Fully Automated Deep Learning Model to Detect Clinically Significant Prostate Cancer at MRI.

Background Multiparametric MRI can help identify clinically significant prostate cancer (csPCa) (Gleason score ≥7) but is limited by reader experience and interobserver variability. In contrast, deep learning (DL) produces deterministic outputs. Purpose To develop a DL model to predict the presence of csPCa by using patient-level labels without information about tumor location and to compare its performance with that of radiologists. Materials and Methods Data from patients without known csPCa who underwent MRI from January 2017 to December 2019 at one of multiple sites of a single academic institution were retrospectively reviewed. A convolutional neural network was trained to predict csPCa from T2-weighted images, diffusion-weighted images, apparent diffusion coefficient maps, and T1-weighted contrast-enhanced images. The reference standard was pathologic diagnosis. Radiologist performance was evaluated as follows: Radiology reports were used for the internal test set, and four radiologists' PI-RADS ratings were used for the external (ProstateX) test set. The performance was compared using areas under the receiver operating characteristic curves (AUCs) and the DeLong test. Gradient-weighted class activation maps (Grad-CAMs) were used to show tumor localization. Results Among 5735 examinations in 5215 patients (mean age, 66 years ± 8 [SD]; all male), 1514 examinations (1454 patients) showed csPCa. In the internal test set (400 examinations), the AUC was 0.89 and 0.89 for the DL classifier and radiologists, respectively (P = .88). In the external test set (204 examinations), the AUC was 0.86 and 0.84 for the DL classifier and radiologists, respectively (P = .68). DL classifier plus radiologists had an AUC of 0.89 (P < .001). Grad-CAMs demonstrated activation over the csPCa lesion in 35 of 38 and 56 of 58 true-positive examinations in internal and external test sets, respectively. Conclusion The performance of a DL model was not different from that of radiologists in the detection of csPCa at MRI, and Grad-CAMs localized the tumor. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Johnson and Chandarana in this issue.

Natural language processing pipeline to extract prostate cancer-related information from clinical notes.

OBJECTIVES: To develop an automated pipeline for extracting prostate cancer-related information from clinical notes. MATERIALS AND METHODS: This retrospective study included 23,225 patients who underwent prostate MRI between 2017 and 2022. Cancer risk factors (family history of cancer and digital rectal exam findings), pre-MRI prostate pathology, and treatment history of prostate cancer were extracted from free-text clinical notes in English as binary or multi-class classification tasks. Any sentence containing pre-defined keywords was extracted from clinical notes within one year before the MRI. After manually creating sentence-level datasets with ground truth, Bidirectional Encoder Representations from Transformers (BERT)-based sentence-level models were fine-tuned using the extracted sentence as input and the category as output. The patient-level output was determined by compilation of multiple sentence-level outputs using tree-based models. Sentence-level classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) on 15% of the sentence-level dataset (sentence-level test set). The patient-level classification performance was evaluated on the patient-level test set created by radiologists by reviewing the clinical notes of 603 patients. Accuracy and sensitivity were compared between the pipeline and radiologists. RESULTS: Sentence-level AUCs were ≥ 0.94. The pipeline showed higher patient-level sensitivity for extracting cancer risk factors (e.g., family history of prostate cancer, 96.5% vs. 77.9%, p < 0.001), but lower accuracy in classifying pre-MRI prostate pathology (92.5% vs. 95.9%, p = 0.002) and treatment history of prostate cancer (95.5% vs. 97.7%, p = 0.03) than radiologists, respectively. CONCLUSION: The proposed pipeline showed promising performance, especially for extracting cancer risk factors from patient's clinical notes. CLINICAL RELEVANCE STATEMENT: The natural language processing pipeline showed a higher sensitivity for extracting prostate cancer risk factors than radiologists and may help efficiently gather relevant text information when interpreting prostate MRI. KEY POINTS: When interpreting prostate MRI, it is necessary to extract prostate cancer-related information from clinical notes. This pipeline extracted the presence of prostate cancer risk factors with higher sensitivity than radiologists. Natural language processing may help radiologists efficiently gather relevant prostate cancer-related text information.

MRI in Adult Patients with Active and Inactive Implanted MR-conditional, MR-nonconditional, and Other Devices.

