Machine Learning Prediction of Lymph Node Metastasis in Breast Cancer: Performance of a Multi-institutional MRI-based 4D Convolutional Neural Network.

Purpose To develop a custom deep convolutional neural network (CNN) for noninvasive prediction of breast cancer nodal metastasis. Materials and Methods This retrospective study included patients with newly diagnosed primary invasive breast cancer with known pathologic (pN) and clinical nodal (cN) status who underwent dynamic contrast-enhanced (DCE) breast MRI at the authors' institution between July 2013 and July 2016. Clinicopathologic data (age, estrogen receptor and human epidermal growth factor 2 status, Ki-67 index, and tumor grade) and cN and pN status were collected. A four-dimensional (4D) CNN model integrating temporal information from dynamic image sets was developed. The convolutional layers learned prognostic image features, which were combined with clinicopathologic measures to predict cN0 versus cN+ and pN0 versus pN+ disease. Performance was assessed with the area under the receiver operating characteristic curve (AUC), with fivefold nested cross-validation. Results Data from 350 female patients (mean age, 51.7 years ± 11.9 [SD]) were analyzed. AUC, sensitivity, and specificity values of the 4D hybrid model were 0.87 (95% CI: 0.83, 0.91), 89% (95% CI: 79%, 93%), and 76% (95% CI: 68%, 88%) for differentiating pN0 versus pN+ and 0.79 (95% CI: 0.76, 0.82), 80% (95% CI: 77%, 84%), and 62% (95% CI: 58%, 67%), respectively, for differentiating cN0 versus cN+. Conclusion The proposed deep learning model using tumor DCE MR images demonstrated high sensitivity in identifying breast cancer lymph node metastasis and shows promise for potential use as a clinical decision support tool. Keywords: MR Imaging, Breast, Breast Cancer, Breast MRI, Machine Learning, Metastasis, Prognostic Prediction Supplemental material is available for this article. Published under a CC BY 4.0 license.

Organizational Breast Cancer Data Mart: A Solution for Assessing Outcomes of Imaging and Treatment.

PURPOSE: In the United States, a comprehensive national breast cancer registry (CR) does not exist. Thus, care and coverage decisions are based on data from population subsets, other countries, or models. We report a prototype real-world research data mart to assess mortality, morbidity, and costs for breast cancer diagnosis and treatment. METHODS: With institutional review board approval and Health Insurance Portability and Accountability Act (HIPPA) compliance, a multidisciplinary clinical and research data warehouse (RDW) expert group curated demographic, risk, imaging, pathology, treatment, and outcome data from the electronic health records (EHR), radiology (RIS), and CR for patients having breast imaging and/or a diagnosis of breast cancer in our institution from January 1, 2004, to December 31, 2020. Domains were defined by prebuilt views to extract data denormalized according to requirements from the existing RDW using an export, transform, load pattern. Data dictionaries were included. Structured query language was used for data cleaning. RESULTS: Five-hundred eighty-nine elements (EHR 311, RIS 211, and CR 67) were mapped to 27 domains; all, except one containing CR elements, had cancer and noncancer cohort views, resulting in a total of 53 views (average 12 elements/view; range, 4-67). EHR and RIS queries returned 497,218 patients with 2,967,364 imaging examinations and associated visit details. Cancer biology, treatment, and outcome details for 15,619 breast cancer cases were imported from the CR of our primary breast care facility for this prototype mart. CONCLUSION: Institutional real-world data marts enable comprehensive understanding of care outcomes within an organization. As clinical data sources become increasingly structured, such marts may be an important source for future interinstitution analysis and potentially an opportunity to create robust real-world results that could be used to support evidence-based national policy and care decisions for breast cancer.

Differentiation of invasive ductal and lobular carcinoma of the breast using MRI radiomic features: a pilot study.

