Manually Graded Research Articles

The Revival of Essay-Type Questions in Medical Education: Harnessing Artificial Intelligence and Machine Learning.

To analyse and compare the assessment and grading of human-written and machine-written formative essays. Quasi-experimental, qualitative cross-sectional study. Place and Duration of the Study: Department of Science of Dental Materials, Hamdard College of Medicine & Dentistry, Hamdard University, Karachi, from February to April 2023. Ten short formative essays of final-year dental students were manually assessed and graded. These essays were then graded using ChatGPT version 3.5. The chatbot responses and prompts were recorded and matched with manually graded essays. Qualitative analysis of the chatbot responses was then performed. Four different prompts were given to the artificial intelligence (AI) driven platform of ChatGPT to grade the summative essays. These were the chatbot's initial responses without grading, the chatbot's response to grading against criteria, the chatbot's response to criteria-wise grading, and the chatbot's response to questions for the difference in grading. Based on the results, four innovative ways of using AI and machine learning (ML) have been proposed for medical educators: Automated grading, content analysis, plagiarism detection, and formative assessment. ChatGPT provided a comprehensive report with feedback on writing skills, as opposed to manual grading of essays. The chatbot's responses were fascinating and thought-provoking. AI and ML technologies can potentially supplement human grading in the assessment of essays. Medical educators need to embrace AI and ML technology to enhance the standards and quality of medical education, particularly when assessing long and short essay-type questions. Further empirical research and evaluation are needed to confirm their effectiveness. Machine learning, Artificial intelligence, Essays, ChatGPT, Formative assessment.

Reducing Workload in Short Answer Grading Using Machine Learning

Machine learning methods can be used to reduce the manual workload in exam grading, making it possible for teachers to spend more time on other tasks. However, when it comes to grading exams, fully eliminating manual work is not yet possible even with very accurate automated grading, as any grading mistakes could have significant consequences for the students. Here, the evaluation of an automated grading approach is therefore extended from measuring workload in relation to the accuracy of automated grading, to also measuring the overall workload required to correctly grade a full exam, with and without the support of machine learning. The evaluation was performed during an introductory computer science course with over 400 students. The exam consisted of 64 questions with relatively short answers and a two-step approach for automated grading was applied. First, a subset of answers to the exam questions was manually graded and next used as training data for machine learning models classifying the remaining answers. A number of different strategies for how to select which answers to include in the training data were evaluated. The time spent on different grading actions was measured along with the reduction of effort using clustering of answers and automated scoring. Compared to fully manual grading, the overall reduction of workload was substantial—between 64% and 74%—even with a complete manual review of all classifier output to ensure a fair grading.

Diagnostic Accuracy of Automated Diabetic Retinopathy Image Assessment Softwares: IDx-DR and Medios Artificial Intelligence

Introduction: Numerous studies have demonstrated the use of artificial intelligence (AI) for early detection of referable diabetic retinopathy (RDR). A direct comparison of these multiple automated diabetic retinopathy (DR) image assessment softwares (ARIAs) is, however, challenging. We retrospectively compared the performance of two modern ARIAs, IDx-DR and Medios AI. Methods: In this retrospective-comparative study, retinal images with sufficient image quality were run on both ARIAs. They were captured in 811 consecutive patients with diabetes visiting diabetic clinics in Poland. For each patient, four non-mydriatic images, 45° field of view, i.e., two sets of one optic disc and one macula-centered image using Topcon NW400 were captured. Images were manually graded for severity of DR as no DR, any DR (mild non-proliferative diabetic retinopathy [NPDR] or more severe disease), RDR (moderate NPDR or more severe disease and/or clinically significant diabetic macular edema [CSDME]), or sight-threatening DR (severe NPDR or more severe disease and/or CSDME) by certified graders. The ARIA output was compared to manual consensus image grading (reference standard). Results: On 807 patients, based on consensus grading, there was no evidence of DR in 543 patients (67%). Any DR was seen in 264 (33%) patients, of which 174 (22%) were RDR and 41 (5%) were sight-threatening DR. The sensitivity of detecting RDR against reference standard grading was 95% (95% CI: 91, 98%) and the specificity was 80% (95% CI: 77, 83%) for Medios AI. They were 99% (95% CI: 96, 100%) and 68% (95% CI: 64, 72%) for IDx-DR, respectively. Conclusion: Both the ARIAs achieved satisfactory accuracy, with few false negatives. Although false-positive results generate additional costs and workload, missed cases raise the most concern whenever automated screening is debated.

