Rare case of mantle cell lymphoma of the lacrimal sac

ABSTRACT Mantle cell lymphoma of the ocular and periorbital regions is extremely rare but should be considered in the differential diagnosis of lesions affecting the periorbital tissues. In this study, we present a rare case of mantle cell lymphoma of the lacrimal sac in a 65-year-old male presenting with a mass in the lacrimal sac region and epiphora. After clinical examinations and imaging studies, the mucocele was misdiagnosed. Considering the unexpected findings during external dacryocystorhinostomy, a frozen biopsy was performed, which confirmed the diagnosis of lymphoma.

Stealth cryptococcus in an immunocompetent patient.

Cryptococcosis occurs primarily in immunocompromised patients. It is difficult to suspect in an immunocompetent patient presenting with a headache. The clinical manifestations of cryptococcosis can be subtle in a patient whose immune system is responding, but inadequate. This is the report of a case of fatal cryptococcosis initially misdiagnosed as a sinus headache on the basis of a telephone call, and then misdiagnosed as aseptic meningitis on the basis of mild findings and negative cerebrospinal fluid cultures. Autopsy revealed unsuspected severe cryptococcal meningoencephalitis. Cerebrospinal fluid nuclear acid amplification (NAA) panels including Cryptococcus should enable the diagnosis of unsuspected cryptococcal meningitis in most cases, but can be false positive, which could be adjudicated by cryptococcal antigen and culture. It will remain important to test for cryptococcal antigen and to maintain a broad differential diagnosis for all patients with meningitis.

Mesothelioma: molecular pathology and biomarkers.

Diffuse mesotheliomas are characterized by recurrent genomic alterations involving tumor suppressors and epigenetic regulators such as BAP1, CDKN2A, MTAP, and NF2. Depending on the differential diagnosis as informed by histologic assessment, one can apply the appropriate immunohistochemical and/or molecular panels to reach the correct pathologic diagnosis, sometimes even in cases with limited tissues. Biomarkers aid in the diagnosis of mesothelioma in the following scenarios: 1) For a tumor that is overtly malignant, how can one distinguish mesothelioma from other tumors? 2) For a mesothelial proliferation, how can one distinguish mesothelioma from a reactive process? To distinguish mesotheliomas from carcinomas, at least two positive and two negative markers are currently recommended. To distinguish sarcomatoid mesothelioma from pleomorphic carcinoma, even more markers-and sometimes molecular testing-are needed. To distinguish mesothelioma from reactive mesothelial conditions, useful immunohistochemical biomarkers include BAP1, MTAP, and merlin, which serve as surrogates for the corresponding gene mutation status. In patients with unusual clinical history, for tumors with a peculiar microscopic appearance, and/or in cases with an equivocal immunophenotypic profile, molecular testing can help to exclude mimics and to confirm the pathologic diagnosis.

The dark side of T2: central nervous system lesions with low signal intensity on T2-weighted imaging.

The majority of central nervous system diseases show high signal intensity on T2-weighted magnetic resonance imaging. Diseases of the central nervous system with low signal intensity are less common, which makes it a finding that helps narrow the differential diagnosis. This was a retrospective analysis of brain and spine magnetic resonance imaging examinations in which that finding was helpful in the diagnostic investigation. We selected the cases of patients examined between 2015 and 2022. All diagnoses were confirmed on the basis of the clinical-radiological correlation or the histopathological findings. We obtained images of 14 patients with the following central nervous system diseases: arteriovenous malformation; cavernous malformation; metastasis from lymphoma; medulloblastoma; embryonal tumor; metastasis from melanoma; Rathke's cleft cyst; Erdheim-Chester disease; aspergillosis; paracoccidioidomycosis; tuberculosis; syphilis; immunoglobulin G4-related disease; and metastasis from a pulmonary neuroendocrine tumor. We described lesions of different etiologies in which the T2-weighted imaging profile helped narrow the differential diagnosis and facilitated the definitive diagnosis.