Background: Breast cancer (BC) is one of the main causes of cancer-related mortality among women. For clinical management to help patients survive longer and spend less time on treatment, early and precise cancer identification and differentiation of breast lesions are crucial. To investigate the accuracy of radiomic features (RF) extracted from dynamic contrast-enhanced Magnetic Resonance Imaging (DCE MRI) for differentiating invasive ductal carcinoma (IDC) from invasive lobular carcinoma (ILC). Methods: This is a retrospective study. The IDC of 30 and ILC of 28 patients from Dukes breast cancer MRI data set of The Cancer Imaging Archive (TCIA), were included. The RF categories such as shape based, Gray level dependence matrix (GLDM), Gray level co-occurrence matrix (GLCM), First order, Gray level run length matrix (GLRLM), Gray level size zone matrix (GLSZM), NGTDM (Neighbouring gray tone difference matrix) were extracted from the DCE-MRI sequence using a 3D slicer. The maximum relevance and minimum redundancy (mRMR) was applied using Google Colab for identifying the top fifteen relevant radiomic features. The Mann-Whitney U test was performed to identify significant RF for differentiating IDC and ILC. Receiver Operating Characteristic (ROC) curve analysis was performed to ascertain the accuracy of RF in distinguishing between IDC and ILC. Results: Ten DCE MRI-based RFs used in our study showed a significant difference (p <0.001) between IDC and ILC. We noticed that DCE RF, such as Gray level run length matrix (GLRLM) gray level variance (sensitivity (SN) 97.21%, specificity (SP) 96.2%, area under curve (AUC) 0.998), Gray level co-occurrence matrix (GLCM) difference average (SN 95.72%, SP 96.34%, AUC 0.983), GLCM interquartile range (SN 95.24%, SP 97.31%, AUC 0.968), had the strongest ability to differentiate IDC and ILC. Conclusions: MRI-based RF derived from DCE sequences can be used in clinical settings to differentiate malignant lesions of the breast, such as IDC and ILC, without requiring intrusive procedures.

3D amide proton transfer-weighted imaging may be useful for diagnosing early-stage breast cancer: a prospective monocentric study.

BACKGROUND: We investigated the value of three-dimensional amide proton transfer-weighted imaging (3D-APTWI) in the diagnosis of early-stage breast cancer (BC) and its correlation with the immunohistochemical characteristics of malignant lesions. METHODS: Seventy-eight women underwent APTWI and dynamic contrast-enhanced (DCE)-MRI. Pathological results were categorized as either benign (n = 43) or malignant (n = 37) lesions. The parameters of APTWI and DCE-MRI were compared between the benign and malignant groups. The diagnostic value of 3D-APTWI was evaluated using the area under the receiver operating characteristic curve (ROC-AUC) to establish a diagnostic threshold. Pearson's correlation was used to analyze the correlation between the magnetization transfer asymmetry (MTRasym) and immunohistochemical characteristics. RESULTS: The MTRasym and time-to-peak of malignancies were significantly lower than those of benign lesions (all p < 0.010). The volume transfer constant, rate constant, and wash-in and wash-out rates of malignancies were all significantly greater than those of benign lesions (all p < 0.010). ROC-AUCs of 3D-APTWI, DCE-MRI, and 3D-APTWI+DCE to differential diagnosis between early-stage BC and benign lesions were 0.816, 0.745, and 0.858, respectively. Only the difference between AUCAPT+DCE and AUCDCE was significant (p < 0.010). When a threshold of MTRasym for malignancy for 2.42%, the sensitivity and specificity of 3D-APTWI for BC diagnosis were 86.5% and 67.6%, respectively; MTRasym was modestly positively correlated with pathological grade (r = 0.476, p = 0.003) and Ki-67 (r = 0.419, p = 0.020). CONCLUSIONS: 3D-APTWI may be used as a supplementary method for patients with contraindications of DCE-MRI. MTRasym can imply the proliferation activities of early-stage BC. RELEVANCE STATEMENT: 3D-APTWI can be an alternative diagnostic method for patients with early-stage BC who are not suitable for contrast injection. KEY POINTS: • 3D-APTWI reflects the changes in the microenvironment of early-stage breast cancer. • Combined 3D-APTWI is superior to DCE-MRI alone for early-stage breast cancer diagnosis. • 3D-APTWI improves the diagnostic accuracy of early-stage breast cancer.

Deep transfer learning with fuzzy ensemble approach for the early detection of breast cancer.

Breast Cancer is a significant global health challenge, particularly affecting women with higher mortality compared with other cancer types. Timely detection of such cancer types is crucial, and recent research, employing deep learning techniques, shows promise in earlier detection. The research focuses on the early detection of such tumors using mammogram images with deep-learning models. The paper utilized four public databases where a similar amount of 986 mammograms each for three classes (normal, benign, malignant) are taken for evaluation. Herein, three deep CNN models such as VGG-11, Inception v3, and ResNet50 are employed as base classifiers. The research adopts an ensemble method where the proposed approach makes use of the modified Gompertz function for building a fuzzy ranking of the base classification models and their decision scores are integrated in an adaptive manner for constructing the final prediction of results. The classification results of the proposed fuzzy ensemble approach outperform transfer learning models and other ensemble approaches such as weighted average and Sugeno integral techniques. The proposed ResNet50 ensemble network using the modified Gompertz function-based fuzzy ranking approach provides a superior classification accuracy of 98.986%.

Use of an AI Score Combining Cancer Signs, Masking, and Risk to Select Patients for Supplemental Breast Cancer Screening.

