- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP) - Anaheim, CA, USA (2018.11.26-2018.11.29)] 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP) - DIGITAL STAINING OF HIGH-RESOLUTION FTIR SPECTROSCOPIC IMAGES
摘要： Histological stains, such as hemotaxylin and eosin (H&E), are commonly used to label tissue in clinical biopsies. However, these labels modify the tissue chemistry, making it difficult to use for further downstream analysis. Fourier transform infrared spectroscopy (FTIR) has shown promising results for characterizing disease-relevant tissues without chemical labels or dyes. However, tissue classification requires human annotation, which is difficult and tedious to acquire for complex samples. In addition, the results of a molecular analysis must be presented in a way that facilitates diagnosis for a trained pathologist. One proposed approach is digital staining, which uses machine learning to map an infrared spectroscopic image to the image that would be ideally produced with a chemical stain. While these methods produce promising results, the resolution is significantly lower than traditional histology. We demonstrate that high-resolution mappings can be obtained using FTIR imaging and histological staining of the same sample. In addition, we demonstrate that better results can be achieved with more recent convolutional neural networks (CNNs) that take advantage of both spatial and spectral features.
关键词： CNN,Digital staining,Image analysis,Histopathology
更新于2025-11-19 16:56:35
-
Fast ScanNet: Fast and Dense Analysis of Multi-Gigapixel Whole-Slide Images for Cancer Metastasis Detection
摘要： Lymph node metastasis is one of the most important indicators in breast cancer diagnosis, that is traditionally observed under the microscope by pathologists. In recent years, with the dramatic advance of high-throughput scanning and deep learning technology, automatic analysis of histology from whole-slide images has received a wealth of interest in the field of medical image computing, which aims to alleviate pathologists’ workload and simultaneously reduce misdiagnosis rate. However, automatic detection of lymph node metastases from whole-slide images remains a key challenge because such images are typically very large, where they can often be multiple gigabytes in size. Also, the presence of hard mimics may result in a large number of false positives. In this paper, we propose a novel method with anchor layers for model conversion, which not only leverages the efficiency of fully convolutional architectures to meet the speed requirement in clinical practice, but also densely scans the whole-slide image to achieve accurate predictions on both micro- and macro-metastases. Incorporating the strategies of asynchronous sample prefetching and hard negative mining, the network can be effectively trained. The efficacy of our method are corroborated on the benchmark dataset of 2016 Camelyon Grand Challenge. Our method achieved significant improvements in comparison with the state-of-the-art methods on tumour localization accuracy with a much faster speed and even surpassed human performance on both challenge tasks.
关键词： metastasis detection,Histopathology image analysis,deep learning,whole-slide image,computational pathology
更新于2025-09-23 15:23:52
-
A novel alignment procedure to assess calcified coronary plaques in histopathology, post-mortem computed tomography angiography and optical coherence tomography
摘要： Purpose: Improve mapping and registration of longitudinal view on histopathology vessels in a three-dimensional alignment procedure for postmortem quantitative coronary plaque analyses. This new procedure is applied and results shown using calcified coronary plaque analyses within post-mortem computed tomography angiography (PMCTA), optical coherence tomography (OCT) and the gold standard of histopathology. Results: In total, 338 annotated histopathology images were included, 166 PMCTA transversal images and 285 OCT images were aligned in the comparison. The results from the comparison using the alignment procedure showed overall that the calcified plaques seem to be overestimated by PMCTA and underestimated by OCT. Conclusions: The 3D fusion approach, aligning the images of PMCTA, OCT and histopathology as gold standard allowed for a slice-based comparison of the different modalities. The results showed that PMCTA overestimates the calcified plaques while OCT underestimates these, compared to histopathology.
关键词： Alignment,Calcified coronary plaques,Histopathology,Optical coherence tomography,Postmortem-computed tomography angiography
更新于2025-09-23 15:23:52
-
[ACM Press the 2018 3rd International Conference - Bari, Italy (2018.10.11-2018.10.13)] Proceedings of the 2018 3rd International Conference on Biomedical Imaging, Signal Processing - ICBSP 2018 - Tissue Region Growing for Hispathology Image Segmentation
摘要： The accurate identification of the tumour tissue border is of crucial importance for histopathology image analysis. However, due to the high morphology variance in histology images, especially in border regions where cancer tissue interfere into the normal region, it is challenging even for the pathologists to define the border, not to say for the machine. In this paper, we present an innovative framework to semantically segment the tumour border area in colorectal liver metastasis (CRLM) on pixel level by integrating the features from deep convolutional networks with spatial and statistical information of the cells. With annotations from the pathologists, a two-level deep neural network including a cell-level model and a tissue-level model, is trained to classify patches from the whole slide scan image. Based on the prediction of trained models, a growing-style algorithm is proposed to finalize the segmentation by leveraging the statistical and spatial properties of the cells. Evaluated against the ground truth created by the experts, the framework demonstrates a significant improvement over a conventional deep network model on the cell-level model or the tissue model alone.
