Artificial intelligence (AI) to enhance breast cancer screening: protocol for population-based cohort study of cancer detection

IntroductionArtificial intelligence (AI) algorithms for interpreting mammograms have the potential to improve the effectiveness of population breast cancer screening programmes if they can detect cancers, including interval cancers, without contributing substantially to overdiagnosis. Studies suggesting that AI has comparable or greater accuracy than radiologists commonly employ ‘enriched’ datasets in which cancer prevalence is higher than in population screening. Routine screening outcome metrics (cancer detection and recall rates) cannot be estimated from these datasets, and accuracy estimates may be subject to spectrum bias which limits generalisabilty to real-world screening. We aim to address these limitations by comparing the accuracy of AI and radiologists in a cohort of consecutive of women attending a real-world population breast cancer screening programme.Methods and analysisA retrospective, consecutive cohort of digital mammography screens from 109 000 distinct women was assembled from BreastScreen WA (BSWA), Western Australia’s biennial population screening programme, from November 2016 to December 2017. The cohort includes 761 screen-detected and 235 interval cancers. Descriptive characteristics and results of radiologist double-reading will be extracted from BSWA outcomes data collection. Mammograms will be reinterpreted by a commercial AI algorithm (DeepHealth). AI accuracy will be compared with that of radiologist single-reading based on the difference in the area under the receiver operating characteristic curve. Cancer detection and recall rates for combined AI–radiologist reading will be estimated by pairing the first radiologist read per screen with the AI algorithm, and compared with estimates for radiologist double-reading.Ethics and disseminationThis study has ethical approval from the Women and Newborn Health Service Ethics Committee (EC00350) and the Curtin University Human Research Ethics Committee (HRE2020-0316). Findings will be published in peer-reviewed journals and presented at national and international conferences. Results will also be disseminated to stakeholders in Australian breast cancer screening programmes and policy makers in population screening.

Fact and Fiction in Autoconfession: A Theoretical Confrontation

The formulation of the topic fact and fiction in auto-confession is a result of earlier research in which the greatest theoretical confrontation takes place in the area of autobiographical prose. This paper investigates and explores issues with which contemporary poetics is faced regarding the concepts in question, especially when they coexist within a work concerned either with genre codification or with undefined status (i.e. hybrid genre). Such discussions are often accompanied by great dilemmas on whether auto-confessional texts such as autobiography or autobiographical prose should be considered fact or fiction. Being a fierce confrontation, especially for a genre that is considered a compromising genre in which the facts are weaved according to the fictional practice, this paper proposes that a double reading (fact-fiction) will highlight issues that are essential to interpret and decode a text of autoconfessional premises and, beyond that, a codification of the genre when dilemmas grow and become even larger: in fiction, nonfiction, novel, autobiographical novel, autobiography, etc. Received: 27 January 2021 / Accepted: 2 September 2021 / Published: 5 November 2021

Коды «мужского» и «не-мужского» в художественном мире Morpho Eugenia А.С. Байетт

Morpho Eugenia is the first part of the postmodernist novel Angels and Insects by A.S. Byatt. The male world is represented here in abundance by numerous names of famous naturalists, philosophers and poets of the XVII-XVIII centuries and of Victorian England, as well as by the male characters of the novel. It is pointed out that the concepts of “masculine” and “non-masculine” in the novel presuppose double reading, namely, the traditional (Victorian) and posttraditional one (neo-Victorian). In the neo-Victorian interpretation, most of the male characters in the novel are devoid of traditional masculine qualities (honor and dignity, commitment to the cause, inner strength), they bear a stigma of vice (incest), while the “male organization” features of the central female character, non-typical for a Victorian woman (talent, efficiency, perseverance, energy, self-reliance), contribute to the formation of an integral harmonious world of men and women as friends, lovers, like-minded people.

Dr Vladimir Kalaydzhiev or the Embodiment of Modernity

The text attempts an experimental “double reading” of a significant figure in the history of Bulgarian health care – Dr. Vladimir Kalaydzhiev, initiator and organiser of a large-scale public health care reform in Bulgaria in the 1960s. The authors' different approaches make it possible, on the one hand, to interpret the specifics of the health reform and the reasons for its (partial) repeal in the context of synchronous developments in Europe and controversial, on the other hand, to contraversially offer a diachronic analysis with basic characteristics of the "Catholic West" and the "Orthodox socialist East".

