scholarly journals A Histogram-Based Low-Complexity Approach for the Effective Detection of COVID-19 Disease from CT and X-ray Images

2021 ◽  
Vol 11 (19) ◽  
pp. 8867
Author(s):  
Michele Scarpiniti ◽  
Sima Sarv Ahrabi ◽  
Enzo Baccarelli ◽  
Lorenzo Piazzo ◽  
Alireza Momenzadeh
Keyword(s):  
State Of The Art ◽  
Early Stage ◽  
Low Complexity ◽  
Distance Measures ◽  
Ct Scans ◽  
X Rays ◽  
Test Image ◽  
A Value ◽  
Current Century ◽  
Computational Simplicity

The global COVID-19 pandemic certainly has posed one of the more difficult challenges for researchers in the current century. The development of an automatic diagnostic tool, able to detect the disease in its early stage, could undoubtedly offer a great advantage to the battle against the pandemic. In this regard, most of the research efforts have been focused on the application of Deep Learning (DL) techniques to chest images, including traditional chest X-rays (CXRs) and Computed Tomography (CT) scans. Although these approaches have demonstrated their effectiveness in detecting the COVID-19 disease, they are of huge computational complexity and require large datasets for training. In addition, there may not exist a large amount of COVID-19 CXRs and CT scans available to researchers. To this end, in this paper, we propose an approach based on the evaluation of the histogram from a common class of images that is considered as the target. A suitable inter-histogram distance measures how this target histogram is far from the histogram evaluated on a test image: if this distance is greater than a threshold, the test image is labeled as anomaly, i.e., the scan belongs to a patient affected by COVID-19 disease. Extensive experimental results and comparisons with some benchmark state-of-the-art methods support the effectiveness of the developed approach, as well as demonstrate that, at least when the images of the considered datasets are homogeneous enough (i.e., a few outliers are present), it is not really needed to resort to complex-to-implement DL techniques, in order to attain an effective detection of the COVID-19 disease. Despite the simplicity of the proposed approach, all the considered metrics (i.e., accuracy, precision, recall, and F-measure) attain a value of 1.0 under the selected datasets, a result comparable to the corresponding state-of-the-art DNN approaches, but with a remarkable computational simplicity.

scholarly journals Cancer

2016 ◽  
Vol 4 (1) ◽  
Author(s):  
S. C. Shukla
Keyword(s):  
Sexually Transmitted Diseases ◽  
Physical Inactivity ◽  
Alcohol Intake ◽  
Early Stage ◽  
Signs And Symptoms ◽  
The Body ◽  
Ct Scans ◽  
X Rays ◽  
Sexually Transmitted ◽  
Blood Tests

A group of diseases involving abnormal cell growth with the potential to invade or spread to other parts of the body, is known as cancer. Majority (90-95%) of cancers are due to environmental factors. Remaining (5-10%) is due to inherited factors. Most of the cancers can be recognized at early stage due to the appearance of signs and symptoms or through screening. Investigations include blood tests, X-rays, CT scans, endoscopy and biopsy. Some cancers can be prevented by avoiding risk factors as tobacco chewing, obesity, physical inactivity, alcohol intake and sexually transmitted diseases etc.

Can abdominal ultrasound replace CT scanning in long-term follow-up of male patients with germ cell tumor?

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. 4602-4602
Author(s):  
Arthur Gerl ◽  
Adina Hauck ◽  
Marcus Hentrich
Keyword(s):  
Early Stage ◽  
Ct Scanning ◽  
Abdominal Ultrasound ◽  
Stage I ◽  
Ct Scans ◽  
X Rays ◽  
International Consensus ◽  
Long Term Outcome