Active implanted medical devices (AIMDs) enable therapy and patient monitoring by way of electrical activity and typically have a battery and electrical leads. The most common types of AIMDs include cardiac implantable electronic devices (CIEDs), spinal cord stimulators, deep brain stimulators, bone growth or fusion stimulators, other neurostimulators, and drug infusion pumps. As more patients with AIMDs undergo MRI, it is important to consider the safety of patients who have these implanted devices during MRI. The authors review the physics concepts related to MRI safety, such as peak spatial gradient magnetic field, specific absorption rate, root mean square value of the effective magnetic component of the transmitted RF pulse, and gradient slew rate, as well as the parameters necessary to remain within safety limits. The roles of MRI safety personnel, as set forth by the International Society of Magnetic Resonance in Medicine, are emphasized. In addition, the relevant information provided in vendor manuals is reviewed, with a focus on how to obtain relevant up-to-date information. The radiologist should be able to modify protocols to meet safety requirements, address possible alternatives to MRI, and weigh the potential benefits of MRI against the potential risks. A few more advanced topics, such as fractured or abandoned device leads and patients with multiple implanted medical devices, also are addressed. Recommended workflows for MRI in patients with implanted medical devices are outlined. It is important to implement an algorithmic MRI safety process, including a review of the MRI safety information; patient screening; optimal imaging; and monitoring patients before, during, and after the examination. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material. See the invited commentary by Shetty et al in this issue.

Imaging of Perirenal and Intrarenal Lymphatic Vessels: Anatomy-based Approach.

The lymphatic system (or lymphatics) consists of lymphoid organs and lymphatic vessels. Despite the numerous previously published studies describing conditions related to perirenal and intrarenal lymphoid organs in the radiology literature, the radiologic findings of conditions related to intrarenal and perirenal lymphatic vessels have been scarcely reported. In the renal cortex, interlobular lymphatic capillaries do not have valves; therefore, lymph can travel along the primary route toward the hilum, as well as toward the capsular lymphatic plexus. These two lymphatic pathways can be opacified by contrast medium via pyelolymphatic backflow at CT urography, which reflects urinary contrast agent leakage into perirenal lymphatic vessels via forniceal rupture. Pyelolymphatic backflow toward the renal hilum should be distinguished from urinary leakage due to urinary injury. Delayed subcapsular contrast material retention via pyelolymphatic backflow, appearing as hyperattenuating subcapsular foci on CT images, mimics other subcapsular cystic diseases. In contrast to renal parapelvic cysts originating from the renal parenchyma, renal peripelvic cysts are known to be of lymphatic origin. Congenital renal lymphangiectasia is mainly seen in children and assessed and followed up at imaging. Several lymphatic conditions, including lymphatic leakage as an early complication and acquired renal lymphangiectasia as a late complication, are sometimes identified at imaging follow-up of kidney transplant. Lymphangiographic contrast material accumulation in the renal hilar lymphatic vessels is characteristic of chylo-urinary fistula. Chyluria appears as a fat-layering fluid-fluid level in the urinary bladder or upper urinary tract. Recognition of the anatomic pathway of tumor spread via lymphatic vessels at imaging is of clinical importance for accurate management at oncologic imaging. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

Local radiotherapy for chemotherapy-refractory Kaposi's sarcoma in an HIV-infected patient: A case report and literature review.

Human immunodeficiency virus-associated Kaposi's sarcoma (HIV-KS) is a well-documented vascular tumor with a pathogenesis involving human herpesvirus-8 (HHV-8) infection. While antiretroviral therapy (ART) and chemotherapy are effective for treating most KS cases, some become refractory. In this report, we present a case of a 58-year-old man with refractory HIV-KS treated with ART and chemotherapy. Chemotherapy was eventually discontinued due to an adverse reaction, and the patient presented with painful plantar lesions that impaired ambulation. With the exclusion of visceral metastases, localized radiotherapy was administered, which resulted in significant cosmetic and functional improvements. The patient regained ambulation and lived independently, receiving additional radiotherapy as needed. This case underscores the potential use of radiotherapy for the treatment of ART-resistant KS, particularly when the patient is unresponsive to conventional chemotherapy. It also highlights the need for future research in this area.

An overlapping case of IgG4-related disease and systemic lupus erythematosus treated with belimumab: a case-based review.

