10
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: not found

      Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review

      research-article

      Read this article at

      ScienceOpenPublisherPMC
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          The challenge of learning a new concept, object, or a new medical disease recognition without receiving any examples beforehand is called Zero-Shot Learning (ZSL). One of the major issues in deep learning based methodologies such as in Medical Imaging and other real-world applications is the requirement of large annotated datasets prepared by clinicians or experts to train the model. ZSL is known for having minimal human intervention by relying only on previously known or trained concepts plus currently existing auxiliary information. This is ever-growing research for the cases where we have very limited or no annotated datasets available and the detection / recognition system has human-like characteristics in learning new concepts. This makes the ZSL applicable in many real-world scenarios, from unknown object detection in autonomous vehicles to medical imaging and unforeseen diseases such as COVID-19 Chest X-Ray (CXR) based diagnosis. In this review paper, we introduce a novel and broaden solution called Few / one-shot learning, and present the definition of the ZSL problem as an extreme case of the few-shot learning. We review over fundamentals and the challenging steps of Zero-Shot Learning, including state-of-the-art categories of solutions, as well as our recommended solution, motivations behind each approach, their advantages over each category to guide both clinicians and AI researchers to proceed with the best techniques and practices based on their applications. Inspired from different settings and extensions, we then review through different datasets inducing medical and non-medical images, the variety of splits, and the evaluation protocols proposed so far. Finally, we discuss the recent applications and future directions of ZSL. We aim to convey a useful intuition through this paper towards the goal of handling complex learning tasks more similar to the way humans learn. We mainly focus on two applications in the current modern yet challenging era: coping with an early and fast diagnosis of COVID-19 cases, and also encouraging the readers to develop other similar AI-based automated detection / recognition systems using ZSL.

