Artificiell intelligence (AI) har blivit vanligare att använda för att stödja människor i deras beslutsfattande. Maskininlärning (ML) är ett delområde inom AI som har börjat användas mer inom hälso-och sjukvården. Patientdata ökar inom vården och ett AI-system kan behandla denna ökade datamängd, vilket vidare kan utveckla ett beslutsstöd som hjälper läkarna. AI-tekniken blir vanligare att använda inom radiologin och specifikt inom mammografin som ett beslutsstöd. Användning av AI-teknik inom mammografin medför fördelar men det finns även utmaningar som inte har något med tekniken att göra.Icke-tekniska utmaningar är viktiga att se över för att generera en lyckad praxis. Studiens syfte var därför att undersöka icke-tekniska utmaningar vid användning av AI som ett beslutsstöd inom mammografi ur ett radiologiskt perspektiv. Radiologer med erfarenhet av mammografi intervjuades i syfte att öka kunskapen kring deras syn på användningen.Resultatet från studien identifierade och utvecklade de icke-tekniska utmaningarna utifrån temana: ansvar, mänskliga förmågor, acceptans, utbildning/kunskap och samarbete. Resultatet indikerade även på att inom dessa teman finns icke-tekniska utmaningar med tillhörande aspekter som är mer framträdande än andra. Studien ökar kunskaperna kring radiologers syn på användningen och bidrar till framtida forskning för samtliga berörda aktörer. Forskning kan ta hänsyn till dessa icke-tekniska utmaningar redan innan tekniken är implementerad i syfte att minska risken för komplikationer. / Artificial intelligence (AI) has become more commonly used to support people when making decisions. Machine learning (ML) is a sub-area of AI that has become more frequently used in health care. Patient data is increasing in healthcare and an AI system can help to process this increased amount of data, which further can develop a decision support that can help doctors. AI technology is becoming more common to use in radiology and specifically in mammography, as a decision support. The usage of AI technology in mammography has many benefits, but there are also challenges that are not connected to technology.Non-technical challenges are important to consider and review in order to generate a successful practice. The purpose of this thesis is therefore to review non-technical challenges when using AI as a decision support in mammography from a radiological perspective. Radiologists with experience in mammography were interviewed in order to increase knowledge about their views on the usage.The results identified and developed the non-technical challenges based on themes: responsibility, human abilities, acceptance, education/knowledge and collaboration. The study also found indications within these themes that there are non-technical challenges with associated aspects that are more prominent than others. This study emphasizes and increases the knowledge of radiologists views on the usage of AI and contributes to future research for all the actors involved. Future research can address these non-technical challenges even before the technology is implemented to reduce the risk of complications.

No description available.

<p>Karcinom dojke predstavlja najče&scaron;ću malignu neoplazmu među ženskom populacijom, a po&scaron;tedna terapija dojke, preferirani je model lečenja bolesnica u ranom stadijumu bolesti. Smatra se da je optimalna hirur&scaron;ka resekciona margina 2 mm. Opisano je mnogo metoda koje služe za intraoperativnu proveru suficijentnosti resekcione hirur&scaron;ke margine i sve one imaju svoje prednosti i mane. Ciljevi ove studije bili su da se utvrdi, da li postoji statistički značajna razlika u određivanju &scaron;irine negativne resekcione hirur&scaron;ke margine izražene u milimetrima pri operacijama karcinoma dojke upotrebom palpatorne metode i intraoperativne mobilne radiografije, poređenjem nalaza merenja hiruga sa većim i manjim iskustvom u hirurgiji karcinoma dojke kao i nalaza radiologa u odnosu na patohistolo&scaron;ku ex tempore analizu. Istraživanje je sprovedeno kao retrospektivno&ndash;prospektivna studija na Klinici za operativnu onkologiju, Instituta za onkologiju Vojvodine i obuhvatilo je 150 bolesnica kod kojih je preoperativno dijagnostikovan karcinom dojke. Kriterijum za uključenje u studiju bilo je izvođenje po&scaron;tedne operacije dojke sa ili bez disekcije ipsilaterale aksile, dok su iz studije isključene bolesnice kod kojih nije bilo moguće izvesti po&scaron;tednu operaciju dojke, one sa radiolo&scaron;ki potvrđenom diseminovanom bole&scaron;ću, kao i bolesnice koje su ranije operisane zbog karcinoma iste dojke. Kod svih 150 ekstirpiranih karcinoma dojke urađena je procena &scaron;irine resekcione hirur&scaron;ke margine intraoperativno palpatornom metodom, zatim na aparatu za mobilnu digitalnu radiografiju, te radiogram analiziran od strane iskusnog i manje iskusnog hiruga u hirurgiji karcinoma dojke, kao