Agreement of a Novel Artificial Intelligence Software With Optical Coherence Tomography and Manual Grading of the Optic Disc in Glaucoma.

The offline artificial intelligence (AI) on a smartphone-based fundus camera shows good agreement and correlation with the vertical cup-to-disc ratio (vCDR) from the spectral-domain optical coherence tomography (SD-OCT) and manual grading by experts. The purpose of this study is to assess the agreement of vCDR measured by a new AI software from optic disc images obtained using a validated smartphone-based imaging device, with SD-OCT vCDR measurements, and manual grading by experts on a stereoscopic fundus camera. In a prospective, cross-sectional study, participants above 18 years (Glaucoma and normal) underwent a dilated fundus evaluation, followed by optic disc imaging including a 42-degree monoscopic disc-centered image (Remidio NM-FOP-10), a 30-degree stereoscopic disc-centered image (Kowa nonmyd WX-3D desktop fundus camera), and disc analysis (Cirrus SD-OCT). Remidio FOP images were analyzed for vCDR using the new AI software, and Kowa stereoscopic images were manually graded by 3 fellowship-trained glaucoma specialists. We included 473 eyes of 244 participants. The vCDR values from the new AI software showed strong agreement with SD-OCT measurements [95% limits of agreement (LoA)=-0.13 to 0.16]. The agreement with SD-OCT was marginally better in eyes with higher vCDR (95% LoA=-0.15 to 0.12 for vCDR>0.8). Interclass correlation coefficient was 0.90 (95% CI, 0.88-0.91). The vCDR values from AI software showed a good correlation with the manual segmentation by experts (interclass correlation coefficient=0.89, 95% CI, 0.87-0.91) on stereoscopic images (95% LoA=-0.18 to 0.11) with agreement better for eyes with vCDR>0.8 (LoA=-0.12 to 0.08). The new AI software vCDR measurements had an excellent agreement and correlation with the SD-OCT and manual grading. The ability of the Medios AI to work offline, without requiring cloud-based inferencing, is an added advantage.

Predicting Progression of Age-Related Macular Degeneration Using OCT and Fundus Photography

To compare the performance of automatically quantified OCT imaging biomarkers and conventional risk factors manually graded on color fundus photographs for predicting progression to late age-related macular degeneration (AMD). Longitudinal observational study. Two hundred eighty eyes from 140 participants with bilateral large drusen. All participants underwent OCT and color fundus photography (CFP) at baseline and were then reviewed at 6-month intervals to determine progression to late AMD. Color fundus photographs were graded manually and OCT scans underwent automated image analyses to quantify risk factors and imaging biomarkers, respectively, based on drusen and AMD pigmentary abnormalities. Four predictive models for progression to late AMD or atrophic AMD were only developed (each including age) based on: (1) CFP only (2 parameters); (2) OCT biomarkers, minimal (3parameters); (3) OCT biomarkers, extended (7 parameters); and (4) CFP and OCT combined (8 parameters). Predictive performance for progression to late AMD, examined based on the area under the receiver operating characteristic curve (AUC) for correctly predicting progression. The AUC for predicting late AMD development was similar for the models based on CFP alone (model 1; 0.80), OCT alone (models 2 and 3; 0.82 for both), and when using both methods together (model 4; 0.85). In addition, these models also performed similarly for predicting the end point of atrophic AMD only (AUC, 0.83, 0.84, 0.85, and 0.88 for models 1, 2, 3, and 4, respectively). OCT imaging biomarkers could provide an automatic method of risk stratification for progression to vision-threatening late AMD as well as manual grading of CFP.