A grande maioria das doenças do sistema nervoso central apresenta alto sinal em ponderações T2 na ressonância magnética. As alterações com baixo sinal são menos comuns, de forma que essa característica permite estreitar o diagnóstico diferencial. Analisamos, retrospectivamente, pacientes com imagens de ressonância magnética de crânio e/ou coluna em que este achado foi útil na investigação diagnóstica. Os pacientes foram selecionados no período entre 2015 e 2022 e todos tiveram seus diagnósticos confirmados por estudo clinicorradiológico ou por estudo histopatológico. Obtivemos imagens de 14 pacientes com as seguintes afecções: malformação arteriovenosa, cavernoma, metástase de linfoma, meduloblastoma, tumor embrionário, metástase de melanoma, cisto da bolsa de Rathke, doença de Erdheim-Chester, aspergilose, paracoccidioidomicose, tuberculose, sífilis, doença relacionada à IgG4 e metástase de tumor neuroendócrino de pulmão. Descrevemos lesões de diversas origens etiológicas que, a partir de suas características nas imagens ponderadas em T2, foi possível reduzir o quadro de diagnósticos diferenciais e chegar mais facilmente à hipótese final.

Diagnosing and managing prescription opioid use disorder in patients prescribed opioids for chronic pain in Australian general practice settings: a qualitative study using the theory of Planned Behaviour.

BACKGROUND: Chronic pain is a debilitating and common health issue. General Practitioners (GPs) often prescribe opioids to treat chronic pain, despite limited evidence of benefit and increasing evidence of harms, including prescription Opioid Use Disorder (pOUD). Australian GPs are worried about the harms of long-term opioids, but few are involved in the treatment of pOUD. There is little research on GPs' experiences diagnosing and managing pOUD in their chronic pain patients. METHODS: This qualitative research used semi-structured interviews and a case study to investigate GPs' experiences through the lens of the Theory of Planned Behaviour (TPB). TPB describes three factors, an individual's perceived beliefs/attitudes, perceived social norms and perceived behavioural controls. Participants were interviewed via an online video conferencing platform. Interviews were transcribed verbatim and thematically analysed. RESULTS: Twenty-four GPs took part. Participants were aware of the complex presentations for chronic pain patients and concerned about long-term opioid use. Their approach was holistic, but they had limited understanding of pOUD diagnosis and suggested that pOUD had only one treatment: Opioid Agonist Treatment (OAT). Participants felt uncomfortable prescribing opioids and were fearful of difficult, conflictual conversations with patients about the possibility of pOUD. This led to avoidance and negative attitudes towards diagnosing pOUD. There were few positive social norms, few colleagues diagnosed or managed pOUD. Participants reported that their colleagues only offered positive support as this would allow them to avoid managing pOUD themselves, while patients and other staff were often unsupportive. Negative behavioural controls were common with low levels of knowledge, skill, professional supports, inadequate time and remuneration described by many participants. They felt OAT was not core general practice and required specialist management. This dichotomous approach was reflected in their views that the health system only supported treatment for chronic pain or pOUD, not both conditions. CONCLUSIONS: Negative beliefs, negative social norms and negative behavioural controls decreased individual behavioural intention for this group of GPs. Diagnosing and managing pOUD in chronic pain patients prescribed opioids was perceived as difficult and unsupported. Interventions to change behaviour must address negative perceptions in order to lead to more positive intentions to engage in the management of pOUD.

Painless Growing Swelling on the Palm of a 4-year-old Boy: Malignant Peripheral Nerve Sheath Tumor.

In this study, we present a 4-year-old male patient with a slowly growing painless mass in the palm of his left hand for 2 years. Although musculoskeletal tumors are rare, hand localized tumors are even rarer in pediatric patients. The fact that very few (less than one in ten) tumors are malignant and there are dozens of subtypes, each with different treatment management, shows the importance of the management of these lesions. Appropriate diagnosis and management of soft tissue masses, especially insidious malignant tumors, is vital. Due to the rarity of soft tissue tumors, adequate guidelines for their management are limited. The purpose of this report is to present an example of the approach to one of the soft tissue tumors.

A retrieval-augmented chatbot based on GPT-4 provides appropriate differential diagnosis in gastrointestinal radiology: a proof of concept study.