4602 Background: To date, there is no international consensus on how best to follow patients (pts) with GCT after their initial management. In the absence of a generally accepted follow-up schedule the possible benefits of regular CT scanning must be weighed against their cost, potential contrast media reactions and the long term risk of cumulative X-ray exposure. The present study focuses on the role of abdominal ultrasound in the follow-up of males with GCT and raises the question whether CT-scanning may be replaced by abdominal ultrasound. Methods: This retrospective single-center cohort study included 887 GCT pts followed between January 2001 and November 2011. The follow-up schedule was predominately based on abdominal ultrasound performed by the same physician (A.G.). Patterns of recurrence and the long-term outcome were analyzed. Results: 462 of 887 pts (52.1%) had stage I, 258 (29.1%) stage II and 130 (14.7%) stage III disease (not evaluable in 37 pts). The median time between baseline and the most recent follow-up examination was 5.0 years. A total of 14.604 abdominal ultrasound examinations (16.5/pt.), 1170 CT scans (1.32/pt.), and 956 chest X-rays (1.08/pt) were performed. A relapse occurred in 58 pts (6.5%) with 11 of 58 pts experiencing multiple relapses. 34 of 58 relapses (58.6%) were detected in pts with stage I GCT. The sites of relapse included the abdomen (n=42), other sites (n=10), and marker elevation only (n=10). 33 of 42 abdominal relapses (78.6%) were detected by abdominal ultrasound. The median size of abdominal lymph nodes was 25 mm (range, 6 - 67 mm). After a median follow-up of 5 years the GCT specific survival of the entire cohort was 98.4%. Regarding the subgroup of pts with relapse the GCT specific survival was 94.7%. Conclusions: Ultrasound appears to be an appropriate method to detect abdominal recurrences in pts with GCT. However, training and cumulative experience is necessary to detect retroperitoneal recurrences at an early stage. The number of expensive and potentially harmful CT scans may be markedly decreased by abdominal ultrasound.

Aortic tortuosity index as a predictor of type A aortic dissection

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
F Scalbert ◽  
O Milleron ◽  
M Para ◽  
R Raffoul ◽  
Q Pellenc ◽  
...  
Keyword(s):  
Aortic Dissection ◽  
Type A ◽  
Ct Scans ◽  
Control Group ◽  
Type A Aortic Dissection ◽  
Total Length ◽  
A Value ◽  
Straight Line ◽  
Patients At Risk ◽  
Geometric Length

Abstract Introduction The risk ok type A aortic dissection (AAD) depends on the degree of aortic wall's alteration, which can result in dilatation or tortuosity. The estimate of this risk relies solely on the evaluation of the diameter of the ascending aorta. Purpose The purpose of this study is to evaluate the presence and importance of aortic tortuosity in patients with type A aortic dissection. Method Postoperative CT scans of patients with type A aortic dissection were compared with CT scans from controls matched for gender and age. After 3D reconstruction, total length (actual distance along aortic center line = Ltot) and geometric length (length of a straight line between start and end of the aortic segment = Lgeo) were measured to calculate the tortuosity index (TI = Ltot / Lgeo). Results Ltot, Lgeo and TI from different aortic segments of the AAD group were higher than in the control group. Ltot and TI of the whole aorta (from aortic valve to bifurcation) were greater in patients with type A aortic dissection (527.7±46.1 mm vs. 475.8±39.7, p<0.0001; and 2.05±0.24 vs. 1.98±0.21, p=0.002 respectively). Total length and TI were greater after exclusion of the ascending part, and a value of this TI >1.3 identifies AAD patients with an accuracy of 74.8% (AUC = 0.792, p<0.0001). TI is altered by risk factors for aortic dissection: it increases with hypertension and age but not by tobacco use, and TI decreases in diabetes. Conclusions Type A aortic dissection is associated with longer aorta and increased aortic tortuosity. This index may help recognize patients at risk for type A aortic dissection. Calculation of tortuosity indexes Funding Acknowledgement Type of funding source: None

scholarly journals New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Young Jae Kim ◽  
Jang Pyo Bae ◽  
Jun-Won Chung ◽  
Dong Kyun Park ◽  
Kwang Gi Kim ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Transfer Learning ◽  
Test Data ◽  
State Of The Art ◽  
Early Stage ◽  
Statistical Significance ◽  
Recall Rate ◽  
Training Data ◽  
Fine Tuning ◽  
Accuracy Evaluation

AbstractWhile colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.