i radiologa te upoređen sa nalazom ex tempore patohistolo&scaron;ke analize. Definitivna &scaron;irina resekcione hirur&scaron;ke margine potvrđena je na parafinskim patohistolo&scaron;kim preparatima. Srednja vrednost praćenja bolesnica, postoperativno, iznosila je 100,97 nedelja. Najveći broj bolesnica pripadao je starijoj životnoj dobi (56,67%). Preoperativna lokalizacija klinički nepalpabilnih tumora u dojci urađena je kod 52 (34,67%) bolesnice. Najče&scaron;će se tumor prezentovao kao solitarni fokus sa okolnim ognji&scaron;tima in situ karcinoma (72, 48%), dok je najče&scaron;ći histolo&scaron;ki subtip bio duktalni invazivni karcinom dojke (112 (74,67%)). Najveći broj operacija dojke okarakterisan je kao kvadrantektomija (85 (56,67)), dok je najučestalija operacija aksile bilo određivanje limfnog čvora stražara (119 (79,33%). Analizom rada aparata za mobilnu digitalnu radiografiju do&scaron;li smo do saznanja da nema statistički značajne razlike u oceni kvaliteta radiograma i &scaron;irine resekcione hirur&scaron;ke margine merene na aparatu za mobilnu digitalnu radiografiju između iskusnog hirurga i radiologa. Statistički značajna razlika nije uočena ni pri merenju &scaron;irine resekcione hirur&scaron;ke margine izražene u milimetrima na aparatu za mobilnu digitalnu radiografiju od strane iskusnog hirurga i radiologa u odnosu na ex tempore patohistolo&scaron;ku analizu, dok je ista uočena nakon definitivne patohistolo&scaron;ke analize. &Scaron;ansa doresekcije tkiva dojke nakon merenja na aparatu za mobilnu digitalnu radiografiju je 1,4 puta veća nego nakon patohistolo&scaron;ke ex tempore analize. Lokalni recidiv javio se kod jedne pacijentkinje tokom perioda praćenja. Ne postoji statistički značajna razlika u određivanju &scaron;irine resekcione hirur&scaron;ke margine izražene u milimetrima upotrebom aparata za mobilnu digitalnu radiografiju od strane iskusnog hirurga i radiologa u odnosu na patohistolo&scaron;ku ex tempore analizu, dok ista postoji nakon analize radiograma od strane manje iskusnog hirurga. Palpatorna metoda se ne može smatrati sigurnom metodom u određivanju &scaron;irine hirur&scaron;ke resekcione margine. Ne postoji statistički značajna razlika u broju doresekcije tkiva dojke između hirurga sa različitim hirur&scaron;kim iskustvom.</p> / <p>Breast cancer is the most common malignant neoplasm in the female population, and conservative breast therapy is the preferred treatment model for patients in early stages of the disease. The optimal surgical resection margin, from healthy breast tissue around the primary tumor is 2 mm. Many methods have been described that serve to check the resection margin during breast conservative surgery and all of them have their advantages and disadvantages. The aim of this study was to determine whether there was a statistically significant difference in the determination of the width of the negative resection margin expressed in millimeters in breast cancer surgery using palpatory method and intraoperative mobile specimen radiography, comparing the findings of measuring of surgeons with greater and lesser experience in breast cancer surgery as well as the findings of the radiologist in relation to histopathological ex tempore and definitive histopathological analysis. The study was conducted as a retrospective - prospective study at the Clinic for Operative Oncology, Oncology Institute of Vojvodina and included 150 patients who were preoperatively diagnosed with breast cancer. The criterion for inclusion in the study was the opportunity to perform breast conservative surgery with or without complete axillary lymph node dissection. Patients that were treated with breast amputation, those with radiological confirmed disseminated disease, as well as patients previously operated from cancer were excluded from the study. For all 150 extirpated breast cancers, an estimate of the width of the resection surgical margin was performed intraoperatively with a palpatory method, followed by measuring on device for mobile specimen digital radiography, and a radiogram was analyzed by an experienced and less experienced surgeon in breast cancer surgery, as well as by a radiologist and compared with an ex tempore histopathological analysis. The definitive width of the resection surgical margin was confirmed on histopathological preparations. The mean follow-up, postoperatively, was 100.97 weeks. The majority of patients belonged to the elderly age (56.67%). Preoperative localization of clinically impalpable breast tumors was performed in 52 (34.67%) patients. Most often the tumor was presented as a solitary focus with surrounding foci of in situ cancer (72, 48%), while the most common histological subtype was invasive ductal breast cancer (112 (74.67%)). The majority of breast operations were characterized like quadrantectomy (85 (56.67)), while the most frequent axillary surgery was the