BACKGROUND: We investigated the potential of an imaging-aware GPT-4-based chatbot in providing diagnoses based on imaging descriptions of abdominal pathologies. METHODS: Utilizing zero-shot learning via the LlamaIndex framework, GPT-4 was enhanced using the 96 documents from the Radiographics Top 10 Reading List on gastrointestinal imaging, creating a gastrointestinal imaging-aware chatbot (GIA-CB). To assess its diagnostic capability, 50 cases on a variety of abdominal pathologies were created, comprising radiological findings in fluoroscopy, MRI, and CT. We compared the GIA-CB to the generic GPT-4 chatbot (g-CB) in providing the primary and 2 additional differential diagnoses, using interpretations from senior-level radiologists as ground truth. The trustworthiness of the GIA-CB was evaluated by investigating the source documents as provided by the knowledge-retrieval mechanism. Mann-Whitney U test was employed. RESULTS: The GIA-CB demonstrated a high capability to identify the most appropriate differential diagnosis in 39/50 cases (78%), significantly surpassing the g-CB in 27/50 cases (54%) (p = 0.006). Notably, the GIA-CB offered the primary differential in the top 3 differential diagnoses in 45/50 cases (90%) versus g-CB with 37/50 cases (74%) (p = 0.022) and always with appropriate explanations. The median response time was 29.8 s for GIA-CB and 15.7 s for g-CB, and the mean cost per case was $0.15 and $0.02, respectively. CONCLUSIONS: The GIA-CB not only provided an accurate diagnosis for gastrointestinal pathologies, but also direct access to source documents, providing insight into the decision-making process, a step towards trustworthy and explainable AI. Integrating context-specific data into AI models can support evidence-based clinical decision-making. RELEVANCE STATEMENT: A context-aware GPT-4 chatbot demonstrates high accuracy in providing differential diagnoses based on imaging descriptions, surpassing the generic GPT-4. It provided formulated rationale and source excerpts supporting the diagnoses, thus enhancing trustworthy decision-support. KEY POINTS: • Knowledge retrieval enhances differential diagnoses in a gastrointestinal imaging-aware chatbot (GIA-CB). • GIA-CB outperformed the generic counterpart, providing formulated rationale and source excerpts. • GIA-CB has the potential to pave the way for AI-assisted decision support systems.

[Consensus for the diagnosis and management of extramedullary plasmacytoma in China(2024)].

Extramedullary plasmacytoma (EMP) is a special type of malignant plasmacytosis, which is complex and heterogeneous. Most EMP patients have poor prognosis and lack a stratified prognostic system or ideal treatment strategy supported by evidence-based medical evidence, which cannot meet clinical needs. In order to improve the understanding of this disease entity, Plasma Cell Disease Group, Chinese Society of Hematology, Chinese Medical Association and Chinese Myeloma Committee-Chinese Hematology Association developed the "Chinese Expert Consensus on the diagnosis and treatment of extramedullary plasmacytoma", which aims to standardize the clinical diagnosis and treatment of EMP and ultimately improve the overall survival of patients with plasmacytoma.

Carcinoma basocelular de vulva: relato de caso / Basal cell carcinoma of the vulva: case report

Introdução: O carcinoma basocelular (CBC) de vulva é uma condição rara que corresponde a menos de 0,4% dos casos de CBC e de 2% a 4% das neoplasias de vulva. O CBC de vulva é mais comum entre mulheres brancas, multíparas e na pósmenopausa, especialmente na sétima década de vida. O objetivo é relatar um caso de CBC de vulva no qual discutiram-se os aspectos do diagnóstico e tratamento. Relato de Caso: Mulher de 63 anos de idade, G1P1A0, chega ao consultório em janeiro de 2022 para tratamento de lesão persistente em vulva. Realizou-se biópsia incisional que mostrou tratar-se de provável carcinoma basocelular nodular com invasão da derme. A paciente submeteu-se a uma ressecção do tumor com margens macroscópicas livres e sutura primária. A cirurgia não teve complicações no pré-operatório e no pós-operatório. O histopatológico da peça cirúrgica mostrou tratar-se de carcinoma basocelular nodular com área irregular, plana, branco, medindo 0,7x0,4cm, com as margens laterais distando 7,0 e 5,0mm e profundas, 5,9mm; todas livres. Conclusão: O caso relatado é raro, tendo sido o tratamento de ressecção cirúrgica do CBC de vulva com margens bem-sucedido. Catorze meses após a cirurgia, a paciente encontra-se sem evidências de recidiva local ou regional.

