COVID19 Diagnosis using AutoML from 3D CT scans

Coronavirus is a pandemic that affects the respiratory system causing cough, shortness of breath, and death in severe cases. Polymerase chain reaction (PCR) tests are used to diagnose coronavirus. The false-negative rate of these tests is high, so there needs a supporting method for an accurate diagnosis. CT scan provides a detailed examination of the chest to diagnose COVID but a single CT scan comprises hundreds of slices. Expert and experienced radiologists and pulmonologists can diagnose COVID from these hundreds of slices, but this is very time-consuming. So an automatic artificial intelligence (AI) based method is required to diagnose coronavirus with high accuracy. Developing this AI-based technique requires a lot of resources and time, but once it is developed, it can significantly help the clinicians. This paper used an Automated machine learning (AutoML) technique that requires fewer resources (optimal architecture trials) and time to develop, resulting in the best diagnosis. The AutoML models are trained on 2D slices instead of 3D CT scans, and the predictions on unknown data (slices of CT scan) are aggregated to form a prediction of 3D CT scan. The aggregation process picked the most occurred case, whether COVID or non-COVID from all CT scan slices and labeled the 3D CT scan accordingly. Different thresholds are also used to label COVID or non-COVID 3D CT scans from 2D slices. The approach resulted in accuracy and F1-score of 89% and 88%, respectively. Implementation is available at github.com/talhaanwarch/mia-covid19

COVID19 Diagnosis using AutoML from 3D CT scans

10.36227/techrxiv.14914851 ◽

2021 ◽

Author(s):

Talha Anwar

Keyword(s):

Ct Scan ◽

False Negative ◽

False Negative Rate ◽

Detailed Examination ◽

Ct Scans ◽

3D Ct ◽

Chain Reaction ◽

3D Ct Scan ◽

Automated Machine Learning ◽

Diagnostic Accuracy of Magnetic Resonance Imaging and Computed Tomography Scan in Young Athletes With Spondylolysis

Clinical Pediatrics ◽

10.1177/0009922819832643 ◽

2019 ◽

Vol 58 (6) ◽

pp. 671-676

Author(s):

Amy M. West ◽

Pierre A. d’Hemecourt ◽

Olivia J. Bono ◽

Lyle J. Micheli ◽

Dai Sugimoto

Keyword(s):

Magnetic Resonance Imaging ◽

Computed Tomography ◽

Magnetic Resonance ◽

Ct Scan ◽

False Negative ◽

False Negative Rate ◽

Ct Scans ◽

Resonance Imaging ◽

Young Athletes ◽

Negative Rate

The objective of this study was to determine diagnostic accuracy of magnetic resonance imaging (MRI) and computed tomography (CT) scans in young athletes diagnosed with spondylolysis. A cross-sectional study was used. Twenty-two young athletes (14.7 ± 1.5 years) were diagnosed as spondylolysis based on a single-photon emission CT. Following the diagnosis, participants underwent MRI and CT scan imaging tests on the same day. The sensitivity and false-negative rate of the MRI and CT scans were analyzed. MRI test confirmed 13 (+) and 9 (−) results while CT test showed 17 (+) and 5 (−) results. The sensitivity and false-negative rate of MRI were, respectively, 59.1% (95% confidence interval [CI] = 36.7% to 78.5%) and 40.9% (95% CI = 21.5% to 63.3%). Furthermore, the sensitivity and false-negative rate of CT scan were 77.3% (95% CI = 54.2% to 91.3%) and 22.7% (95% CI = 0.09% to 45.8%). Our results indicated that CT scan is a more accurate imaging modality to diagnose spondylolysis compared with MRI in young athletes.