determination of the sentinel lymph node (119 (79.33%). No significant difference was observed in the evaluation of radiography quality and the width of the resection surgical margin measured on the mobile digital radiography device between the experienced surgeon and the radiologist. No statistically significant difference was observed in the measurement of the width of the resection surgical margin expressed in millimeters on the mobile digital radiography device by the experienced surgeon and radiologist versus ex tempore histopathological analysis, while the statistical difference was observed after definite histopathological analysis. The chance of breast tissue reexcision after measurement on a mobile digital radiography device is 1.4 times higher than after histopathological ex tempore analysis. Local relapse occurred in one patient during the follow-up period. There is no statistically significant difference in the determination of the width of the resection surgical margin expressed in millimeters using a mobile digital radiography device by an experienced surgeon in breast cancer surgery and radiologist with respect to histopathological ex tempore analysis. However, the statistical difference exists after radiogram analysis by a less experienced surgeon. The palpatory method cannot be considered as a safe method in determining the width of a surgical resection margin. There is no statistically significant difference in the number of breast tissue additional resections between surgeons with different surgical experience.</p>

Cette thèse avait deux buts principaux : a) l'implémentation et l'amélioration d'une méthode de calcul de densité volumique du sein (VBD), et b) la proposition d'une mesure d'irradiation utilisable pour l'évaluation du risque individuel en mammographie avec une méthode pour l'estimer. La densité du sein est connue comme indicateur de risque du cancer. Une méthode de quantification objective de la VBD a été développée, à partir d'approches existantes, et améliorée. La méthode a été implémentée pour deux systèmes de mammographie. Elle repose sur l'étalonnage du système de mammographie et la chaîne d'acquisition avec des fantômes équivalents aux tissus mammaires. Une carte de densité est calculée.La contribution majeure de la thèse consiste en une nouvelle méthode de validation, applicable à tout calcul de VBD d'image de mammographie. Elle consiste à comparer les résultats aux valeurs de densité obtenues par des scanners thoraciques pour la même patiente. Cette validation a été appliquée à notre méthode de calcul et nous avons trouvé 10% d'écart moyen entre les deux méthodes, ce qui est comparable aux résultats de l'état de l'art. Pour le risque d'irradiation individuel, nous proposons de remplacer la dose glandulaire moyenne par l'énergie déposée, qui dépend de la quantité et de la distribution du tissu glandulaire, qui est le tissu à risque. L'énergie volumique déposée est calculée par simulation de Monte Carlo. Le VBD, calculé pour l'image de projection à 0° en tomosynthèse, aide à localiser le tissu glandulaire et à attribuer l'énergie déposée dans les tissus différents. Une proposition a été faite pour des fantômes géométriques, un fantôme texturé et un cas de patiente / In this research project the main goals were a) to implement a method for the computation of the volumetric breast density (VBD), and b) to propose an improved quantity for the assessment of individual radiation-induced risk, in particular during mammography, together with a method to quantify it. The breast density is known as a breast cancer risk factor. The objective quantification of the volumetric breast density was developed, based on already published methods, and improved. The method was implemented for two mammography systems. It is based on the calibration of the mammography system acquisition chain with breast equivalent phantoms and computes a breast density map. Our most important contribution resides in a new validation method applicable to any VBD computation, consisting in comparing its results with the VBD obtained from a thorax CT examination for the same patient. This validation method was applied to our VBD computation. We found an average deviation between mammography and CT of less than 10%. Our results are comparable to the state-of-the-art results for other validation methods. For the individual radiation risk, we proposed to replace the average glandular dose by the imparted energy, which depends on the quantity and distribution of the glandular tissue, which is the tissue at risk. The volumetric imparted energy is computed from Monte Carlo simulations. The VBD, computed for the 0° projection of tomosynthesis exams, helps us to localize the glandular tissue and to attribute the imparted energy to the different tissues. A proposition was implemented for geometric phantoms, a textured phantom and a patient case.

