scholarly journals Colon Tissues Classification and Localization in Whole Slide Images Using Deep Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1398
Author(s):  
Pushpanjali Gupta ◽  
Yenlin Huang ◽  
Prasan Kumar Sahoo ◽  
Jeng-Fu You ◽  
Sum-Fu Chiang ◽  
...  
Keyword(s):  
Interobserver Variability ◽  
Tissue Sample ◽  
Treatment Strategies ◽  
Region Of Interest ◽  
Final Diagnosis ◽  
Colon Tissue ◽  
Automated Method ◽  
Slide Image ◽  
Colon Tissue Sample ◽  
Whole Slide Images

Colorectal cancer is one of the leading causes of cancer-related death worldwide. The early diagnosis of colon cancer not only reduces mortality but also reduces the burden related to the treatment strategies such as chemotherapy and/or radiotherapy. However, when the microscopic examination of the suspected colon tissue sample is carried out, it becomes a tedious and time-consuming job for the pathologists to find the abnormality in the tissue. In addition, there may be interobserver variability that might lead to conflict in the final diagnosis. As a result, there is a crucial need of developing an intelligent automated method that can learn from the patterns themselves and assist the pathologist in making a faster, accurate, and consistent decision for determining the normal and abnormal region in the colorectal tissues. Moreover, the intelligent method should be able to localize the abnormal region in the whole slide image (WSI), which will make it easier for the pathologists to focus on only the region of interest making the task of tissue examination faster and lesser time-consuming. As a result, artificial intelligence (AI)-based classification and localization models are proposed for determining and localizing the abnormal regions in WSI. The proposed models achieved F-score of 0.97, area under curve (AUC) 0.97 with pretrained Inception-v3 model, and F-score of 0.99 and AUC 0.99 with customized Inception-ResNet-v2 Type 5 (IR-v2 Type 5) model.

scholarly journals Standardized Method for Defining a 1-mm2 Region of Interest for Calculation of Mitotic Rate on Melanoma Whole Slide Images

2021 ◽  
Author(s):  
Minhua Wang ◽  
Phyu P. Aung ◽  
Victor G. Prieto
Keyword(s):  
Hot Spot ◽  
Standard Procedure ◽  
Region Of Interest ◽  
Mitotic Rate ◽  
Routine Practice ◽  
Glass Slides ◽  
Slide Image ◽  
Standardized Method ◽  
Mitotic Figures ◽  
Whole Slide Images

Context.— Mitotic rate counting is essential in pathologic evaluations in melanoma. The American Joint Committee on Cancer recommends reporting the number of mitotic figures (MFs) in a 1-mm2 area encompassing the “hot spot.” There is currently no standard procedure for delineating a 1-mm2 region of interest for MF counting on a digital whole slide image (WSI) of melanoma. Objective.— To establish a standardized method to enclose a 1-mm2 region of interest for MF counting in melanoma based on WSIs and assess the method's effectiveness. Design.— Whole slide images were visualized using the ImageScope viewer (Aperio). Different monitors and viewing magnifications were explored and the annotation tools provided by ImageScope were evaluated. For validation, we compared mitotic rates obtained from WSIs with our method and those from glass slides with traditional microscopy with 30 melanoma cases. Results.— Of the monitors we examined, a 32-inch monitor with 3840 × 2160 resolution was optimal for counting MFs within a 1-mm2 region of interest in melanoma. When WSIs were viewed in the ImageScope viewer, ×10 to ×20 magnification during screening could efficiently locate a hot spot and ×20 to ×40 magnification during counting could accurately identify MFs. Fixed-shape annotations with 500 × 500-μm squares or circles can precisely and efficiently enclose a 1-mm2 region of interest. Our method on WSIs was able to produce a higher mitotic rate than with glass slides. Conclusions.— Whole slide images may be used to efficiently count MFs. We recommend fixed-shape annotation with 500 × 500-μm squares or circles for routine practice in counting MFs for melanoma.