          Related collections

          Most cited references30

          • Record: found
          • Abstract: found
          • Article: not found

          Sensitivity of Chest CT for COVID-19: Comparison to RT-PCR

          Summary In a series of 51 patients with chest CT and RT-PCR assay performed within 3 days, the sensitivity of CT for COVID-19 infection was 98% compared to RT-PCR sensitivity of 71% (p<.001). Introduction In December 2019, an outbreak of unexplained pneumonia in Wuhan [1] was caused by a new coronavirus infection named COVID-19 (Corona Virus Disease 2019). Noncontrast chest CT may be considered for early diagnosis of viral disease, although viral nucleic acid detection using real-time polymerase chain reaction (RT-PCR) remains the standard of reference. Chung et al. reported that chest CT may be negative for viral pneumonia of COVID-19 [2] at initial presentation (3/21 patients). Recently, Xie reported 5/167 (3%) patients who had negative RT-PCR for COVID-19 at initial presentation despite chest CT findings typical of viral pneumonia [3]. The purpose of this study was to compare the sensitivity of chest CT and viral nucleic acid assay at initial patient presentation. Materials and Methods The retrospective analysis was approved by institutional review board and patient consent was waived. Patients at Taizhou Enze Medical Center (Group) Enze Hospital were evaluated from January 19, 2020 to February 4, 2020. During this period, chest CT and RT-PCR (Shanghai ZJ Bio-Tech Co, Ltd, Shanghai, China) was performed for consecutive patients who presented with a history of 1) travel or residential history in Wuhan or local endemic areas or contact with individuals with individuals with fever or respiratory symptoms from these areas within 14 days and 2) had fever or acute respiratory symptoms of unknown cause. In the case of an initial negative RT-PCR test, repeat testing was performed at intervals of 1 day or more. Of these patients, we included all patients who had both noncontrast chest CT scan (slice thickness, 5mm) and RT-PCR testing within an interval of 3 days or less and who had an eventual confirmed diagnosis of COVID-19 infection by RT-PCR testing (Figure 1). Typical and atypical chest CT findings were recorded according to CT features previously described for COVD-19 (4,5). The detection rate of COVID-19 infection based on the initial chest CT and RT-PCR was compared. Statistical analysis was performed using McNemar Chi-squared test with significance at the p <.05 level. Figure 1: Flowchart for patient inclusion. Results 51 patients (29 men and 22 women) were included with median age of 45 (interquartile range, 39- 55) years. All patients had throat swab (45 patients) or sputum samples (6 patients) followed by one or more RT-PCR assays. The average time from initial disease onset to CT was 3 +/- 3 days; the average time from initial disease onset to RT-PCR testing was 3 +/- 3 days. 36/51 patients had initial positive RT-PCR for COVID-19. 12/51 patients had COVID-19 confirmed by two RT-PCR nucleic acid tests (1 to 2 days), 2 patients by three tests (2-5 days) and 1 patient by four tests (7 days) after initial onset. 50/51 (98%) patients had evidence of abnormal CT compatible with viral pneumonia at baseline while one patient had a normal CT. Of 50 patients with abnormal CT, 36 (72%) had typical CT manifestations (e.g. peripheral, subpleural ground glass opacities, often in the lower lobes (Figure 2) and 14 (28%) had atypical CT manifestations (Figure 3) [2]. In this patient sample, difference in detection rate for initial CT (50/51 [98%, 95% CI 90-100%]) patients was greater than first RT-PCR (36/51 [71%, 95%CI 56-83%]) patients (p<.001). Figure 2a: Examples of typical chest CT findings compatible with COVID-19 pneumonia in patients with epidemiological and clinical presentation suspicious for COVID-19 infection. A, male, 74 years old with fever and cough for 5 days. Axial chest CT shows bilateral subpleural ground glass opacities (GGO). B, female, 55 years old, with fever and cough for 7 days. Axial chest CT shows extensive bilateral ground glass opacities and consolidation; C, male, 43 years old, presenting with fever and cough for 1 week. Axial chest CT shows small bilateral areas of peripheral GGO with minimal consolidation; D, female, 43 years old presenting with fever with cough for 5 days. Axial chest CT shows a right lung region of peripheral consolidation. Figure 2b: Examples of typical chest CT findings compatible with COVID-19 pneumonia in patients with epidemiological and clinical presentation suspicious for COVID-19 infection. A, male, 74 years old with fever and cough for 5 days. Axial chest CT shows bilateral subpleural ground glass opacities (GGO). B, female, 55 years old, with fever and cough for 7 days. Axial chest CT shows extensive bilateral ground glass opacities and consolidation; C, male, 43 years old, presenting with fever and cough for 1 week. Axial chest CT shows small bilateral areas of peripheral GGO with minimal consolidation; D, female, 43 years old presenting with fever with cough for 5 days. Axial chest CT shows a right lung region of peripheral consolidation. Figure 2c: Examples of typical chest CT findings compatible with COVID-19 pneumonia in patients with epidemiological and clinical presentation suspicious for COVID-19 infection. A, male, 74 years old with fever and cough for 5 days. Axial chest CT shows bilateral subpleural ground glass opacities (GGO). B, female, 55 years old, with fever and cough for 7 days. Axial chest CT shows extensive bilateral ground glass opacities and consolidation; C, male, 43 years old, presenting with fever and cough for 1 week. Axial chest CT shows small bilateral areas of peripheral GGO with minimal consolidation; D, female, 43 years old presenting with fever with cough for 5 days. Axial chest CT shows a right lung region of peripheral consolidation. Figure 2d: Examples of typical chest CT findings compatible with COVID-19 pneumonia in patients with epidemiological and clinical presentation suspicious for COVID-19 infection. A, male, 74 years old with fever and cough for 5 days. Axial chest CT shows bilateral subpleural ground glass opacities (GGO). B, female, 55 years old, with fever and cough for 7 days. Axial chest CT shows extensive bilateral ground glass opacities and consolidation; C, male, 43 years old, presenting with fever and cough for 1 week. Axial chest CT shows small bilateral areas of peripheral GGO with minimal consolidation; D, female, 43 years old presenting with fever with cough for 5 days. Axial chest CT shows a right lung region of peripheral consolidation. Figure 3a: Examples of chest CT findings less commonly reported in COVID-19 infection (atypical) in patients with epidemiological and clinical presentation suspicious for COVID-19 infection. A, male, 36 years old with cough for 3 days. Axial chest CT shows a small focal and central ground glass opacity (GGO) in the right upper lobe; B, female, 40 years old. Axial chest CT shows small peripheral linear opacities bilaterally. C, male, 38 years old. Axial chest CT shows a GGO in the central left lower lobe; D, male, 31 years old with fever for 1 day. Axial chest CT shows a linear opacity in the left lower lateral mid lung. Figure 3b: Examples of chest CT findings less commonly reported in COVID-19 infection (atypical) in patients with epidemiological and clinical presentation suspicious for COVID-19 infection. A, male, 36 years old with cough for 3 days. Axial chest CT shows a small focal and central ground glass opacity (GGO) in the right upper lobe; B, female, 40 years old. Axial chest CT shows small peripheral linear opacities bilaterally. C, male, 38 years old. Axial chest CT shows a GGO in the central left lower lobe; D, male, 31 years old with fever for 1 day. Axial chest CT shows a linear opacity in the left lower lateral mid lung. Figure 3c: Examples of chest CT findings less commonly reported in COVID-19 infection (atypical) in patients with epidemiological and clinical presentation suspicious for COVID-19 infection. A, male, 36 years old with cough for 3 days. Axial chest CT shows a small focal and central ground glass opacity (GGO) in the right upper lobe; B, female, 40 years old. Axial chest CT shows small peripheral linear opacities bilaterally. C, male, 38 years old. Axial chest CT shows a GGO in the central left lower lobe; D, male, 31 years old with fever for 1 day. Axial chest CT shows a linear opacity in the left lower lateral mid lung. Figure 3d: Examples of chest CT findings less commonly reported in COVID-19 infection (atypical) in patients with epidemiological and clinical presentation suspicious for COVID-19 infection. A, male, 36 years old with cough for 3 days. Axial chest CT shows a small focal and central ground glass opacity (GGO) in the right upper lobe; B, female, 40 years old. Axial chest CT shows small peripheral linear opacities bilaterally. C, male, 38 years old. Axial chest CT shows a GGO in the central left lower lobe; D, male, 31 years old with fever for 1 day. Axial chest CT shows a linear opacity in the left lower lateral mid lung. Discussion In our series, the sensitivity of chest CT was greater than that of RT-PCR (98% vs 71%, respectively, p<.001). The reasons for the low efficiency of viral nucleic acid detection may include: 1) immature development of nucleic acid detection technology; 2) variation in detection rate from different manufacturers; 3) low patient viral load; or 4) improper clinical sampling. The reasons for the relatively lower RT-PCR detection rate in our sample compared to a prior report are unknown (3). Our results support the use of chest CT for screening for COVD-19 for patients with clinical and epidemiologic features compatible with COVID-19 infection particularly when RT-PCR testing is negative.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Time Course of Lung Changes On Chest CT During Recovery From 2019 Novel Coronavirus (COVID-19) Pneumonia

