Discrimination of ground-glass nodular lung adenocarcinoma pathological subtypes via transfer learning: A multicenter study.

BACKGROUND: The surgical approach and prognosis for invasive adenocarcinoma (IAC) and minimally invasive adenocarcinoma (MIA) of the lung differ. However, they both manifest as identical ground-glass nodules (GGNs) in computed tomography images, and no effective method exists to discriminate them. METHODS: We developed and validated a three-dimensional (3D) deep transfer learning model to discriminate IAC from MIA based on CT images of GGNs. This model uses a 3D medical image pre-training model (MedicalNet) and a fusion model to build a classification network. Transfer learning was utilized for end-to-end predictive modeling of the cohort data of the first center, and the cohort data of the other two centers were used as independent external validation data. This study included 999 lung GGN images of 921 patients pathologically diagnosed with IAC or MIA at three cohort centers. RESULTS: The predictive performance of the model was assessed using the area under the receiver operating characteristic curve (AUC). The model had high diagnostic efficacy for the training and validation groups (accuracy: 89%, sensitivity: 95%, specificity: 84%, and AUC: 95% in the training group; accuracy: 88%, sensitivity: 84%, specificity: 93%, and AUC: 92% in the internal validation group; accuracy: 83%, sensitivity: 83%, specificity: 83%, and AUC: 89% in one external validation group; accuracy: 78%, sensitivity: 80%, specificity: 77%, and AUC: 82% in the other external validation group). CONCLUSIONS: Our 3D deep transfer learning model provides a noninvasive, low-cost, rapid, and reproducible method for preoperative prediction of IAC and MIA in lung cancer patients with GGNs. It can help clinicians to choose the optimal surgical strategy and improve the prognosis of patients.

Predictive Efficacy of a Radiomics Random Forest Model for Identifying Pathological Subtypes of Lung Adenocarcinoma Presenting as Ground-Glass Nodules.

Purpose: To establish and verify the ability of a radiomics prediction model to distinguish invasive adenocarcinoma (IAC) and minimal invasive adenocarcinoma (MIA) presenting as ground-glass nodules (GGNs). Methods: We retrospectively analyzed 118 lung GGN images and clinical data from 106 patients in our hospital from March 2016 to April 2019. All pathological classifications of lung GGN were confirmed as IAC or MIA by two pathologists. R language software (version 3.5.1) was used for the statistical analysis of the general clinical data. ITK-SNAP (version 3.6) and A.K. software (Analysis Kit, American GE Company) were used to manually outline the regions of interest of lung GGNs and collect three-dimensional radiomics features. Patients were randomly divided into training and verification groups (ratio, 7:3). Random forest combined with hyperparameter tuning was used for feature selection and prediction modeling. The receiver operating characteristic curve and the area under the curve (AUC) were used to evaluate model prediction efficacy. The calibration curve was used to evaluate the calibration effect. Results: There was no significant difference between IAC and MIA in terms of age, gender, smoking history, tumor history, and lung GGN location in both the training and verification groups (P>0.05). For each lung GGN, the collected data included 396 three-dimensional radiomics features in six categories. Based on the training cohort, nine optimal radiomics features in three categories were finally screened out, and a prediction model was established. We found that the training group had a high diagnostic efficacy [accuracy, sensitivity, specificity, and AUC of the training group were 0.89 (95%CI, 0.73 - 0.99), 0.98 (95%CI, 0.78 - 1.00), 0.81 (95%CI, 0.59 - 1.00), and 0.97 (95%CI, 0.92-1.00), respectively; those of the validation group were 0.80 (95%CI, 0.58 - 0.93), 0.82 (95%CI, 0.55 - 1.00), 0.78 (95%CI, 0.57 - 1.00), and 0.92 (95%CI, 0.83 - 1.00), respectively]. The model calibration curve showed good consistency between the predicted and actual probabilities. Conclusions: The radiomics prediction model established by combining random forest with hyperparameter tuning effectively distinguished IAC from MIA presenting as GGNs and represents a noninvasive, low-cost, rapid, and reproducible preoperative prediction method for clinical application.

Emerging applications of radiomics in rectal cancer: State of the art and future perspectives.

