model results in terms of accuracy, and an overview on the future progress of this topic.

Dual-energy computed tomography with new virtual monoenergetic image reconstruction enhances prostate lesion image quality and improves the diagnostic efficacy for prostate cancer

BACKGROUND

Prostate cancer is one of the most common malignant tumors in middle-aged and elderly men and carries significant prognostic implications, and recent studies suggest that dual-energy computed tomography (DECT) utilizing new virtual monoenergetic images can enhance cancer detection rates. This study aimed to assess the impact of virtual monoenergetic images reconstructed from DECT arterial phase scans on the image quality of prostate lesions and their diagnostic performance for prostate cancer.

METHODS

We conducted a retrospective analysis of 83 patients with prostate cancer or prostatic hyperplasia who underwent DECT scans at Meizhou People's Hospital between July 2019 and December 2023. The variables analyzed included age, tumor diameter and serum prostate-specific antigen (PSA) levels, among others. We also compared CT values, signal-to-noise ratio (SNR), subjective image quality ratings, and contrast-to-noise ratio (CNR) between virtual monoenergetic images (40-100 keV) and conventional linear blending images. Receiver operating characteristic (ROC) curve analyses were performed to evaluate the diagnostic efficacy of virtual monoenergetic images (40 keV and 50 keV) compared to conventional images.

RESULTS

Virtual monoenergetic images at 40 keV showed significantly higher CT values (168.19 ± 57.14) compared to conventional linear blending images (66.66 ± 15.5) for prostate cancer (P < 0.001). The 50 keV images also demonstrated elevated CT values (121.73 ± 39.21) compared to conventional images (P < 0.001). CNR values for the 40 keV (3.81 ± 2.13) and 50 keV (2.95 ± 1.50) groups were significantly higher than the conventional blending group (P < 0.001). Subjective evaluations indicated markedly better image quality scores for 40 keV (median score of 5) and 50 keV (median score of 5) images compared to conventional images (P < 0.05). ROC curve analysis revealed superior diagnostic accuracy for 40 keV (AUC: 0.910) and 50 keV (AUC: 0.910) images based on CT values compared to conventional images (AUC: 0.849).

CONCLUSIONS

Virtual monoenergetic images reconstructed at 40 keV and 50 keV from DECT arterial phase scans substantially enhance the image quality of prostate lesions and improve diagnostic efficacy for prostate cancer.

An effective no-reference image quality index prediction with a hybrid Artificial Intelligence approach for denoised MRI images

As the quantity and significance of digital pictures in the medical industry continue to increase, Image Quality Assessment (IQA) has recently become a prevalent subject in the research community. Due to the wide range of distortions that Magnetic Resonance Images (MRI) can experience and the wide variety of information they contain, No-Reference Image Quality Assessment (NR-IQA) has always been a challenging study issue. In an attempt to address this issue, a novel hybrid Artificial Intelligence (AI) is proposed to analyze NR-IQ in massive MRI data. First, the features from the denoised MRI images are extracted using the gray level run length matrix (GLRLM) and EfficientNet B7 algorithm. Next, the Multi-Objective Reptile Search Algorithm (MRSA) was proposed for optimal feature vector selection. Then, the Self-evolving Deep Belief Fuzzy Neural network (SDBFN) algorithm was proposed for the effective NR-IQ analysis. The implementation of this research is executed using MATLAB software. The simulation results are compared with the various conventional methods in terms of correlation coefficient (PLCC), Root Mean Square Error (RMSE), Spearman Rank Order Correlation Coefficient (SROCC) and Kendall Rank Order Correlation Coefficient (KROCC), and Mean Absolute Error (MAE). In addition, our proposed approach yielded a quality number approximately we achieved significant 20% improvement than existing methods, with the PLCC parameter showing a notable increase compared to current techniques. Moreover, the RMSE number decreased by 12% when compared to existing methods. Graphical representations indicated mean MAE values of 0.02 for MRI knee dataset, 0.09 for MRI brain dataset, and 0.098 for MRI breast dataset, showcasing significantly lower MAE values compared to the baseline models.

Retinex theory-based nonlinear luminance enhancement and denoising for low-light endoscopic images

BACKGROUND

The quality of low-light endoscopic images involves applications in medical disciplines such as physiology and anatomy for the identification and judgement of tissue structures. Due to the use of point light sources and the constraints of narrow physiological structures, medical endoscopic images display uneven brightness, low contrast, and a lack of texture information, presenting diagnostic challenges for physicians.