Background Mammographic density measurements are used to identify patients who should undergo supplemental imaging for breast cancer detection, but artificial intelligence (AI) image analysis may be more effective. Purpose To assess whether AISmartDensity-an AI-based score integrating cancer signs, masking, and risk-surpasses measurements of mammographic density in identifying patients for supplemental breast imaging after a negative screening mammogram. Materials and Methods This retrospective study included randomly selected individuals who underwent screening mammography at Karolinska University Hospital between January 2008 and December 2015. The models in AISmartDensity were trained and validated using nonoverlapping data. The ability of AISmartDensity to identify future cancer in patients with a negative screening mammogram was evaluated and compared with that of mammographic density models. Sensitivity and positive predictive value (PPV) were calculated for the top 8% of scores, mimicking the proportion of patients in the Breast Imaging Reporting and Data System "extremely dense" category. Model performance was evaluated using area under the receiver operating characteristic curve (AUC) and was compared using the DeLong test. Results The study population included 65 325 examinations (median patient age, 53 years [IQR, 47-62 years])-64 870 examinations in healthy patients and 455 examinations in patients with breast cancer diagnosed within 3 years of a negative screening mammogram. The AUC for detecting subsequent cancers was 0.72 and 0.61 (P < .001) for AISmartDensity and the best-performing density model (age-adjusted dense area), respectively. For examinations with scores in the top 8%, AISmartDensity identified 152 of 455 (33%) future cancers with a PPV of 2.91%, whereas the best-performing density model (age-adjusted dense area) identified 57 of 455 (13%) future cancers with a PPV of 1.09% (P < .001). AISmartDensity identified 32% (41 of 130) and 34% (111 of 325) of interval and next-round screen-detected cancers, whereas the best-performing density model (dense area) identified 16% (21 of 130) and 9% (30 of 325), respectively. Conclusion AISmartDensity, integrating cancer signs, masking, and risk, outperformed traditional density models in identifying patients for supplemental imaging after a negative screening mammogram. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Kim and Chang in this issue.

Public data homogenization for AI model development in breast cancer.

BACKGROUND: Developing trustworthy artificial intelligence (AI) models for clinical applications requires access to clinical and imaging data cohorts. Reusing of publicly available datasets has the potential to fill this gap. Specifically in the domain of breast cancer, a large archive of publicly accessible medical images along with the corresponding clinical data is available at The Cancer Imaging Archive (TCIA). However, existing datasets cannot be directly used as they are heterogeneous and cannot be effectively filtered for selecting specific image types required to develop AI models. This work focuses on the development of a homogenized dataset in the domain of breast cancer including clinical and imaging data. METHODS: Five datasets were acquired from the TCIA and were harmonized. For the clinical data harmonization, a common data model was developed and a repeatable, documented "extract-transform-load" process was defined and executed for their homogenization. Further, Digital Imaging and COmmunications in Medicine (DICOM) information was extracted from magnetic resonance imaging (MRI) data and made accessible and searchable. RESULTS: The resulting harmonized dataset includes information about 2,035 subjects with breast cancer. Further, a platform named RV-Cherry-Picker enables search over both the clinical and diagnostic imaging datasets, providing unified access, facilitating the downloading of all study imaging that correspond to specific series' characteristics (e.g., dynamic contrast-enhanced series), and reducing the burden of acquiring the appropriate set of images for the respective AI model scenario. CONCLUSIONS: RV-Cherry-Picker provides access to the largest, publicly available, homogenized, imaging/clinical dataset for breast cancer to develop AI models on top. RELEVANCE STATEMENT: We present a solution for creating merged public datasets supporting AI model development, using as an example the breast cancer domain and magnetic resonance imaging images. KEY POINTS: • The proposed platform allows unified access to the largest, homogenized public imaging dataset for breast cancer. • A methodology for the semantically enriched homogenization of public clinical data is presented. • The platform is able to make a detailed selection of breast MRI data for the development of AI models.

Investigation of correlation between shear wave elastography and lymphangiogenesis in invasive breast cancer and diagnosis of axillary lymph node metastasis.