Thermography as an Economical Alternative Modality to Mammography for Early Detection of Breast Cancer

Breast cancer has become a menacing form of cancer among women accounting for 11.6% of total deaths of 9.6 million due to all types of cancer every year all over the world. Early detection increases chances of survival and reduces the cost of treatment as well. Screening modalities such as mammography or thermography are used to detect cancer early; thus, several lives can be saved with timely treatment. But, there are interpretational failures on the part of the radiologists to read the mammograms or thermograms and also there are interobservational and intraobservational differences between them. So, the degree of variations among the different radiologists in the interpretation of results is very high resulting in false positives and false negatives. The double reading can reduce the human errors involved in the interpretation of mammograms. But, the limited number of medical professionals in developing or underdeveloped countries puts a limitation on this remedial way. So, a computer-aided system (CAD) is proposed to detect the benign cases from the abnormal cases that can result in automatic detection of breast cancer or can provide a double reading in the case of nonavailability of the trained medical professionals in developing economies. The generally accepted screening modality is mammography for the early detection of cancer. But thermography has been tried for early detection of breast cancer in recent times. The high metabolic activity of the cancer cells results in an early change in the temperature profile of the region. This shows asymmetry between normal and cancerous breast which can be detected using different techniques. Thus, this work is focussed on the use of thermography in the early detection of breast cancer. An experimental study is conducted to find the results of classification accuracy to compare the efficacy of thermography and mammography in classifying the normal from abnormal ones and further abnormal ones into benign and malignant cases. Thermography is found to have classification accuracy almost at par with mammography for classifying the cancerous breasts from healthy ones with classification accuracies of thermography and mammography being 96.57% and 98.11%, respectively. Thermography is found to have much better accuracy in identifying benign cases from the malignant ones with the classification accuracy of 92.70% as compared to 82.05% with mammography. This will result in the early detection of cancer. The advantage of being portable and inexpensive makes thermography an attractive modality to be used in economically backward rural areas where mammography is not practically possible.

Large-scale evaluation of an AI system as an independent reader for double reading in breast cancer screening

Screening mammography with two human readers increases cancer detection and lowers recall rates, but high resource requirements and a shortage of qualified readers make double reading unsustainable in many countries. The use of AI as an independent reader may yield more objective, accurate and outcome-based screening. Clinical validation of AI requires large-scale, multi-site, multi-vendor studies on unenriched cohorts. This retrospective study evaluated the performance of the MiaTM version 2.0.1 AI system from Kheiron Medical Technologies on an unenriched sample (275,900 cases from 177,882 participants) collected across seven screening sites in two countries and four hardware vendors, and is representative of a real-world screening population over 10 years. Performance was determined for standalone AI and simulated double reading to assess non-inferiority and superiority on relevant screening metrics. Standalone AI showed superiority on sensitivity and non-inferiority on specificity while detecting 29.7% of cancers found within three years after screening, and 29.8% of missed interval cancers. Double reading with AI was at least non-inferior compared to human double reading at every metric, with superiority for recall rate, specificity and positive predictive value (PPV). AI as an independent reader reduced the workload, but increased arbitration rate from 3.3% to 12.3%. Applying the AI system under investigation would have reduced the overall number of human reads required by 44.8%. The recall rate was reduced by a relative 4.1%, suggesting there could be fewer follow-up procedures, reduced stress for patients, and less administrative and clinical work. Using the AI system as an independent reader maintains the standard of care of double reading, detects cancers missed by human readers, while automating a substantial part of the workflow, and could therefore bring significant clinical and operational benefits.