Quantitative Analysis of Ellipsoid Zone in Acute Posterior Multifocal Placoid Pigment Epitheliopathy.

Purpose:Quantitative end points for uveitis are needed. Here we quantify the rate of ellipsoid zone (EZ) recovery on optical coherence tomography (OCT) and correlate it with visual acuity (VA) improvement in patients with acute posterior multifocal placoid pigmented epitheliopathy (APMPPE). We use automated and manually graded EZ area analysis to assess EZ recovery in APMPPE.Methods:We performed a retrospective review of 9 APMPPE cases (18 eyes) that had characteristic clinical examination and fluorescein angiography findings, outer retinal disruption on spectral-domain OCT, and treatment with systemic steroids after an unambiguous laboratory workup. The EZ was delineated using custom software to perform automated analysis and manual grading by 2 independent physicians. Quantitation of EZ changes was performed in ImageJ (National Institutes of Health). EZ maps were compared with equivalent findings from EZ en face OCT segmentation.Results:The 9 cases in our study were followed for an average of 198 days. Symptomatic improvement occurred in all eyes. VA recovery occurred in 83% of eyes and depended on presenting foveal involvement. Positive slopes of EZ area over time demonstrated recovery. EZ recovery profiles determined by manual and automated software demonstrated high Pearson correlation coefficients (0.78-0.94). Slab en face EZ analysis demonstrated moderate agreement.Conclusions:EZ recovery correlates with symptomatic and VA recovery. Automated EZ analysis shows strong agreement with manually graded EZ analysis in APMPPE. EZ recovery in patients with APMPPE provides a biomarker for recovery and may be applied to other diseases affecting the outer retina.

Multivariate product adapted grading of Scots pine sawn timber for an industrial customer, part 1: Method development

ABSTRACTRule-based automatic grading (RBAG) of sawn timber is a common type of sorting system used in sawmills, which is intricate to customise for specific customers. This study further develops an automatic grading method to grade sawn timber according to a customer's resulting product quality. A sawmill's automatic sorting system used cameras to scan the 308 planks included in the study. Each plank was split at a planing mill into three boards, each planed, milled, and manually graded as desirable or not. The plank grade was correlated by multivariate partial least squares regression to aggregated variables, created from the sorting system's measurements at the sawmill. Grading models were trained and tested independently using 5-fold cross-validation to evaluate the grading accuracy of the holistic-subjective automatic grading (HSAG), and compared with a re-substitution test. Results showed that using the HSAG method at the sawmill graded on average 74% of planks correctly, while 83% of desirable planks were correctly identified. Results implied that a sawmill sorting station could grade planks according to a customer's product quality grade with similar accuracy to HSAG conforming with manual grading of standardised sorting classes, even when the customer is processing the planks further.

Automated Diabetic Retinopathy Image Assessment Software: Diagnostic Accuracy and Cost-Effectiveness Compared with Human Graders