COVID-19 automatic diagnosis with CT images using the novel Transformer architecture

10.5753/sbcas.2021.16073 ◽

2021 ◽

Author(s):

Gabriel Sousa Silva Costa ◽

Anselmo C. Paiva ◽

Geraldo Braz Júnior ◽

Marco Melo Ferreira

Keyword(s):

Intelligent System ◽

State Of The Art ◽

False Negative ◽

False Negative Rate ◽

Ct Images ◽

The Novel ◽

Chain Reaction ◽

High False Negative Rate ◽

Polymerase Chain ◽

Low Sensitivity

Even though vaccines are already in use worldwide, the COVID-19 pandemic is far from over, with some countries re-establishing the lockdown state, the virus has taken over 2 million lives until today, being a serious health issue. Although real-time reverse transcription-polymerase chain reaction (RTPCR) is the ﬁrst tool for COVID-19 diagnosis, its high false-negative rate and low sensitivity might delay accurate diagnosis. Therefore, fast COVID-19 diagnosis and quarantine, combined with effective vaccination plans, is crucial for the pandemic to be over as soon as possible. To that end, we propose an intelligent system to classify computed tomography (CT) of lung images between a normal, pneumonia caused by something other than the coronavirus or pneumonia caused by the coronavirus. This paper aims to evaluate a complete selfattention mechanism with a Transformer network to capture COVID-19 pattern over CT images. This approach has reached the state-of-the-art in multiple NLP problems and just recently is being applied for computer vision tasks. We combine vision transformer and performer (linear attention transformers), and also a modiﬁed vision transformer, reaching 96.00% accuracy.

Diagnostic accuracy of chest computed tomography in improving the false negative rate as compared to reverse transcriptase polymerase chain reaction in coronavirus disease 2019 pneumonia: A cross sectional analysis of 348 cases from India

Lung India ◽

10.4103/lungindia.lungindia_410_20 ◽

2021 ◽

Vol 38 (7) ◽

pp. 11

Author(s):

Reddy Ravikanth

Keyword(s):

Computed Tomography ◽

Diagnostic Accuracy ◽

False Negative ◽

False Negative Rate ◽

Chain Reaction ◽

Cross Sectional ◽

Chest Computed Tomography ◽

Polymerase Chain ◽

Sectional Analysis

High False-Negative Rate of HER2 Quantitative Reverse Transcription Polymerase Chain Reaction of the Oncotype DX Test: An Independent Quality Assurance Study

Journal of Clinical Oncology ◽

10.1200/jco.2011.34.7963 ◽

2011 ◽

Vol 29 (32) ◽

pp. 4279-4285 ◽

Cited By ~ 120

Author(s):

David J. Dabbs ◽

Molly E. Klein ◽

Syed K. Mohsin ◽

Raymond R. Tubbs ◽

Yongli Shuai ◽

...

Keyword(s):

Quality Assurance ◽

Reverse Transcription ◽

False Negative ◽

False Negative Rate ◽

Oncotype Dx ◽

Rt Pcr ◽

Chain Reaction ◽

Negative Rate ◽

Purpose HER2 (ERBB2) status is an important prognostic and predictive marker in breast carcinoma. In recent years, Genomic Health (GHI), purveyors of the Oncotype DX test, has been separately reporting HER2 by reverse transcription polymerase chain reaction (RT-PCR) to oncologists. Because of the lack of independent evaluation, this quality assurance study was undertaken to define the concordance rate between immunohistochemistry (IHC)/fluorescent in situ hybridization (FISH) and GHI RT-PCR HER2 assay. Methods All patients at three participating laboratories (Magee-Womens Hospital [Pittsburgh, PA], Cleveland Clinic [Cleveland, OH], and Riverside Methodist Hospital [Columbus, OH]) with available HER2 RT-PCR results from GHI were included in this study. All IHC-positive and equivocal patient cases were further evaluated and classified by FISH at respective laboratories. Results Of the total 843 patient cases, 784 (93%) were classified as negative, 36 (4%) as positive, and 23 (3%) as equivocal at the three institutions using IHC/FISH. Of the 784 negative patient cases, 779 (99%) were also classified as negative by GHI RT-PCR assay. However, all 23 equivocal patient cases were reported as negative by GHI. Of the 36 positive cases, only 10 (28%; 95% CI, 14% to 45%) were reported as positive, 12 (33%) as equivocal, and 14 (39%) as negative. Conclusion There was an unacceptable false-negative rate for HER2 status with GHI HER2 assay in this independent study. This could create confusion in the decision-making process for targeted treatment and potentially lead to mismanagement of patients with breast cancer if only GHI HER2 information is used.