Studying human-AI collaboration protocols: the case of the Kasparov’s law in radiological double reading

Purpose The integration of Artificial Intelligence into medical practices has recently been advocated for the promise to bring increased efficiency and effectiveness to these practices. Nonetheless, little research has so far been aimed at understanding the best human-AI interaction protocols in collaborative tasks, even in currently more viable settings, like independent double-reading screening tasks. Methods To this aim, we report about a retrospective case–control study, involving 12 board-certified radiologists, in the detection of knee lesions by means of Magnetic Resonance Imaging, in which we simulated the serial combination of two Deep Learning models with humans in eight double-reading protocols. Inspired by the so-called Kasparov’s Laws, we investigate whether the combination of humans and AI models could achieve better performance than AI models alone, and whether weak reader, when supported by fit-for-use interaction protocols, could out-perform stronger readers. Results We discuss two main findings: groups of humans who perform significantly worse than a state-of-the-art AI can significantly outperform it if their judgements are aggregated by majority voting (in concordance with the first part of the Kasparov’s law); small ensembles of significantly weaker readers can significantly outperform teams of stronger readers, supported by the same computational tool, when the judgments of the former ones are combined within “fit-for-use” protocols (in concordance with the second part of the Kasparov’s law). Conclusion Our study shows that good interaction protocols can guarantee improved decision performance that easily surpasses the performance of individual agents, even of realistic super-human AI systems. This finding highlights the importance of focusing on how to guarantee better co-operation within human-AI teams, so to enable safer and more human sustainable care practices.

Coronavirus Disease 2019 (COVID-19) in Italy: Double Reading of Chest CT Examination

To assess the performance of the second reading of chest compute tomography (CT) examinations by expert radiologists in patients with discordance between the reverse transcription real-time fluorescence polymerase chain reaction (RT-PCR) test for COVID-19 viral pneumonia and the CT report. Three hundred and seventy-eight patients were included in this retrospective study (121 women and 257 men; 71 years median age, with a range of 29–93 years) and subjected to RT-PCR tests for suspicious COVID-19 infection. All patients were subjected to CT examination in order to evaluate the pulmonary disease involvement by COVID-19. CT images were reviewed first by two radiologists who identified COVID-19 typical CT patterns and then reanalyzed by another two radiologists using a CT structured report for COVID-19 diagnosis. Weighted k values were used to evaluate the inter-reader agreement. The median temporal window between RT-PCRs execution and CT scan was zero days with a range of (−9, 11) days. The RT-PCR test was positive in 328/378 (86.8%). Discordance between RT-PCR and CT findings for viral pneumonia was revealed in 60 cases. The second reading changed the CT diagnosis in 16/60 (26.7%) cases contributing to an increase the concordance with the RT-PCR. Among these 60 cases, eight were false negative with positive RT-PCR, and 36 were false positive with negative RT-PCR. Sensitivity, specificity, positive predictive value and negative predictive value of CT were respectively of 97.3%, 53.8%, 89.0%, and 88.4%. Double reading of CT scans and expert second readers could increase the diagnostic confidence of radiological interpretation in COVID-19 patients.

Retrospective comparison between single reading plus an artificial intelligence algorithm and two-view digital tomosynthesis with double reading in breast screening

Objective To examine the breast cancer detection rate by single reading of an experienced radiologist supported by an artificial intelligence (AI) system, and compare with two-dimensional full-field digital mammography (2D-FFDM) double reading. Materials and methods Images (3D-tomosynthesis) of 161 biopsy-proven cancers were re-read by the AI algorithm and compared to the results of first human reader, second human reader and consensus following double reading in screening. Detection was assessed in subgroups by tumour type, breast density and grade, and at two operating points, referred to as a lower and a higher sensitivity threshold. Results The AI algorithm method gave similar results to double-reading 2D-FFDM, and the detection rate was significantly higher compared to single-reading 2D-FFDM. At the lower sensitivity threshold, the algorithm was significantly more sensitive than reader A (97.5% vs. 89.4%, p = 0.02), non-significantly more sensitive than reader B (97.5% vs. 94.4%, p = 0.2) and non-significantly less sensitive than the consensus from double reading (97.5% vs. 99.4%, p = 0.2). At the higher sensitivity threshold, the algorithm was significantly more sensitive than reader A (99.4% vs. 89.4%, p < 0.001) and reader B (99.4% vs. 94.4%, p = 0.02) and identical to the consensus sensitivity (99.7% in both cases, p = 1.0). There were no significant differences in the detection capability of the AI system by tumour type, grading and density. Conclusion In this proof of principle study, we show that sensitivity using single reading with a suitable AI algorithm is non-inferior to that of standard of care using 2D mammography with double reading, when tomosynthesis is the primary screening examination.