BACKGROUND: Accurate evaluation of axillary lymph node metastasis (LNM) in breast cancer is very important. A large number of hyperplastic and dilated lymphangiogenesis cases can usually be found in the pericancerous tissue of breast cancer to promote the occurrence of tumor metastasis.Shear wave elastography (SWE) can be used as an important means for evaluating pericancerous stiffness. We determined the stiffness of the pericancerous by SWE to diagnose LNM and lymphangiogenesis in invasive breast cancer (IBC). METHODS: Patients with clinical T1-T2 stage IBC who received surgical treatment in our hospital from June 2020 to December 2020 were retrospectively enrolled. A total of 299 patients were eventually included in the preliminary study, which included an investigation of clinicopathological features, ultrasonic characteristics, and SWE parameters. Multivariable logistic regression analysis was used to establish diagnostic model and evaluated its diagnostic performance of LNM. The correlation among SWE values, collagen volume fraction (CVF), and microlymphatic density (MLD) in primary breast cancer lesions was analyzed in another 97 patients. RESULTS: The logistic regression model is Logit(P)=-1.878 + 0.992*LVI-2.010*posterior feature enhancement + 1.230*posterior feature shadowing + 0.102*posterior feature combined pattern + 0.009*Emax. The optimum cutoff value of the logistic regression model was 0.365, and the AUC (95% CI) was 0.697 (0.636-0.758); the sensitivity (70.7 vs. 54.3), positive predictive value (PPV) (54.0 vs. 50.8), negative predictive value (NPV) (76.9 vs. 69.7), and accuracy (65.2 vs. 61.9) were all higher than Emax. There was no correlation between the SWE parameters and MLD in primary breast cancer lesions. CONCLUSIONS: The logistic regression model can help us to determine LNM, thus providing more imaging basis for the selection of preoperative treatment. The SWE parameter of the primary breast cancer lesion cannot reflect the peritumoral lymphangiogenesis, and we still need to find a new ultrasonic imaging method.

Biocompatible and Water-Soluble Shortwave-Infrared (SWIR)-Emitting Cyanine-Based Fluorescent Probes for In Vivo Multiplexed Molecular Imaging.

Extending molecular imaging into the shortwave-infrared (SWIR, 900-1400 nm) region provides deep tissue visualization of biomolecules in the living system resulting from the low tissue autofluorescence and scattering. Looking at the Food and Drug Administration-approved and clinical trial near-infrared (NIR) probes, only indocyanine green (ICG) and its analogues have been approved for biomedical applications. Excitation wavelength less than 800 nm limits these probes from deep tissue penetration and noninvasive fluorescence imaging. Herein, we present the synthesis of ICG-based π-conjugation-extended cyanine dyes, ICG-C9 and ICG-C11 as biocompatible, and water-soluble SWIR-emitting probes with emission wavelengths of 922 and 1010 nm in water, respectively. Also, ICG-, ICG-C9-, and ICG-C11-based fluorescent labeling agents have been synthesized for the development of SWIR molecular imaging probes. Using the fluorescence of ICG, ICG-C9, and ICG-C11, we demonstrate three-color SWIR fluorescence imaging of breast tumors by visualizing surface receptors (EGFR and HER2) and tumor vasculature in living mice. Furthermore, we demonstrate two-color SWIR fluorescence imaging of breast tumor apoptosis using an ICG-conjugated anticancer drug, Kadcyla and ICG-C9 or ICG-C11-conjugated annexin V. Finally, we show long-term (38 days) SWIR fluorescence imaging of breast tumor shrinkage induced by Kadcyla. This study provides a general strategy for multiplexed fluorescence molecular imaging with biocompatible and water-soluble SWIR-emitting cyanine probes.

Detección de la infiltración de la cadena mamaria interna en pacientes con cáncer de mama mediante PET/RM con 18F-FDG y sus implicaciones terapéuticas / Detection of internal mammary chain infiltration in breast cancer patients by [18F]FDG PET/MRI: Therapy implications

Objetivo: Evaluar la tasa de detección y la implicación terapéutica de la infiltración de la cadena mamaria interna (ICMI) mediante tomografía por emisión de positrones (PET) y resonancia magnética (RM) con 18F-fluorodesoxiglucosa (18F-PET/RM) en la estadificación de pacientes con cáncer de mama. Método: Estudio prospectivo, 41 mujeres con cáncer de mama (estadio ≥ IIB) estadificadas mediante 18F-FDG-PET/RM. Estudio en dos fases: imágenes mamarias (decúbito prono), cuerpo completo (supino). Estadificación TNM por consenso entre especialista en Medicina Nuclear y Radiología. Estudio vaso aferente (VA) a cadena mamaria interna (CMI) por RM mamaria. Correlación ICMI con edad, VA-CMI, estadificación T, cuadrante, infiltración axilar y a distancia. Revaloración terapéutica en comité multidisciplinar. Resultados: Tasa de detección de ICMN de 34% (14/41), siendo 8/14 < 55 años. Todas las 14 pacientes con ICMI muestran VA-CMI, en seis de ellas (43,9%) sin VA-axilar. De 27/41 sin ICMI, en 13 (48,1%) solo VA-axilar, en los 14 restantes (51,9%) VA-axilar y VA-CMI. Un total de 57% (8/14) son multicéntricos y 42% (6/14) focales, en cuadrantes internos en 4/6 (66,7%). En 1/14 (7,1%) solo ICMI, en 9/14 (64,3%) axilar y CMI y en 4/14 (28,6%) lesiones a distancia. Decisión del comité: sin tratamiento adicional en 27/41 (65,8%), radioterapia torácica en 10/41 (24,4%) y terapia sistémica en 4/41 (9,7%). Conclusión: La tasa de detección de la ICMI en la estadificación del cáncer de mama mediante 18F-FDG PET/RM es de 34%. Son factores asociados la edad, los tumores multicéntricos, los de cuadrantes internos, la existencia de VA-CMI, la estadificación NM. La evidencia de ICMI permite la individualización de la terapia, indicando la radioterapia torácica en 24,4%.(AU)