scholarly journals State-of-the-Art Management of Germ Cell Tumors

2018 ◽  
pp. 319-323 ◽  
Author(s):  
Darren R. Feldman
Keyword(s):  
Germ Cell ◽  
State Of The Art ◽  
Early Stage ◽  
Germ Cell Tumors ◽  
High Stakes ◽  
Inappropriate Use ◽  
Common Mistake ◽  
Relative Rarity ◽  
Cure Rates ◽  
Perfect Storm

The state of the art management of germ cell tumors (GCT) in 2018 does not include novel agents targeting genomic alterations or exciting immunologic-based approaches but rather the avoidance of pitfalls in everyday practice. The relative rarity of GCT and high curability with correct management create the "perfect storm" for high-stakes errors to occur. This review focuses on several common pitfalls that should be avoided in staging and management of early-stage and advanced GCT in order to maximize patient outcomes. A particularly frequent misstep is to base treatment decisions on pre- rather than postorchiectomy tumor markers that, depending on marker directionality, can lead to either undertreatment with potentially inferior outcomes or overtreatment with excess toxicity. Another common mistake is the failure to consider the unique ability of GCT to differentiate and the distinct biology of teratoma (chemoresistance and lack of increased glucose uptake compared with normal tissue), which exerts a pervasive influence on nonseminoma management. This may lead to inappropriate use of PET scan to evaluate the postchemotherapy residual mass and, if negative, the conclusion that surgery is not needed whereas (FDG-negative) teratoma should be removed. It could also result in administration of additional unnecessary chemotherapy to patients with marker normalization but without robust radiographic response after 3 to 4 cycles of BEP. Finally, oncologists should strive to maintain standard chemotherapy doses, not substitute carboplatin for cisplatin, and refer to expert centers when expertise (e.g., RPLND) is not available locally in order to achieve optimal cure rates in advanced disease.

scholarly journals Deep neural network to detect COVID-19: one architecture for both CT Scans and Chest X-rays

2020 ◽  
Author(s):  
Himadri Mukherjee ◽  
Subhankar Ghosh ◽  
Ankita Dhar ◽  
Sk Md Obaidullah ◽  
K. C. Santosh ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Ct Scans ◽  
X Rays

scholarly journals Is There a Place for Immune Checkpoint Inhibitors in Vulvar Neoplasms? A State of the Art Review

2020 ◽  
Vol 22 (1) ◽  
pp. 190
Author(s):  
Fulvio Borella ◽  
Mario Preti ◽  
Luca Bertero ◽  
Giammarco Collemi ◽  
Isabella Castellano ◽  
...  
Keyword(s):  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
State Of The Art ◽  
Checkpoint Inhibitors ◽  
Early Stage ◽  
Survival Rates ◽  
Younger Women ◽  
Multiple Tumor ◽  
Tumor Types

Vulvar cancer (VC) is a rare neoplasm, usually arising in postmenopausal women, although human papilloma virus (HPV)-associated VC usually develop in younger women. Incidences of VCs are rising in many countries. Surgery is the cornerstone of early-stage VC management, whereas therapies for advanced VC are multimodal and not standardized, combining chemotherapy and radiotherapy to avoid exenterative surgery. Randomized controlled trials (RCTs) are scarce due to the rarity of the disease and prognosis has not improved. Hence, new therapies are needed to improve the outcomes of these patients. In recent years, improved knowledge regarding the crosstalk between neoplastic and tumor cells has allowed researchers to develop a novel therapeutic approach exploiting these molecular interactions. Both the innate and adaptive immune systems play a key role in anti-tumor immunesurveillance. Immune checkpoint inhibitors (ICIs) have demonstrated efficacy in multiple tumor types, improving survival rates and disease outcomes. In some gynecologic cancers (e.g., cervical cancer), many studies are showing promising results and a growing interest is emerging about the potential use of ICIs in VC. The aim of this manuscript is to summarize the latest developments in the field of VC immunoncology, to present the role of state-of-the-art ICIs in VC management and to discuss new potential immunotherapeutic approaches.

Sign in / Sign up

Export Citation Format

Share Document