关键词： image segmentation,Histopathology image,deep learning.
更新于2025-09-19 17:15:36
-
Digital Staining of High-Definition Fourier Transform Infrared (FT-IR) Images Using Deep Learning
摘要： Histological stains, such as hematoxylin and eosin (H&E), are routinely used in clinical diagnosis and research. While these labels offer a high degree of specificity, throughput is limited by the need for multiple samples. Traditional histology stains, such as immunohistochemical labels, also rely only on protein expression and cannot quantify small molecules and metabolites that may aid in diagnosis. Finally, chemical stains and dyes permanently alter the tissue, making downstream analysis impossible. Fourier transform infrared (FT-IR) spectroscopic imaging has shown promise for label-free characterization of important tissue phenotypes and can bypass the need for many chemical labels. Fourier transform infrared classification commonly leverages supervised learning, requiring human annotation that is tedious and prone to errors. One alternative is digital staining, which leverages machine learning to map IR spectra to a corresponding chemical stain. This replaces human annotation with computer-aided alignment. Previous work relies on alignment of adjacent serial tissue sections. Since the tissue samples are not identical at the cellular level, this technique cannot be applied to high-definition FT-IR images. In this paper, we demonstrate that cellular-level mapping can be accomplished using identical samples for both FT-IR and chemical labels. In addition, higher-resolution results can be achieved using a deep convolutional neural network that integrates spatial and spectral features.
关键词： convolutional neural networks,FT-IR,deep learning,Fourier transform infrared,histopathology,Histology,classification,digital staining
更新于2025-09-19 17:15:36
-
Biomedical applications of mid-infrared quantum cascade lasers – a review
摘要： Mid-infrared spectroscopy has been applied to research in biology and medicine for more than 20 years and conceivable applications have been identified. More recently, these applications have been shown to benefit from the use of quantum cascade lasers due to their specific properties, namely high spectral power density, small beam parameter product, narrow emission spectrum and, if needed, tuning capabilities. This review provides an overview of the achievements and illustrates some applications which benefit from the key characteristics of quantum cascade laser-based mid-infrared spectroscopy using examples such as breath analysis, the investigation of serum, non-invasive glucose monitoring in bulk tissue and the combination of spectroscopy and microscopy of tissue thin sections for rapid histopathology.
关键词： quantum cascade lasers,glucose monitoring,mid-infrared spectroscopy,histopathology,breath analysis,biomedical applications
更新于2025-09-19 17:15:36
-
Evaluating and comparing the morphological and histopathological changes induced by erbium:yttrium‐aluminum‐garnet laser and diamond bur on enamel, dentin and pulp tissue
摘要： Aim: Lasers are used for different types of dental treatments. Using the erbium:yttrium‐aluminum‐garnet (Er:YAG) laser to remove dental hard tissue is simple, advantageous and influences the type of cavity preparation, whether conventional or conservative in nature. The aim of the present study was to evaluate and compare the morphological and histopathological changes in the enamel, dentin and pulp tissue of the teeth treated by Er:YAG laser and conventional burs. Methods: A conventional class I cavity was prepared in orthodontic patients by laser and bur. The teeth were extracted and analyzed for morphological changes using a scanning electron microscope, ground sections and histopathological changes under a light microscope. Results: The time with laser was longer than the conventional methods. The lased cavity showed irregular appearance with absence of smear layer which is suitable for the resin restoration. The ground section and the histopathological study showed no differences between the groups. Conclusion: The Er:YAG laser is effective in the removal of dental hard tissue without damaging the pulp when coupled with ideal energy output. It is widely used in different dental fields. It needs time to be accepted by dentist and patients and further studies are required to explore its advantages.