With the increasing prevalence of diabetes, annual screening for diabetic retinopathy (DR) by expert human grading of retinal images is challenging. Automated DR image assessment systems (ARIAS) may provide clinically effective and cost-effective detection of retinopathy. We aimed to determine whether ARIAS can be safely introduced into DR screening pathways to replace human graders. Observational measurement comparison study of human graders following a national screening program for DR versus ARIAS. Retinal images from 20 258 consecutive patients attending routine annual diabetic eye screening between June 1, 2012, and November 4,2013. Retinal images were manually graded following a standard national protocol for DR screening and were processed by 3 ARIAS: iGradingM, Retmarker, and EyeArt. Discrepancies between manual grades and ARIAS results were sent to a reading center for arbitration. Screening performance (sensitivity, false-positive rate) and diagnostic accuracy (95% confidence intervals of screening-performance measures) were determined. Economic analysis estimated the cost per appropriate screening outcome. Sensitivity point estimates (95% confidence intervals) of the ARIAS were as follows: EyeArt 94.7% (94.2%-95.2%) for any retinopathy, 93.8% (92.9%-94.6%) for referable retinopathy (human graded as either ungradable, maculopathy, preproliferative, or proliferative), 99.6% (97.0%-99.9%) for proliferative retinopathy; Retmarker 73.0% (72.0 %-74.0%) for any retinopathy, 85.0% (83.6%-86.2%) for referable retinopathy, 97.9% (94.9%-99.1%) for proliferative retinopathy. iGradingM classified all images as either having disease or being ungradable. EyeArt and Retmarker saved costs compared with manual grading both as a replacement for initial human grading and as a filter prior to primary human grading, although the latter approach was less cost-effective. Retmarker and EyeArt systems achieved acceptable sensitivity for referable retinopathy when compared with that of human graders and had sufficient specificity to make them cost-effective alternatives to manual grading alone. ARIAS have the potential to reduce costs in developed-world health care economies and to aid delivery of DR screening in developing or remote health care settings.

An observational study to assess if automated diabetic retinopathy image assessment software can replace one or more steps of manual imaging grading and to determine their cost-effectiveness.

Diabetic retinopathy screening in England involves labour-intensive manual grading of retinal images. Automated retinal image analysis systems (ARIASs) may offer an alternative to manual grading. To determine the screening performance and cost-effectiveness of ARIASs to replace level 1 human graders or pre-screen with ARIASs in the NHS diabetic eye screening programme (DESP). To examine technical issues associated with implementation. Observational retrospective measurement comparison study with a real-time evaluation of technical issues and a decision-analytic model to evaluate cost-effectiveness. A NHS DESP. Consecutive diabetic patients who attended a routine annual NHS DESP visit. Retinal images were manually graded and processed by three ARIASs: iGradingM (version 1.1; originally Medalytix Group Ltd, Manchester, UK, but purchased by Digital Healthcare, Cambridge, UK, at the initiation of the study, purchased in turn by EMIS Health, Leeds, UK, after conclusion of the study), Retmarker (version 0.8.2, Retmarker Ltd, Coimbra, Portugal) and EyeArt (Eyenuk Inc., Woodland Hills, CA, USA). The final manual grade was used as the reference standard. Arbitration on a subset of discrepancies between manual grading and the use of an ARIAS by a reading centre masked to all grading was used to create a reference standard manual grade modified by arbitration. Screening performance (sensitivity, specificity, false-positive rate and likelihood ratios) and diagnostic accuracy [95% confidence intervals (CIs)] of ARIASs. A secondary analysis explored the influence of camera type and patients' ethnicity, age and sex on screening performance. Economic analysis estimated the cost per appropriate screening outcome identified. A total of 20,258 patients with 102,856 images were entered into the study. The sensitivity point estimates of the ARIASs were as follows: EyeArt 94.7% (95% CI 94.2% to 95.2%) for any retinopathy, 93.8% (95% CI 92.9% to 94.6%) for referable retinopathy and 99.6% (95% CI 97.0% to 99.9%) for proliferative retinopathy; and Retmarker 73.0% (95% CI 72.0% to 74.0%) for any retinopathy, 85.0% (95% CI 83.6% to 86.2%) for referable retinopathy and 97.9% (95% CI 94.9 to 99.1%) for proliferative retinopathy. iGradingM classified all images as either 'disease' or 'ungradable', limiting further iGradingM analysis. The sensitivity and false-positive rates for EyeArt were not affected by ethnicity, sex or camera type but sensitivity declined marginally with increasing patient age. The screening performance of Retmarker appeared to vary with patient's age, ethnicity and camera type. Both EyeArt and Retmarker were cost saving relative to manual grading either as a replacement for level 1 human grading or used prior to level 1 human grading, although the latter was less cost-effective. A threshold analysis testing the highest ARIAS cost per patient before which ARIASs became more expensive per appropriate outcome than human grading, when used to replace level 1 grader, was Retmarker £3.82 and EyeArt £2.71 per patient. The non-randomised study design limited the health economic analysis but the same retinal images were processed by all ARIASs in this measurement comparison study. Retmarker and EyeArt achieved acceptable sensitivity for referable retinopathy and false-positive rates (compared with human graders as reference standard) and appear to be cost-effective alternatives to a purely manual grading approach. Future work is required to develop technical specifications to optimise deployment and address potential governance issues. The National Institute for Health Research (NIHR) Health Technology Assessment programme, a Fight for Sight Grant (Hirsch grant award) and the Department of Health's NIHR Biomedical Research Centre for Ophthalmology at Moorfields Eye Hospital and the University College London Institute of Ophthalmology.