METHODS

In this paper, a nonlinear brightness enhancement and denoising network based on Retinex theory is designed to improve the brightness and details of low-light endoscopic images. The nonlinear luminance enhancement module uses higher-order curvilinear functions to improve overall brightness; the dual-attention denoising module captures detailed features of anatomical structures; and the color loss function mitigates color distortion.

RESULTS

Experimental results on the Endo4IE dataset demonstrate that the proposed method outperforms existing state-of-the-art methods in terms of Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS). The PSNR is 27.2202, SSIM is 0.8342, and the LPIPS is 0.1492. It provides a method to enhance image quality in clinical diagnosis and treatment.

CONCLUSIONS

It offers an efficient method to enhance images captured by endoscopes and offers valuable insights into intricate human physiological structures, which can effectively assist clinical diagnosis and treatment.

Metal implant segmentation in CT images based on diffusion model

BACKGROUND

Computed tomography (CT) is widely in clinics and is affected by metal implants. Metal segmentation is crucial for metal artifact correction, and the common threshold method often fails to accurately segment metals.

PURPOSE

This study aims to segment metal implants in CT images using a diffusion model and further validate it with clinical artifact images and phantom images of known size.

METHODS

A retrospective study was conducted on 100 patients who received radiation therapy without metal artifacts, and simulated artifact data were generated using publicly available mask data. The study utilized 11,280 slices for training and verification, and 2,820 slices for testing. Metal mask segmentation was performed using DiffSeg, a diffusion model incorporating conditional dynamic coding and a global frequency parser (GFParser). Conditional dynamic coding fuses the current segmentation mask and prior images at multiple scales, while GFParser helps eliminate high-frequency noise in the mask. Clinical artifact images and phantom images are also used for model validation.

RESULTS

Compared with the ground truth, the accuracy of DiffSeg for metal segmentation of simulated data was 97.89% and that of DSC was 95.45%. The mask shape obtained by threshold segmentation covered the ground truth and DSCs were 82.92% and 84.19% for threshold segmentation based on 2500 HU and 3000 HU. Evaluation metrics and visualization results show that DiffSeg performs better than other classical deep learning networks, especially for clinical CT, artifact data, and phantom data.

CONCLUSION

DiffSeg efficiently and robustly segments metal masks in artifact data with conditional dynamic coding and GFParser. Future work will involve embedding the metal segmentation model in metal artifact reduction to improve the reduction effect.

Development of a flexible liver phantom for hepatocellular carcinoma treatment planning: a useful tool for training & education

PURPOSE

Hepatocellular carcinoma (HCC) is one of the most common types of liver cancer that could potentially be surrounded by healthy arteries or veins that a surgeon would have to avoid during treatment. A realistic 3D liver model is an unmet need for HCC preoperative planning.

METHODS

This paper presents a method to create a soft phantom model of the human liver with the help of a 3D-printed mold, silicone, ballistic gel, and a blender.

RESULTS

For silicone, the elastic modulus of seven different ratios of base silicone and silicone hardener are tested; while for ballistic gel, a model using 20% gelatin and 10% gelatin is created for the tumor and the rest of the liver, respectively. It is found that the silicone modulus of elasticity matches with the real liver modulus of elasticity. It is also found that the 10% gelatin part of the ballistic gel model is an excellent emulation of a healthy human liver.

CONCLUSION

The 3D flexible liver phantom made from a 10% gelatin-to-water mixture demonstrates decent fidelity to real liver tissue in terms of texture and elasticity. It holds significant potential for improving medical training, preoperative planning, and surgical research. We believe that continued development and validation of such models could further enhance their utility and impact in the field of hepatobiliary treatment planning and education.