scholarly journals Region of interest demarcation for quantification of the apparent diffusion coefficient in breast lesions and its interobserver variability

2015 ◽  
Vol 21 (2) ◽  
pp. 123-127 ◽  
Author(s):  
Luísa Nogueira ◽  
Sofia Brandão ◽  
Eduarda Matos ◽  
Rita Gouveia Nunes ◽  
Hugo Alexandre Ferreira ◽  
...  
Keyword(s):  
Diffusion Coefficient ◽  
Apparent Diffusion Coefficient ◽  
Interobserver Variability ◽  
Region Of Interest ◽  
Breast Lesions ◽  
Apparent Diffusion

scholarly journals Prognostic Value of Homotypic Cell Internalization by Nonprofessional Phagocytic Cancer Cells

2015 ◽  
Vol 2015 ◽  
pp. 1-14 ◽  
Author(s):  
Manuela Schwegler ◽  
Anna M. Wirsing ◽  
Hannah M. Schenker ◽  
Laura Ott ◽  
Johannes M. Ries ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Cancer ◽  
Tissue Sample ◽  
Apoptotic Cell ◽  
Treatment Strategies ◽  
Tissue Microarrays ◽  
Cell Internalization ◽  
Cell Structures

Background. In this study, we investigated the prognostic role of homotypic tumor cell cannibalism in different cancer types.Methods. The phenomenon of one cell being internalized into another, which we refer to as “cell-in-cell event,” was assessed in 416 cases from five head and neck cancer cohorts, as well as one anal and one rectal cancer cohort. The samples were processed into tissue microarrays and immunohistochemically stained for E-cadherin and cleaved caspase-3 to visualize cell membranes and apoptotic cell death.Results. Cell-in-cell events were found in all of the cohorts. The frequency ranged from 0.7 to 17.3 cell-in-cell events per mm2. Hardly any apoptotic cells were found within the cell-in-cell structures, although apoptotic cell rates were about 1.6 to two times as high as cell-in-cell rates of the same tissue sample. High numbers of cell-in-cell events showed adverse effects on patients’ survival in the head and neck and in the rectal cancer cohorts. In multivariate analysis, high frequency was an adverse prognostic factor for overall survival in patients with head and neck cancer (p=0.008).Conclusion. Cell-in-cell events were found to predict patient outcomes in various types of cancer better than apoptosis and proliferation and might therefore be used to guide treatment strategies.

scholarly journals Differentiation of Parkinson’s disease and Parkinsonism predominant multiple system atrophy in early disease stages by means of objective measurement in Susceptibility Weighted Imaging

2021 ◽  
Author(s):  
Qingguo Ren ◽  
Yihua Wang ◽  
Xiaomin Nan ◽  
Jianyuan Zhang ◽  
Xiangshui Meng ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Multiple System Atrophy ◽  
Signal Intensity ◽  
Early Stage ◽  
Region Of Interest ◽  
Final Diagnosis ◽  
Susceptibility Weighted Imaging ◽  
Lentiform Nucleus ◽  
Potential Marker

Abstract Background We have established radiological protocol and made morphological measurement of the lentiform nucleus (LN) and the signal intensity which we used to discriminate parkinsonism predominant multiple system atrophy (MSA-P) from Parkinson’s disease (PD). But we don’t know whether it works especially in early stage of MSA-P. This case-control study aimed to investigate whether the new measurement of the morphological and intensity changes in susceptibility weighted imaging (SWI) of the LN could discriminate MSA-P from PD in their early stage and controls. Methods We retrospectively enrolled patients with MSA-P, PD, and sex- and age-matched controls between January 2015 and July 2020 at the Movement Disorder Center who underwent brain MR scanning with SWI sequence. Two specialists at the center reviewed the medical records and made the final diagnosis, and two experienced neuroradiologists performed MRI image analysis based on a defined radiological protocol to conduct the region of interest (ROI) based morphological measurements of the LN and the signal intensity. Results A total of 17 patients with MSA-P, 17 patients with PD within 2 years of the disease duration and 17 controls were enrolled in this study. We found that patients with MSA-P had significant decreased size in the short line (SL, cSL), and the ratio of the SL and the long line (SLLr, cSLLr) compared with the patients with PD and with the controls (P < 0.05). Combining these four indexes, this finding had a sensitivity of 58.8% and a specificity of 100% to distinguish MSA-P from PD. Conclusions As compared to PD and control subjects, the MSA-P patients are characterized by narrowing morphology of the posterior region of LN. The quantitative morphological change is a possible potential marker to differentiate MSA-P from PD in the early stage.