Rectal cancer (RC) is the third most commonly diagnosed cancer and has a high risk of mortality, although overall survival rates have improved. Preoperative assessments and predictions, including risk stratification, responses to therapy, long-term clinical outcomes, and gene mutation status, are crucial to guide the optimization of personalized treatment strategies. Radiomics is a novel approach that enables the evaluation of the heterogeneity and biological behavior of tumors by quantitative extraction of features from medical imaging. As these extracted features cannot be captured by visual inspection, the field holds significant promise. Recent studies have proved the rapid development of radiomics and validated its diagnostic and predictive efficacy. Nonetheless, existing radiomics research on RC is highly heterogeneous due to challenges in workflow standardization and limitations of objective cohort conditions. Here, we present a summary of existing research based on computed tomography and magnetic resonance imaging. We highlight the most salient issues in the field of radiomics and analyze the most urgent problems that require resolution. Our review provides a cutting-edge view of the use of radiomics to detect and evaluate RC, and will benefit researchers dedicated to using this state-of-the-art technology in the era of precision medicine.

Deep Learning for Accurate Diagnosis of Liver Tumor Based on Magnetic Resonance Imaging and Clinical Data.

Background: Early-stage diagnosis and treatment can improve survival rates of liver cancer patients. Dynamic contrast-enhanced MRI provides the most comprehensive information for differential diagnosis of liver tumors. However, MRI diagnosis is affected by subjective experience, so deep learning may supply a new diagnostic strategy. We used convolutional neural networks (CNNs) to develop a deep learning system (DLS) to classify liver tumors based on enhanced MR images, unenhanced MR images, and clinical data including text and laboratory test results. Methods: Using data from 1,210 patients with liver tumors (N = 31,608 images), we trained CNNs to get seven-way classifiers, binary classifiers, and three-way malignancy-classifiers (Model A-Model G). Models were validated in an external independent extended cohort of 201 patients (N = 6,816 images). The area under receiver operating characteristic (ROC) curve (AUC) were compared across different models. We also compared the sensitivity and specificity of models with the performance of three experienced radiologists. Results: Deep learning achieves a performance on par with three experienced radiologists on classifying liver tumors in seven categories. Using only unenhanced images, CNN performs well in distinguishing malignant from benign liver tumors (AUC, 0.946; 95% CI 0.914-0.979 vs. 0.951; 0.919-0.982, P = 0.664). New CNN combining unenhanced images with clinical data greatly improved the performance of classifying malignancies as hepatocellular carcinoma (AUC, 0.985; 95% CI 0.960-1.000), metastatic tumors (0.998; 0.989-1.000), and other primary malignancies (0.963; 0.896-1.000), and the agreement with pathology was 91.9%.These models mined diagnostic information in unenhanced images and clinical data by deep-neural-network, which were different to previous methods that utilized enhanced images. The sensitivity and specificity of almost every category in these models reached the same high level compared to three experienced radiologists. Conclusion: Trained with data in various acquisition conditions, DLS that integrated these models could be used as an accurate and time-saving assisted-diagnostic strategy for liver tumors in clinical settings, even in the absence of contrast agents. DLS therefore has the potential to avoid contrast-related side effects and reduce economic costs associated with current standard MRI inspection practices for liver tumor patients.

Neural Stem Cells Transfected with Reactive Oxygen Species-Responsive Polyplexes for Effective Treatment of Ischemic Stroke.

Neural stem cells (NSCs), capable of ischemia-homing, regeneration, and differentiation, exert strong therapeutic potentials in treating ischemic stroke, but the curative effect is limited in the harsh microenvironment of ischemic regions rich in reactive oxygen species (ROS). Gene transfection to make NSCs overexpress brain-derived neurotrophic factor (BDNF) can enhance their therapeutic efficacy; however, viral vectors must be used because current nonviral vectors are unable to efficiently transfect NSCs. The first polymeric vector, ROS-responsive charge-reversal poly[(2-acryloyl)ethyl(p-boronic acid benzyl)diethylammonium bromide] (B-PDEA), is shown here, that mediates efficient gene transfection of NSCs and greatly enhances their therapeutics in ischemic stroke treatment. The cationic B-PDEA/DNA polyplexes can effectively transfect NSCs; in the cytosol, the B-PDEA is oxidized by intracellular ROS into negatively charged polyacrylic acid, quickly releasing the BDNF plasmids for efficient transcription and secreting a high level of BDNF. After i.v. injection in ischemic stroke mice, the transfected NSCs (BDNF-NSCs) can home to ischemic regions as efficiently as the pristine NSCs but more efficiently produce BDNF, leading to significantly augmented BDNF levels, which in turn enhances the mouse survival rate to 60%, from 0% (nontreated mice) or ≈20% (NSC-treated mice), and enables more rapid and superior functional reconstruction.