STC-UNet: renal tumor segmentation based on enhanced feature extraction at different network levels

Renal tumors are one of the common diseases of urology, and precise segmentation of these tumors plays a crucial role in aiding physicians to improve diagnostic accuracy and treatment effectiveness. Nevertheless, inherent challenges associated with renal tumors, such as indistinct boundaries, morphological variations, and uncertainties in size and location, segmenting renal tumors accurately remains a significant challenge in the field of medical image segmentation. With the development of deep learning, substantial achievements have been made in the domain of medical image segmentation. However, existing models lack specificity in extracting features of renal tumors across different network hierarchies, which results in insufficient extraction of renal tumor features and subsequently affects the accuracy of renal tumor segmentation. To address this issue, we propose the Selective Kernel, Vision Transformer, and Coordinate Attention Enhanced U-Net (STC-UNet). This model aims to enhance feature extraction, adapting to the distinctive characteristics of renal tumors across various network levels. Specifically, the Selective Kernel modules are introduced in the shallow layers of the U-Net, where detailed features are more abundant. By selectively employing convolutional kernels of different scales, the model enhances its capability to extract detailed features of renal tumors across multiple scales. Subsequently, in the deeper layers of the network, where feature maps are smaller yet contain rich semantic information, the Vision Transformer modules are integrated in a non-patch manner. These assist the model in capturing long-range contextual information globally. Their non-patch implementation facilitates the capture of fine-grained features, thereby achieving collaborative enhancement of global-local information and ultimately strengthening the model's extraction of semantic features of renal tumors. Finally, in the decoder segment, the Coordinate Attention modules embedding positional information are proposed aiming to enhance the model's feature recovery and tumor region localization capabilities. Our model is validated on the KiTS19 dataset, and experimental results indicate that compared to the baseline model, STC-UNet shows improvements of 1.60%, 2.02%, 2.27%, 1.18%, 1.52%, and 1.35% in IoU, Dice, Accuracy, Precision, Recall, and F1-score, respectively. Furthermore, the experimental results demonstrate that the proposed STC-UNet method surpasses other advanced algorithms in both visual effectiveness and objective evaluation metrics.

Enhancing ECG-based heart age: impact of acquisition parameters and generalization strategies for varying signal morphologies and corruptions

Electrocardiogram (ECG) is a non-invasive approach to capture the overall electrical activity produced by the contraction and relaxation of the cardiac muscles. It has been established in the literature that the difference between ECG-derived age and chronological age represents a general measure of cardiovascular health. Elevated ECG-derived age strongly correlates with cardiovascular conditions (e.g., atherosclerotic cardiovascular disease). However, the neural networks for ECG age estimation are yet to be thoroughly evaluated from the perspective of ECG acquisition parameters. Additionally, deep learning systems for ECG analysis encounter challenges in generalizing across diverse ECG morphologies in various ethnic groups and are susceptible to errors with signals that exhibit random or systematic distortions To address these challenges, we perform a comprehensive empirical study to determine the threshold for the sampling rate and duration of ECG signals while considering their impact on the computational cost of the neural networks. To tackle the concern of ECG waveform variability in different populations, we evaluate the feasibility of utilizing pre-trained and fine-tuned networks to estimate ECG age in different ethnic groups. Additionally, we empirically demonstrate that finetuning is an environmentally sustainable way to train neural networks, and it significantly decreases the ECG instances required (by more than 100 × ) for attaining performance similar to the networks trained from random weight initialization on a complete dataset. Finally, we systematically evaluate augmentation schemes for ECG signals in the context of age estimation and introduce a random cropping scheme that provides best-in-class performance while using shorter-duration ECG signals. The results also show that random cropping enables the networks to perform well with systematic and random ECG signal corruptions.

Generation of virtual monoenergetic images at 40 keV of the upper abdomen and image quality evaluation based on generative adversarial networks

BACKGROUND

Abdominal CT scans are vital for diagnosing abdominal diseases but have limitations in tissue analysis and soft tissue detection. Dual-energy CT (DECT) can improve these issues by offering low keV virtual monoenergetic images (VMI), enhancing lesion detection and tissue characterization. However, its cost limits widespread use.

PURPOSE

To develop a model that converts conventional images (CI) into generative virtual monoenergetic images at 40 keV (Gen-VMI40keV) of the upper abdomen CT scan.

METHODS

Totally 444 patients who underwent upper abdominal spectral contrast-enhanced CT were enrolled and assigned to the training and validation datasets (7:3). Then, 40-keV portal-vein virtual monoenergetic (VMI40keV) and CI, generated from spectral CT scans, served as target and source images. These images were employed to build and train a CI-VMI40keV model. Indexes such as Mean Absolute Error (MAE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity (SSIM) were utilized to determine the best generator mode. An additional 198 cases were divided into three test groups, including Group 1 (58 cases with visible abnormalities), Group 2 (40 cases with hepatocellular carcinoma [HCC]) and Group 3 (100 cases from a publicly available HCC dataset). Both subjective and objective evaluations were performed. Comparisons, correlation analyses and Bland-Altman plot analyses were performed.