scholarly journals Efficient pan-cancer whole-slide image classification and outlier detection using convolutional neural networks

2019 ◽  
Author(s):  
Seda Bilaloglu ◽  
Joyce Wu ◽  
Eduardo Fierro ◽  
Raul Delgado Sanchez ◽  
Paolo Santiago Ocampo ◽  
...  
Keyword(s):  
Visual Analysis ◽  
Classification Problem ◽  
Classification Performance ◽  
Neoplastic Tissue ◽  
Multiple Tumor ◽  
Slide Image ◽  
Prediction Systems ◽  
Multi Class Classification ◽  
The Many ◽  
Whole Slide Images

AbstractVisual analysis of solid tissue mounted on glass slides is currently the primary method used by pathologists for determining the stage, type and subtypes of cancer. Although whole slide images are usually large (10s to 100s thousands pixels wide), an exhaustive though time-consuming assessment is necessary to reduce the risk of misdiagnosis. In an effort to address the many diagnostic challenges faced by trained experts, recent research has been focused on developing automatic prediction systems for this multi-class classification problem. Typically, complex convolutional neural network (CNN) architectures, such as Google’s Inception, are used to tackle this problem. Here, we introduce a greatly simplified CNN architecture, PathCNN, which allows for more efficient use of computational resources and better classification performance. Using this improved architecture, we trained simultaneously on whole-slide images from multiple tumor sites and corresponding non-neoplastic tissue. Dimensionality reduction analysis of the weights of the last layer of the network capture groups of images that faithfully represent the different types of cancer, highlighting at the same time differences in staining and capturing outliers, artifacts and misclassification errors. Our code is available online at: https://github.com/sedab/PathCNN.

The Role of Ultrasonography in the Diagnosis and Decision Algorithm for the Management of Pneumothorax after Transbronchial Lung Cryobiopsy

Respiration ◽  
2021 ◽  
pp. 1-9
Author(s):  
David Barros Coelho ◽  
Rita Boaventura ◽  
Leonor Meira ◽  
Susana Guimarães ◽  
Conceição Souto Moura ◽  
...  
Keyword(s):  
Clinical Status ◽  
Treatment Strategies ◽  
Final Diagnosis ◽  
Decision Algorithm ◽  
Chest X Ray ◽  
Transbronchial Lung Cryobiopsy ◽  
Ionizing Radiation Exposure ◽  
Point Projection ◽  
Lung Point