Introduction: Basal cell carcinoma (BCC) of the vulva is a rare condition that accounts for less than 0.4% of BCC cases and 2% to 4% of vulvar neoplasms. BCC of the vulva is more common among white, multiparous and postmenopausal women, especially in the seventh decade of life. The aim is to report a case of BCC of the vulva in which aspects of diagnosis and treatment were discussed. Case report: A 63-year-old woman, G1P1A0, arrives at the office in January 2022 for treatment of a persistent lesion on her vulva. An incisional biopsy was performed and showed that it was likely nodular basal cell carcinoma with invasion of the dermis. The patient underwent tumor resection with free macroscopic margins and primary suture. The surgery had no complications preoperatively or postoperatively. The histopathology of the surgical specimen showed that it was a nodular basal cell carcinoma with an irregular, flat, white area, measuring 0.7x0.4cm, with the lateral margins 7.0 and 5.0mm apart and 5.9mm deep; all free. Conclusion: The reported case is rare, with surgical resection of BCC of the vulva with margins being successful. Fourteen months after surgery, the patient has no evidence of local or regional recurrence.

Tumor filoide borderline gigante e recidivante: ressecção e reconstrução da mama / Recurrent giant borderline phyllodes tumor: resection and breast reconstruction

O tumor filoide é uma neoplasia fibroepitelial rara que representa 0,3 a 1% de todas as neoplasias mamárias. De acordo com a classificação histopatológica, 12 a 26% são do tipo borderline e aproximadamente 15% desses tumores recorrem após excisão cirúrgica. O tratamento recomendado para todos os tipos de tumor filoide é a excisão cirúrgica, e no caso de tumores gigantes o tratamento deve ser multidisciplinar. Apresentamos o caso de uma mulher de 46 anos com tumor filoide na mama esquerda que recorreu 4 anos após a excisão cirúrgica. O estudo anatomopatológico qualificou-o como tumor gigante e o estudo histopatológico relatou tumor filoide borderline. Foi submetida a excisão cirúrgica com mastectomia esquerda e reconstrução mamária com retalho de grande dorsal mais enxerto de gordura. A paciente apresentou evolução favorável sem recidiva. Concluindo, o tumor filoide gigante borderline recorrente é raro e seu manejo cirúrgico representa um desafio tanto na excisão quanto na reconstrução mamária.

Phyllodes tumor is a rare fibroepithelial neoplasm that represents 0.3 to 1% of all breast neoplasms. According to histopathologic classification, 12 to 26% are borderline type and approximately 15% of these tumors recur after surgical excision. The recommended treatment for all types of phyllodes tumor is surgical excision, and in the case of giant tumors the treatment should be multidisciplinary. We present the case of a 46-yearold woman with a phyllodes tumor in the left breast that recurred 4 years after surgical excision. The anatomopathological study qualified it as a giant tumor and the histopathological study reported a borderline phyllodes tumor. She underwent surgical excision with left mastectomy and breast reconstruction by means of a latissimus dorsi flap plus fat graft. The patient presented a favorable evolution without recurrence. In conclusion, the recurrent giant borderline phyllodes tumor is rare and its surgical management represents a challenge both in breast excision and reconstruction.

Case series of complicated bronchopulmonary lophomoniasis. Differential diagnosis of tuberculosis?

Pulmonary lophomoniasis is a rare and life-threatening disease, most commonly reported across Asian and Latin American countries. Here, we have reported two cases of pulmonary lophomoniasis presenting with atypical manifestations. Case #1 represents a 19-year-old male patient with clinical characteristics suggestive of tuberculosis, presenting with hemoptysis and receiving antituberculosis treatment. Case #2 represents a 69-year-old man with post-tuberculosis pulmonary disease with cystic bronchiectasis presenting with polymicrobial co-infection. Based on our case experience, lophomoniasis should be considered in patients with pneumonia who do not respond to antibiotic treatment, and the corresponding epidemiological factors should be carefully considered in addition to bronchoscopy for precise diagnosis.

Discrimination between ventricular tachycardia and wide-QRS preexcited tachycardia.

