A hierarchical fusion strategy of deep learning networks for detection and segmentation of hepatocellular carcinoma from computed tomography images.

BACKGROUND: Automatic segmentation of hepatocellular carcinoma (HCC) on computed tomography (CT) scans is in urgent need to assist diagnosis and radiomics analysis. The aim of this study is to develop a deep learning based network to detect HCC from dynamic CT images. METHODS: Dynamic CT images of 595 patients with HCC were used. Tumors in dynamic CT images were labeled by radiologists. Patients were randomly divided into training, validation and test sets in a ratio of 5:2:3, respectively. We developed a hierarchical fusion strategy of deep learning networks (HFS-Net). Global dice, sensitivity, precision and F1-score were used to measure performance of the HFS-Net model. RESULTS: The 2D DenseU-Net using dynamic CT images was more effective for segmenting small tumors, whereas the 2D U-Net using portal venous phase images was more effective for segmenting large tumors. The HFS-Net model performed better, compared with the single-strategy deep learning models in segmenting small and large tumors. In the test set, the HFS-Net model achieved good performance in identifying HCC on dynamic CT images with global dice of 82.8%. The overall sensitivity, precision and F1-score were 84.3%, 75.5% and 79.6% per slice, respectively, and 92.2%, 93.2% and 92.7% per patient, respectively. The sensitivity in tumors < 2 cm, 2-3, 3-5 cm and > 5 cm were 72.7%, 92.9%, 94.2% and 100% per patient, respectively. CONCLUSIONS: The HFS-Net model achieved good performance in the detection and segmentation of HCC from dynamic CT images, which may support radiologic diagnosis and facilitate automatic radiomics analysis.

Prediction of extranodal extension in head and neck squamous cell carcinoma by CT images using an evolutionary learning model.

BACKGROUND: Extranodal extension (ENE) in head and neck squamous cell carcinoma (HNSCC) correlates to poor prognoses and influences treatment strategies. Deep learning may yield promising performance of predicting ENE in HNSCC but lack of transparency and interpretability. This work proposes an evolutionary learning method, called EL-ENE, to establish a more interpretable ENE prediction model for aiding clinical diagnosis. METHODS: There were 364 HNSCC patients who underwent neck lymph node (LN) dissection with pre-operative contrast-enhanced computerized tomography images. All the 778 LNs were divided into training and test sets with the ratio 8:2. EL-ENE uses an inheritable bi-objective combinatorial genetic algorithm for optimal feature selection and parameter setting of support vector machine. The diagnostic performances of the ENE prediction model and radiologists were compared using independent test datasets. RESULTS: The EL-ENE model achieved the test accuracy of 80.00%, sensitivity of 81.13%, and specificity of 79.44% for ENE detection. The three radiologists achieved the mean diagnostic accuracy of 70.4%, sensitivity of 75.6%, and specificity of 67.9%. The features of gray-level texture and 3D morphology of LNs played essential roles in predicting ENE. CONCLUSIONS: The EL-ENE method provided an accurate, comprehensible, and robust model to predict ENE in HNSCC with interpretable radiomic features for expanding clinical knowledge. The proposed transparent prediction models are more trustworthy and may increase their acceptance in daily clinical practice.

Evolutionary Learning-Derived Clinical-Radiomic Models for Predicting Early Recurrence of Hepatocellular Carcinoma after Resection.

BACKGROUND AND AIMS: Current prediction models for early recurrence of hepatocellular carcinoma (HCC) after surgical resection remain unsatisfactory. The aim of this study was to develop evolutionary learning-derived prediction models with interpretability using both clinical and radiomic features to predict early recurrence of HCC after surgical resection. METHODS: Consecutive 517 HCC patients receiving surgical resection with available contrast-enhanced computed tomography (CECT) images before resection were retrospectively enrolled. Patients were randomly assigned to a training set (n = 362) and a test set (n = 155) in a ratio of 7:3. Tumor segmentation of all CECT images including noncontrast phase, arterial phase, and portal venous phase was manually performed for radiomic feature extraction. A novel evolutionary learning-derived method called genetic algorithm for predicting recurrence after surgery of liver cancer (GARSL) was proposed to design prediction models for early recurrence of HCC within 2 years after surgery. RESULTS: A total of 143 features, including 26 preoperative clinical features, 5 postoperative pathological features, and 112 radiomic features were used to develop GARSL preoperative and postoperative models. The area under the receiver operating characteristic curves (AUCs) for early recurrence of HCC within 2 years were 0.781 and 0.767, respectively, in the training set, and 0.739 and 0.741, respectively, in the test set. The accuracy of GARSL models derived from the evolutionary learning method was significantly better than models derived from other well-known machine learning methods or the early recurrence after surgery for liver tumor (ERASL) preoperative (AUC = 0.687, p < 0.001 vs. GARSL preoperative) and ERASL postoperative (AUC = 0.688, p < 0.001 vs. GARSL postoperative) models using clinical features only. CONCLUSION: The GARSL models using both clinical and radiomic features significantly improved the accuracy to predict early recurrence of HCC after surgical resection, which was significantly better than other well-known machine learning-derived models and currently available clinical models.

