The Rapid Non-Destructive Differentiation of Different Varieties of Rice by Fluorescence Hyperspectral Technology Combined with Machine Learning.

A rice classification method for the fast and non-destructive differentiation of different varieties is significant in research at present. In this study, fluorescence hyperspectral technology combined with machine learning techniques was used to distinguish five rice varieties by analyzing the fluorescence hyperspectral features of Thai jasmine rice and four rice varieties with a similar appearance to Thai jasmine rice in the wavelength range of 475-1000 nm. The fluorescence hyperspectral data were preprocessed by a first-order derivative (FD) to reduce the background and baseline drift effects of the rice samples. Then, a principal component analysis (PCA) and t-distributed stochastic neighborhood embedding (t-SNE) were used for feature reduction and 3D visualization display. A partial least squares discriminant analysis (PLS-DA), BP neural network (BP), and random forest (RF) were used to build the rice classification models. The RF classification model parameters were optimized using the gray wolf algorithm (GWO). The results show that FD-t-SNE-GWO-RF is the best model for rice classification, with accuracy values of 99.8% and 95.3% for the training and test sets, respectively. The fluorescence hyperspectral technique combined with machine learning is feasible for classifying rice varieties.

A Study of the Correlation of Perfusion Parameters in High-Resolution GRASP MRI With Microvascular Density in Lung Cancer.

BACKGROUND: The histological count of microvascular density (MVD) is the current clinical standard for assessing tumor angiogenesis. Although it is hypothesized that perfusion MRI can be a noninvasive alternative to MVD, there have been few studies to validate their correlations, particularly in lung cancer. PURPOSE: To investigate the correlation between MVD and perfusion parameters obtained from high-resolution GRASP (Golden-angle RAdial Sparse Parallel) dynamic contrast-enhanced (DCE)-MRI in a cohort of lung cancer patients, and to validate that GRASP MRI can serve as a free-breathing, noninvasive imaging approach for studying tumor angiogenesis. STUDY TYPE: Prospective. POPULATION: Twenty-five lung cancer patients (16 male, 9 female, mean age = 57.3 ± 11.7 years). FIELD STRENGTH/SEQUENCE: 3T MRI; a prototype golden-angle stack-of-stars sequence. ASSESSMENT: Contrast-enhanced MR data were acquired during free breathing and were reconstructed using GRASP with a temporal resolution of ∼3 sec/phase. For all data, perfusion analysis was performed using a standard Tofts model to generate the volume transfer coefficient (Ktrans ) and the interstitial volume (Ve ). The MVD of corresponding tumor specimens, obtained from Computed Tomography-guided biopsies, were counted with CD34 staining. STATISTICAL TESTS: Pearson correlation analysis; one-way analysis of variance analysis; least significant difference-t method of multiple comparisons. RESULTS: The correlation coefficient was 0.983 and 0.972 for the measurement and remeasurement of Ktrans and Ve . The mean values of Ktrans , Ve , and MVD were 0.33 ± 0.22 min-1 , 0.25 ± 0.12, and 49.68 ± 27.08 vessels/0.723 mm2 , respectively, in all patients (n = 25); 0.36 ± 0.26 min-1 , 0.27 ± 0.13, and 49.09 ± 29.84 vessels/0.723 mm2 , respectively, in adenocarcinoma (n = 15); 0.34 ± 0.17 min-1 , 0.26 ± 0.12, and 53.85 ± 23.53 vessels/0.723 mm2 , respectively, in squamous cell carcinoma (n = 8); and 0.13 ± 0.15 min-1 , 0.14 ± 0.06, and 37.20 ± 28.28 vessels/0.723 mm2 , respectively, in small-cell carcinoma (n = 2). There was a positive relationship between the Ktrans and MVD in all patients (r = 0.738, P < 0.001). DATA CONCLUSION: High spatiotemporal resolution DCE-MRI using GRASP is a promising noninvasive alternative to the histological count of MVD for assessing tumor angiogenesis in lung cancer. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1186-1194.

Identification and quantification of adulteration in collagen powder by terahertz spectroscopy - the effect of spectral characteristics on performance is considered.

Terahertz spectroscopy is an emerging rapid detection method that can be used to detect and analyze food quality issues. However, models developed based on various spectral characteristics of terahertz have shown different performances in food identification. Therefore, we preliminarily analyzed the effect of terahertz spectral characteristics on the identification and quantification of collagen powder adulterated with food powders (plant protein powder, corn starch, wheat flour) with the use of random forest (RF), linear discriminant analysis (LDA), and partial least squares regression (PLSR), and determined the spectral characteristics suitable for identification and quantitative analysis. Then, the selected spectral characteristics data were preprocessed using baseline correction (BC), gaussian filter (GF), moving average (MA), and savitzky-golay (SG). Feature variables were extracted from preprocessed spectral characteristics data using genetic algorithm (GA), random forest (RF), and least angle regression (LAR). The study indicated that the BC-GA-LDA classification model based on the absorption coefficient spectra achieved an accuracy of 96.96% in identifying adulterated collagen powder. Additionally, the GA-PLSR model developed based on the power spectra demonstrated excellent performance in predicting adulteration levels, with the coefficient of determination (Rp2) values ranging from 0.93 to 0.99. The results showed that the rational selection of terahertz spectral characteristics is highly feasible for the accurate detection of collagen powder adulteration.