            Background Chest CT is used to assess the severity of lung involvement in COVID-19 pneumonia. Purpose To determine the change in chest CT findings associated with COVID-19 pneumonia from initial diagnosis until patient recovery. Materials and Methods This retrospective review included patients with RT-PCR confirmed COVID-19 infection presenting between 12 January 2020 to 6 February 2020. Patients with severe respiratory distress and/ or oxygen requirement at any time during the disease course were excluded. Repeat Chest CT was obtained at approximately 4 day intervals. The total CT score was the sum of lung involvement (5 lobes, score 1-5 for each lobe, range, 0 none, 25 maximum) was determined. Results Twenty one patients (6 males and 15 females, age 25-63 years) with confirmed COVID-19 pneumonia were evaluated. These patients under went a total of 82 pulmonary CT scans with a mean interval of 4±1 days (range: 1-8 days). All patients were discharged after a mean hospitalized period of 17±4 days (range: 11-26 days). Maximum lung involved peaked at approximately 10 days (with the calculated total CT score of 6) from the onset of initial symptoms (R2=0.25), p<0.001). Based on quartiles of patients from day 0 to day 26 involvement, 4 stages of lung CT were defined: Stage 1 (0-4 days): ground glass opacities (GGO) in 18/24 (75%) patients with the total CT score of 2±2; (2)Stage-2 (5-8d days): increased crazy-paving pattern 9/17 patients (53%) with a increase in total CT score (6±4, p=0.002); (3) Stage-3 (9-13days): consolidation 19/21 (91%) patients with the peak of total CT score (7±4); (4) Stage-4 (≥14 days): gradual resolution of consolidation 15/20 (75%) patients with a decreased total CT score (6±4) without crazy-paving pattern. Conclusion In patients recovering from COVID-19 pneumonia (without severe respiratory distress during the disease course), lung abnormalities on chest CT showed greatest severity approximately 10 days after initial onset of symptoms.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Chest CT for Typical 2019-nCoV Pneumonia: Relationship to Negative RT-PCR Testing

              Some patients with positive chest CT findings may present with negative results of real time reverse-transcription–polymerase chain- reaction (RT-PCR) for 2019 novel coronavirus (2019-nCoV). In this report, we present chest CT findings from five patients with 2019-nCoV infection who had initial negative RT-PCR results. All five patients had typical imaging findings, including ground-glass opacity (GGO) (5 patients) and/or mixed GGO and mixed consolidation (2 patients). After isolation for presumed 2019-nCoV pneumonia, all patients were eventually confirmed with 2019-nCoV infection by repeated swab tests. A combination of repeated swab tests and CT scanning may be helpful when for individuals with high clinical suspicion of nCoV infection but negative RT-PCR screening
                Bookmark

                Author and article information

                Journal
                Intell Based Med
                Intelligence-Based Medicine
                Elsevier B.V.
                2666-5212
                2 October 2020
                2 October 2020
                : 100005
                Affiliations
                [a ]Institute for Transport Studies, The University of Leeds, Leeds LS2 9JT, United Kingdom
                [b ]Faculty of Computer and IT Engineering, Qazvin Branch, Islamic Azad University, Qazvin, IR
                Author notes
                []Corresponding author. Institute for Transport Studies, The University of Leeds, 34-40 University Road, Woodhouse Lane, Leeds, LS2 9JT, UK
                [1]

                Assistant Professor in Computer Vision and Machine Learning and Academic Fellow at the University of Leeds, United Kingdom; Honorary Academic Staff at Auckland University of Technology; and Senior Member of CeRV Research Centre, Auckland, New Zealand

                [2]

                Researcher at SYNTECH Technology & Innovation Centre, Qazvin, IR

                Article
                S2666-5212(20)30005-3 100005
                10.1016/j.ibmed.2020.100005
                7531283
                33043311
                5ffe0708-15c8-4884-962e-5359b825e66a
                © 2020 Elsevier B.V.

                Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.

                History
                : 20 June 2020
                : 17 September 2020
                : 24 September 2020
                Categories
                Article

                covid-19 pandemic,sars-cov-2,chest x-ray (cxr),zero-shot learning,deep learning,semantic embedding,machine learning,autonomous vehicles,supervised annotation

                Comments

                Comment on this article