Removal of micropollutants from municipal wastewater by graphene adsorption and simultaneous electrocoagulation/electrofiltration process.

In this work the optimal operating conditions for removing selected micropollutants (also known as emerging contaminants, ECs) from actual municipal wastewater by graphene adsorption (GA) and simultaneous electrocoagulation/electrofiltration (EC/EF) process, respectively, were first determined and evaluated. Then, performance and mechanisms for the removal of selected phthalates and pharmaceuticals from municipal wastewater simultaneously by the GA and EC/EF process were further assessed. ECs of concern included di-n-butyl phthalate (DnBP), di-(2-ethylhexyl) phthalate (DEHP), acetaminophen (ACE), caffeine (CAF), cefalexin (CLX) and sulfamethoxazole (SMX). It was found that GA plus EC/EF process yielded the following removal efficiencies: DnBP, 89 ± 2%; DEHP, 85 ± 3%; ACE, 99 ± 2%; CAF, 94 ± 3%; CLX, 100 ± 0%; and SMX, 98 ± 2%. Carbon adsorption, size exclusion, electrostatic repulsion, electrocoagulation, and electrofiltration were considered as the main mechanisms for the removal of target ECs by the integrated process indicated above.

Performance and mechanisms for the removal of phthalates and pharmaceuticals from aqueous solution by graphene-containing ceramic composite tubular membrane coupled with the simultaneous electrocoagulation and electrofiltration process.

In this study, commonly detected emerging contaminants (ECs) in water, including di-n-butyl phthalate (DnBP), di(2-ethylhexyl) phthalate (DEHP), cephalexin (CLX), sulfamethoxazole (SMX) and caffeine (CAF), were selected as the target contaminants. A lab-prepared graphene-containing ceramic composite tubular membrane (TGCCM) coupled with the simultaneous electrocoagulation and electrofiltration process (EC/EF) in crossflow filtration mode was used to remove target contaminants in model solution. Meanwhile, a comparison of the removal efficiency was made among various tubular composite membranes reported, including carbon fibers/carbon/alumina composite tubular membrane (TCCACM), titania/alumina composite tubular membrane (TTACM) and alumina tubular membrane (TAM). The results of this study showed that the removal efficiencies for DnBP and DEHP were 99%, whereas 32-97% for cephalexin (CLX), sulfamethoxazole (SMX) and caffeine (CAF). In this work the mechanisms involved in removing target ECs were proposed and their roles in removing various ECs were also discussed. Further, two actual municipal wastewaters were treated to evaluate the applicability of the aforementioned treatment technology (i.e., TGCCM coupled with EC/EF) to various aqueous solutions in the real world.

Monitoring and removal of residual phthalate esters and pharmaceuticals in the drinking water of Kaohsiung City, Taiwan.

This study monitored the occurrence and removal efficiencies of 8 phthalate esters (PAEs) and 13 pharmaceuticals present in the drinking water of Kaohsiung City, Taiwan. The simultaneous electrocoagulation and electrofiltration (EC/EF) process was used to remove the contaminants. To this end, a monitoring program was conducted and a novel laboratory-prepared tubular carbon nanofiber/carbon/alumina composite membrane (TCCACM) was incorporated into the EC/EF treatment module (collectively designated as "TCCACM-EC/EF treatment module") to remove the abovementioned compounds from water samples. The monitoring results showed that the concentrations of PAEs were lower in water samples from drinking fountains as compared with tap water samples. No significant differences were found between the concentrations of pharmaceuticals in the two types of water samples. Under optimal operating conditions, the TCCACM-EC/EF treatment module yielded the lowest residual concentrations, ranging from not detected (ND) to 52ng/L for PAEs and pharmaceuticals of concern in the tap water samples. Moreover, the performance of the TCCACM-EC/EF treatment module is comparable with a series of treatment units employed for the drinking fountain water treatment system. The relevant removal mechanisms involved in the TCCACM-EC/EF treatment module were also discussed in this work.