Objective: To evaluate the detection rate and therapeutic implication of the infiltration of the internal mammary chain (IMCI) by [18F]FDG PET/MRI for staging of patients with breast cancer. Methods: Prospective study including 41 women with breast cancer (stage ≥IIB) staged by [18F]FDG PET/MR. Two-phase exam: breast imaging (prone), whole-body (supine). TNM stage assessed by peer consensus with Nuclear Medicine and Radiology specialists. Study of the afferent vessel (AV) to IMC by breast MRI. IMCI was correlated with age, AV-IMC, T stage, breast quadrants, axillary and distant infiltration. Therapeutic re-evaluation by a multidisciplinary committee. Results: IMCI detection rate of 34% (14/41), with 8/14 patients under 55 years of age. All 14 patients with IMCI showed AV-IMC, 6 of them (43.9%) without VA-axillary. Of 27/41 patients without IMCI, in 13 (48.1%) only AV-axillary was found, in the remaining 14 (51.9%), AV-axillary and AV-IMC was found. In 57% (8/14) tumours were multicentric and 42% (6/14) focal, in inner quadrants in 4/6 (66.7%). In 1/14 patient (7.1%) only IMCI was found, in 9/14 (64.3%) axillary and IMC, in 4/14 patients (28.6%) distant lesions were detected. Committee re-evaluation: no further treatment in 27/41 patients (65.8%), thoracic radiotherapy in 10/41 patients (24.4%), systemic therapy in 4/41 patients (9.7%). Conclusion: Our detection rate of IMCI in breast cancer staging by [18F]FDG PET/MR was 34%. Related factors were age, multicentric tumours, inner quadrants, detection of AV-IMC, NM staging.The evidence of IMCI allowed tailored therapy, with thoracic radiotherapy implementation in 24.4% of patients.(AU)

Concordancia entre SPECT portátil y la gammagrafía convencional para detección de ganglio centinela en cáncer de mama / Concordance between freehand SPECT and conventional scintigraphy for sentinel lymph node detection in breast cancer

Introducción: La SPECT portátil puede ser una técnica de imagen útil para la planificación preoperatoria de la biopsia selectiva del ganglio centinela (BSGC) ya que permite la localización del ganglio centinela (GC) mediante imágenes tomográficas en 3D y en tiempo real y determina su profundidad, después de unos minutos de exploración. El objetivo del estudio fue evaluar la correlación entre el número de GC detectados entre las imágenes de la SPECT portátil y la linfogammagrafía (LG). Materiales y métodos: Cien pacientes con diagnóstico de cáncer de mama infiltrante y sin evidencia clínica de afectación ganglionar, se sometieron prospectivamente a una BSGC. El estudio preoperatorio incluyó imágenes de SPECT portátil a los 15 min tras la inyección y de LG a los 25 y 60-90 min (precoz y tardía). Se analizó el acuerdo observado y se realizó un estudio de concordancia entre el número de GC detectados con SPECT portátil y LG. Resultados: El acuerdo observado en la detección de GC entre SPECT portátil y LG precoz fue del 72%; entre SPECT portátil y LG tardía del 85%, y entre la LG precoz y la tardía de un 87%. En el estudio de concordancia se registró una concordancia moderada entre la SPECT portátil y la LG precoz (coeficiente kappa: 0,42); una concordancia moderada-alta entre la SPECT portátil y la LG tardía (coeficiente kappa: 0,60), y una concordancia de moderada-alta entre la LG precoz y la tardía (coeficiente kappa: 0,70), sin diferencias significativas entre ellos (valor p=0,16). Conclusión: La SPECT portátil presentó una concordancia moderada-alta con los estudios de imagen convencional y podría ser una alternativa válida para el estudio prequirúrgico de la BSGC en el cáncer de mama.(AU)