A study of whether automated Diabetic Retinopathy Image Assessment could replace manual grading steps in the English National Screening Programme.

Diabetic retinopathy screening in England involves labour intensive manual grading of digital retinal images. We present the plan for an observational retrospective study of whether automated systems could replace one or more steps of human grading. Patients aged 12 or older who attended the Diabetes Eye Screening programme, Homerton University Hospital (London) between 1 June 2012 and 4 November 2013 had macular and disc-centred retinal images taken. All screening episodes were manually graded and will additionally be graded by three automated systems. Each system will process all screening episodes, and screening performance (sensitivity, false positive rate, likelihood ratios) and diagnostic accuracy (95% confidence intervals of screening performance measures) will be quantified. A sub-set of gradings will be validated by an approved Reading Centre. Additional analyses will explore the effect of altering thresholds for disease detection within each automated system on screening performance. 2,782/20,258 diabetes patients were referred to ophthalmologists for further examination. Prevalence of maculopathy (M1), pre-proliferative retinopathy (R2), and proliferative retinopathy (R3) were 7.9%, 3.1% and 1.2%, respectively; 4749 (23%) patients were diagnosed with background retinopathy (R1); 1.5% were considered ungradable by human graders. Retinopathy prevalence was similar to other English diabetic screening programmes, so findings should be generalizable. The study population size will allow the detection of differences in screening performance between the human and automated grading systems as small as 2%. The project will compare performance and economic costs of manual versus automated systems.

Customer adapted grading of Scots pine sawn timber using a multivariate method

To define new grading rules, or to customize the ones in use in a rule-based automatic grading (RBAG) system of boards, is a time-consuming job for a sawmill engineer. This has the effect that changes are rarely made. The objective of this study was to continue the development of a method that replaces the calibration of grading rule settings by a holistic-subjective automatic grading, using multivariate models. The objective was also to investigate if this approach can improve sawmill profitability and at the same time have a satisfied customer. For the study, 323 Scots pine (Pinus sylvestris L.) boards were manually graded according to the preferences of an important customer. That is, a customer that regularly purchases significant volumes of sawn timber. This manual grading was seen as reference grading in this work. The same boards were also scanned and graded by a RBAG system, calibrated for the same customer. Multivariate models for prediction of board grade based on aggregated knot variables, obtained from the scanning, were calibrated using partial least squares regression. The results show that prediction of board grades by the multivariate models were more correct, with respect to the manual grading, than the grading by the RBAG system. The prediction of board grades based on multivariate models resulted in 76–87% of the boards graded correctly, according to the manual grading, while the corresponding number was 63% for the RBAG system.

Sensitivity and specificity of automated detection of early repolarization in standard 12-lead electrocardiography.