关键词： laser,histopathology,restoration,bur,scanning electron microscope
更新于2025-09-11 14:15:04
-
Deep transfer learning-based prostate cancer classification using 3 Tesla multi-parametric MRI
摘要： Purpose The purpose of the study was to propose a deep transfer learning (DTL)-based model to distinguish indolent from clinically significant prostate cancer (PCa) lesions and to compare the DTL-based model with a deep learning (DL) model without transfer learning and PIRADS v2 score on 3 Tesla multi-parametric MRI (3T mp-MRI) with whole-mount histopathology (WMHP) validation. Methods With IRB approval, 140 patients with 3T mp-MRI and WMHP comprised the study cohort. The DTL-based model was trained on 169 lesions in 110 arbitrarily selected patients and tested on the remaining 47 lesions in 30 patients. We compared the DTL-based model with the same DL model architecture trained from scratch and the classification based on PIRADS v2 score with a threshold of 4 using accuracy, sensitivity, specificity, and area under curve (AUC). Boot-strapping with 2000 resamples was performed to estimate the 95% confidence interval (CI) for AUC. Results After training on 169 lesions in 110 patients, the AUC of discriminating indolent from clinically significant PCa lesions of the DTL-based model, DL model without transfer learning and PIRADS v2 score C 4 were 0.726 (CI [0.575, 0.876]), 0.687 (CI [0.532, 0.843]), and 0.711 (CI [0.575, 0.847]), respectively, in the testing set. The DTL-based model achieved higher AUC compared to the DL model without transfer learning and PIRADS v2 score C 4 in discriminating clinically significant lesions in the testing set. Conclusion The DeLong test indicated that the DTL-based model achieved comparable AUC compared to the classification based on PIRADS v2 score (p = 0.89).
关键词： Whole-mount histopathology,Multi-parametric MRI,Prostate cancer,Deep learning,Clinically significant lesion classification,PIRADS v2 score
更新于2025-09-10 09:29:36
-
Blood Flow in Monocular Retinoblastoma Assessed by Color Doppler and Correlations With High-Risk Pathologic Features
摘要： PURPOSE. To use color Doppler to analyze blood ?ow in the retrobulbar central retinal artery (CRA) and central retinal vein (CRV) in monocular retinoblastoma. METHODS. This prospective study included patients with group D and E retinoblastomas managed with only enucleation. Peak blood velocities were assessed in the CRA and CRV of tumor-containing eyes (CRAv and CRVv, respectively). The resistivity index in the CRA (RIa) and pulse index in the CRV (PIv) were calculated and related to optic nerve invasion (ONi), choroid invasion (mCHi), and tumor volume. RIa and PIv were also calculated for healthy eyes. RESULTS. In total, 25 patients with a mean age of 30.8-months old were included. The means (SD) for CRAv, CRVv, RIa, and PIv were 26.94 (12.32) cm/s, 16.2 (9.56) cm/s, 0.88 (0.12) and 0.79 (0.29), respectively. Tumor volume was signi?cantly correlated with CRAv (P ? 0.025) and RIa (P ? 0.032). ONi was present in 19 eyes and correlated with a smaller PIv (P < 0.001). A PIv less than 0.935 had a sensitivity of 89.5% and speci?city of 83.3% for predicting ONi. mCHi was not correlated with ?ow values. Healthy eyes had a signi?cantly lower RIa (P < 0.001) and lower PIv than eyes with (P ? 0.009) and without (P < 0.001) ONi. tumor volume was directly CONCLUSIONS. correlated with CRAv and RIa, and lower PIv was correlated with optic nerve invasion when a predictive cut-off value of less than 0.935 was applied. Comparisons with healthy eyes showed that tumor-containing eyes were associated with higher RIa and PIv values.
关键词： histopathology,eye enucleation,blood flow velocity,retinoblastoma,color doppler ultrasonography
更新于2025-09-09 09:28:46
-
Comparison of Digital Breast Tomosynthesis (DBT) and Digital Mammography (DM) for Detection of Breast Cancer in Women in Kuwait
摘要： Objective: To investigate the sensitivity and specificity of digital mammography (DM) and digital breast tomosynthesis (DBT) for the detection of breast cancer in comparison to histopathology findings. Subjects and Methods: We included 65 breast lesions in 58 women, each detected by two diagnostic mammography techniques: DM and DBT using Senographe Essential machine (GE Healthcare, Buc, France), and subsequently confirmed by histopathology. The Breast Imaging-Reporting and Data System (BI-RADS) was used for characterizing the lesions. Results: The average age of women was 48.3 years (range; 26-81 years). There were 34 malignant and 31 benign breast lesions. The sensitivity for DM and DBT, was 73.5% and 100%, respectively, while the specificity was 67.7% and 94%, respectively. Receiver-operating characteristic curve analysis showed an overall diagnostic advantage of DBT over DM, with significant a difference between DBT and DM (p < 0.001). By performing Cohen’s kappa test, we found that there was a strong level of agreement according to Altman guidelines between DBT and histopathology findings (0.97), but there was weak agreement between DM and histopathology findings (0.47). Conclusion: DBT improves the clinical accuracy of mammography by increasing both sensitivity and specificity. We believe this improvement is due to improved image visibility and quality. These results could be of interest to health care institutions as it may impact their decision on whether to upgrade to DBT not only for diagnosis but also for screening.
关键词： Digital breast tomosynthesis,Digital mammography,Histopathology,Breast cancer
更新于2025-09-09 09:28:46