AI in medical imaging is promising. Breast cancer screening has particularly seen advancements as researchers have demonstrated how commercially available AI algorithms could detect breast cancer at the same level as the best radiologists. The clinical uptake of AI implementations has however been slow and research studies on the real-life effects AI would have when it is implemented in healthcare settings, are lacking. As AI is integrated into the workflows of hospitals, new risks, are likely to be introduced. The breast radiology department at the hospital of Capio S:t Göran is among the first in the world to clinically let AI act as an independent reader, replacing one of the two radiologists reading the mammograms. This study thus aimed to investigate how a hospital like Capio S:t Göran may prepare for the clinical uptake of AI by exploring risks from an enterprise risk management perspective, i.e., looking beyond risks associated with patient safety, and proposing risk mitigation strategies. Data was qualitatively collected through different means. Brainstorming sessions were conducted with personnel at the hospital, either directly or indirectly involved with AI, with the purpose of identifying risks. Two external experts with competencies in cybersecurity, machine learning, and the ethical aspects of AI, were interviewed as a complement. Insights were also gained via observations at the hospital and internal documents/information. The risks identified were analyzed according to an enterprise risk management framework adopted for healthcare, that assumes risks to be emerging from eight different domains. Additionally, appropriate risk mitigation strategies were identified and discussed. The findings from the study demonstrates 23 risks associated with the clinical AI implementation in medical imaging and proposes risk mitigation strategies to each identifiedrisk. Not only does the study indicate the emergence of clinical/patient safety risks, but it also shows that there are operational, strategic, financial, human capital, legal, and technological risks. In addition, the study emphasizes the existence of possible synergies between the risks. The study concludes on the significance for hospitals to view risks holistically and to manage them proactively. / Användandet av AI inom bild- och funktionsmedicin är lovande. Det har framför allt skett framsteg inom bröstcancerscreening i takt med att forskare lyckats demonstrera hur kommersiellt tillgängliga AI algoritmer kan detektera bröstcancer på samma nivå som de bästa bröstradiologerna. AI införandet inom klinisk praxis har däremot varit långsam och det finns en avsaknad på forskningsstudier som studerat effekterna av ett AI-införande när det implementeras i den verkliga sjukvårdsmiljön. När ett AI system ska integreras i ett sjukhusarbetsflöde är det sannolikt att nya risker introduceras. Mammografiavdelningen på Capio S:t Görans sjukhus är det första sjukhuset i världen som ska börja använda AI kliniskt i syfte att ersätta en av två radiologer. Planen är att låta ett AI-system agera som en oberoende granskare och därmed ersätta en av de två radiologer som normalt sett granskar mammografibilderna. Syftet med denna studie har därav varit att undersöka hur sjukhus, såsom Capio S:t Göran bör förbereda sig för ett kliniskt införande av AI. Detta har gjorts genom att både identifiera risker från ett Enterprise Risk Managementperspektiv, vilket ur en sjukvårdskontext bland annat innebär att titta bortom patientsäkerhetsrisker, samt identifiera och föreslå riskhanteringsstrategier. För att identifiera risker hölls brainstorming sessioner med personal på Capio S:t Görans sjukhus med antingen direkta eller indirekta kopplingar till AI implementeringen. Detta kompletterades med två expertintervjuer där den ena hade kompetens inom cybersäkerhet och maskininlärning och den andra inom de etiska aspekterna av AI. Dessutom erhölls insikter via observationer gjorda på sjukhuset samt genom tillgång till intern information. Riskerna som identifierades analyserades därefter enligt ett Enterprise Risk Management ramverk som anpassats till sjukvården och som utgår från åtta olika risk domäner. Till sist diskuterades och identifierades lämpliga riskhanteringsstrategier. Resultatet från studien kunde indikera 23 risker relaterade till ett kliniskt användande av AI inom bild- och funktionsmedicin samt föreslå riskhanteringsstrategier till respektive risk som identifierades. Studien kunde identifiera operativa risker, patientsäkerhetsrisker, strategiska risker, finansiella risker, humankapitalrisker, juridiska risker och tekniska risker samt synliggöra eventuella synergier som existerar mellan riskerna. Slutsatsen av studien är att en holistisk syn på riskhantering och att en proaktiv hantering av risker är av avgörande betydelse för sjukhus som ska genomgå en implementering av AI.