Early repolarization (ER) is defined as an elevation of the QRS-ST junction in at least two inferior or lateral leads of the standard 12-lead electrocardiogram (ECG). Our purpose was to create an algorithm for the automated detection and classification of ER. A total of 6,047 electrocardiograms were manually graded for ER by two experienced readers. The automated detection of ER was based on quantification of the characteristic slurring or notching in ER-positive leads. The ER detection algorithm was tested and its results were compared with manual grading, which served as the reference. Readers graded 183 ECGs (3.0%) as ER positive, of which the algorithm detected 176 recordings, resulting in sensitivity of 96.2%. Of the 5,864 ER-negative recordings, the algorithm classified 5,281 as negative, resulting in 90.1% specificity. Positive and negative predictive values for the algorithm were 23.2% and 99.9%, respectively, and its accuracy was 90.2%. Inferior ER was correctly detected in 84.6% and lateral ER in 98.6% of the cases. As the automatic algorithm has high sensitivity, it could be used as a prescreening tool for ER; only the electrocardiograms graded positive by the algorithm would be reviewed manually. This would reduce the need for manual labor by 90%.

Detection and Analysis of Hard Exudates by Polarization-Sensitive Optical Coherence Tomography in Patients With Diabetic Maculopathy

To image and analyze hard exudates (HEs) and their precursors in patients with diabetic macular edema (DME) by using polarization-sensitive optical coherence tomography (PS-OCT). Twenty-two eyes of 16 patients with DME were imaged by using color fundus photography (CF) and PS-OCT. In PS-OCT, HEs were automatically detected by their distinct polarization-scrambling qualities. Color fundus images were manually graded for the presence of HEs by two masked graders and correlated with the corresponding PS-OCT HE maps: corresponding images were overlaid and an identical grid of 128 × 128 fields was used for correlation of detected HEs. In all eyes, HEs were present owing to DME. Agreement of a pixel-to-pixel analysis of HEs in CF images was 0.72 (Cohen's κ) between graders and 0.44 between graders and automated detection by PS-OCT. Mean ± SD detection of HEs was significantly higher in PS-OCT than in manual grading (1180.5 ± 1009.8 fields versus 828.8 ± 695.0 fields; P = 0.02). The higher detection rate of PS-OCT was confirmed by a linear regression analysis with a slope of β = 1.18 (r = 0.81). PS-OCT enables not only two-dimensional imaging of the extent of HEs, as in CF, but also allows tissue-specific, three-dimensional imaging of HEs throughout retinal layers, based on their distinct polarization-scrambling characteristics. The higher detection rate in PS-OCT images indicates an increased sensitivity of PS-OCT imaging over conventional CF.

Retinal artery–vein caliber grading using color fundus imaging

Recent research suggests that retinal vessel caliber (or cross-sectional width) measured from retinal photographs is an important feature for predicting cardiovascular diseases (CVDs). One of the most utilized measures is to quantify retinal arteriolar and venular caliber as the Central Retinal Artery Equivalent (CRAE) and Central Retinal Vein Equivalent (CRVE). However, current computer tools utilize manual or semi-automatic grading methods to estimate CRAE and CRVE. These methods involve a significant amount of grader's time and can add a significant level of inaccuracy due to repetitive nature of grading and intragrader distances. An automatic and time efficient grading of the vessel caliber with highly repeatable measurement is essential, but is technically challenging due to a substantial variation of the retinal blood vessels’ properties. In this paper, we propose a new technique to measure the retinal vessel caliber, which is an “edge-based” vessel tracking method. We measured CRAE and CRVE from each of the vessel types. We achieve very high accuracy (average 96.23%) for each of the cross-sectional width measurement compared to manually graded width. For overall vessel caliber measurement accuracy of CRAE and CRVE, we compared the results with an existing semi-automatic method which showed high correlation of 0.85 and 0.92, respectively. The intra-grader reproducibility of our method was high, with the correlation coefficient of 0.881 for CRAE and 0.875 for CRVE.

