Evaluation of a chest radiograph reading and recording system for tuberculosis in a HIV-positive cohort

Kosack, Cara; Spijker, Saskia; Halton, Jarred; Bonnet, Maryline; Nicholas, Susanne B.; Chetcuti, Karen; Mesic, Anita; Brant, William E.; Joekes, Elizabeth; Andronikou, Savvas

doi:10.1016/j.crad.2017.01.008

Cited by 11 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high level of inter-reader variability of CXR images has been well documented in TB programs since the late 1960s 36 , particularly among less experienced readers 37 . A strength of this CAD software evaluation was the involvement of two TB clinicians with different levels of experience as benchmarks for the software solutions.…”

Section: Discussionmentioning

confidence: 99%

Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis

Codlin¹,

Dao²,

Vo³

et al. 2021

Sci Rep

View full text Add to dashboard Cite

There have been few independent evaluations of computer-aided detection (CAD) software for tuberculosis (TB) screening, despite the rapidly expanding array of available CAD solutions. We developed a test library of chest X-ray (CXR) images which was blindly re-read by two TB clinicians with different levels of experience and then processed by 12 CAD software solutions. Using Xpert MTB/RIF results as the reference standard, we compared the performance characteristics of each CAD software against both an Expert and Intermediate Reader, using cut-off thresholds which were selected to match the sensitivity of each human reader. Six CAD systems performed on par with the Expert Reader (Qure.ai, DeepTek, Delft Imaging, JF Healthcare, OXIPIT, and Lunit) and one additional software (Infervision) performed on par with the Intermediate Reader only. Qure.ai, Delft Imaging and Lunit were the only software to perform significantly better than the Intermediate Reader. The majority of these CAD software showed significantly lower performance among participants with a past history of TB. The radiography equipment used to capture the CXR image was also shown to affect performance for some CAD software. TB program implementers now have a wide selection of quality CAD software solutions to utilize in their CXR screening initiatives.

show abstract

Section: Discussionmentioning

confidence: 99%

Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis

Codlin¹,

Dao²,

Vo³

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In the pathology pleural effusion, we furthermore noted that radiologists tend to express suspicion more often than non-radiologists since BCR and RR groups chose option 0 less frequently than group NRR (Figure 2A,B). A more sensitive pleural effusion detection rate can be of clinical advantage as even a small pleural effusion might have to be controlled or even treateduncertainty in pleural effusion detection can also be easily and quickly validated by an additional ultrasound of the pleura [17]. Example case (B) in Figure 4 shows that a certain overlap might have occurred in the detection of consolidation suspicious of pneumonia and pleural effusion when pathologies were found in the basal lungs.…”

Section: Discussionmentioning

confidence: 99%

“…In addition, co-occurence of pathologies would be possible. Probability was determined on a Likert scale from 0 to 4 (0-no suspicion of pathology, 1-unlikely, 2-possible, 3-likely, 4-safe presence) [15] twice per case, one for each hemithorax (right and left). In the case of detected nodules, readers had to additionally note if they consider malignancy and would therefore recommend a follow-up computed tomography (CT) scan.…”

Section: Patient Identification and Readingmentioning

confidence: 99%

Interpretation of Thoracic Radiography Shows Large Discrepancies Depending on the Qualification of the Physician—Quantitative Evaluation of Interobserver Agreement in a Representative Emergency Department Scenario

et al. 2021

View full text Add to dashboard Cite

(1) Background: Chest radiography (CXR) is still a key diagnostic component in the emergency department (ED). Correct interpretation is essential since some pathologies require urgent treatment. This study quantifies potential discrepancies in CXR analysis between radiologists and non-radiology physicians in training with ED experience. (2) Methods: Nine differently qualified physicians (three board-certified radiologists [BCR], three radiology residents [RR], and three non-radiology residents involved in ED [NRR]) evaluated a series of 563 posterior-anterior CXR images by quantifying suspicion for four relevant pathologies: pleural effusion, pneumothorax, pneumonia, and pulmonary nodules. Reading results were noted separately for each hemithorax on a Likert scale (0–4; 0: no suspicion of pathology, 4: safe existence of pathology) adding up to a total of 40,536 reported pathology suspicions. Interrater reliability/correlation and Kruskal–Wallis tests were performed for statistical analysis. (3) Results: While interrater reliability was good among radiologists, major discrepancies between radiologists’ and non-radiologists’ reading results could be observed in all pathologies. Highest overall interrater agreement was found for pneumothorax detection and lowest agreement in raising suspicion for malignancy suspicious nodules. Pleural effusion and pneumonia were often suspected with indifferent choices (1–3). In terms of pneumothorax detection, all readers mainly decided for a clear option (0 or 4). Interrater reliability was usually higher when evaluating the right hemithorax (all pathologies except pneumothorax). (4) Conclusions: Quantified CXR interrater reliability analysis displays a general uncertainty and strongly depends on medical training. NRR can benefit from radiology reporting in terms of time efficiency and diagnostic accuracy. CXR evaluation of long-time trained ED specialists has not been tested.

show abstract

“…The value of point of care ultrasound (POCUS) in pediatric TB, especially in demonstrating mediastinal lymphadenopathy [20] and extrapulmonary involvement [21], has been established. Vast improvements in film quality and interpretation have also been demonstrated following global outreach efforts [22][23][24], which include the introduction of digital platforms and teleradiology consultations [22,25]. While the need for and benefits of teleradiology are well known [26], it is important to note that teleradiology efforts can be very difficult to sustain.…”

Section: Discussionmentioning

confidence: 99%

Pediatric radiology mission work: opportunities, challenges and outcomes

Shah

Binkovitz

et al. 2018

Pediatr Radiol

View full text Add to dashboard Cite

Evaluation of a chest radiograph reading and recording system for tuberculosis in a HIV-positive cohort

Abstract: This study demonstrated limited impact of the introduction of a CRRS on CXR accuracy and agreement amongst non-expert readers. The role in which CXRs are used for TB diagnosis in a HIV-positive cohort in similar clinical contexts should be reviewed.

Cited by 11 publications

References 13 publications

Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis

Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis

Interpretation of Thoracic Radiography Shows Large Discrepancies Depending on the Qualification of the Physician—Quantitative Evaluation of Interobserver Agreement in a Representative Emergency Department Scenario

Pediatric radiology mission work: opportunities, challenges and outcomes

Contact Info

Product

Resources

About