Bakgrund: Bröstcancer är den vanligaste cancerformen hos kvinnor. Mammografiscreening har minskat antalet dödsfall i bröstcancer. Kvinnor upplever undersökningen som ångestfylld, besvärlig och smärtsam, vilket orsakar minskat deltagande. För ökat välbefinnande är det viktigt med förståelse för kvinnors erfarenheter.  Syfte: Syftet med litteraturstudien var att belysa kvinnors erfarenheter av mammografiscreening.  Metod: En litteraturstudie med resultat från tio kvalitativa studier. Sökningar genomfördes i PubMed och CINAHL. Artiklarna kvalitetsgranskades sedan analyserades och sammanställdes studiernas resultat.  Resultat: Analysen resulterade i tre kategorier och nio underkategorier. Huvudkategorierna var oro och rädsla, känsla av utsatthet samt behov av trygghet. Resultatet visar att erfarenheterna varierade men det upplevdes främst som fyllt av ångest, oro och smärta. Dessa känslor kunde lugnas med tiden, genom adekvat information eller om röntgensjuksköterskan var omtänksam och gav god omvårdnad.  Konklusion: Röntgensjuksköterskan har stort inflytande på undersökningen och kan med små medel förbättra kvinnors erfarenheter. Den kliniska verksamheten och röntgensjuksköterskan uppmuntras anpassa arbetssättet mot en mer personcentrerad omvårdnad. Då genomförs undersökningen på ett smidigare sätt och bilderna blir bättre vilket genererar ett minskat behov av omtag, och därmed kostnad, samt minskad psykisk påfrestning för kvinnorna. / Background: Breast cancer is the most common form of cancer among women. Mammography screening has reduced the number of deaths from breast cancer, but women experience the examination as anxiety-ridden and painful.  Aim: The purpose of the literature study was to illuminate women's experiences of mammography screening.  Methods: A literature study with results from ten qualitative studies. Searches were conducted in PubMed and CINAHL. The quality of the articles was reviewed, then the results of the articles were analyzed and compiled.  Results: The analysis resulted in three main categories and nine subcategories. The main categories were anxiety and fear, feelings of vulnerability and the need for safety. Although results varied, the examination was mainly described as worrisome and painful. Time, information, or good care provided by the radiographer could improve the experience.  Conclusion: The radiographer has a great influence on the examination and can with small means improve women's experiences. The clinical practice and the radiographer are encouraged to apply a more person-centered care. The examination is then performed more easily and the image quality increases, which reduces the need for recalls as well as the mental strain for women.

Röntgen av bröst görs med hjälp av en mammograf och den första mammografen tillverkades 1968. En mammografiundersökning utförs av en röntgensjuksköterska som komprimerar bröstet mellan en platta och en detektor. Röntgensjuksköterskans intention är att verka för varje unik individ, då alla individer har olika mängd vävnad i brösten. Bröstkompressionen vid mammografiundersökningen är komplex och det finns en bristande kunskap om helheten i området. Syfte: Att sammanställa kunskapsläget gällande vilka parametrar som har inverkan på bröstkompression vid mammografiundersökningar. Metod: En allmän litteraturöversikt utfördes. I analysen ingick 12 artiklar. Resultat: Tre kategorier framkom under analysen, dessa var: patientrelaterade egenskaper, självkomprimering och tekniska egenskaper. Kategorin patientrelaterade egenskaper innefattar densitet, brösttjocklek, stråldos, kompressionskraft och kompressionstryck, självkomprimering innehåller artiklar där patienten delvis utför mammografiundersökningen själv och tekniska egenskaper innehåller artiklar som tar upp kompressionsplattor, fabrikat och detektorer. Slutsats: Slutsatsen av denna allmänna litteraturöversikt är att bröstkompressionen har stor betydelse vid mammografiundersökningar och att förbättringsområden finns inom självkomprimering, brösttomosyntes, kompressionskraft och kompressionstryck. Det behövs mer forskning i ämnet.