Primary pulmonary hyalinizing clear cell carcinoma with fusions of both EWSR1::CREM and IRF2::NTRK3: report of a case with an aggressive behavior.

Primary pulmonary hyalinizing clear cell carcinoma (HCCC) is a rare salivary gland-type tumor newly recognized in recent years, with approximately 21 cases reported to date in the English literature, which constitutes a challenge in pathology diagnosis, particularly in small biopsy specimens. Here, we present a case of pulmonary HCCC diagnosed by computed tomography-guided percutaneous lung biopsy in a 70-year-old man's right lower lung. Although the morphology and immunophenotype of the tumor suggested the diagnosis of mucoepidermoid carcinoma, fluorescence in situ hybridization failed to reveal the rearrangement of MAML2 gene, which is characteristic of mucoepidermoid carcinoma. Instead, further molecular genetic testing showed that the tumor harbored a rare EWSR1::CREM fusion combined with a previously unreported IRF2::NTRK3 fusion. Pulmonary HCCC is commonly regarded as a low-grade malignant tumor with an indolent course, but this case has a different biological behavior, presenting extensive dissemination and metastases at the time of diagnosis, which expands our understanding of the prognosis of this tumor. The patient has had five cycles of combination chemotherapy and has been alive with the tumor for eight months.

Distinguishing Different Varieties of Oolong Tea by Fluorescence Hyperspectral Technology Combined with Chemometrics.

Oolong tea is a semi-fermented tea that is popular among people. This study aims to establish a classification method for oolong tea based on fluorescence hyperspectral technology(FHSI) combined with chemometrics. First, the spectral data of Tieguanyin, Benshan, Maoxie and Huangjingui were obtained. Then, standard normal variation (SNV) and multiple scatter correction (MSC) were used for preprocessing. Principal component analysis (PCA) was used for data visualization, and with tolerance ellipses that were drawn according to Hotelling, outliers in the spectra were removed. Variable importance for the projection (VIP) > 1 in partial least squares discriminant analysis (PLS−DA) was used for feature selection. Finally, the processed spectral data was entered into the support vector machine (SVM) and PLS−DA. MSC_VIP_PLS−DA was the best model for the classification of oolong tea. The results showed that the use of FHSI could accurately distinguish these four types of oolong tea and was able to identify the key wavelengths affecting the tea classification, which were 650.11, 660.29, 665.39, 675.6, 701.17, 706.31, 742.34 and 747.5 nm. In these wavelengths, different kinds of tea have significant differences (p < 0.05). This study could provide a non-destructive and rapid method for future tea identification.

Perivascular Epithelioid Cell Tumor of Urinary Bladder.

OBJECTIVES: To review the clinicopathologic features of perivascular epithelioid cell tumor (PEComa) of the urinary bladder. METHODS: Seven cases of bladder PEComa were studied by light microscopy, immunohistochemistry, and fluorescence in situ hybridization (FISH). RESULTS: In our 7 cases, 5 patients were female and 2 were male, with ages between 26 and 78 years. Patients presented with hematuria and recurrent abdominal discomfort as the main clinical symptoms. Microscopically, the epithelioid and spindle-shaped tumor cells with clear to granular eosinophilic cytoplasm were arranged in fascicular, acinar, or nested patterns. The tumor cells were positive for HMB45, melan-A, and SMA, but no TFE3 gene rearrangement was detected in any of the 7 samples by FISH. The analysis of all 35 cases from the literature and ours showed a patient age range from 16 to 78 years (mean age, 39 years), a male-to-female ratio of 1:1.3, maximal tumor diameters from 0.6 to 18.8 cm (mean, 4.5 cm). With a mean follow-up of 27 months, the recurrence, metastasis, and mortality rates were 10.7%, 10.7%, and 7.1%, respectively. CONCLUSIONS: Bladder PEComa is extremely rare, remains a diagnostic challenge, and needs more attention. Strengthening the understanding of this tumor will improve diagnostic accuracy.

Nodal follicular dendritic cell sarcoma with four atypical histomorphologic features: an unusual case report.