Variation in False-Negative Rate of Reverse Transcriptase Polymerase Chain Reaction–Based SARS-CoV-2 Tests by Time Since Exposure

Annals of Internal Medicine ◽

10.7326/m20-1495 ◽

2020 ◽

Vol 173 (4) ◽

pp. 262-267 ◽

Cited By ~ 267

Author(s):

Lauren M. Kucirka ◽

Stephen A. Lauer ◽

Oliver Laeyendecker ◽

Denali Boon ◽

Justin Lessler

Keyword(s):

Reverse Transcriptase ◽

False Negative ◽

False Negative Rate ◽

Chain Reaction ◽

Negative Rate ◽

Urgent care study of the LumiraDx SARS-CoV-2 Ag Test for rapid diagnosis of COVID-19

Diagnostic and Prognostic Research ◽

10.1186/s41512-021-00113-7 ◽

2021 ◽

Vol 5 (1) ◽

Author(s):

Jared Gresh ◽

Harold Kisner ◽

Brian DuChateau

Keyword(s):

False Negative ◽

False Negative Rate ◽

Urgent Care ◽

Reference Laboratory ◽

Chain Reaction ◽

Community Based ◽

Negative Results ◽

Polymerase Chain ◽

Care Study ◽

Regional Reference

Abstract Background Testing individuals suspected of severe acute respiratory syndrome–like coronavirus 2 (SARS-CoV-2) infection is essential to reduce the spread of disease. The purpose of this retrospective study was to determine the false negativity rate of the LumiraDx SARS-CoV-2 Ag Test when utilized for testing individuals suspected of SARS-CoV-2 infection. Methods Concurrent swab samples were collected from patients suspected of SARS-CoV-2 infection by their healthcare provider within two different urgent care centers located in Easton, MA, USA and East Bridgewater, MA, USA. One swab was tested using the LumiraDx SARS-CoV-2 Ag Test. Negative results in patients considered at moderate to high risk of SARS-CoV-2 infection were confirmed at a regional reference laboratory by polymerase chain reaction (PCR) using the additional swab sample. The data included in this study was collected retrospectively as an analysis of routine clinical practice. Results From October 19, 2020 to January 3, 2021, a total of 2241 tests were performed using the LumiraDx SARS-CoV-2 Ag Test, with 549 (24.5%) testing positive and 1692 (75.5%) testing negative. A subset (800) of the samples rendering a negative LumiraDx SARS-CoV-2 Ag Test was also tested using a PCR-based test for SARS-CoV-2. Of this subset, 770 (96.3%) tested negative, and 30 (3.8%) tested positive. Negative results obtained with the LumiraDx SARS-CoV-2 Ag test demonstrated 96.3% agreement with PCR-based tests (CI 95%, 94.7–97.4%). A cycle threshold (CT) was available for 17 of the 30 specimens that yielded discordant results, with an average CT value of 31.2, an SD of 3.0, and a range of 25.2–36.3. CT was > 30.0 in 11/17 specimens (64.7%). Conclusions This study demonstrates that the LumiraDx SARS-CoV-2 Ag Test had a low false-negative rate of 3.8% when used in a community-based setting.