Breast cancer is the most common cancer type for women worldwide. Early detection is key to improve prognosis and treatment success. A cost-efficient way of finding breast cancer early is mammography screening on a population basis. A major issue with mammography screening is in-between screening cancers. One method of targeting this issue is calculating breast cancer risk stratification on healthy mammography scans, however, this method is as of today insufficient. One proposed addition to refine risk stratification is to use Artificial Intelligence guided age prediction. The aim of this study was to investigate to what extent there is an additive value of age prediction on breast cancer risk stratification. Convolutional Neural Networks (CNNs) were used to train a model on an age prediction task using healthy mammography scans from the Cohort of Screen-Aged Women. The predicted ages and delta ages, calculated as predicted age minus chronological age, were then added to a logistic regression task together with, and without, the known risk factor mammographic density. The results showed an increase in breast cancer detection with the risk model incorporating age prediction for some age groups. This suggests age prediction using CNNs might increase breast cancer detection. More studies are needed to confirm these findings. / Bröstcancer är den vanligaste cancertypen för kvinnor globalt. Tidig upptäckt är en nyckelfaktor för att förbättra prognos och behandlingsframgång. Ett kostnadseffektivt sätt att hitta tidigt utvecklad bröstcancer är allmän screening med mammografi. Ett problem med denna screening är cancer som uppkommer mellan screeningtillfällen. En metod för att lösa detta problem är riskstratifiering som ämnar att beräkna risken att utveckla cancer från friska mammografibilder, men denna metod är idag otillräcklig. Ett förslag på tillägg för att förfina resultatet av detta är att använda artificiell intelligens guidad åldersbedömning. I den här studien var syftet att undersöka i vilken utsträckning det finns ett additivt värde av åldersbedömning för modellering av risken att utveckla bröstcancer. Convolutional Neural Networks (CNNs) användes för att träna en åldersbedömningssmodell på friska mammografibilder från Cohort of ScreenAged Women. De bedömda åldrarna samt deltaåldrarna, beräknade som bedömd ålder minus kronologisk ålder, användes sedan som input till en logistisk regressionsuppgift tillsammans med, samt utan, den kända riskfaktorn mammografisk densitet. Resultaten visade en ökad upptäckt av bröstcancer för vissa åldersgrupper då riskmodellen inkluderade deltaåldrarna. Detta tyder på att åldersbedömning med CNNs kan öka upptäckten av bröstcancer. Fler studier behövs för att bekräfta dessa fynd.

Abstrakt Bakgrund: Idag är bröstcancer en av de vanligaste cancerorsakerna för kvinnor i västvärlden. Diagnostisering för att upptäcka patologi i bröstvävnad sker vanligtvis genom röntgenbildtagning av brösten, antingen genom ett nationellt screeningprogram eller genom att patienten själv väljer att besöka en mammografisk mottagning. Proceduren för att ta bröstbilder kan upplevas smärtsam eller obehaglig och flertalet tekniker för att minska dessa obehagskänslor har genom åren framkommit, däribland patientassisterad bröstkompression. Erfarenheter från praktik och arbete vid mammografiska enheter lyfte intresset av metoder som kunde minska patientens obehag, vilket föranledde denna litteraturstudie. Syfte: Att undersöka effekten av patientassisterad bröstkompression vid mammografiska undersökningar på upplevelsen av smärta, obehag och nöjdhet jämfört med traditionell bröstkompression. Metod: Kvantitativ litteraturstudie med bas i åtta studier framtagna från databaserna PubMed och Cinahl.Resultat: Obetydlig effekt på smärtupplevelsen men fördelaktigt resultat på lindring av obehagskänslor och större patientnöjdhet jämfört med vanlig mammografisk bröstkompression. Konklusion: Resultatet tyder på att patientassisterad bröstkompression i mammografisk miljö kan minska upplevelsen av obehag som är associerat med mammografiska undersökningar och bidra till större patientnöjdhet och patientautonomi i enlighet med svensk vårddoktrin.  