Because of its multifactorial nature, predicting the presence of cancer using a single biomarker is difficult. We aimed to establish a novel machine-learning model for predicting hepatocellular ...carcinoma (HCC) using real-world data obtained during clinical practice. To establish a predictive model, we developed a machine-learning framework which developed optimized classifiers and their respective hyperparameter, depending on the nature of the data, using a grid-search method. We applied the current framework to 539 and 1043 patients with and without HCC to develop a predictive model for the diagnosis of HCC. Using the optimal hyperparameter, gradient boosting provided the highest predictive accuracy for the presence of HCC (87.34%) and produced an area under the curve (AUC) of 0.940. Using cut-offs of 200 ng/mL for AFP, 40 mAu/mL for DCP, and 15% for AFP-L3, the accuracies of AFP, DCP, and AFP-L3 for predicting HCC were 70.67% (AUC, 0.766), 74.91% (AUC, 0.644), and 71.05% (AUC, 0.683), respectively. A novel predictive model using a machine-learning approach reduced the misclassification rate by about half compared with a single tumor marker. The framework used in the current study can be applied to various kinds of data, thus potentially become a translational mechanism between academic research and clinical practice.
Background
Ultrasonography (US) is widely used for the diagnosis of liver tumors. However, the accuracy of the diagnosis largely depends on the visual perception of humans. Hence, we aimed to ...construct artificial intelligence (AI) models for the diagnosis of liver tumors in US.
Methods
We constructed three AI models based on still B-mode images: model-1 using 24,675 images, model-2 using 57,145 images, and model-3 using 70,950 images. A convolutional neural network was used to train the US images. The four-class liver tumor discrimination by AI, namely, cysts, hemangiomas, hepatocellular carcinoma, and metastatic tumors, was examined. The accuracy of the AI diagnosis was evaluated using tenfold cross-validation. The diagnostic performances of the AI models and human experts were also compared using an independent test cohort of video images.
Results
The diagnostic accuracies of model-1, model-2, and model-3 in the four tumor types are 86.8%, 91.0%, and 91.1%, whereas those for malignant tumor are 91.3%, 94.3%, and 94.3%, respectively. In the independent comparison of the AIs and physicians, the percentages of correct diagnoses (accuracies) by the AIs are 80.0%, 81.8%, and 89.1% in model-1, model-2, and model-3, respectively. Meanwhile, the median percentages of correct diagnoses are 67.3% (range 63.6%–69.1%) and 47.3% (45.5%–47.3%) by human experts and non-experts, respectively.
Conclusion
The performance of the AI models surpassed that of human experts in the four-class discrimination and benign and malignant discrimination of liver tumors. Thus, the AI models can help prevent human errors in US diagnosis.
Hydrogen embrittlement (HE) characteristics in Fe–C–Mn-xNb steels were examined via various analyses, including electron backscatter diffraction analysis, scanning transmission electron microscopy ...and three-dimensional atom-probe tomography. For the investigation, the steel samples were prepared with varying Nb contents and heat treatment processes. The material properties of steel samples that were subjected to: (i) water quenching and (ii) quenching and tempering at 170 °C for 20 min, were determined to be nearly similar, although different degrees of HE were detected. After the tempering process, ε-carbide precipitated clearly in the matrix, which could act as a trapping site for hydrogen atoms and lead to improved HE resistance. Moreover, with addition of Nb, niobium base precipitates (e.g., NbC) with a diameter of a few nanometers were obtained in the martensite matrix, which could also function as hydrogen trapping sites. There was slight improvement in the HE resistance with NbC. Hydrogen-assisted failure mechanisms under both static and cyclic loading were observed with intergranular brittle cracking for the water quenched sample, even though the brittle and ductile mix failure mode was detected for the sample after the quenching and tempering process.
Despite recent improvements in therapeutic interventions, hepatocellular carcinoma is still associated with a poor prognosis in patients with an advanced disease at diagnosis. Recently, significant ...progress has been made in image recognition through advances in the field of artificial intelligence (AI) (or machine learning), especially deep learning. AI is a multidisciplinary field that draws on the fields of computer science and mathematics for developing and implementing computer algorithms capable of maximizing the predictive accuracy from static or dynamic data sources using analytic or probabilistic models. Because of the multifactorial and complex nature of liver diseases, the machine learning approach to integrate multiple factors would appear to be an advantageous approach to improve the likelihood of making a precise diagnosis and predicting the response of treatment and prognosis of liver diseases. In this review, we attempted to summarize the potential use of AI in the diagnosis and management of liver diseases, especially hepatocellular carcinoma.