IgG4-related disease (IgG4-RD) is a systemic condition in which IgG4+ plasma cell infiltration and fibrosis cause organ swelling and lead to diverse clinical manifestations. Although IgG4-RD typically responds to glucocorticoids (GCs), relapse during tapering occurs and an early GC-sparing approach might therefore be beneficial. Systemic lupus erythematosus (SLE) is a chronic inflammatory disease with multiple symptoms that is also treated with GCs as a first-line therapy. Recently, belimumab, a recombinant human IgG-1λ monoclonal antibody that inhibits B-cell activating factor, was approved, but reports of use for IgG4-RD are scarce. Here, we present a rare case of IgG4-RD complicated with SLE which was successfully treated with belimumab. A 67-year-old man was diagnosed with IgG4-RD based on a high serum IgG4 level and histopathological findings. Furthermore, he had pericardial effusion on echocardiography, and laboratory tests revealed thrombocytopenia, autoimmune hemolysis, positive anti-nuclear antibodies, positive anti-DNA antibodies, and hypocomplementemia. These data led to an SLE diagnosis. Treatment was started with prednisolone at 40 mg/day, plus hydroxychloroquine, which initially improved both the SLE and IgG4-RD symptoms. During the GC tapering, belimumab was added and clinical symptoms resolved completely. Our case and the literature review summarize reported rare overlapping cases of IgG4-RD and SLE and suggest that belimumab is a promising candidate for the treatment of IgG4-RD.

Clinical importance of anti-Ro52 antibody for polymyositis and dermatomyositis.

OBJECTIVES: To clarify clinical features of anti-Ro52 antibody (Ab)-positive polymyositis (PM)/dermatomyositis (DM). PATIENTS AND METHODS: We retrospectively examined clinical features and status of anti-Ro52 Ab in patients with PM/DM admitted at the University of Tsukuba Hospital between January 2019 and February 2023. We compared anti-Ro52 Ab-positive and -negative groups. RESULTS: A total of 40 patients were selected and analyzed. Median age at diagnosis was 61.5 (48.8-69.3) years and 34 cases were female. Twenty-three cases were PM and 17 cases were DM (including 6 clinically amyopathic dermatomyositis: CADM). Twenty-two cases were positive for anti-Ro52 Ab, 14 for anti-ARS Ab, and 6 for anti-MDA5 Ab. Interstitial lung disease (ILD) was detected in 29 cases, 9 of which were rapidly progressive. Glucocorticoid (GC)-resistant cardiomyopathy was detected in 6 cases, malignancy in 3 cases, and Sjögren's syndrome (SS) in 4 cases. Of the 22 anti-Ro52 Ab positive cases, only 3 were single-positive and the remaining 19 cases simultaneously had other autoantibodies. Comparing the anti-Ro52 Ab-positive and -negative groups, the frequencies of anti-ARS Ab positivity (63.6% vs. 0%), ILD (95.5% vs. 44.4%), GC-resistant cardiomyopathy (27.3% vs. 0%), concomitant use of immunosuppressants (95.5% vs. 55.6%), and levels of C-reactive protein (CRP) were significantly higher in the anti-Ro52 Ab-positive group (p<0.05). The frequencies of PM/DM, positivity of anti-MDA5 Ab, malignancies, and SS were comparable between groups. CONCLUSION: Anti-Ro52 Ab were frequently positive in PM/DM and anti-Ro52 Ab-positive patients showed significantly higher rates of anti-ARS Ab positivity and ILD, GC-resistant cardiomyopathy, concomitant use of immunosuppressants, and higher levels of CRP. Anti-Ro52 Ab may be useful as a severity marker in PM/DM.

Writing Case Reports Can Improve Seven Components in Clinical Reasoning.

Case reports provide scientific knowledge and opportunities for new clinical research. However, it is estimated that less than 5% of cases presented by Japanese generalists at academic conferences are published due to various barriers such as the complex process of writing articles, conducting literature searches, the significant time required, the reluctance to write in English, and the challenge of selecting appropriate journals for publication. Therefore, the purpose of this opinion paper is to provide clinicians with practical tips for writing case reports that promote diagnostic excellence. In recent years, clinical practitioners have been striving for diagnostic excellence and optimal methods to accurately and comprehensively understand the patient's condition. To write a case report, it is essential to be mindful of the elements of diagnostic excellence and consider the quality of the diagnostic reasoning process. We (the authors) are seven academic generalists who are members of the Japanese Society of Hospital General Medicine (JSHGM) - Junior Doctors Association, with a median of 7 years after graduation and extensive experience publishing case reports in international peer-reviewed journals. We conducted a narrative review and discussed ways to write case reports to promote diagnostic excellence, leveraging our unique perspectives as academic generalists. Our review did not identify any reports addressing the critical points in writing case reports that embody diagnostic excellence. Therefore, this report proposes a methodology that describes the process involved in writing diagnostic excellence-promoting case reports and provides an overview of the lessons learned. Based on our review and discussion, we explain the essential points for promoting diagnostic excellence through case reports categorized into seven components of clinical reasoning. These strategies are useful in daily clinical practice and instrumental in promoting diagnostic excellence through case reports.

Image quality comparison of 1.5T and 3T prostate MRIs of the same post-hip arthroplasty patients: multi-rater assessments including PI-QUAL version 2.