Peran pemeriksaan radiologis pada diagnosis Coronavirus disease 2019

Jurnal Kedokteran Syiah Kuala ◽

10.24815/jks.v20i1.18300 ◽

2020 ◽

Vol 20 (1) ◽

Author(s):

Budi Yanti ◽

Ulfa Hayatun

Keyword(s):

Ct Scan ◽

Real Time ◽

False Negative ◽

Ground Glass Opacity ◽

Rt Pcr ◽

Chain Reaction ◽

Lung Abnormalities ◽

Polymerase Chain ◽

Radiological Examinations

Abstrak. Coronavirus Disease 19 (COVID-19) telah menjadi pandemi di seluruh dunia dengan angka kejadian yang terus meningkat di beberapa negara. Kecepatan dan ketepatan diagnosis diperlukan untuk mencegah perburukan kondisi pasien. Real-Time Transcription Polymerase Chain Reaction (RT-PCR) sampai saat ini masih menjadi baku emas untuk menegakkan diagnosis COVID-19, namun uji diagnostik ini dilaporkan banyak menunjukkan hasil negatif palsu. Pemeriksaan radiologi berupa foto toraks dan CT-Scan dada banyak dilakukan untuk menunjang diagnosis COVID-19. Gambaran foto toraks yang paling sering ditemukan adalah konsolidasi, ground-glass opacity (GGO), distribusi bilateral, perifer dan di lobus bawah paru-paru, namun pemeriksaan ini dianggap tidak sensitif untuk menemukan kelainan paru pada tahap awal penyakit. Meskipun demikian, foto toraks dapat digunakan untuk memantau perkembangan kelainan paru akibat COVID-19, salah satunya dengan metode Brixia Score. Pada sisi lain,CT-scan dada dinilai lebih sensitif daripada foto toraks serta mampu menunjukkan kelainan paru tahap awal pada pasien dengan hasil RT-PCR yang negatif. Gambaran pada CT-scan dada umumnya menunjukkan GGO, konsolidasi, crazy-paving stone, dan air bronchogram. CT-scan dapat mengurangi angka negatif palsu pada RT-PCR dan sebagai alat skrining pada pasien yang dicurigai COVID-19 di lokasi epidemis saat hasil RT-PCR tidak tersedia. Penggunaan pemeriksaan radiologi dan RT-PCR dapat menghemat waktu serta membantu diagnosis dan manajemen COVID-19. Kata Kunci: Pencitraan COVID-19, Radiologi SARS-CoV-2Abstract. Coronavirus Disease 19 (COVID-19) has become a worldwide pandemic with an increasing incidence in several countries. Speed and accuracy of diagnosis are needed to prevent worsening of patient's condition. Real-Time Transcription Polymerase Chain Reaction (RT-PCR) is still a gold standard of COVID-19 diagnosis, however, this test shown false negative results in several case. Radiological examinations, chest X-Ray (CXR) and CT scan, are used to support the diagnosis. The most commonly found in CXR are consolidation, ground-glass opacity (GGO), bilateral distribution, peripheral and in the lower lobe, but this examination is insensitive to find lung abnormalities in early stages of disease. However, CXR can be used to monitor the development of lung abnormalities due to COVID-19, such as the Brixia Score method. On the other hand, CT-Scan is more sensitive than CXR and able to show early lung abnormalities in negative RT-PCR results. CT scan show the presence of GGO, consolidation, crazy-paving stone, and air bronchogram. CT-scanning can reduce the false-negative rate on RT-PCR and become a screening tool in suspected COVID-19 patients at epidemic area where RT-PCR is not available. The use of radiological examinations and RT-PCR can save the time and help in the diagnosis and management of COVID-19.Keywords: COVID-19’s Radiology, Imaging of SARS-CoV-2

Digital Droplet PCR for SARS-CoV-2 Resolves Borderline Cases

American Journal of Clinical Pathology ◽

10.1093/ajcp/aqab041 ◽

2021 ◽

Author(s):

Jing Xu ◽

Timothy Kirtek ◽

Yan Xu ◽

Hui Zheng ◽

Huiyu Yao ◽

...