Introduction: Freehand SPECT can be a useful imaging technique for preoperative planning of sentinel lymph node biopsy (SLNB) as it allows localization of the sentinel node by 3D and real-time tomographic imaging and determines its depth after a few minutes of scanning. The aim of the study was to evaluate the correlation between the number of detected SNs between freehand SPECT images and lymphoscintigraphy (LS). Materials and methods: One hundred patients with a diagnosis of invasive breast cancer and no clinical evidence of lymph node involvement prospectively underwent SLNB. The preoperative study included freehand SPECT imaging at 15min after injection and LS imaging at 25 and 60–90min after injection (early and late). The observed agreement was analyzed and a concordance study was performed between the number of SNs detected with freehand SPECT and LS. Results: The observed agreement in the detection of SNs between freehand SPECT and early LS was 72%; between freehand SPECT and late LS was 85%; and between early and late LS was 87%. In the concordance study, there was moderate concordance between freehand SPECT and early LS (kappa coefficient: 0.42); moderate-high concordance between freehand SPECT and late LS (kappa coefficient: 0.60); and moderate-high concordance between early and late LS (kappa coefficient: 0.70), with no significant differences between them (p-value=0.16). Conclusion: Freehand SPECT showed a moderate-high concordance with conventional imaging studies and could be a valid alternative for the presurgical study of SLNB in breast cancer.(AU)

Equipo multidisciplinar de cirugía radioguiada: Alternativa de cambio al paradigma actual / Multidisciplinary radio-guided surgery team: Alternative to change the current paradigm

IntroducciónAnte el aumento constante de la demanda asistencial de exploraciones relacionadas con cirugía radioguiada (CRG), nuestro hospital adoptó incluir en el equipo de CRG nuevos perfiles profesionales con el fin de reducir parcialmente el tiempo de dedicación de los médicos nucleares a esta tarea.Objetivos: Analizar el proceso de incorporación de los perfiles de Técnico Superior en Imagen para el Diagnóstico (TSID) y Enfermera Referente de Ganglio Centinela (ERGC), evaluando su despliegue en los procedimientos ligados a la técnica. Material y métodos: Análisis de la actividad de CRG durante el periodo 2018-2022, centrándolo en los procedimientos prequirúrgicos y quirúrgicos relativos a cáncer de mama (CaM) y melanoma maligno (MM), por ser aquellas patologías en las que se concentró la transferencia de competencias asistenciales. Evolución cronológica de las competencias asumidas por los diferentes perfiles durante su integración en el equipo de CRG. Resultados: La actividad asistencial de CRG durante el periodo analizado experimentó un incremento del 109%. CaM y MM son las patologías que aglutinaron con diferencia una mayor demanda asistencial. La transferencia de competencias en estas dos patologías se ha producido de manera progresiva, asumiendo en 2022 el 74% (460/622) de la fase de administración el ERGC y el 64% (333/519) de las cirugías el TSID. Conclusiones: La creación de un equipo multidisciplinar de CRG, que incluye distintos perfiles profesionales (MN, ERGC y TSID), es una eficaz estrategia para dar respuesta al incremento de la complejidad y número de todos los procedimientos relacionados con la CRG.(AU)

Introduction: Given the constant increase in the healthcare demand for examinations related to radio-guided surgery (RGS), our hospital adopted new professional profiles in the RGS team, in order to partially reduce the time spent by nuclear medicine physicians on this task. Aim: To analyze the process of incorporating the profiles of Superior Diagnostic Imaging Technician (TSID) and Sentinel Node Referent Nurse (ERGC), evaluating their deployment in the procedures linked to the technique. Material and methods: Analysis of RGS activity during the period 2018-2022, focusing on pre-surgical and surgical procedures related to breast cancer (BC) and malignant melanoma (MM), as they are those pathologies on which the transfer of care competencies was concentrated. Chronological evolution of the competencies assumed by the different profiles during their integration into the RGS team. Results: RGS's healthcare activity during the analyzed period experienced an increase of 109%. BC and MM were the pathologies that accounted for by far the greatest demand for care. The transfer of competencies in these two pathologies occurred in a progressive and staggered manner, with 74% (460/622) of the administration phase being carried out by the ERGC and 64% (333/519) of the surgeries by the TSID in 2022. Conclusions: The creation of a multidisciplinary RGS team that includes different professional profiles (NM, ERGC and TSID) is an effective strategy to respond to the increase in the complexity and number of all procedures related to RGS.(AU)

Paget's disease of the breast: Presentation, treatment, and outcomes in a modern cohort.