BACKGROUND: To develop a new algorithm to differentiate ventricular tachycardia (VT) from preexcited tachycardia (pre-ET) according to left bundle branch block (LBBB) and right bundle branch block (RBBB) patterns. METHODS: This study included 67 electrocardiograms (ECGs) with VT and 63 ECGs with pre-ET, collected from our hospital and through PubMed. Of those, 64 were allocated to the derivation cohort and the rest to the validation cohort. The diagnoses of the ECGs were confirmed using an electrophysiological study. Parameters and classifiers from prior algorithms along with the propagation speeds in the early portion of the QRS complex (initial deflection index) in leads V1, V6, aVR, II, and III were manually measured. The performance of the new algorithm was compared with that of prior algorithms. RESULTS: The initial deflection index in lead III was the strongest predictor of pre-ET in LBBB-pattern wide-QRS tachycardia (p = 0.003, AUC 0.805). The initial deflection index in lead V1 was the most powerful predictor of pre-ET in RBBB-pattern wide-QRS tachycardia (p = 0.001, AUC 0.848). Compared to earlier algorithms, those using the initial deflection indexes: lead III in LBBB patterns (cutoff value >0.3) and lead V1 in RBBB patterns (cutoff value ≤0.48), demonstrated superior performance in screening VT, with AUC values of 0.828. The initial deflection indexes proved effective as discriminators between VT and pre-ET in the validation cohort. CONCLUSIONS: In LBBB-pattern wide-QRS tachycardia, the early propagation speed of pre-ET was faster than that in VT. Conversely, in RBBB-pattern wide-QRS tachycardia, it was slower.

Comparison contrast-enhanced CT with contrast-enhanced US in diagnosing combined hepatocellular-cholangiocarcinoma: a propensity score-matched study.

OBJECTIVES: To develop and compare noninvasive models for differentiating between combined hepatocellular-cholangiocarcinoma (cHCC-CCA) and HCC based on serum tumor markers, contrast-enhanced ultrasound (CEUS), and computed tomography (CECT). METHODS: From January 2010 to December 2021, patients with pathologically confirmed cHCC-CCA or HCC who underwent both preoperative CEUS and CECT were retrospectively enrolled. Propensity scores were calculated to match cHCC-CCA and HCC patients with a near-neighbor ratio of 1:2. Two predicted models, a CEUS-predominant (CEUS features plus tumor markers) and a CECT-predominant model (CECT features plus tumor markers), were constructed using logistic regression analyses. Model performance was evaluated by the area under the curve (AUC), sensitivity, specificity, and accuracy. RESULTS: A total of 135 patients (mean age, 51.3 years ± 10.9; 122 men) with 135 tumors (45 cHCC-CCA and 90 HCC) were included. By logistic regression analysis, unclear boundary in the intratumoral nonenhanced area, partial washout on CEUS, CA 19-9 > 100 U/mL, lack of cirrhosis, incomplete tumor capsule, and nonrim arterial phase hyperenhancement (APHE) volume < 50% on CECT were independent factors for a diagnosis of cHCC-CCA. The CECT-predominant model showed almost perfect sensitivity for cHCC-CCA, unlike the CEUS-predominant model (93.3% vs. 55.6%, p < 0.001). The CEUS-predominant model showed higher diagnostic specificity than the CECT-predominant model (80.0% vs. 63.3%; p = 0.020), especially in the ≤ 5 cm subgroup (92.0% vs. 70.0%; p = 0.013). CONCLUSIONS: The CECT-predominant model provides higher diagnostic sensitivity than the CEUS-predominant model for CHCC-CCA. Combining CECT features with serum CA 19-9 > 100 U/mL shows excellent sensitivity. CRITICAL RELEVANCE STATEMENT: Combining lack of cirrhosis, incomplete tumor capsule, and nonrim arterial phase hyperenhancement (APHE) volume < 50% on CECT with serum CA 19-9 > 100 U/mL shows excellent sensitivity in differentiating cHCC-CCA from HCC. KEY POINTS: 1. Accurate differentiation between cHCC-CCA and HCC is essential for treatment decisions. 2. The CECT-predominant model provides higher accuracy than the CEUS-predominant model for CHCC-CCA. 3. Combining CECT features and CA 19-9 levels shows a sensitivity of 93.3% in diagnosing cHCC-CCA.

Intrahepatic cholangiocarcinoma: histological diversity and the role of the pathologist.

Intrahepatic cholangiocarcinoma (iCCA) is one of the primary liver cancers and presents with tumor heterogeneity. About 50% of iCCAs comprise actionable mutations, which completely change patient management. In addition, the precise diagnosis of iCCA, including subtype, has become crucial, and pathologists play an important role in this regard. This review focuses on iCCA heterogeneity; looking at different perspectives to guide diagnosis and optimal treatment choice.

Development of a combined radiomics and CT feature-based model for differentiating malignant from benign subcentimeter solid pulmonary nodules.