<b><i>Background:</i></b> Pneumothorax is one of the main complications of transbronchial lung cryobiopsy (TBLC). Chest ultrasound (CUS) is a radiation-free alternative method for pneumothorax detection. <b><i>Objective:</i></b> We tested CUS diagnostic accuracy for pneumothorax and assessed its role in the decision algorithm for pneumothorax management. Secondary objectives were to evaluate the post-procedure pneumothorax occurrence and risk factors. <b><i>Methods:</i></b> Eligible patients underwent TBLC, followed by chest X-ray (CXR) evaluation 2 h after the procedure, as our standard protocol. Bedside CUS was performed within 30 min and 2 h after TBLC. Pneumothorax by CUS was defined by the absence of lung sliding and comet-tail artefacts and confirmed with the stratosphere sign on M-mode. Pneumothorax size was determined through lung point projection on CUS and interpleural distance on CXR and properly managed according to clinical status. <b><i>Results:</i></b> Sixty-seven patients were included. Nineteen pneumothoraces were detected at 2 h after the procedure, of which 8 (42.1%) were already present at the first CUS evaluation. All CXR-detected pneumothoraces had a positive CUS detection. There were 3 discordant cases (κ = 0.88, 95% CI: 0.76–1.00, <i>p</i> &#x3c; 0.001), which were detected by CUS but not by inspiration CXR. We calculated a specificity of 97.5% (95% CI: 86.8–99.9) and a sensitivity of 100% (95% CI: 87.2–100) for CUS. Pneumothorax rate was higher when biopsies were taken in 2 lobes and if histology had pleural representation. Final diagnosis was achieved in 79.1% of patients, with the most frequent diagnosis being hypersensitivity pneumonitis. Regarding patients with large-volume pneumothorax needing drainage, the rate of detection was similar between CUS and CRX. <b><i>Conclusion:</i></b> CUS can replace CXR in detecting the presence of pneumothorax after TBLC, and the lung point site can reliably indicate its size. This useful method optimizes time spent at the bronchology unit and allows immediate response in symptomatic patients, helping to choose optimal treatment strategies, while preventing ionizing radiation exposure.

scholarly journals Intra- and Interobserver Reliability and Variability of Femoral Artery Pseudoaneurysm Measurements Between Pre- and Postprocessed B-mode Sonographic Images

2018 ◽  
Vol 35 (2) ◽  
pp. 87-94 ◽  
Author(s):  
Reham Kaifi ◽  
Lauren Price ◽  
Andrew Chen ◽  
Babak Sarani ◽  
Vesna Zderic
Keyword(s):  
Femoral Artery ◽  
Interobserver Variability ◽  
Interobserver Reliability ◽  
Intraclass Correlation ◽  
Region Of Interest ◽  
Body Width ◽  
Artery Pseudoaneurysm ◽  
Neck Width ◽  
Contrast Enhanced ◽  
Trained Observers

The objective was to enhance the contrast and segment the femoral artery pseudoaneurysm (FAP) area from patients’ ultrasonography (US) images. In addition, this study compared the intra- and interobserver reliability and variability of the FAP measurements from the original, contrast-enhanced, and segmented US. Retrospectively, 25 FAP sonograms were evaluated by four observers (two trained and two novice). They twice measured the FAP body width, neck width, and length from original, enhanced, and segmented US. The intra- and interobserver reliability for measuring FAP body width, neck width, and neck length improved by 10% after enhancing the original 2D US contrast and segmenting the region of interest across all observers. Also, the intra- and interobserver variability among measurements across all observers decreased by 44%. Using US processing was more profound for novice observers (intraclass correlation coefficient [ICC], 0.76–0.93) compared to trained observers (ICC, 0.94–0.99). US postprocessing resulted in a decrease in variability for FAP measurements.

scholarly journals NI-09 Amide Proton Transfer (APT) image is useful for diagnostic imaging of glioma

2020 ◽  
Vol 2 (Supplement_3) ◽  
pp. ii13-ii13
Author(s):  
Masami Shirota ◽  
Masayuki Nitta ◽  
Taiichi Saitou ◽  
Syunsuke Tuduki ◽  
Atsushi Fukui ◽  
...  
Keyword(s):  
Diagnostic Imaging ◽  
Malignant Tumors ◽  
Treatment Strategies ◽  
Region Of Interest ◽  
Amide Proton ◽  
Diagnostic Ability ◽  
Accumulation Ratio ◽  
Significant Difference ◽  
Met Pet