BACKGROUND: Surgical management for Paget's disease (PD) of the breast is controversial. This study aims to assess outcomes of PD patients based on procedure type and determine the reliability of imaging in estimating disease extent. METHODS: A retrospective review analyzed clinicopathologic data of PD patients between 2009 and 2022. Pre-operative imaging size (PIS) was compared to post-operative pathology size (PPS) looking at concordance. RESULTS: Thirty patients had PD, 21 underwent total mastectomy (TM) and 9 breast conserving surgery (BCS). Seventeen patients (56.7 â€‹%) had a final diagnosis of invasive cancer (14 â€‹TM, 3 BCS), with no local recurrences. Only 6/19 (31.6 â€‹%) patients with positive findings on ultrasound/mammogram had concordance between PIS and PPS. There were no breast/chest wall recurrences with a median follow up of 35.9 months. CONCLUSION: Ultrasound and mammogram had poor concordance with pathological size. BCS is feasible in select patients. MRI may help guide management.

Lymph node metastasis prediction and biological pathway associations underlying DCE-MRI deep learning radiomics in invasive breast cancer.

BACKGROUND: The relationship between the biological pathways related to deep learning radiomics (DLR) and lymph node metastasis (LNM) of breast cancer is still poorly understood. This study explored the value of DLR based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in LNM of invasive breast cancer. It also analyzed the biological significance of DLR phenotype based on genomics. METHODS: Two cohorts from the Cancer Imaging Archive project were used, one as the training cohort (TCGA-Breast, n = 88) and one as the validation cohort (Breast-MRI-NACT Pilot, n = 57). Radiomics and deep learning features were extracted from preoperative DCE-MRI. After dual selection by principal components analysis (PCA) and relief methods, radiomics and deep learning models for predicting LNM were constructed by the random forest (RF) method. A post-fusion strategy was used to construct the DLR nomograms (DLRNs) for predicting LNM. The performance of the models was evaluated using the receiver operating characteristic (ROC) curve and Delong test. In the training cohort, transcriptome data were downloaded from the UCSC Xena online database, and biological pathways related to the DLR phenotypes were identified. Finally, hub genes were identified to obtain DLR gene expression (RadDeepGene) scores. RESULTS: DLRNs were based on area under curve (AUC) evaluation (training cohort, AUC = 0.98; validation cohort, AUC = 0.87), which were higher than single radiomics models or GoogLeNet models. The Delong test (radiomics model, P = 0.04; GoogLeNet model, P = 0.01) also validated the above results in the training cohorts, but they were not statistically significant in the validation cohort. The GoogLeNet phenotypes were related to multiple classical tumor signaling pathways, characterizing the biological significance of immune response, signal transduction, and cell death. In all, 20 genes related to GoogLeNet phenotypes were identified, and the RadDeepGene score represented a high risk of LNM (odd ratio = 164.00, P < 0.001). CONCLUSIONS: DLRNs combining radiomics and deep learning features of DCE-MRI images improved the preoperative prediction of LNM in breast cancer, and the potential biological characteristics of DLRN were identified through genomics.

Ultrasonography is an effective tool for breast cancer screening in individuals with severe motor and intellectual disabilities.

BACKGROUND: Individuals with severe motor and intellectual disabilities have become an aging population, and high cancer morbidity and mortality are critical issues affecting their survival. Cancer screening is a crucial method of resolving this issue; however, a suitable screening method for them has not been established. METHODS: We used ultrasonography alone and performed breast cancer screening for women over 30 years old in our facility from 2016 to 2023. We observed the outcomes and calculated the recall/detection rate in this screening. RESULTS: Three cases among 379 tested positive in this screening, all of which underwent radical surgery. They are alive and well without relapse present. We detected these breast cancer cases with a low recall rate. CONCLUSION: We were able to successfully detect breast cancer cases using ultrasonography alone. Ultrasonography is an effective and feasible tool for breast cancer screening in individuals with severe motor and intellectual disabilities.

An improved breast cancer classification with hybrid chaotic sand cat and Remora Optimization feature selection algorithm.

Breast cancer is one of the most often diagnosed cancers in women, and identifying breast cancer histological images is an essential challenge in automated pathology analysis. According to research, the global BrC is around 12% of all cancer cases. Furthermore, around 25% of women suffer from BrC. Consequently, the prediction of BrC depends critically on the quick and precise processing of imaging data. The primary reason deep learning models are used in breast cancer detection is that they can produce findings more quickly and accurately than current machine learning-based techniques. Using a BreakHis dataset, we demonstrated in this work the viability of automatically identifying and classifying BrC. The first stage is pre-processing, which employs an Adaptive Switching Modified Decision Based Unsymmetrical Trimmed Median Filter (ASMDBUTMF) to remove high-density noise. After the image has been pre-processed, it is segmented using the Thresholding Level set approach. Next, we propose a hybrid chaotic sand cat optimization technique, together with the Remora Optimization Algorithm (ROA) for feature selection. The suggested strategy facilitates the acquisition of precise functionality attributes, hence simplifying the detection procedure. Additionally, it aids in resolving problems pertaining to global optimization. Following the selection, the best characteristics proceed to the categorization procedure. A DL classifier called the Conditional Variation Autoencoder is used to discriminate between cancerous and benign tumors while categorizing them. Consequently, a classification accuracy of 99.4%, Precision of 99.2%, Recall of 99.1%, F- score of 99%, Specificity of 99.14%, FDR of 0.54, FNR of 0.001, FPR of 0.002, MCC of 0.98 and NPV of 0.99 were obtained using the proposed approach. Furthermore, compared to other research using the current BreakHis dataset, the results of our research are more desirable.