BACKGROUND: We aimed to develop a combined model based on radiomics and computed tomography (CT) imaging features for use in differential diagnosis of benign and malignant subcentimeter (≤ 10 mm) solid pulmonary nodules (SSPNs). METHODS: A total of 324 patients with SSPNs were analyzed retrospectively between May 2016 and June 2022. Malignant nodules (n = 158) were confirmed by pathology, and benign nodules (n = 166) were confirmed by follow-up or pathology. SSPNs were divided into training (n = 226) and testing (n = 98) cohorts. A total of 2107 radiomics features were extracted from contrast-enhanced CT. The clinical and CT characteristics retained after univariate and multivariable logistic regression analyses were used to develop the clinical model. The combined model was established by associating radiomics features with CT imaging features using logistic regression. The performance of each model was evaluated using the area under the receiver-operating characteristic curve (AUC). RESULTS: Six CT imaging features were independent predictors of SSPNs, and four radiomics features were selected after a dimensionality reduction. The combined model constructed by the logistic regression method had the best performance in differentiating malignant from benign SSPNs, with an AUC of 0.942 (95% confidence interval 0.918-0.966) in the training group and an AUC of 0.930 (0.902-0.957) in the testing group. The decision curve analysis showed that the combined model had clinical application value. CONCLUSIONS: The combined model incorporating radiomics and CT imaging features had excellent discriminative ability and can potentially aid radiologists in diagnosing malignant from benign SSPNs. RELEVANCE STATEMENT: The model combined radiomics features and clinical features achieved good efficiency in predicting malignant from benign SSPNs, having the potential to assist in early diagnosis of lung cancer and improving follow-up strategies in clinical work. KEY POINTS: • We developed a pulmonary nodule diagnostic model including radiomics and CT features. • The model yielded the best performance in differentiating malignant from benign nodules. • The combined model had clinical application value and excellent discriminative ability. • The model can assist radiologists in diagnosing malignant from benign pulmonary nodules.

Unenhanced Breast MRI With Diffusion-Weighted Imaging for Breast Cancer Detection: Effects of Training on Performance and Agreement of Subspecialty Radiologists.

OBJECTIVE: To investigate whether reader training improves the performance and agreement of radiologists in interpreting unenhanced breast magnetic resonance imaging (MRI) scans using diffusion-weighted imaging (DWI). MATERIALS AND METHODS: A study of 96 breasts (35 cancers, 24 benign, and 37 negative) in 48 asymptomatic women was performed between June 2019 and October 2020. High-resolution DWI with b-values of 0, 800, and 1200 sec/mm² was performed using a 3.0-T system. Sixteen breast radiologists independently reviewed the DWI, apparent diffusion coefficient maps, and T1-weighted MRI scans and recorded the Breast Imaging Reporting and Data System (BI-RADS) category for each breast. After a 2-h training session and a 5-month washout period, they re-evaluated the BI-RADS categories. A BI-RADS category of 4 (lesions with at least two suspicious criteria) or 5 (more than two suspicious criteria) was considered positive. The per-breast diagnostic performance of each reader was compared between the first and second reviews. Inter-reader agreement was evaluated using a multi-rater κ analysis and intraclass correlation coefficient (ICC). RESULTS: Before training, the mean sensitivity, specificity, and accuracy of the 16 readers were 70.7% (95% confidence interval [CI]: 59.4-79.9), 90.8% (95% CI: 85.6-94.2), and 83.5% (95% CI: 78.6-87.4), respectively. After training, significant improvements in specificity (95.2%; 95% CI: 90.8-97.5; P = 0.001) and accuracy (85.9%; 95% CI: 80.9-89.8; P = 0.01) were observed, but no difference in sensitivity (69.8%; 95% CI: 58.1-79.4; P = 0.58) was observed. Regarding inter-reader agreement, the κ values were 0.57 (95% CI: 0.52-0.63) before training and 0.68 (95% CI: 0.62-0.74) after training, with a difference of 0.11 (95% CI: 0.02-0.18; P = 0.01). The ICC was 0.73 (95% CI: 0.69-0.74) before training and 0.79 (95% CI: 0.76-0.80) after training (P = 0.002). CONCLUSION: Brief reader training improved the performance and agreement of interpretations by breast radiologists using unenhanced MRI with DWI.