Image analysis in the assessment of HER-2 immunohistochemical grading: comparison with manual grading and chromogenic/silver in situ hybridisation

Aims Manual grading is currently employed for HER-2 immuno-histochemistry (IHC). However, recent guidelines incorporated the use image analysisto reduce scoring variability.1 We utiliseda freely available image analysis programme to develop a semi-quantitative grading system for HER-2 IHC, validated it and compared it with manual grading and HER-2 gene amplification by CISH/SISH. Methods Initial testing was performed on 50 separate HER-2 immunohistochemically stained slides using ImageJ image analysis software v1.43 (NIH, Bethesda, MD, USA; http://rsb.in-fo.nih.gov/ij/). An image analysis grading system for HER-2 IHC (negative, equivocal and positive) was developed from the initial data. Another 60 cases were used for validation and comparison with manual grading and CISH/SISH (Pathology Department, Peter MacCallum Cancer Centre, Victoria). Results The concordance between the image analysis and the manual grading systems was 86.7% (k 0.79). Negative cases and positive cases on HER-2 IHC reached 98% and 100% concordance, respectively, with CISH/SISH for both the image analysis and the manual grading systems. However, the number of equivocal cases was reduced by 86% by image analysis when compared to manual grading. Discussion While both the image analysis and the manual grading have high sensitivity and specificity in predicting HER-2 gene amplification by CISH/SISH, image analysis can be utilised to reduce significantly the number of equivocal manually graded cases. Manual grading is currently employed for HER-2 immuno-histochemistry (IHC). However, recent guidelines incorporated the use image analysisto reduce scoring variability.1 We utiliseda freely available image analysis programme to develop a semi-quantitative grading system for HER-2 IHC, validated it and compared it with manual grading and HER-2 gene amplification by CISH/SISH. Initial testing was performed on 50 separate HER-2 immunohistochemically stained slides using ImageJ image analysis software v1.43 (NIH, Bethesda, MD, USA; http://rsb.in-fo.nih.gov/ij/). An image analysis grading system for HER-2 IHC (negative, equivocal and positive) was developed from the initial data. Another 60 cases were used for validation and comparison with manual grading and CISH/SISH (Pathology Department, Peter MacCallum Cancer Centre, Victoria). The concordance between the image analysis and the manual grading systems was 86.7% (k 0.79). Negative cases and positive cases on HER-2 IHC reached 98% and 100% concordance, respectively, with CISH/SISH for both the image analysis and the manual grading systems. However, the number of equivocal cases was reduced by 86% by image analysis when compared to manual grading. While both the image analysis and the manual grading have high sensitivity and specificity in predicting HER-2 gene amplification by CISH/SISH, image analysis can be utilised to reduce significantly the number of equivocal manually graded cases.

Automated grading for diabetic retinopathy: a large-scale audit using arbitration by clinical experts

Background/aimsAutomated grading software has the potential to reduce the manual grading workload within diabetic retinopathy screening programmes. This audit was undertaken at the request of Scotland's National Diabetic Retinopathy Screening...

A multivariate approach to automatic grading of Pinus sylvestris sawn timber

The objective of this study was to create an easier way to handle the often complicated and intricate situations with which the operator of an automatic grading system is faced each time a change to the grading rules is proposed. The scope of the study was the possibility of a holistic method of automatic appearance grading of sawn wood similar to manual grading and based on multivariate statistics. The study was based on 90 Scots pine (Pinus sylvestris L.) sawlogs. The logs were sawn and the boards were scanned and manually graded. The result of the manual grading was defined as the true grade. Models for prediction of board grade based on aggregated defect variables were calibrated using partial least squares regression. The classification based on the multivariate models resulted in 80–85% of the boards being correctly graded according to the manual grading. In conclusion, this paper shows that a multivariate statistical approach for grading timber is a possible way to simplify the process of grading and to customize the grading rules when using an automatic grading system.