Multimodality Imaging of Postmastectomy Breast Reconstruction Techniques, Complications, and Tumor Recurrence.

For women undergoing mastectomy, breast reconstruction can be performed by using implants or autologous tissue flaps. Mastectomy options include skin- and nipple-sparing techniques. Implant-based reconstruction can be performed with saline or silicone implants. Various autologous pedicled or free tissue flap reconstruction methods based on different tissue donor sites are available. The aesthetic outcomes of implant- and flap-based reconstructions can be improved with oncoplastic surgery, including autologous fat graft placement and nipple-areolar complex reconstruction. The authors provide an update on recent advances in implant reconstruction techniques and contemporary expanded options for autologous tissue flap reconstruction as it relates to imaging modalities. As breast cancer screening is not routinely performed in this clinical setting, tumor recurrence after mastectomy and reconstruction is often detected by palpation at physical examination. Most local recurrences occur within the skin and subcutaneous tissue. Diagnostic breast imaging continues to have a critical role in confirmation of disease recurrence. Knowledge of the spectrum of benign and abnormal imaging appearances in the reconstructed breast is important for postoperative evaluation of patients, including recognition of early and late postsurgical complications and breast cancer recurrence. The authors provide an overview of multimodality imaging of the postmastectomy reconstructed breast, as well as an update on screening guidelines and recommendations for this unique patient population. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

Application of deep learning on mammographies to discriminate between low and high-risk DCIS for patient participation in active surveillance trials.

BACKGROUND: Ductal Carcinoma In Situ (DCIS) can progress to invasive breast cancer, but most DCIS lesions never will. Therefore, four clinical trials (COMET, LORIS, LORETTA, AND LORD) test whether active surveillance for women with low-risk Ductal carcinoma In Situ is safe (E. S. Hwang et al., BMJ Open, 9: e026797, 2019, A. Francis et al., Eur J Cancer. 51: 2296-2303, 2015, Chizuko Kanbayashi et al. The international collaboration of active surveillance trials for low-risk DCIS (LORIS, LORD, COMET, LORETTA),  L. E. Elshof et al., Eur J Cancer, 51, 1497-510, 2015). Low-risk is defined as grade I or II DCIS. Because DCIS grade is a major eligibility criteria in these trials, it would be very helpful to assess DCIS grade on mammography, informed by grade assessed on DCIS histopathology in pre-surgery biopsies, since surgery will not be performed on a significant number of patients participating in these trials. OBJECTIVE: To assess the performance and clinical utility of a convolutional neural network (CNN) in discriminating high-risk (grade III) DCIS and/or Invasive Breast Cancer (IBC) from low-risk (grade I/II) DCIS based on mammographic features. We explored whether the CNN could be used as a decision support tool, from excluding high-risk patients for active surveillance. METHODS: In this single centre retrospective study, 464 patients diagnosed with DCIS based on pre-surgery biopsy between 2000 and 2014 were included. The collection of mammography images was partitioned on a patient-level into two subsets, one for training containing 80% of cases (371 cases, 681 images) and 20% (93 cases, 173 images) for testing. A deep learning model based on the U-Net CNN was trained and validated on 681 two-dimensional mammograms. Classification performance was assessed with the Area Under the Curve (AUC) receiver operating characteristic and predictive values on the test set for predicting high risk DCIS-and high-risk DCIS and/ or IBC from low-risk DCIS. RESULTS: When classifying DCIS as high-risk, the deep learning network achieved a Positive Predictive Value (PPV) of 0.40, Negative Predictive Value (NPV) of 0.91 and an AUC of 0.72 on the test dataset. For distinguishing high-risk and/or upstaged DCIS (occult invasive breast cancer) from low-risk DCIS a PPV of 0.80, a NPV of 0.84 and an AUC of 0.76 were achieved. CONCLUSION: For both scenarios (DCIS grade I/II vs. III, DCIS grade I/II vs. III and/or IBC) AUCs were high, 0.72 and 0.76, respectively, concluding that our convolutional neural network can discriminate low-grade from high-grade DCIS.