Abstract Introduction: APT image(APT),which images the concentration of amide groups that increases in tumors, is expected to be applied clinically in diagnostic imaging of glioma. Purpose: APT was compared with MET-PET based on the pathological diagnosis results, and it was retrospectively verified that APT was useful for diagnostic imaging of glioma. Methods: A total of 46cases with glioma (WHO 2016 Grade: GII/III/IV) and Pseudoprogression were included. APT measured the APT measurement value by placing the region of interest in the tumor part. MET-PET was administered with 370MBq and the accumulation ratio(TNR) between the tumor part and the normal part was measured. Results: The APT measurement value in all cases was 2.22±1.01 and the TNR was 2.58±1.50,and a correlation was observed between the APT measurement value and the TNR(r=0.6, p&lt;0.001).When the accuracy of discrimination between GII/III/IV (32cases) and Pseudoprogression(14cases) by APT measurement was verified, the sensitivity was 91% and the specificity was 100% at the threshold of 1.81. In the verification of malignancy diagnosis, the measured APT value of GII (6cases) was 2.18±0.43,the measured APT value of GIII (11cases) was 2.67±0.69,and the measured APT value of GIV (15cases) was 2.99±0.61.The measured value showed a significant difference. The measured APT value in the oligodendroglioma group (GII/III:10cases) was 2.37±0.66,the TNR was 3.52±1.41,and the measured APT value in the astrocytoma group (GII/III: 7cases)Was 2.67±0.45 and TNR was 2.41±0.87.In the oligodendroglioma group, the measured APT value was lower and the TNR was higher than in the astrocytoma group. Conclusion: It was suggested that APT may have the same diagnostic ability as MET-PET in diagnosing malignant tumors and distinguishing between recurrence and Pseudoprogression. Patients with an actual APT of 1.81 or higher should consider treatment strategies, and follow-up may be an option for patients with an APT of &lt;1.81.APT,which is not affected by the blood-brain barrier, has little variation in measured values and is considered to be useful for diagnostic imaging of glioma.

scholarly journals A novel, reproducible, and objective method for volumetric magnetic resonance imaging assessment of enhancing glioblastoma

2014 ◽  
Vol 121 (3) ◽  
pp. 536-542 ◽  
Author(s):  
Charles W. Kanaly ◽  
Ankit I. Mehta ◽  
Dale Ding ◽  
Jenny K. Hoang ◽  
Peter G. Kranz ◽  
...  
Keyword(s):  
Interobserver Variability ◽  
Intraclass Correlation ◽  
Evaluation Criteria ◽  
Correlation Coefficients ◽  
Response Assessment ◽  
Volumetric Method ◽  
Kappa Statistics ◽  
Macdonald Criteria ◽  
Automated Method ◽  
Radiological Response

Object Robust methodology that allows objective, automated, and observer-independent measurements of brain tumor volume, especially after resection, is lacking. Thus, determination of tumor response and progression in neurooncology is unreliable. The objective of this study was to determine if a semi-automated volumetric method for quantifying enhancing tissue would perform with high reproducibility and low interobserver variability. Methods Fifty-seven MR images from 13 patients with glioblastoma were assessed using our method, by 2 neuroradiologists, 1 neurosurgeon, 1 neurosurgical resident, 1 nurse practitioner, and 1 medical student. The 2 neuroradiologists also performed traditional 1-dimensional (1D) and 2-dimensional (2D) measurements. Intraclass correlation coefficients (ICCs) assessed interobserver variability between measurements. Radiological response was determined using Response Evaluation Criteria In Solid Tumors (RECIST) guidelines and Macdonald criteria. Kappa statistics described interobserver variability of volumetric radiological response determinations. Results There was strong agreement for 1D (RECIST) and 2D (Macdonald) measurements between neuroradiologists (ICC = 0.42 and 0.61, respectively), but the agreement using the authors' novel automated approach was significantly stronger (ICC = 0.97). The volumetric method had the strongest agreement with regard to radiological response (κ = 0.96) when compared with 2D (κ = 0.54) or 1D (κ = 0.46) methods. Despite diverse levels of experience of the users of the volumetric method, measurements using the volumetric program remained remarkably consistent in all users (0.94). Conclusions Interobserver variability using this new semi-automated method is less than the variability with traditional methods of tumor measurement. This new method is objective, quick, and highly reproducible among operators with varying levels of expertise. This approach should be further evaluated as a potential standard for response assessment based on contrast enhancement in brain tumors.

Sign in / Sign up

Export Citation Format

Share Document