This article examines Bella Abzug's activities with regard to the Arab-Israeli conflict at home and abroad during her congressional career (1971–1977), with a focus on the dilemmas she faced, her ...approach to overcoming them, and her ability to mobilize like-minded but diverse American women for her struggle. After tracing her Labor Zionist background and her activities in the early 1970s, this article investigates her strategy for defending Israel during and after the 1975 International Women's Year Conference in Mexico. Abzug's story offers a useful window into the connection between women's politics and the Middle East question; it also illuminates the active role of a group of American women in making the US-Israeli relationship closer during the 1970s. This article concludes that, ironically, in order to endorse Zionism, Abzug, a staunch critic of the Cold War, relied on the US Cold War strategy of eliminating Communist influence from women's politics.
Background & Aims Obesity defined by body mass index (BMI) significantly increases the risk of hepatocellular carcinoma (HCC). In contrast, not only obesity but also underweight is associated with ...poor prognosis in patients with HCC. Differences in body composition rather than BMI were suggested to be true determinants of prognosis. However, this hypothesis has not been demonstrated conclusively. Methods We measured skeletal muscle index (SMI), mean muscle attenuation (MA), visceral adipose tissue index, subcutaneous adipose tissue index, and visceral to subcutaneous adipose tissue area ratios (VSR) via computed tomography in a large-scale retrospective cohort of 1257 patients with different stages of HCC, and comprehensively analyzed the impact of body composition on the prognoses. Results Among five body composition components, low SMI (called sarcopenia), low MA (called intramuscular fat IMF deposition), and high VSR (called visceral adiposity) were significantly associated with mortality, independently of cancer stage or Child-Pugh class. A multivariate analysis revealed that sarcopenia (hazard ratio HR, 1.52; 95% confidence interval CI, 1.18–1.96; p = 0.001), IMF deposition (HR, 1.34; 95% CI, 1.05–1.71; p = 0.020), and visceral adiposity (HR, 1.35; 95% CI, 1.09–1.66; p = 0.005) but not BMI were significant predictors of survival. The prevalence of poor prognostic body composition components was significantly higher in underweight and obese patients than in normal weight patients. Conclusions Sarcopenia, IMF deposition, and visceral adiposity independently predict mortality in patients with HCC. Body composition rather than BMI is a major determinant of prognosis in patients with HCC.
In the present work, a hot-stamping system for carbon fiber reinforced thermoplastic (CFRTP) plates based on electrical resistance heating was developed, where CFRTP consisted of polyphenylene and ...polyacrylonitrile. With the hot-stamping process, a simple hat-shaped sample was made. The heating rate and maximum sample temperature varied depending on the electrical resistance of the CFRTP plate. Moreover, the contact conditions between the electrodes and the CFRTP plate also affected the sample temperature owing to their influence on the electrical resistance, which was determined by the amount of exposed carbon fiber (CF) on the sample surface. Temperature measurements performed using samples with various amounts of exposed CF (20%–95% CF) revealed that approximately 65% CF afforded the highest sample temperature and fastest heating rate. The CFRTP plate underwent non-uniform heating, especially during the early stages, e.g. less than 10 s. Sample heating to 150℃ resulted in permanent deformation of the hat-shaped CFRTP samples with less springback, whereas heating to higher temperatures above the melting point led to meandering of the samples. In contrast, CFRTP samples subjected to hot-stamping at lower temperatures, such as 110℃, exhibited rough surfaces. In addition to the sample temperature, the formability of CFRTP during hot-stamping was affected by the holding time. When hot-stamping was performed without a holding time, even at high temperatures of 150℃ and above, low-quality samples with dented surfaces and irregular sample thickness were obtained. The results of this study indicate that a temperature of 150℃ and a holding time of 10 s are optimal for fabricating high-quality hot-stamped CFRTP with smooth surfaces and uniform thickness.