RESULTS

The 192nd iteration produced the best generator mode (lower MAE and highest PSNR and SSIM). In the Test groups (1 and 2), both VMI40keV and Gen-VMI40keV significantly improved CT values, as well as SNR and CNR, for all organs compared to CI. Significant positive correlations for objective indexes were found between Gen-VMI40keV and VMI40keV in various organs and lesions. Bland-Altman analysis showed that the differences between both imaging types mostly fell within the 95% confidence interval. Pearson's and Spearman's correlation coefficients for objective scores between Gen-VMI40keV and VMI40keV in Groups 1 and 2 ranged from 0.645 to 0.980. In Group 3, Gen-VMI40keV yielded significantly higher CT values for HCC (220.5HU vs. 109.1HU) and liver (220.0HU vs. 112.8HU) compared to CI (p < 0.01). The CNR for HCC/liver was also significantly higher in Gen-VMI40keV (2.0 vs. 1.2) than in CI (p < 0.01). Additionally, Gen-VMI40keV was subjectively evaluated to have a higher image quality compared to CI.

CONCLUSION

CI-VMI40keV model can generate Gen-VMI40keV from conventional CT scan, closely resembling VMI40keV.

Ensemble learning enhances the precision of preliminary detection of primary hepatocellular carcinoma based on serological and demographic indices

Primary hepatocellular carcinoma (PHC) is associated with high rates of morbidity and malignancy in China and throughout the world. In clinical practice, a combination of ultrasound and alpha-fetoprotein (AFP) measurement is frequently employed for initial screening. However, the accuracy of this approach often falls short of the desired standard. Consequently, this study aimed to investigate the enhancement of precision of preliminary detection of PHC by ensemble learning techniques. To achieve this, 712 patients with PHC and 1887 healthy controls were enrolled for the assessment of four ensemble learning methods, namely, Random Forest (RF), LightGBM, Xgboost, and Catboost. A total of eleven characteristics, comprising nine serological indices and two demographic indices, were selected from the participants for use in detecting PHC. The findings identified an optimal feature subset consisting of eight features, namely AFP, albumin (ALB), alanine aminotransferase (ALT), platelets (PLT), age, alkaline phosphatase (ALP), hemoglobin (Hb), and body mass index (BMI), that achieved the highest classification accuracy of 96.62%. This emphasizes the importance of the collective use of these features in PHC diagnosis. In conclusion, the results provide evidence that the integration of serological and demographic indices together with ensemble learning models, can contribute to the precision of preliminary diagnosis of PHC.

Deep learning for ECG Arrhythmia detection and classification: an overview of progress for period 2017-2023

Cardiovascular diseases are a leading cause of mortality globally. Electrocardiography (ECG) still represents the benchmark approach for identifying cardiac irregularities. Automatic detection of abnormalities from the ECG can aid in the early detection, diagnosis, and prevention of cardiovascular diseases. Deep Learning (DL) architectures have been successfully employed for arrhythmia detection and classification and offered superior performance to traditional shallow Machine Learning (ML) approaches. This survey categorizes and compares the DL architectures used in ECG arrhythmia detection from 2017-2023 that have exhibited superior performance. Different DL models such as Convolutional Neural Networks (CNNs), Multilayer Perceptrons (MLPs), Transformers, and Recurrent Neural Networks (RNNs) are reviewed, and a summary of their effectiveness is provided. This survey provides a comprehensive roadmap to expedite the acclimation process for emerging researchers willing to develop efficient algorithms for detecting ECG anomalies using DL models. Our tailored guidelines bridge the knowledge gap allowing newcomers to align smoothly with the prevailing research trends in ECG arrhythmia detection. We shed light on potential areas for future research and refinement in model development and optimization, intending to stimulate advancement in ECG arrhythmia detection and classification.

Efficacy of fusion imaging for immediate post-ablation assessment of malignant liver neoplasms: A systematic review

BACKGROUND

Percutaneous thermal ablation has become the preferred therapeutic treatment option for liver cancers that cannot be resected. Since ablative zone tissue changes over time, it becomes challenging to determine therapy effectiveness over an extended period. Thus, an immediate post-procedural evaluation of the ablation zone is crucial, as it could influence the need for a second-look treatment or follow-up plan. Assessing treatment response immediately after ablation is essential to attain favorable outcomes. This study examines the efficacy of image fusion strategies immediately post-ablation in liver neoplasms to determine therapeutic response.