Nyckelord: PAC, radiografi, smärta, mammografi, obehag, nöjdhet, bröstkompression, patientassisterad, litteraturöversikt / Abstract Background: Today, breast cancer is one of the leading forms of cancer for women in the western world. Mammograms, x-ray pictures of the breast, are usually taken to diagnose pathologies in breast tissue either through a national screening programme, or by remittance from a physician due to patient symptoms. The experience of taking mammographic images are often viewed as painful or uncomfortable and methods to alleviate such feelings have been developed, such as patient-assisted compression. Experiences from work and internship at mammography units gave rise to an interest in methods to decrease patient discomfort, which prompted this particular literature study. Objective: To examine the effect of patient-assisted compression on the patient experience of pain, discomfort and satisfaction compared to traditional breast compression in mammography. Method: Quantitative literature study with basis in eight articles from the PubMed and Cinahl databases. Results: The results show no definitive effect of patient-assisted compression on the patients experience of pain, although there is a favorable result on the experience of discomfort and patient satisfaction compared to traditional breast compression. Conclusion: The result points towards positive effects on lowering patient discomfort and improving patient satisfaction during mammographic breast compressions, and has potential to enhance patient autonomy in accordance with Swedish healthcare doctrine. Keywords: PAC, radiography, pain, mammography, discomfort, satisfaction, compression, patient-assisted, literature review

[pt] Com o avanço recente do uso de aprendizagem profunda supervisionada (supervised deep learning) em aplicações no ramo da visão computacional, a indústria e a comunidade acadêmica vêm evidenciando que uma das principais dificuldades para o sucesso destas aplicações é a falta de datasets com a suficiente quantidade de dados anotados. Nesse sentido aponta-se a necessidade de alavancar grandes quantidades de dados rotulados para que estes modelos inteligentes possam solucionar problemas pertinentes ao seu contexto para atingir os resultados desejados. O uso de técnicas para gerar dados anotados de maneira mais eficiente está sendo cada vez mais explorado, juntamente com técnicas para o apoio à geração dos datasets que servem de insumos para o treinamento dos modelos de inteligência artificial. Este trabalho tem como propósito propor estratégias para otimizar processos de anotação e geração de datasets de segmentação semântica. Dentre as abordagens utilizadas neste trabalho destacamos o Interactive Segmentation e Active Learning. A primeira, tenta melhorar o processo de anotação de dados, tornando-o mais eficiente e eficaz do ponto de vista do anotador ou especialista responsável pela rotulagem dos dados com uso de um modelo de segmentação semântica que tenta imitar as anotações feitas pelo anotador. A segunda, consiste em uma abordagem que permite consolidar um modelo deep learning utilizando um critério inteligente, visando a seleção de dados não anotados mais informativos para o treinamento do modelo a partir de uma função de aquisição que se baseia na estimação de incerteza da rede para realizar a filtragem desses dados. Para aplicar e validar os resultados de ambas as técnicas, o trabalho os incorpora em um caso de uso relacionado em imagens de mamografia para segmentação de estruturas anatômicas. / [en] With the recent advancement of the use of supervised deep learning in applications in the field of computer vision, the industry and the academic community have been showing that one of the main difficulties for the success of these applications is the lack of datasets with a sufficient amount of annotated data. In this sense, there is a need to leverage large amounts of labeled data so that these intelligent models can solve problems relevant to their context to achieve the desired results. The use of techniques to generate annotated data more efficiently is being increasingly explored, together with techniques to support the generation of datasets that serve as inputs for the training of artificial intelligence models. This work aims to propose strategies to optimize annotation processes and generation of semantic segmentation datasets. Among the approaches used in this work, we highlight Interactive Segmentation and Active Learning. The first one tries to improve the data annotation process, making it more efficient and effective from the point of view of the annotator or specialist responsible for labeling the data using a semantic segmentation model that tries to imitate the annotations made by the annotator. The second consists of an approach that allows consolidating a deep learning model using an intelligent criterion, aiming at the selection of more informative unannotated data for training the model from an acquisition function that is based on the uncertainty estimation of the network to filter these data. To apply and validate the results of both techniques, the work incorporates them in a use case in mammography images for segmentation of anatomical structures.