OBJECTIVES: To compare the image quality of 1.5T and 3T prostate MRIs of the same post-hip arthroplasty patients, with a specific focus on the degree of susceptibility artifacts. METHODS: This single-center retrospective study included post-hip arthroplasty patients who underwent 1.5T prostate MRIs between 2021 and 2023, as well as comparative 3T prostate MRIs. Three blinded abdominal radiologists retrospectively reviewed their diffusion-weighted imaging (DWI, 50 s/mm2), T2-weighted imaging (T2WI), and dynamic contrast-enhanced imaging (DCE) to evaluate the image quality. The degree of susceptibility artifacts was categorized using a three-point scale, with 3 indicating the least artifact and 1 indicating the most. Image quality was also evaluated using Prostate Imaging Quality (PI-QUAL) version 2. The median of the three raters' scores was compared between 1.5T and 3T prostate MRIs using the Wilcoxon signed-rank test. The inter-rater agreement was evaluated using the multi-rater generalized kappa. RESULTS: Twenty pairs of 1.5T and 3T prostate MRI examinations from 20 unique patients were included. The DWI susceptibility artifact score at 1.5T was significantly higher than at 3T (mean score ± standard deviation, 2.80 ± 0.41 vs. 2.35 ± 0.93, p = 0.014). In contrast, no significant differences were observed in the susceptibility artifact scores in T2WI and DCE, or in the PI-QUAL score. The inter-reader agreement in the susceptibility artifact score was moderate (multi-rater generalized kappa: 0.60) in DWI, perfect in T2WI (not applicable), and substantial (0.65) in DCE. The inter-reader agreement was fair (0.27) in the PI-QUAL score. CONCLUSION: Using 1.5T scanners may be preferable to reduce susceptibility artifacts from hip prostheses in DWI.

Comparison of model-based versus deep learning-based image reconstruction for thin-slice T2-weighted spin-echo prostate MRI.

PURPOSE: To compare a previous model-based image reconstruction (MBIR) with a newly developed deep learning (DL)-based image reconstruction for providing improved signal-to-noise ratio (SNR) in high through-plane resolution (1 mm) T2-weighted spin-echo (T2SE) prostate MRI. METHODS: Large-area contrast and high-contrast spatial resolution of the reconstruction methods were assessed quantitatively in experimental phantom studies. The methods were next evaluated radiologically in 17 subjects at 3.0 Tesla for whom prostate MRI was clinically indicated. For each subject, the axial T2SE raw data were directed to MBIR and to the DL reconstruction at three vendor-provided levels: (L)ow, (M)edium, and (H)igh. Thin-slice images from the four reconstructions were compared using evaluation criteria related to SNR, sharpness, contrast fidelity, and reviewer preference. Results were compared using the Wilcoxon signed-rank test using Bonferroni correction, and inter-reader comparisons were done using the Cohen and Krippendorf tests. RESULTS: Baseline contrast and resolution in phantom studies were equivalent for all four reconstruction pathways as desired. In vivo, all three DL levels (L, M, H) provided improved SNR versus MBIR. For virtually, all other evaluation criteria DL L and M were superior to MBIR. DL L and M were evaluated as superior to DL H in fidelity of contrast. For 44 of the 51 evaluations, the DL M reconstruction was preferred. CONCLUSION: The deep learning reconstruction method provides significant SNR improvement in thin-slice (1 mm) T2SE images of the prostate while retaining image contrast. However, if taken to too high a level (DL High), both radiological sharpness and fidelity of contrast diminish.

Transition-zone PSA-density calculated from MRI deep learning prostate zonal segmentation model for prediction of clinically significant prostate cancer.