Discovery, Semisynthesis, Antiparasitic and Cytotoxic Evaluation of 14-Membered Resorcylic Acid Lactones and Their Derivatives.

Ten antifouling 14-membered resorcylic acid lactones 1-10 were isolated previously with low or trace natural abundance from the zoanthid-derived Cochliobolus lunatus fungus. Further optimization of fermentation conditions led to the isolation of two major natural compounds 7 and 8 with multi-gram quantities. By one or two steps, we semisynthesized the six trace natural compounds 1-6 and a series of derivatives 11-27 of compounds 7 and 8 with high yields (65-95%). Compounds 11-13 showed strong antiplasmodial activity against Plasmodium falciparum with IC50 values of 1.84, 8.36, and 6.95 µM, respectively. Very importantly, 11 and 12 were non-toxic with very safety and high therapeutic indices (CC50/IC50 > 180), and thus representing potential promising leads for antiplasmodial drug discovery. Furthermore, 11 was the only compound showed obvious antileishmanial activity against Leishmania donovani with an IC50 value of 9.22 µM. Compounds 11 and 12 showed the values of IC50 at 11.9 and 17.2 µM against neglected Chagas' disease causing Trypanosoma cruzi, respectively.

Correlation between Calpain-10 single-nucleotide polymorphisms and obstructive sleep apnea/hypopnoea syndrome with ischemic stroke in a Chinese population: A population-based study.

BACKGROUND: Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a common chronic disorder which is followed by various complications. Calpain-10 belongs to a commonly expressed member of the Calpain-like cysteine protease family, which acts as risk marker for some diseases. The purpose of this study is to elucidate correlation between Calpain-10 single-nucleotide polymorphisms (SNPs) and the incidence of OSAHS followed by ischemic stroke (IS). METHODS: OSAHS patients were divided as OSAHS + IS, OSAHS, and control groups, respectively. Immunohistochemistry was performed for Calpain-10 protein expression, polymerase chain reaction (PCR)-restriction fragment length polymorphism for detection of gene polymorphisms of SNP 43 and SNP 19, and PCR-allele specific amplification for SNP 44. Polysomnography was conducted to check the nocturnal polysomnography indicators, and also Montreal Cognitive Assessment (MoCA), Scientific Data System scores cognition and anxiety of patients, respectively. Logistic analysis was used for the risky factors for OSAHS. RESULTS: Calpain-10 protein expression was significantly increased in the OSAHS + IS and OSAHS groups compared with the control group. Significant differences in SNP 43 and SNP 44 genotype, and also allele frequency were observed in 3 groups, among which the OSAHS + IS group had higher SNP 43 and SNP 44 allele frequency than the control and OSAHS groups. There were differences regarding apnea-hypopnea index, minimum fingertip blood oxygen saturation (LSaO2 [%]), oxygen reduction index (ODI) between patients with different genotypes of SNP 43 and SNP 44 in OSAHS patients, and also GC and AT frequency in the OSAHS + IS and OSAHS groups. As compared with the OSAHS group, the MoCA scores and MoCA subitems in the OSAHS + IS group were declined, whereas the Scientific Data System scores were elevated. Additionally, GG 43 genotype, high apnea-hypopnea index, and body mass index were detected as the risk factors of OSAHS. CONCLUSION: These findings indicate that the Calpain-10 SNP 43 may be related to OSAHS with IS, with SNP 43 GG genotype as a risk factor for OSAHS with IS.

Low molecular weight polyethylenimine-conjugated gold nanospheres: a platform for selective gene therapy controlled by near-infrared light.

AIM: Whether PEI2k-HAuNS could promote gene transfection efficiency controlled by near-infrared (NIR) light. MATERIALS & METHODS: This safe nonviral gene delivery system was obtained by conjugating low molecular weight (2 kDa) polyethylenimine (PEI) onto hollow gold nanospheres (PEI2k-HAuNS). Upon NIR laser irradiation, there was a conspicuous increase both in the in vitro and in vivo transfection achieved by the nanocomplexes. Furthermore, a plasmid encoding the tumor suppressor TP53 (pTP53) was applied to test antitumor activity. RESULTS: The enhanced gene transfection efficiency and therapy of PEI2k-HAuNS were achieved via the mediation of an NIR laser compared with the other treatments in vitro and in vivo. CONCLUSION: The application of NIR laser irradiated PEI2k-HAuNS can be used as a promising gene delivery systems in vitro and in vivo.