BACKGROUND: Follicular dendritic cell sarcoma (FDCS) is a rare malignancy. In addition to the classical histopathologic features, it has also some special morphological variants that can present a challenge in the diagnosis of this disease. CASE PRESENTATION: A 45-year-old male who presented with a left supraclavicular mass was given a final diagnosis of FDCS after lymph node biopsy. The specimen obtained during radical resection revealed five different morphologies, including the classical histological appearance and atypical areas resembling desmoplastic infiltrative carcinoma, anaplastic large cell lymphoma (ALCL), hemangiopericytoma and classical Hodgkin's lymphoma (CHL). Immunohistochemistry was notable for positive CD21 and CD23 expression across all morphologies. Given the atypical appearance and location, the specimen was initially misdiagnosed as a metastatic carcinoma based on histology alone at an outside institution. The patient eventually underwent surgical resection followed by adjuvant chemotherapy and radiation. Despite treatment, the disease progressed, and the patient passed away 36 months after surgery. CONCLUSIONS: This unusual case of FDCS contains four types of atypical histomorphologies within a single tumor specimen, including those resembling ALCL and hemangiopericytoma which are described here for the first time. Our report further expands the histopathologic spectrum of FDCS and may help assist in the diagnosis of other such challenging cases.

Mediastinal follicular dendritic cell sarcoma: a rare, potentially under-recognized, and often misdiagnosed disease.

BACKGROUND: Mediastinal follicular dendritic cell sarcoma (FDCS) is extremely rare. Due to potential under-recognization of this disease, it happens to be misdiagnosed, especially on core needle biopsy. We report 3 cases of mediastinal FDCS and provide a literature review to improve better understanding of the tumor and to reduce misdiagnosis. METHODS: Three cases of mediastinal FDCS in our clinic practice were studied, including their core needle biopsy and resected specimens, and those cases reported previously in English literature were retrieved and analyzed. RESULTS: The core needle biopsy of case 1 showed a tumor reminiscent of classical Hodgkin's lymphoma (CHL), while the resected mass was finally diagnosed with FDCS combined with hyaline-vascular Castleman's disease. Both the biopsy and resected tissue of case 2 were constitutive of the clear epithelioid cells with marked atypia. In both cases, definitive diagnoses were not made on core needle biopsy. In case 3, there were some areas morphologically similar to CHL, and some areas contained ovoid to spindle-shaped tumor cells with fascicular pattern. The analysis of 43 cases of mediastinal FDCS showed the age of patients were from 16 to 76 years old, the male to female ratio was 1.5:1, the maximal tumor diameters were 3-17 cm. 18 cases were underwent preoperative biopsy, whereas 15 (83.3%) of which were misdiagnosed initially, often as lymphoma. 32 patients had available follow-up data, the rates of recurrence, metastasis, and mortality were 12.5, 18.8 and 28.1%, respectively. Current limited data suggested no statistical differences between adverse prognosis and gender, age, tumor size, necrosis, or different therapeutics, respectively. CONCLUSIONS: Mediastinal FDCS is a rare malignancy that has yet not been fully understood and been often misdiagnosed, particularly when making a diagnosis on core needle biopsy. Increased awareness of this enigmatic tumor is crucial to avoid diagnostic pitfalls.

Fast smooth second-order sliding mode control for systems with additive colored noises.

In this paper, a fast smooth second-order sliding mode control is presented for a class of stochastic systems with enumerable Ornstein-Uhlenbeck colored noises. The finite-time mean-square practical stability and finite-time mean-square practical reachability are first introduced. Instead of treating the noise as bounded disturbance, the stochastic control techniques are incorporated into the design of the controller. The finite-time convergence of the prescribed sliding variable dynamics system is proved by using stochastic Lyapunov-like techniques. Then the proposed sliding mode controller is applied to a second-order nonlinear stochastic system. Simulation results are presented comparing with smooth second-order sliding mode control to validate the analysis.

Primary follicular dendritic cell sarcoma of the urinary bladder: the first case report and potential diagnostic pitfalls.

BACKGROUND: Extranodal follicular dendritic cell sarcoma (FDCS) is a very rare malignancy with a variable clinical course. It is often not considered and has the potential to result in a misdiagnosis of other common sarcomas or sarcomatoid carcinomas. This is particularly true with the preoperative biopsy specimen, in which the tissue sample is often small. CASE PRESENTATION: A case of FDCS in a 63-year-old woman, arising in the urinary bladder, a previously unreported site, is described. The patient presented with the typical clinical symptoms of a bladder cancer, and the morphology of the tumor was similar to a lymphoepithelioma-like carcinoma, ultimately resulting in it being misdiagnosed. The patient received radical cystectomy, without further radiotherapy or chemotherapy. Two years after operation, a metastatic tumor to the lung was found. The mass of the right main bronchus lumen was frozen and resected through bronchoscopy, and radiotherapy was performed. The patient has lived with the tumor since then. CONCLUSIONS: This paper presents the first FDCS occurring in the urinary bladder with metastasis to the lung and emphasizes potential diagnostic pitfalls.