PURPOSE: To develop a deep learning (DL) zonal segmentation model of prostate MR from T2-weighted images and evaluate TZ-PSAD for prediction of the presence of csPCa (Gleason score of 7 or higher) compared to PSAD. METHODS: 1020 patients with a prostate MRI were randomly selected to develop a DL zonal segmentation model. Test dataset included 20 cases in which 2 radiologists manually segmented both the peripheral zone (PZ) and TZ. Pair-wise Dice index was calculated for each zone. For the prediction of csPCa using PSAD and TZ-PSAD, we used 3461 consecutive MRI exams performed in patients without a history of prostate cancer, with pathological confirmation and available PSA values, but not used in the development of the segmentation model as internal test set and 1460 MRI exams from PI-CAI challenge as external test set. PSAD and TZ-PSAD were calculated from the segmentation model output. The area under the receiver operating curve (AUC) was compared between PSAD and TZ-PSAD using univariate and multivariate analysis (adjusts age) with the DeLong test. RESULTS: Dice scores of the model against two radiologists were 0.87/0.87 and 0.74/0.72 for TZ and PZ, while those between the two radiologists were 0.88 for TZ and 0.75 for PZ. For the prediction of csPCa, the AUCs of TZPSAD were significantly higher than those of PSAD in both internal test set (univariate analysis, 0.75 vs. 0.73, p < 0.001; multivariate analysis, 0.80 vs. 0.78, p < 0.001) and external test set (univariate analysis, 0.76 vs. 0.74, p < 0.001; multivariate analysis, 0.77 vs. 0.75, p < 0.001 in external test set). CONCLUSION: DL model-derived zonal segmentation facilitates the practical measurement of TZ-PSAD and shows it to be a slightly better predictor of csPCa compared to the conventional PSAD. Use of TZ-PSAD may increase the sensitivity of detecting csPCa by 2-5% for a commonly used specificity level.

Amebiasis as a sexually transmitted infection: A re-emerging health problem in developed countries.

Amebiasis, which is caused by Entamoeba histolytica (E. histolytica), is the second leading cause of parasite-related death worldwide. It manifests from asymptomatic carriers to severe clinical conditions, like colitis and liver abscesses. Amebiasis is commonly seen in developing countries, where water and food are easily contaminated by feces because of the poor sanitation. However, a recently challenge in many developed countries is the increase in domestic cases of invasive amebiasis as a sexually transmitted infection (STI amebiasis). In contrast to food-/ waterborne transmission of E. histolytica in developing countries, transmission of STI amebiasis occurs directly through human-to-human sexual contact (e.g., men who have sex with men and people who engage in oral-anal sex); in this setting, asymptomatic infected individuals are the main reservoir of E. histolytica. The Development of screening methods for the early diagnosis of asymptomatic E. histolytica infection is the key to epidemiologic control. Moreover, delay in diagnosis of severe cases (e.g., fulminant amebiasis) leads to death even in developed countries. It is also important to increase clinical awareness of domestically transmitted STI amebiasis in the clinical settings. This review considers the changing epidemiology and clinical manifestations of STI amebiasis, and finally discusses the future strategies for the better practice.

Valor de la tomografía helicoidal en litiasis urinaria: ¿puede este estudio predecir la evolución clínica? / The value of helical tomography in ureterolithiasis: can this study predict the clinic evolution?

Evaluar el valor de la tomografía helicoidal sin contraste endovenoso en litiasis ureteral como predictora de una evolución clínica favorable. 174 pacientes con sospecha de litiasis ureteral fueron sometidos a tomografía helicoidal abdominopélvica sin contraste endovenoso durante un período de 17 meses. 69 pacientes presentaron litiasis ureteral única no localizada en la unión ureteropiélica. Las tomografías de estos 69 pacientes fueron revisadas por dos radiólogos y dos urólogos. Se determinó la presencia o ausencia del signo de anillo tisular, hidronefrosis, retorcimiento de la grasa perirrenal, colecciones perirrenales, y engrosamiento de la fascia renal, otorgándole a cada uno, una gradación en una escala de 0-3. También se determinó el tamaño del cálculo y del parénquima renal. La evolución clínica de cada uno de los 69 pacientes fue categorizada de acuerdo a: pasaje espontáneo documentado, fracaso del manejo conservador, y pacientes perdidos durante el seguimiento. Se determinó la sensibilidad, especificidad y valor predictivo positivo para los parámetros considerados estadísticamente significativos en predecir cual sería la evolución clínica en cada caso. De los 69 pacientes con litiasis ureteral única, 22 presentaron pasaje espontáneo, 12 fracasaron con manejo conservador, y 35 pacientes fueron perdidos durante el seguimiento. Excluyendo estos últimos (35 pacientes), los hallazgos de retorcimiento de la grasa perirrenal y colecciones perirrenales fueron graduados mayormente en pacientes con pasaje espontáneo. El tamaño medio del cálculo fue mayor en pacientes que fracasaron con manejo conservador (media=7.8mms.) comparado con pacientes con pasaje espontáneo (media=2.9mms.). La presencia del signo del anillo tisular, hidronefrosis, engrosamiento de la fascia renal y aumento del tamaño renal no fueron significativamente diferentes entre los dos grupos. El tamaño del cálculo, el grado de retorcimiento de la grasa perirrenal, y la presencia de colecciones perirrenales constituyen signos radiológicos capaces de predecir la posibilidad de pasaje espontáneo en pacientes con litiasis ureteral