Background
Reported mortalities and morbidities of therapeutic procedures for liver tumors vary between studies, because of different designs and small sample sizes. We investigated the mortalities ...and complication rates for hepatectomy, radiofrequency ablation (RFA), and trans-catheter arterial embolization (TAE) for hepatocellular carcinoma (HCC) in a large sample, using a nationwide Japanese database (the Diagnosis Procedure Combination database).
Methods
Data from the Diagnosis Procedure Combination database were analyzed for July 1 to December 31, 2007 and the same period in 2008. We identified 54,145 patients with HCC who underwent hepatectomy (
n
= 5,270), RFA (
n
= 11,688), or TAE (
n
= 37,187). In-hospital mortality and morbidity were analyzed for each procedure. The relationships between mortality and factors including patient characteristics and procedural backgrounds were assessed.
Results
In-hospital mortalities associated with hepatectomy, RFA, and TAE were 2.6 % 95 % confidence interval (CI) 2.2–3.1, 0.3 % (0.2–0.4), and 1.0 % (0.9–1.1), and post-procedural complication rates were 14.5 % (13.5–15.5), 4.5 % (4.2–4.9), and 4.5 % (4.3–4.7), respectively. Increased mortality following hepatectomy was significantly associated with older age, extended lobectomy (vs. partial hepatectomy; odds ratio OR 3.80,
p
< 0.001), lower hospital volume (OR 2.74,
p
< 0.001), and renal comorbidity (OR 3.01,
p
= 0.02). Older age and cardiac comorbidity (OR 5.14,
p
= 0.001) were significantly associated with RFA-related mortality, and lower hospital volume was significantly associated with TAE-related mortality (OR 1.60,
p
< 0.001).
Conclusions
Mortalities and morbidities associated with therapeutic procedures for liver tumors were acceptably low in Japan, but were affected by patient and institutional characteristics.
We propose a methodology that uses the relative positional information of multiple antennas to estimate the Wrong Fix, which refers to an erroneous determination of the carrier-phase ambiguity ...utilized in GNSS satellites. The proposed approach is based on the fundamental notion that the mutual positional relationship of multiple antennas mounted on a mobile robot remains constant, and it uses machine-learning techniques based on the relative position information among the antennas to identify instances of Wrong Fixes. The relative distance between the antennas is derived from the real-time kinematic (RTK) position information of each antenna. The confidence level of the RTK positioning results was calculated using logistic regression, considering the measurement error with respect to the true value. To determine the Wrong Fixes, a labeled dataset was constructed, indicating that data were categorized as wrong fixes when the error from the true value exceeded 0.1 m. This dataset served as the training database for the logistic regression model. Experimental results demonstrate that the proposed methodology effectively reduced the root mean squared error between the measured location, classified as fixed by a trained discriminator, and the true value.
Background
Liquid biopsies, particularly those involving circulating tumor DNA (ctDNA), are rapidly emerging as a non-invasive alternative to tumor biopsies. However, clinical applications of ctDNA ...analysis in hepatocellular carcinoma (HCC) have not been fully elucidated.
Methods
We measured the amount of plasma-derived cell-free DNA (cfDNA) in HCC patients before (
n
= 100) and a few days after treatment (
n
= 87), including radiofrequency ablation, transarterial chemoembolization, and molecular-targeted agents (MTAs), and prospectively analyzed their associations with clinical parameters and prognosis.
TERT
promoter mutations in cfDNA were analyzed using droplet digital PCR. Furthermore, we performed a comprehensive mutational analysis of post-treatment cfDNA via targeted ultra-deep sequencing (22,000× coverage) in a panel of 275 cancer-related genes in selected patients.
Results
Plasma cfDNA levels increased significantly according to HCC clinical stage, and a high cfDNA level was independently associated with a poor prognosis.
TERT
promoter mutations were detected in 45% of all cases but were not associated with any clinical characteristics. cfDNA levels increased significantly a few days after treatment, and a greater increase in post-treatment cfDNA levels was associated with a greater therapeutic response to MTAs. The detection rate of
TERT
mutations increased to 57% using post-treatment cfDNA, suggesting that the ctDNA was enriched. Targeted ultra-deep sequencing using post-treatment cfDNA after administering lenvatinib successfully detected various gene mutations and obtained promising results in lenvatinib-responsive cases.
Conclusions
Post-treatment cfDNA analysis may facilitate the construction of biomarkers for predicting MTA treatment effects.