Keyword(s):

Limit Of Detection ◽

False Negative ◽

Accurate Method ◽

Viral Envelope ◽

Chain Reaction ◽

Borderline Cases ◽

Droplet Pcr ◽

Polymerase Chain ◽

Digital Polymerase Chain Reaction

Abstract Objectives The Bio-Rad SARS-CoV-2 ddPCR Kit (Bio-Rad Laboratories) was the first droplet digital polymerase chain reaction (ddPCR) assay to receive Food and Drug Administration (FDA) Emergency Use Authorization approval, but it has not been evaluated clinically. We describe the performance of ddPCR—in particular, its ability to confirm weak-positive severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) results. Methods We clinically validated the Bio-Rad Triplex Probe ddPCR Assay. The limit of detection was determined by using serial dilutions of SARS-CoV-2 RNA in an artificial viral envelope. The ddPCR assay was performed according to the manufacturer’s specifications on specimens confirmed to be positive (n = 48) or negative (n = 30) by an FDA-validated reverse transcription–polymerase chain reaction assay on the m2000 RealTime system (Abbott). Ten borderline positive cases were also evaluated. Results The limit of detection was 50 copies/mL (19 of 20 positive). Forty-seven specimens spanning a range of quantification cycles (2.9-25.9 cycle numbers) were positive by this assay (47 of 48; 97.9% positive precent agreement), and 30 negative samples were confirmed as negative (30 of 30; 100% negative percent agreement). Nine of 10 borderline cases were positive when tested in triplicate. Conclusions The ddPCR of SARS-CoV-2 is an accurate method, with superior sensitivity for viral RNA detection. It could provide definitive evaluation of borderline positive cases or suspected false-negative cases.

A meta-analysis of accuracy and sensitivity of chest CT and RT-PCR in COVID-19 diagnosis

Scientific Reports ◽

10.1038/s41598-020-80061-2 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Fatemeh Khatami ◽

Mohammad Saatchi ◽

Seyed Saeed Tamehri Zadeh ◽

Zahra Sadat Aghamir ◽

Alireza Namazi Shabestari ◽

...

Keyword(s):

Reverse Transcriptase ◽

Ct Scan ◽

Predictive Value ◽

Meta Analysis ◽

Chest Ct ◽

Rt Pcr ◽

Chain Reaction ◽

Polymerase Chain ◽

Chest Ct Scan

AbstractNowadays there is an ongoing acute respiratory outbreak caused by the novel highly contagious coronavirus (COVID-19). The diagnostic protocol is based on quantitative reverse-transcription polymerase chain reaction (RT-PCR) and chests CT scan, with uncertain accuracy. This meta-analysis study determines the diagnostic value of an initial chest CT scan in patients with COVID-19 infection in comparison with RT-PCR. Three main databases; PubMed (MEDLINE), Scopus, and EMBASE were systematically searched for all published literature from January 1st, 2019, to the 21st May 2020 with the keywords "COVID19 virus", "2019 novel coronavirus", "Wuhan coronavirus", "2019-nCoV", "X-Ray Computed Tomography", "Polymerase Chain Reaction", "Reverse Transcriptase PCR", and "PCR Reverse Transcriptase". All relevant case-series, cross-sectional, and cohort studies were selected. Data extraction and analysis were performed using STATA v.14.0SE (College Station, TX, USA) and RevMan 5. Among 1022 articles, 60 studies were eligible for totalizing 5744 patients. The overall sensitivity, specificity, positive predictive value, and negative predictive value of chest CT scan compared to RT-PCR were 87% (95% CI 85–90%), 46% (95% CI 29–63%), 69% (95% CI 56–72%), and 89% (95% CI 82–96%), respectively. It is important to rely on the repeated RT-PCR three times to give 99% accuracy, especially in negative samples. Regarding the overall diagnostic sensitivity of 87% for chest CT, the RT-PCR testing is essential and should be repeated to escape misdiagnosis.