METHODOLOGY

A comprehensive systematic search using PRISMA methodology was conducted using EMBASE, MEDLINE (via PUBMED), and Cochrane Library Central Registry electronic databases to identify articles that assessed the immediate post-ablation response in malignant hepatic tumors with fusion imaging (FI) systems. The data were retrieved on relevant clinical characteristics, including population demographics, pre-intervention clinical history, lesion characteristics, and intervention type. For the outcome metrics, variables such as average fusion time, intervention metrics, technical success rate, ablative safety margin, supplementary ablation rate, technical efficacy rate, LTP rates, and reported complications were extracted.

RESULTS

Twenty-two studies were included for review after fulfilling the study eligibility criteria. FI's immediate technical success rate ranged from 81.3% to 100% in 17/22 studies. In 16/22 studies, the ablative safety margin was assessed immediately after ablation. Supplementary ablation was performed in 9 studies following immediate evaluation by FI. In 15/22 studies, the technical effectiveness rates during the first follow-up varied from 89.3% to 100%.

CONCLUSION

Based on the studies included, we found that FI can accurately determine the immediate therapeutic response in liver cancer ablation image fusion and could be a feasible intraprocedural tool for determining short-term post-ablation outcomes in unresectable liver neoplasms. There are some technical challenges that limit the widespread adoption of FI techniques. Large-scale randomized trials are warranted to improve on existing protocols. Future research should emphasize improving FI's technological capabilities and clinical applicability to a broader range of tumor types and ablation procedures.

A lightweight neural network with multiscale feature enhancement for liver CT segmentation

Segmentation of abdominal Computed Tomography (CT) scan is essential for analyzing, diagnosing, and treating visceral organ diseases (e.g., hepatocellular carcinoma). This paper proposes a novel neural network (Res-PAC-UNet) that employs a fixed-width residual UNet backbone and Pyramid Atrous Convolutions, providing a low disk utilization method for precise liver CT segmentation. The proposed network is trained on medical segmentation decathlon dataset using a modified surface loss function. Additionally, we evaluate its quantitative and qualitative performance; the Res16-PAC-UNet achieves a Dice coefficient of 0.950 ± 0.019 with less than half a million parameters. Alternatively, the Res32-PAC-UNet obtains a Dice coefficient of 0.958 ± 0.015 with an acceptable parameter count of approximately 1.2 million.

Practical utility of liver segmentation methods in clinical surgeries and interventions

Clinical imaging (e.g., magnetic resonance imaging and computed tomography) is a crucial adjunct for clinicians, aiding in the diagnosis of diseases and planning of appropriate interventions. This is especially true in malignant conditions such as hepatocellular carcinoma (HCC), where image segmentation (such as accurate delineation of liver and tumor) is the preliminary step taken by the clinicians to optimize diagnosis, staging, and treatment planning and intervention (e.g., transplantation, surgical resection, radiotherapy, PVE, embolization, etc). Thus, segmentation methods could potentially impact the diagnosis and treatment outcomes. This paper comprehensively reviews the literature (during the year 2012-2021) for relevant segmentation methods and proposes a broad categorization based on their clinical utility (i.e., surgical and radiological interventions) in HCC. The categorization is based on the parameters such as precision, accuracy, and automation.

A review on treatments of hepatocellular carcinoma—role of radio wave ablation and possible improvements

Background

Currently, several treatment options are available for liver cancer depending on various factors such as location, size, shape, and liver function. Image fusion is required for the diagnosis, intervention, and follow-up of certain HCCs. Presently, mental fusion is the only way while diagnosing liver lesions by comparing the ultrasound (US) image with the computed tomography (CT) image. Nevertheless, mental fusion is bound to have errors. The objective of this paper is to study the present treatment options for hepatocellular carcinoma and review the present treatment options, list out their potential limitations, and present a possible alternative solution based on the findings to reduce errors and mistargeting.

Methods

This is a systematic review on the present treatment options for hepatocellular carcinoma, especially radio wave ablation.

Results

It is found that computer fusion is the possible alternative to the present mental registration.

Conclusions

Although computer fusion is the best alternative to use radio wave ablation, there have been a few open-ended questions to further explore.