Single-walled carbon nanotubes alter cytochrome c electron transfer and modulate mitochondrial function.

Single-walled carbon nanotubes (SWCNTs) are broadly used for various biomedical applications such as drug delivery, in vivo imaging, and cancer photothermal therapy due to their unique physiochemical properties. However, once they enter the cells, the effects of SWCNTs on the intracellular organelles and macromolecules are not comprehensively understood. Cytochrome c (Cyt c), as a key component of the electron transport chain in mitochondria, plays an essential role in cellular energy consumption, growth, and differentiation. In this study, we found the mitochondrial membrane potential and mitochondrial oxygen uptake were greatly decreased in human epithelial KB cells treated with SWCNTs, which accompanies the reduction of Cyt c. SWCNTs deoxidized Cyt c in a pH-dependent manner, as evidenced by the appearance of a 550 nm characteristic absorption peak, the intensity of which increased as the pH increased. Circular dichroism measurement confirmed the pH-dependent conformational change, which facilitated closer association of SWCNTs with the heme pocket of Cyt c and thus expedited the reduction of Cyt c. The electron transfer of Cyt c is also disturbed by SWCNTs, as measured with electron spin resonance spectroscopy. In conclusion, the redox activity of Cyt c was affected by SWCNTs treatment due to attenuated electron transfer and conformational change of Cyt c, which consequently changed mitochondrial respiration of SWCNTs-treated cells. This work is significant to SWCNTs research because it provides a novel understanding of SWCNTs' disruption of mitochondria function and has important implications for biomedical applications of SWCNTs.

Bimodal visualization of colorectal uptake of nanoparticles in dimethylhydrazine-treated mice.

AIM: To investigate colorectal uptake of solid lipid nanoparticles (SLNs) in mice receiving different doses of 1,2-dimethylhydrazine (DMH) using magnetic resonance (MR) and laser-scanning confocal fluorescence microscope (LSCFM) imaging. METHODS: Eight mice were sacrificed in a pilot study to establish the experimental protocol and to visualize colorectal uptake of SLNs in normal mice. Gadopentetate dimeglumine and fluorescein isothiocyanate (FITC)-loaded SLN (Gd-FITC-SLN) enemas were performed on mice receiving DMH for 10 wk (group 1, n = 9) or 16 wk (group 2, n = 7) and FITC-SLN enema was performed on 4 DMH-treated mice (group 3). Pre- and post-enema MR examinations were made to visualize the air-inflated distal colorectum. Histological and LSCFM examinations were performed to verify colorectal malignancy and to track the distribution of SLNs. RESULTS: Homogeneous enhancement and dense fluorescence (FITC) deposition in colorectal wall were observed in normal mice and 1 DMH-treated mouse (group 1) on fluid attenuated inversion recovery (FLAIR) and LSCFM images, respectively. Heterogeneous mural enhancement was found in 6 mice (4 in group 1; 2 in group 2). No visible mural enhancement was observed in the other mice. LSCFM imaging revealed linear fluorescence deposition along the colorectal mucosa in all groups. Nine intraluminal masses and one prolapsed mass were detected by MR imaging with different enhancement modes and pathologies. Interstitial FITC deposition was identified where obvious enhancement was observed in FLAIR images. Bladder imaging agent accumulations were observed in 11 of 16 DMH-treated mice of groups 1 and 2. CONCLUSION: There are significant differences in colorectal uptake and distribution of SLNs between normal and DMH-treated mice, which may provide a new mechanism of contrast for MR colonography.

Coexistence of small cell neuroendocrine carcinoma and villous adenoma in the ampulla of Vater.

Small cell neuroendocrine carcinoma of the ampulla of Vater is extremely rare and different from the common ampullary adenocarcinoma. The ampullary adenoma is also a rare neoplasm and has the potential to develop an adenocarcinoma. Their coexistence has been rarely reported in the literature. We herein describe an unusual case of a small cell neuroendocrine carcinoma associated with a villous adenoma in the ampulla of Vater with emphasis on computed tomography (CT) and histopathological findings. We also discuss their clinical, histopathological and radiological features as well as possible histogenesis.